Detecting fake accounts on Online Social Networks is a pressing issue due to the rise in unethical online activities. This study presents a new Quantum Beta-behaved Multi-Objective Particle Swarm Optimization Algorithm (QB-MOPSO) for machine learning-based fake account detection. QB-MOPSO aims to enhance the learning process of a random forest algorithm by simultaneously minimizing feature dimensionality and classification error rates. It proposes a novel architecture that employs two optimization profiles: one improves exploratory behavior using a quantum-behaved equation, while the other enhances exploitation through a beta function. The main contributions of this study are as follows: the design of a novel Quantum Beta Distributed Multi-Objective Particle Swarm Optimization algorithm that integrates quantum-behaved exploration and beta-distributed exploitation, the application of this algorithm to enhance artificial intelligence–based fake account detection on Twitter datasets, and a comprehensive experimental evaluation demonstrating superior accuracy, F-measure, and MCC compared to existing methods. Experimental results on two Twitter datasets with 1982 and 928 accounts respectively show QB-MOPSO's effectiveness, achieving accuracy rates of about 99.19 % and 97.52 %. Comparisons with the original architecture demonstrate QB-MOPSO's ability to enhance the performance of the random forest algorithm.

This study investigates the classification of two prominent movement disorders: Parkinson’s Disease (PD) and Essential Tremor (ET) using a comprehensive machine learning framework. A novel dataset was meticulously created which contains handwriting samples collected at Habib Bourguiba Hospital in Sfax, Tunisia, specifically designed for differentiating between PD and ET. Preprocessing techniques such as image resizing, normalization, and data augmentation were employed to enhance robustness. Feature extraction was performed using the ResNet50 model, effectively capturing essential image characteristics through global average pooling. Recursive Feature Elimination (RFE) was then applied to identify the most significant features, followed by the training and validation of two classification models Random Forest and SVM using these selected features. The performance of these models is rigorously assessed through various metrics, revealing that the Random Forest model attained an accuracy of $92.83 \% \pm 2$, while the SVM model achieved an average accuracy of $94.66 \% \pm 1$. Visualizations such as confusion matrices and ROC curves provide deeper insights into model performance. Overall, the findings demonstrate the potential of machine learning techniques to enhance diagnostic accuracy in distinguishing between PD and ET, ultimately contributing to improved clinical decision-making.

The central objective of this initiative is to equip drivers with the tools to plan their routes effectively and overcome roadway congestion. Conventional navigation systems primarily focus on identifying the shortest distance, but modern demands for travelers and commercial operators-who often need to visit multiple locations or deliver merchandise-necessitate a more sophisticated system. Our solution dynamically processes userselected destinations, integrates real-time traffic information, and accounts for varying travel times to ascertain the most timeefficient path. To address this challenge, we developed a system based on a time-dependent Particle Swarm Optimization-Ant Colony Optimization (PSO-ACO) algorithm, specifically designed to prioritize the fastest route over the shortest. Furthermore, we engineered a dynamic real-world test generator that leverages substantial Global Positioning System (GPS) data to accurately model live traffic conditions and produce adaptable problem scenarios. A dedicated mobile application has been developed to furnish drivers with accurate guidance for navigating their chosen locations and to suggest optimal departure times, thereby helping them avoid delays and reach their destinations promptly. Extensive experimental validation confirms the efficacy of our algorithm in handling dynamic optimization challenges, outperforming the widely recognized MMASUS algorithm.

The rapid expansion of the Internet of Things (IoT) in sectors such as agriculture, healthcare, smart cities, and industrial automation has increased demand for low-energy, highprecision devices for real-time localization. However, accurate localization in large-scale, resource-constrained IoT networks remains challenging due to increased data communication, energy consumption, and network dynamics. Traditional methods such as GPS, triangulation, and RSSI often fail in obstructed or indoor environments. Although machine learning techniques such as Convolutional Neural Networks (CNNs) offer potential, their data and computational requirements limit their use in IoT settings. Similarly, stochastic models and swarm intelligence algorithms face issues such as slow convergence and difficulty modeling complex environments. This paper proposes hybrid models that integrate CNNs, stochastic models, and swarm intelligence to tackle localization challenges in dynamic IoT networks. We introduce two novel energy-efficient hybrid frameworks, MarkovCNN and SSA-Markov-CNN, which combine CNNs for feature extraction, Markov models for uncertainty management, and swarm intelligence for global optimization. Experiments show that these models significantly improve localization accuracy while reducing energy consumption and latency, offering a promising solution for energy-conscious IoT deployments. Our findings provide insights for selecting optimal localization models for low-latency, energy-efficient IoT applications.

Accurate and secure localization is critical for mission-critical IoT applications, yet networks remain vulnerable to attacks such as Neutralization-Inspired Fake Signal (NIFS) attacks. We address accurate positioning under adversarial conditions while respecting latency and energy constraints. We formulate a secure localization problem optimizing accuracy, cryptographic overhead (Ed25519), and robustness against malicious anchors, and propose a Hybrid Quantum-Convolutional Neural Network (HQC-NN) with K-Means clustering for region-specific specialization. The framework integrates cryptographic verification and monitors performance, energy, and security metrics. Simulations show that HQC-NN and HQC-NN-KMeans outperform CNN and CNN-KMeans baselines in accuracy, efficiency, latency, and attack detection, demonstrating their potential for resilient IoT localization.

In the midst of the rapid proliferation of the Internet of Things (IoT), precise location of distributed IoT devices is paramount for a multitude of applications, ranging from emergency services to environmental monitoring. However, achieving such precision while maintaining energy efficiency and minimizing latency remains a persistent challenge, especially within distributed IoT sensing environments. This paper introduces innovative hybrid localization models tailored to address these requirements by amalgamating the virtues of Salp Swarm Algorithms (SSA) with stochastic methodologies, thereby attaining accuracy, energy efficiency, and low latency, vital in resourceconstrained IoT settings. By combining SSA with the Markov model and harnessing a fusion of SSA with the Gauss model, our models ensure enhanced accuracy while curtailing energy consumption. Extensive simulations validate the efficacy of these hybrid models, showcasing their superiority over conventional baseline approaches. Noteworthy reductions in latency, coupled with enhancements in IoT localization accuracy and energy efficiency relative to traditional baseline models, underscore their potential to fortify distributed sensing applications and nurture a more sustainable IoT ecosystem.

The recognition of Arabic and Latin text for autonomous cars involves developing systems and algorithms capable of accurately detecting and understanding Arabic characters and words from images. This technology is crucial in enabling autonomous vehicles to interpret and respond to Arabic and Latin traffic signs, road markings, and other textual information on the roads. The development of a reliable identification system, particularly for Arabic is challenging if a dataset contains differences in text size, typefaces, colors, orientation, illumination and noise. These problems become more difficult to solve. By exploiting the benefits of both CTC (Connectionist Temporal Classification) and Attention mechanisms to improve the accuracy and robustness of the recognition system, a hybrid CTC and Attention model is used in the prediction stage for Arabic-Latin image text recognition. Current research is focusing intensively on text panels in Latin, while other scripts, such as Arabic, remain little valued. For this reason, the NaSTSArLaTR (Natural Scene Traffic Sign and Panel Guide Arabic-Latin Text Recognition) dataset has been set up to validate our experiments. Our tests found that the suggested hybrid CTC and Attention model outperformed either Attention or CTC alone in the prediction phase. The dataset is publicly available in IEEE DataPort https://dx.doi.org/10.21227/phyg-_jc98.

Fake news has become a major issue owing to its quick growth on the internet, difficulty in identifying it from true news, and people's reliance on social media platforms as primary sources. It has negative effects at several levels, including individual, communal, political, and economical. Detecting Arabic fake news requires significant effort owing to limited datasets and studies in the sector. In this study, Employ Perturbation Adversarial attacks was applied as a regularization technique for fake news classification. Adversarial examples are generated by perturbing the model's word embedding matrix. The AraBERTv2 model is utilized for preprocessing operations. Five different machine learning models were trained on clean data and tested using both clean and adversarial examples to evaluate the generalization capabilities of the classification models. To address the scarcity of Arabic datasets, A translated English fake news was utilized dataset Experimental results indicate that the LightGBM and AdaBoost algorithms exhibited the best performance (90%) compared to other classifiers.

the rapid spread of fake news online, coupled with the difficulty of distinguishing it from real news, has become a serious issue, especially with social media being a primary news source for many people. The fake news can have damaging effects on individuals, communities, and political and economic systems. Detecting Arabic fake news presents additional challenges due to the limited availability of relevant datasets and research. In this study, Perturbation Adversarial attacks was applied as a regularization technique for fake news detection, generating adversarial examples by modifying the model’s word embedding matrix. The AraBERTv2 model is used for preprocessing, and the lack of Arabic data was overcome by utilizing a translated English fake news dataset. A Recurrent Neural Network (RNN) model was trained on clean data, testing it with both clean and adversarial examples to evaluate its generalization capability. The results demonstrate that the RNN model performs effectively, achieving strong accuracy in Arabic fake news detection.

The complexity of overlapping symptoms and interactions among multiple diseases makes it very difficult to accurately diagnose comorbidities. This article presents an innovative comorbidity diagnosis improvement approach that integrates conflicting group learning and numerous diverse machine learning algorithms such as Random Forest, Gradient Boosting, AdaBoost, Bagging and Extra Trees. The ensemble model is advantageous over individual models because it improves diagnostic accuracy while improving adversarial robustness. Effective adversarial training methods can also be used to strengthen the model against interference which may interfere with the diagnosis. Benchmark comorbidity datasets explore the effectiveness of the proposed method that is not solely more efficient in terms of accuracy compared to other methods, but similarly more efficient in its aptitude to endure adversarial instances. The current study is supposed to be merged into the investigative pipeline to allow for the development of vigorous diagnosis schemes. Of the algorithms tested in the study, the Extra Trees algorithm achieved 91.845% which was the highest performance obtained among the other algorithms.

For single-image reconstruction and enhancement techniques, deep convolutional neural networks (CNNs) performed better at producing super-resolution (SR) images from the details of low-resolution (LR) images. As a result, by utilizing intra- and cross-view information, Stereo Super Resolution approaches increased the effectiveness of these convolutional networks in recovering the original texture of individual images and provided further information about their tiny details. This paper presents a model of the Stereo Image Super Resolution Algorithm (SSRnlmd) reinforced by non-local means denoising (NLMD). Using two weight-sharing networks (NAFNet Blocks) to extract intra-view features of the left and right input image pair, then fuse these features to SR reconstruction, is one method for recovering super-resolution (SR) image details from low-resolution and improving the visual rendering of their surface textures. The resolution levels of the images generated by NAFNet Blocks have been reinforced using the non-local means denoising algorithm to remove noise and distortion and obtain an explicit scene close to the original image (HR Image). Quantitative results of (SSRnlmd) model demonstrated that our method outperformed state-of-the-art methods in terms of metric (PNSR/ SSIM), It was 31.29dB/0.8722 of 0376 Image on the DIV2K dataset. Quantitative scores on the BSD100 dataset were 38.88dB/0.9739 of 3096 Image. The result on the Set5 dataset was 32.29dB/0.8879 for the baby Image. The scores on the Set14 dataset were 21.46dB/0.5414 for the baboon Image. The visual evaluation of the images reconstructed by our method achieved high accuracy and clarity in the scene with less noise and enhanced quality.

The proliferation of the Internet of Things (IoT) has had a significant impact in the improvements of localization techniques in wireless sensor networks (WSNs). However, current positing algorithms have shown their limitation in indoor localization and incurred low convergence to accurately predict sensors localization. Thus, there is a need to develop efficient localization algorithms for WSNs to offer better location accuracy and lower energy footprint. This paper explores well known localization algorithms (i.e., Markov optimization model, Gaussian model, Particle Swarm Optimization (PSO), and Salp Swarm Algorithm (SSA)) to assess their capabilities and provides a comparative study, critical discussion and analysis of these algorithms. It describes their algorithms during the self-localization procedure. Empirical results show the performance of these algorithms in terms of energy consumption, location accuracy, and network latency.

Contactless fingerprint authentication has gained popularity as a field of research in biometrics in recent years. Unlike traditional fingerprint recognition systems that require direct contact of the person’s finger with the sensor, contactless fingerprint systems offer several advantages, among them ease of capture and cost-effectiveness. Despite the progress made in this field, poor contrast, background noise, and limited image information continue to pose difficulties for fingerprint recognition in contactless environments. Furthermore, the number of images in published fingerprint biometric datasets for each person is restricted, and there is insufficient data for efficient training. Nevertheless, Convolutional Neural Network (CNN) architectures have been widely used, necessitating large databases. To address these issues, this paper introduces a Siamese network designed for the purpose of identity Verification, using the contactless thumb fingerprint modality to enhance recognition results. The Siamese network is able to extract pertinent features from noisy images with low contrast and limited information, even if they have limited information and low contrast. Additionally, this work proposes the use of the contactless thumb fingerprint modality instead of the contactless index fingerprint modality, which is more commonly used in related works. Consequently, the Mobile FingerPrint (MFP) dataset is introduced and constructed for evaluation. Experimental results demonstrate the efficiency of the proposed method, achieving an accuracy of 98.68% for thumb fingerprint Verification.

The real risk in the privacy of a plain image transmitted over an unsecured connection is content alteration or illegal eavesdropping. The architecture proposed in this paper provides Encryption and Authentication (EA) in their comprehensively for protecting a transmitted image from unauthorized with an average execution time of one second for each 256*256 color image. At the origin point (sender side), it encrypts and signs the image’s content. On the receiver side, it decrypts and verifies the cipher image, achieving two stages of confidentiality and two stages of verification for the image content without depending upon any third party and reinforced with two key chaos equal size color images. Every image has a unique hash value (signature or identity) with QR Code watermarking used to detect forgeries, even if the change is slight (even by one bit). EA has features that make it more resistant to security attacks, as shown by the experiments in this paper.

Parkinson’s disease (PD) is a common and progressive neurodegenerative disorder with motor symptoms and a variety of non-motor symptoms. Experts regularly include handwriting as one of the Parkinsonian motor symptoms of PD and as a valuable tool that can aid in diagnosing and tracking the disease’s progression. PD patients have two periods. ‘On’ time is when levodopa is working well and your symptoms are controlled. ‘Off’ time is when levodopa is no longer working well and symptoms such as tremor, rigidity and slow movement re-emerge. To our knowledge, all existing publicly available datasets allow PD to be identified using only one period. No publicly available online handwriting datasets are dedicated to the analysis of PD using these two periods. Therefore, in this paper, we present our new online Arabic handwriting dataset for analysing PD, which we will make publicly available so that it could potentially be used for diagnosis, screening and monitoring the progression of PD. Our dataset was collected from 30 healthy controls and 30 PD patients in both “off” and “on” at the Neurology Department, Habib Bourguiba Hospital, Sfax, Tunisia. All participants performed five different handwriting tasks. The tasks included drawing repetitive ellipses, a spiral, repetitive digits and Arabic word writing. We hope that our new dataset will help researchers in the early detection of Parkinson’s disease, inpatient rehabilitation and quantification of therapeutic effects.

Facial Expressions Recognition (FER) has become an active area of research. To accomplish emotion recognition, several of machine learning algorithms have been employed. However, these models require a significant amount of data, a large training memory and an important time for training. This paper presents a Facial Expression Recognition method based on ArcFace features and TinySiamese network to solve these problems. The proposed method consists of two parts: the first part is for feature extraction and the second is for feature recognition. In the first part, a feature extractor was used to extract features from the embedded image. The feature extractor was based on a ResNet-50 network and ArcFace loss function. In the second part, the TinySiamese network was used for feature classification and verification. The proposed method was evaluated on three popular datasets: FER2013, RAF-DS, and ExpW. The experimental part shows that the proposed method achieved competitive results compared to related works with classification rates equal to 60.43%, 85.14%, 65.13% and verification rates equal to 73.31%, 84.29%, 76.08% on the FER2013, RAF-DS and ExpW datasets respectively.

Machine learning has become a key driver of technological development, but the rising demand for AI applications involving human interaction necessitates access to large databases of human image data. However, the use of large real-world image datasets, particularly those that contain faces, has given rise to valid privacy concerns. We examine the critical issue of anonymizing image datasets that contain facial information in this paper. We hope to strike a balance between the requirement for data-driven advancements and preserving people’s right to privacy by addressing these issues. In this paper, we propose a new method named FaceAnonym that de-identifies facial images by projecting them onto the latent space of a GAN model. This allows us to preserve the important characteristics of the face, such as shape, expression, and luminance, while still obscuring the identity of the individual. Finally, our method has been shown to be more effective than other methods at de-identifying facial images. It is also fast and easy to use, making it a practical solution for de-identifying large datasets of facial images.

The segmentation of online handwritten Arabic text into graphemes/characters is a challenging task for the recognition system due to the nature of this script. That is why, it is better to employ dependency in the context of segments written before and after it, to improve recognition accuracy. In this paper, we introduce Multi-Head Self-Attention (MHSA) and Bidirectional Gated Recurrent Units (BGRU) models for online handwritten Arabic text segmentation, both of which simulate our previous grapheme segmentation model (GSM). The proposed framework consists of word embedding and the combination of complementary Multi-Head Self-Attention and BGRU, which help detect the control points (CPs) for handwritten text segmentation. The CPs delimit each grapheme composed of three main geometric points: starting point (SP), ligature valley point (LVP), angular point (AP), and ending point (EP). To show the effectiveness of our MHSA-BGRU model for online handwritten segmentation and its comparison with GSM, both mean absolute error (MAE), and word error rate (WER) evaluation metrics are used. Experimental results on benchmark ADAB and online-KHATT datasets show the efficiency of our model, which achieves 3.17% and 5.28% for MAE, 12.25% and 25.13% for WER respectively.

People can be recognized by a lot of unique biometric features either physiological or behavioral. Therefore, a biometric security method for a smartphone is proposed in this paper for easier use and to improve recognition results by using a new knuckle modality: the major knuckle of the thumb finger modality instead of the major knuckle of the middle finger modality which is the most used in related works. In finger knuckle recognition domains, different CNN (Convolutional Neural Network) architectures have been applied, requiring a huge database. To deal with this problem, this paper presents a Siamese network for identity verification using contactless major knuckle of thumb finger modality. Actually, the Siamese network has been well used for one-shot learning that aims at learning and recognizing from little data. The FMK (Finger Major Knuckle) dataset was proposed and constructed for testing and evaluation. In fact, this study achieved good results with accuracy of 82% for the major knuckle of the left thumb finger and 79.63% for the major knuckle of the left middle finger.

To ensure successful innovative development, the living lab needs a robust methodology that can provide the agility in the project development process in order to manage end-users changing requirements. The Framework for Agile Living Lab projects (FALL), that combines the living lab approach with agile methodologies, succeeds in providing the needed agility in the living lab. By considering the smart cities as ultra-large-scale (ULS) systems, FALL is unable to face its expected complexity. Hence, a new regulatory approach is required. In this paper, we propose a Framework for Agile Smart City Open Living Lab (FASCOLL), based on FALL, to make regulations for different smart city projects. Furthermore, we provide a detailed description of the FASCOLL adoption in the management and development process of two work packages, namely educational and social projects.

Telemedicine, particularly when conducted through unprotected connections, necessitates secure delivery of medical data. In the context of medical image transmission, watermarking techniques are frequently employed to enhance the security and privacy of digital content. This paper proposes a secure and blind watermarking algorithm based on spatial domain Least Significant Bit (LSB), chaotic sequences and key point detection using BRISK (Binary Robust Invariant Scalable Keypoints) and GFTT (Good Feature To Track) algorithms, combined with K-means clustering. Chaotic sequences are used for watermark encryption and embedding, ensuring robust security. The algorithm converts the message to binary format, then divides the cover medical image into three bands (red, green, blue) and hides the encrypted watermark within the green and blue bands. The merged bands (red, modified green, modified blue) create the final image with hidden watermark. The proposed approach has undergone experimental investigation within the field of fundus images, which are a specialized form of medical images capturing the back portion of the eye, known as the fundus. In this particular application, fundus images incorporate a watermark encrypting patient-related data and ensuring its integrity during transmission and storage. In addition, integrity check data and other important data are delivered to the recipient to verify the watermark. Through the experimental study, the proposed approach showcases its effectiveness and ability to withstand different attacks, making it highly suitable for secure telemedicine applications.

The diagnosis of common diseases, in which people suffer from several bad health conditions, is a complex medical challenge. This study investigated the use of machine learning methods combined with the Chi-square feature selection technique to improve the accuracy and efficiency of comorbidity diseases diagnosis. Using various decision trees of machine learning algorithms, random forest, Gradient Boost, AdaBoost, Bagging, and extra trees, this research aimed to improve the identification and prediction of comorbid conditions and ultimately advance early detection and treatment strategies. Using the selection of Chi-Square features helped give priority to the most relevant attributes, reduce noise, and refine the models. The results showed that both the AdaBoost and Gradient Boost algorithms obtained an accuracy rate of 91.33%, confirming their efficacy in comorbidity diseases diagnosis. However, it is essential to ensure their reliability and efficacy in the real clinical environment, including the practical implementation and validation of these methods, to improve patient care and medical decisions.

We have witnessed a sharp increase in violence in Tunisia over the past few years. Violence affecting households, minorities, political parties, and public figures has increased more widely on social media. As a result, it has become easier for extremist, racist, misogynistic, and offensive articles, posts, and comments to be shared. Today, various international and governmental groups vowed to fight internet hate speech. This paper proposes a deep-learning solution to find hateful and offensive speech on Arabic social media sites like Facebook. We introduce two models: a Bi-LSTM based on an attention mechanism with integrating the BERT for Facebook comment classification toward hate speech detection. For this task, we collected 2k Tunisian dialect comments from Facebook. The proposed approach has been evaluated on three datasets, and the obtained results demonstrate that the proposed models can improve Arabic hate detection with an accuracy of 98.89%.

Companies need to be creative and flexible, especially regarding customer-specific web applications, because there is a lot of competition, and the market is changing quickly. The hybrid cloud is now a popular choice for businesses that want to make the most of their resources and get things done faster by combining private and public cloud implementations. Some parts of the new apps would be set aside for the private cloud option, while others would be set aside for the public cloud option when the apps were being used. For this, a hybrid algorithm based on GA and BPSO is suggested, which can help keep the successful optimization of service bursting in the hybrid cloud platform. Based on the IBM benchmark, the experiment results show that our advanced algorithm-scored results were less cost-effective than related works experiments.

This paper presents a new$\beta$-Multi-Objective Whale Optimization Algorithm,$\beta$-MOWOA. The$\beta$-MOWOA algorithm uses two profiles to control both exploration and exploitation phases based on the beta function. The exploitation processing step follow a narrow beta distribution, while the exploration phase uses a large Gaussian-like beta. The experimental study focused on 13 Dynamic Multi-Objective Optimization Problems (DMOPs). Comparative results are based on the Wilcoxon signed rank and the one-way ANOVA. Results proven the statistical significance of the$\beta$-MOWOA algorithm toward state of art methods for solving DMOPs: 9/13 problems using Inverted General Distance and 10/13 using Hypervolume Difference.

Machine learning is widely recognized as a key driver of technological progress. Artificial Intelligence (AI) applications that interact with humans require access to vast quantities of human image data. However, the use of large, real-world image datasets containing faces raises serious concerns about privacy. In this paper, we examine the issue of anonymizing image datasets that include faces. Our approach modifies the facial features that contribute to personal identification, resulting in an altered facial appearance that conceals the person's identity. This is achieved without compromising other visual features such as posture, facial expression, and hairstyle while maintaining a natural-looking appearance. Finally, Our method offers adjustable levels of privacy, computationally efficient, and has demonstrated superior performance compared to existing methods.

Cloud computing has allowed the sharing of applications with a lot of data, like scientific workflows. Using scientific workflows to process big data is expensive regarding data transfer, execution time, and bandwidth costs. A data placement method based on fuzzy sets is used to cut these costs. It helps optimize data placement and reduce the costs of processing big data. This paper presents a new method for scientific cloud workflow data placement involving fuzzy sets to realize collaborative clustering. The proposed method explores each data center's datasets through data dependencies, clusters them by the clustering algorithm Fuzzy C-Means (FCM), and re-clusters them based on the data collaboration. Our suggested method of using fuzzy sets to realize collaborative clustering can help cope with uncertainties in data and thus reduce the overall data placement amounts, with better results than previous approaches.

Compared to traditional biometric systems, in-air signatures are considered more robust and secure than classical pen paper. A few datasets capturing in-air signatures have been introduced, utilizing various devices such as the Leap Motion and the Microsoft Kinect sensor camera. However, these devices are not exempt from shortcomings and exhibit certain limitations. The expenses associated with their implementation and the requirement for technical proficiency in operating them present notable challenges for in-air signature analysis. Additionally, users may encounter difficulties in adapting their finger movements to fit within the device's limited field of view, particularly if they lack familiarity with these devices. To address these concerns, this paper proposes the creation of three in-air signature datasets using solely the camera of a laptop or a smartphone, eliminating the need for any additional specialized equipment. Our datasets were collected in three ways. The first is the In-Air Signature dataset (IAS dataset) and the second is the In-Air Signature dataset using a transparent Glass Plate (IASGP dataset) while the third is the In-Air Signature dataset using Smart Phone (IASSP dataset). Forty volunteers participated in the construction of these datasets. Their ages ranged from 21 to 40 years. Each volunteer signs in the air five signatures and imitates five signatures of five other volunteers. Our in-air signatures datasets are publicly available and can be used for various research tasks like in-air signature verification and identification.

In real-world applications such as emotion recognition from recorded brain activity, data are captured from electrodes over time. These signals constitute a multidimensional time series. In this article, Echo State Network (ESN), a recurrent neural network with great success in time series prediction and classification, is optimized with different neural plasticity rules for classification of emotions based on electroencephalogram (EEG) time series. The developed network could automatically extract valid features from EEG signals. We use the filtered signals as the network input and do not take any feature extraction methods. Evaluated on two well-known benchmarks, the DEAP dataset, and the SEED dataset, the performance of the ESN with intrinsic plasticity greatly outperforms the feature-based methods and shows certain advantages compared with other existing methods. Thus, the proposed network can form a more complete and efficient representation, whilst retaining the advantages such as faster learning speed and more reliable performance.

Similarity measures have been widely used in applications dealing with reasoning, classification, and information retrieval. In this article, we first propose three new interval type-2 fuzzy similarity measures (IT-2 FSMs) as a dual concept of some semimetric distances between intuitionistic fuzzy sets (IFSs). We also prove that the extended IT-2 FSMs satisfy many common properties (i.e., reflexivity, transivity, symmetry, and overlapping). Experiments are carried out on a variety of datasets including UCI learning machine and real data. Comparative studies between the proposed IT-2 FSMs and the other well-known existing similarity measures (Gorzalczany, Bustince, Mitchell, Zeng, and Li as well as VSM and Jaccard) are performed. Obviously, the best results are obtained with the IT-2 FSMs being resilient to the high levels of uncertainty noise. We also prove that our IT-2 FSMs can overcome the drawbacks of some existing similarity measures based on the accuracy rate measure. In addition, the proposed IT-2 FSMs are joined with fuzzy C-means algorithm as a clustering method and the proposed system is compared against the existing clustering algorithms (type-1 fuzzy k-means, type-1, and type-2 fuzzy C-means, cluster forest, bagged clustering, evidence accumulation, and random projection). Relying on the clustering quality parameters R and C (equivalent to the standard classification accuracy), the advanced IT-2FSMs show higher classification accuracy of about 86% which outperforms nearly the other classifiers.

In computer-based search systems, similarity plays a key role in replicating the human search process which underlies many natural abilities, such as image recovery, language comprehension, decision-making, or pattern recognition. The search for images consists of establishing a correspondence between the available images and those sought by the user, by measuring the similarity between the images. In fact, image search per content is generally based on the similarity between the visual characteristics of the images. The distance function used to evaluate the similarity between images depends not only on the criteria of the search but also on the representation of the characteristics of the image. This is the main idea of a content-based image retrieval system. In this article, we first constructed type-2 beta fuzzy membership of descriptor vectors to help manage inaccuracy and uncertainty of the characteristics extracted from the feature of images. Subsequently, the retrieved images are ranked according to the novel similarity measure, which is noted type-2 fuzzy nearness measure (IT2FNM). By analogy to type-2 fuzzy logic, and motivated by a near sets theory, we advanced a new fuzzy similarity measure (FSM) noted as IT2FNM. Then, we propose three new IT2FSMs and provide mathematical justification to demonstrate that the proposed FSMs satisfy proximity properties (i.e., reflexivity, transitivity, symmetry, and overlapping). The experimental results generated using three image databases show consistent and significant results.

Urban Traffic Networks are characterized by their high dynamics and increased traffic congestion cases, leading to a more complex road traffic management. The present research work suggests an innovative advanced vehicle guidance system based on Hierarchical Interval Type-2 Fuzzy Logic model optimized by the Particle Swarm Optimization (PSO) method. Indeed, this system allows an intelligent and prompt adjustment of the road traffic network in a dynamic way and improves the entire road network quality, particularly in case of congestions or jams, considering real-time traffic information. The best followed road is selected according to the quality of traffic and route length, together with contextual factors pertaining to the driver, the environment, and the path. The proposed system is executed and simulated using SUMO (Simulation of Urban Mobility), for which four large areas situated in the cities of Sfax, Luxembourg, Bologna and Cologne have been tested. The simulation results proved the effectiveness of learning the Hierarchical Interval Type-2 Fuzzy Logic model using PSO real time technique to accomplish multi-objective optimality regarding two criteria: number of cars that attain their destination and average travel time. The obtained results have confirmed the efficiency of the proposed system.

Traffic congestion is a problem in most large cities world wide. It occurs when the capacity of road is surpassed, resulting in augmented vehicular queuing and slower average speeds. The traffic congestion can be caused or increased by various conditions like weather, road work, road traffic incidents. To deal with these problems, we propose a novel cooperative Multi-Agent system (MAS) for Road Traffic Decision Making in Vehicular Ad-Hoc network (VANET) based on a Hierarchical Interval Type-2 Fuzzy Knowledge Representation System (CMRHFS) used for travel route guidance. Our proposal aims to increase the road safety and the quality of the entire road network, especially in case of congestions, accidents and jams, considering traffic information in real-time as well as drivers travel time to attain their destinations. The obtained simulation results have proved our suggested system efficiency compared to Dijkstra's algorithm and Hierarchical Interval Type-2 Fuzzy Logic System (HIT2FLS) regarding two criteria: average travel time and path flow.

The goal of our project is to help drivers to preplan their trips and overcome the traffic congestion on roads. Unlike the traditional systems which provided the shortest path, travellers and salespersons need a reliable system to guide them to visit several cities or deliver merchandises in different locations in the shortest possible duration. Our system should deal with the different selected locations and get information about the congested roads and the travel time in a dynamic environment to estimate the fastest path.In this paper, we developed a system based on a time-dependent Ant Colony Optimization (ACO) algorithm to solve the problem of finding the fastest traffic path instead of the shortest path. In addition, we implemented a dynamic real tests generator based on big Global Positioning System (GPS) datasets to get information about the traffic states in roads and generate dynamic problem instances. A mobile application has been developed to provide the drivers with accurate details of the path to visit the selected locations as well as the best time to begin the trip to avoid congestion and reach their destination as fast as possible. The exhaustive experimentations have shown the capabilities of the modified time-dependent ACO in solving dynamic optimization problems.

Dynamic Multi-objective optimization problems (DMOPs) involve multiple objectives, constraints, and parameters that may change over time. For solving such types of problems, the conventional particle swarm optimization algorithm should not only be able to evolve near-optimal and diverse optimal solutions but also continually track the time-changing environment. To address these challenges, we propose a novel dynamic multiobjective particle swarm optimization approach with cooperative agents. In this strategy, the ability of tracking based on particle memory and multiple populations with sharing knowledge are combined to deal with environmental changing. If a change is detected, solutions with no improvement are re-evaluated and the worst solutions are replaced with the newly generated one. In addition, a movement strategy based on the sharing of the best knowledge is introduced to promote the population diversity. Experiments on several optimization problems are carried out to prove the performance of the proposed algorithm and the statistical results show that the proposed algorithm performs well with DMOPs.

In multi-criteria decision making (MCDM) methods, if decision makers (DMs) are not able to treat the precise data in order to define their preferences, the intuitionistic fuzzy set (IFS) theory enables them. Therefore, the IFS attributes are connected with the degree of membership and non-membership functions. In this work we propose a new version of the intuitionistic fuzzy PROMETHEE II (IF-PROMETHEE II) method aiming and solving the MCDM problems. A distance and similarity measures are employed to measure the deviations between alternatives on intuitionistic fuzzy sets. We propose to apply the distance and the similarity measure between alternatives to determine the preference matrix. Then, a ranking algorithm is applied to indicate the order of superiority of alternatives. Finally, a practical example is provided for an application of organization evaluations.

Deep learning (DL) has been expensively applied in multiple fields like computer vision, speech recognition and natural language processing. The field of Epileptic seizure prediction didn't receive the deserved attention by DL community, even though, deep neural networks can handle the challenging task of onsets prediction whilst achieving the highest rates of sensitivity, despite the complex nature of EEG signals. In the literature, this issue was addressed differently most of the time using handcrafted temporal and spectral features, machine learning techniques and rarely deep learning with extracted features. In this paper, we introduce an LSTM model designed to address the chaotic nature of an EEG signal in order to predict pre-ictal and inter-ictal states. Our model is evaluated on the publicly available CHBMIT database. We achieved an average sensitivity rate of 0.84 using a Raw EEG data segment as input to the LSTM model.

In this paper, deep EEG feature learning method is proposed for emotion recognition. It is well known that EEG signals dramatically vary from person to person, thereby making subject-independent emotion recognition very challenging. To address the above challenge, this work presents a deep echo state network (DeepESN) to learn temporal representation from raw EEG data. DeepESN as an input-driven discrete time non-linear dynamical system allows to process the temporal information at each time step in a deep temporal fashion by means of a hierarchical composition of multiple levels of recurrent neurons. To make the DeepESN robust, we pre-train the reservoir connections with an unsupervised intrinsic plasticity rule to generate activities following a desired Gaussian distribution. Then, we propose a hybrid learning algorithm for training the output weights which benefits from both the ridge regression and the online delta rule. Our leaky DeepESN achieved encouraging results when tested on the well-known affective benchmarks DEAP and DREAMER.

Following the importance of distance measures in pattern classification, and their application to many kinds of data, crisp, fuzzy, etc, distance measures between intuitionistic fuzzy sets (IFSs) are proposed and generalized to distances between interval valued intuitionistic fuzzy sets (IVIFSs). The measures are applied to pattern classification and to a decision making problem. The measures shows their efficiency in the both domains comparing to some measures from literature.

The main purpose of this work is the study of distance measures between interval valued intuitionistic fuzzy sets (IVIFSs). Thus, some distances from literature are presented and two new measures are proposed. The latter prove their efficiency in pattern recognition and show their superiority in some cases of counter intuitive compared with those from literature, which motivate its application to multi-criteria decision making (MCDM) problems to compute distance degrees between alternatives and ideal solutions and to find the appropriate solution.Comparisons between distance results are performed following their application to MCDM methods under IVIFSs environment.

In this paper, we present an original framework for offline handwriting recognition. Our developed recognition system is based on Sequence to Sequence model employing the encoder decoder LSTM, for recovering temporal order from offline handwriting. Handwriting temporal recovery consists of two parts which are respectively extracting features using a Convolution Neural Network (CNN) followed by an LSTM layer and decoding the encoded vectors to generate temporal information using BLSTM. To produce a human-like velocity, we make a Sampling operation by the consideration of trajectory curvatures. Our work is validated by the LSTM recognition system based on Beta Elliptic model that is applied on Arabic and Latin On/Off dual handwriting character database.

The deep learning-based approaches have proven highly successful in handwriting recognition which represents a challenging task that satisfies its increasingly broad application in mobile devices. Recently, several research initiatives in the area of pattern recognition studies have been introduced. The challenge is more earnest for Arabic scripts due to the inherent cursiveness of their characters, the existence of several groups of similar shape characters, large sizes of respective alphabets, etc. In this paper, we propose an online Arabic character recognition system based on hybrid Beta-Elliptic model (BEM) and convolutional neural network (CNN) feature extractor models and combining deep bidirectional long short-term memory (DBLSTM) and support vector machine (SVM) classifiers. First, we use the extracted online and offline features to make the classification and compare the performance of single classifiers. Second, we proceed by combining the two types of feature-based systems using different combination methods to enhance the global system discriminating power. We have evaluated our system using LMCA and Online-KHATT databases. The obtained recognition rate is in a maximum of 95.48% and 91.55% for the individual systems using the two databases respectively. The combination of the on-line and off-line systems allows improving the accuracy rate to 99.11% and 93.98% using the same databases which exceed the best result for other state-of-the-art systems.

Unconstrained handwriting text recognition is a stimulating field in the branch of pattern recognition. This field is still an open search due to the wide variability of human writing. Recent trends show a potential improvement of recognition by adoption a novel representation of extracted features. In the present paper, we propose a novel feature extraction model by learning a Bag of Features Framework for handwritten text recognition based on Deep Sparse Auto-Encoder. The Hidden Markov Models are then used for sequences modeling. For features learned quality evaluation, our proposed system was tested on two handwritten text datasets IFN/ENIT word images benchmark and MNIST handwritten digits. Our method achieves promising recognition on both datasets.

This paper presents a new methodology for building and evolving hierarchical fuzzy systems. For the system design, a tree-based encoding method is adopted to hierarchically link low-dimensional fuzzy systems. Such tree structural representation has by nature a flexible design offering more adjustable and modifiable structures. The proposed hierarchical structure employs a type-2 beta fuzzy system to cope with the faced uncertainties, and the resulting system is called the hierarchical interval type-2 beta fuzzy system (HT2BFS). For the system optimization, two main tasks of structure learning and parameter tuning are applied. The structure learning phase aims to evolve and learn the structures of a population of the HT2BFS in a multi-objective context taking into account the optimization of both the accuracy and the interpretability metrics. The parameter tuning phase is applied to refine and adjust the parameters of the system. To accomplish these two tasks in the most optimal way, we further employ a multi-agent architecture to provide both a distributed and a cooperative management of the optimization tasks. Agents are divided into two different types based on their functions: a structure agent and a parameter agent. The main function of the structure agent is to perform a multi-objective evolutionary structure learning step by means of the multi-objective immune programming algorithm. The parameter agents have the function of managing different hierarchical structures simultaneously to refine their parameters by means of the hybrid harmony search algorithm. In this architecture, agents use cooperation and communication concepts to create high-performance HT2BFSs. The performance of the proposed system is evaluated by several comparisons with various state-of-the-art approaches on noise-free and noisy time series prediction datasets and regression problems. The results clearly demonstrate a great improvement in accuracy rate, convergence speed, and the number of used rules as compared to other existing approaches.

Deep neural networks have proved promising results in many applications and fields, but they are still assimilated to a black box. Thus, it is very useful to introduce interpretability aspects to prevent the blind application of deep networks. This paper proposed an interpretable morphological convolutional neural network called Morph-CNN for pattern recognition, where morphological operations were incorporated using counter-harmonic mean into the convolutional layer in order to generate enhanced feature maps. Morph-CNN was extensively evaluated on MNIST and SVHN benchmarks for digit recognition. The different tested configurations showed that Morph-CNN outperforms the existing methods.

Reading the text embedded in natural scene images is essential to many applications. In this paper, we propose a method for detecting text in scene images based on multi-level connected component (CC) analysis and learning text component features via convolutional neural networks (CNN), followed by a graph-based grouping of overlapping text boxes. The multi-level CC analysis allows the extraction of redundant text and non-text components at multiple binarization levels to minimize the loss of any potential text candidates. The features of the resulting raw text/non-text components of different granularity levels are learned via a CNN. Those two modules eliminate the need for complex ad-hoc preprocessing steps for finding initial candidates, and the need for hand-designed features to classify such candidates into text or non-text. The components classified as text at different granularity levels, are grouped in a graph based on the overlap of their extended bounding boxes, then, the connected graph components are retained. This eliminates redundant text components and forms words or textlines. When evaluated on the "Robust Reading Competition" dataset for natural scene images, our method achieved better detection results compared to state-of-the-art methods. In addition to its efficacy, our method can be easily adapted to detect multi-oriented or multi-lingual text as it operates at low level initial components, and it does not require such components to be characters.

Presently, cloud computing technologies have enabled to maintain the distribution of massive data applications, such as scientific workflows. They have helped greatly in ensuring the processing of immensely huge scientific data stored among distributed data centers. Actually, the processing of massive data via scientific workflows appears to be costly in terms of data transmission, execution delay and bandwidth cost. Consequently, for the execution workflow and data transmission costs to be noticeably reduced, certain data placement optimization techniques turn out to be necessary. Hence, whenever a workflow task appears to require the location of some datasets in different specified data centers, the placement of massive data volumes turns out to constitute a hard challenge. In the present work, a data placement strategy associated with scientific cloud workflow is advanced, as based on fuzzy c-means clustering technique. Actually, the proposed data placement methodology involves a two-stage strategy. The first stage, an offline one, involves grouping the initial datasets into k data centers, and then, regrouping them via fuzzy c-means technique. In the second stage, the online one, and following execution of the workflow, the generated datasets are placed in the data centers according to their dependencies, based on the application of the same fuzzy c-means technique, too. Eventually, the proposed two-stage strategy appears to be effective in reducing the overall data placement amounts in respect of the state-of-the art strategies.

Remarkable performance on computer vision, and especially on pattern recognition field has been known for a long time to be produced by Deep learning algorithms. It is clear that amongst the successful applications in the pattern recognition domain, Arabic handwriting recognition (AHR) is a must. In this survey, we use two deep networks: Deep Belief Network (DBN) and Convolutional Neural Networks (CNN), for Arabic handwritten script (AHS) recognition. Despite the triumph of DBN and CNN methods, over-fitting is able to take place on these networks thanks to the massive number of parameters. In order to fight over-fitting, we have deeply inquired two regularization techniques called Dropout and DropConnect. While training with the two regularization methods, a randomly chosen subsets of activations/weights are dropped. Consequently, the assessment on the HACDB database to treat character level proves shows an improvement of classification error rate once adding Dropout and DropConnect techniques.

Data clustering is an important step which evolves in many pattern recognition problems and decision making applications. This step had gained great interest and several approaches were proposed to improve the clustering quality. In this context, we proposed a new ensemble clustering system based on the use of a dynamic fuzzy exponent within fuzzy C-Means clustering, an unsupervised feature selection based on the building of a strong feature vector and the use of a modified version of normalized cuts spectral image clustering algorithm applied to general data clustering. The proposed clustering algorithm was validated on eight benchmarks from UC Irvine Machine Learning Repository. Our findings are very promising and prove the effectiveness of our algorithm.

Fuzzy Similarity Measure (FSM) is one of the most used techniques for classification, pattern recognition or knowledge reduction. While many type-1 FSMs exist, few ones exist for type-2 fuzzy sets. In this paper, we introduce three similarity measures between Interval Type-2 Fuzzy Sets (IT-2 FSs) as an extension of some distance measures between Intuitionistic Fuzzy Sets (IFSs). Many definitions and properties are exposed in order to prove that the formulas presented are indeed similarity measures. Experimental results are presented, comparison with other existing type-2 FSMs is done and interpretation is given in order to satisfy FSM properties.

In this work we propose an approach of multi-criteria decision making (MCDM) using Elimination Et Choice Transiting Reality (ELECTRE) methods, interval-valued intuitionistic fuzzy (IVIF) sets and possibility theory. The proposition concerns the computation of concordance sets and discordance sets using possibility measures. The proposed approach is applied to select the best investment projects decision problem from literature. Therefore results are compared and concluding remarks are given.

In the automated search system, similarity is a key concept for solving the human task. The human process is a natural categorization, which underlies many natural abilities such as image recovery, language comprehension, decision making or pattern recognition. In this paper, the focus is on the use of similarities in image retrieval search using near sets of similarity approaches. The results showed that a general framework for Near set is compatible with these foundations, and that similarity measurements can be involved in all steps of the image research process. We therefore focus on the fuzzy logic which provides interesting tools for data mining mainly because of its ability to represent imperfect information. We then introduce a new category of a fuzzy set : the Beta function. We finally illustrate our work with examples of similarities used in the real world of image retrieval problems.

In this paper we proposed a writer adaptation system based on an adaptive fuzzy inference system (AFIS) that can be plug-in for any writer-independent handwriting recognition systems. The AFIS starts with an empty rule set. Subsequently, a supervised incremental learning algorithm is operated. When the user reports a misclassification, rule are added or updated. The proposed learning algorithm is evaluated by the adaptation of a writer-independent recognition system (LipiTk). Moreover, the results using a benchmark database named LaViola prove the efficiency of the proposed system. The error rate reduction varies between 66.32% and 41.05%.

This study addresses evolutionary structure optimization and parameter tuning processes for evolving a proposed Hierarchical interval Type-2 Beta Fuzzy System (HT2BFS). The structure learning phase is performed in a multi-objective context by applying the Multi-Objective Extended Genetic Programming (MOEGP) algorithm. This phase aims to obtain a near-optimal structure of HT2BFS taking into account the optimization of two objectives, which are the accuracy maximization and the number of rules minimization. Moreover, a second parameter tuning phase is also performed in order to refine the parameters of the obtained near-optimal structure by applying the PSO-based Update Memory for Improved Harmony Search (PSOUM-IHS) algorithm. The system's performance is validated through two classification problems. Results prove the efficiency of the proposed approach.

In this paper, we propose to present a novel numerical information fusion method at the feature level. This method is based on the possibility theory using the Beta function and the type1 fuzzy theory. In this method, we proceed to estimate the possibility distribution of the numerical features by using the Beta function. So, we constitute the Beta-possbilistic knowledge base. Then, this Beta-possibilistic knowledge base will be the input of the fuzzy numerical features fusion method. We have evaluated this numerical information method on 15 benchmark databases. Besides, we have compared this method with three numerical information fusion methods in order to determine the best one.

Traffic congestion leads to many problems, namely road users' dissatisfaction, air pollution and waste of time and fuel. For this reason, congestion detection at an early stage is required to perform an efficient exploitation of resources. This paper proposed a Hierarchical Type-2 Beta Fuzzy Knowledge Representation system for the selection of optimal route. Consequently, this system aims to avoid longer travel times, and to decrease traffic accidents and the number of traffic congestion situations. The selection is performed through itineraries assessment by contextual factors such as Max speed and density of a given path. For the validation, the traffic simulation was done with the open source microscopic road traffic simulator SUMO. When compared with the Dijkstra's algorithm, the proposed system showed better performance in terms of average travel time and path flow. These promising results prove the potential of our method to relieve traffic congestion.

The detection and recognition of a vehicle License Plate (LP) is a key technique in most of the applications related to vehicle movement. Moreover, it is a quite popular and active research topic in the field of image processing. Different methods, techniques and algorithms have been developed to detect and recognize LPs. Nevertheless, due to the LP characteristics that vary from one country to another in terms of numbering system, colors, language of characters, fonts and size. Further investigations are still needed in this field in order to make the detection and recognition process very efficient. Although this domain has been covered by a lot of researchers, various existing systems operate under well-defined and controlled conditions. For example, some frameworks require complicated hardware to make good quality images or capture images from vehicles with very slow speed. For this reason the detection and recognition of LPs in different conditions and under several climatic variations remains always difficult to realize with good results. For that, we present in this paper an automatic system for LP detection and recognition based on deep learning approach, which is divided into three parts: detection, segmentation, and character recognition. To detect an LP, many pretreatment steps should be made before applying the first Convolution Neural Network (CNN) model for the classification of plates / non-plates. Subsequently, we apply a few pre-processing steps to segment the LP and finally to recognize all the characters in upper case format (A-Z) and digits (0-9), using a second CNN model with 37 classes. The performance of the suggested system is tested on two datasets which contain images under various conditions, such as poor picture quality, image perspective distortion, bright day, night and complex environment. A great percentage of the results show the accuracy of the suggested system.

Text detection in natural scenes holds great importance in the field of research and still remains a challenge and an important task because of size, various fonts, line orientation, different illumination conditions, weak characters and complex backgrounds in image. The contribution of our proposed method is to filtering out complex backgrounds by combining three strategies. These are enhancing the edge candidate detection in HSV space color using the fractal dimension (FD) to transform the image intensities, then using MSER candidate detection to get different masks applied in HSV space color as well as gray color. After that, we opt for the Stroke Width Transform (SWT) and heuristic filtering. Such strategies are followed so as to maximize the capacity of zones text pixels candidates and distinguish between text boxes and the rest of the image. The components selected non text are filtered by classifying the characters candidates using Support Vector Machines (SVM) exploring Convolutional Neural Networks (CNN) features and Histogram of Oriented Gradients (HOG) vector features. We use the technique of word grouping who the boundary box localization select different words in the image where false positives text blocks are eliminated by geometrical properties. The evaluation of the proposed method demonstrate the effectiveness of our method for complex foreground through the experimental results tested on three benchmarks ICDAR2013, ICDAR2015 and MSRA-TD500.

This paper investigates the problems of stability and synchronization for high-order recurrent neural networks with mixed delays. Firstly, we establish sufficient conditions to ensure the asymptotic stability and then the exponential synchronization. Furthermore, our results are applied to two chosen systems to demonstrate the effectiveness of the obtained theoretical results.

The problems of our life can have many solutions (alternatives) and can be resolved based on different criteria (attributes). Thus, different weight methods exist on literature to accord an importance for each criteria. In this work TOPSIS, multi-criteria decision making (MCDM) method is presented using intuitionistic fuzzy data set with different techniques of weight proposed in literature. Therefore, interval-valued intuitionistic fuzzy TOPSIS (IVIF-TOPSIS) is applied on interval-valued intuitionistic fuzzy data set using methods of weights existing in literature. The latter are interval valued intuitionistic generalization of intuitionistic weights technique. We propose to extend the Standard Deviation (SD) and the preference selection index to interval-valued intuitionistic fuzzy sets for weight computation. Obtained results are compared to assess the impact of weight methods in the resolution of decision making problem.

We introduce a new method Near-Fuzzy set for analysis image. Indeed, near sets are considered a generalization of the rough sets theory. A set X is close to another set Y insofar as the description of at least one of the object of X corresponds to the description of least one of objects of Y. Find the tolerance classes with objects of the same description is a major problem. Maximal Clique Enumeration Algorithm solves the same problem and improves field performance image resemblance. We propose an innovative technique that hybrids both near sets approach with Fuzzy sets approaches. In this paper we use the Near-Fuzzy sets method to obtain better results in the resemblance of facial images. The performance of use of near set approach has been proved throughout the Japanese Female Facial Expression (JAFFE) database.

This paper provides a new method for arranging data sets into clusters. The proposed model, called FlyAntClass, starts from the ants collective sorting behavior and overwrites it with additional behaviors inspired from birds and spiders: in this context, birds' moving behavior is used to control next relative positions for a moving ant; and spiders' homing behavior is provided to manage movements of ants with conflict situation.

Nowadays, Internet users act deeply on Internet content through Web 2.0. They are increasingly directing Web 2.0 and so political, economic, financial and social environments all over the world and particularly in Tunisia that is suffering from environment unsteadiness since the political revolution in 2011. Thus, Web 2.0 monitoring, that requires the use of natural language processing tools, is becoming increasingly necessary. Indeed, Tunisian Web 2.0 monitoring requires the use of Tunisian Arabic processing tools seen that Tunisian Internet users are intensively using Tunisian Arabic for communication. However, Tunisian Arabic is an under-resourced language. Few contributions exist for Tunisian Arabic processing and particularly for Tunisian Arabic morphological analysis. In this case, we suggest an intelligent Tunisian Arabic morphological analyzer that extracts words morphemes and identifies lexical and grammatical labels out of context. For, our analyzer adopts rule-based approach through an expert system and calls aebWordNet and Tunisian Arabic lexical dictionary. In this paper, we present this morphological analyzer that attempts 98.4% as decision and, 58.94% and 84.41% as precision respectively for morphemes decomposition and labeling.

Lying is among the most common wrong human acts that merits spending time thinking about it. The lie detection is until now posing a problem in recent research which aims to develop a non-contact application in order to estimate physiological changes. In this paper, we have proposed a preliminary investigation on which relevant acoustic parameter can be useful to classify lie or truth from speech signal. Our proposed system in is based on the Mel Frequency Cepstral Coefficient (MFCC) commonly used in automatic speech processing on our own constructed database ReLiDDB (ReGIM-Lab Lie Detection DataBase) for both cases lie detection and person voice recognition. We have performed on this database the Support Vector Machines (SVM) classifier using Linear kernel and we have obtained an accuracy of Lie and Truth detection of speech audio respectively 88.23% and 84.52%.

Feature selection is a very important technique in machine learning and pattern classification. Feature selection studies using batch learning methods are inefficient when handling big data in real world, especially when data arrives sequentially. Online Feature Selection is a new paradigm which is more efficient than batch feature selection methods but it still very challenging in large-scale ultra-high dimensional sparse domains. In this paper, we propose a framework of online feature selection for binary classification exploiting first-order and second-order information. This framework is designed to assume an efficient and scalable online feature selection process. In the experimental studies, we adopt first-order and second-order online learning based online feature selection methods FOOL-OFS and SOOL-OFS. We conduct extensive experiments to evaluate the learning accuracy and time cost of different algorithms on several benchmarks and some real-world datasets.

Text detection in natural scenes holds great importance in the field of research and still remains a challenge because of size, various fonts, line orientation, different illumination conditions, weak character and complex background in image. The contribution of the proposed method is filtering out complex backgrounds by utilizing two masks filtering based on text confidence map in the first step and multi-channel maximally stable extremal regions (MSERs) in the second step. Both steps are designed to enhancement, maximize capacity of zones text pixels candidates to distinguish text boxes from the rest of the image. Then non-text components are filtered by the classification of character candidate based on Support Vector Machines (SVM) using HOG features. The false positives are eliminated by geometrical properties of text blocks. Finally we apply boundary box localization after a stage of word grouping. The proposed method has been evaluated on ICDAR 2013 scene text detection competition dataset and the encouraging experiments results demonstrate the robustness of our method.

A spiking neural network model for handwriting movement generation is proposed, in which curvilinear velocity signals are modeled with Beta profiles. In the trajectory domain each Beta profile is replaced by an elliptic arc to fit the initial stroke. The spiking neural network architecture is constituted by an input layer which uploads the Beta-elliptic parameters as input, hidden layer and the output layer where script coordinates X(t) and Y(t) are generated. A separate timing network prepares the initial state of the network. This latter involves the time-index starting time of each simple stroke for an appropriate handwriting movement signal. The experiments showed that our spiking neural network model could be applied for the both cases of Latin and Arabic handwriting scripts. Similarity degree is measured between original scripts and generated scripts to evaluate our model. New ways are proposed for the application of the spiking neural network model such as: generation of complex handwriting movements, signature verification and shape recognition.

The paper handles the problem of segmentation of handwriting on mobile devices. Many applications have been developed in order to facilitate the recognition of handwriting and to skip the limited numbers of keys in keyboards and try to introduce a space of drawing for writing instead of using keyboards. In this one, we will present a mobile theory for the segmentation of for handwriting uses PerTOHS theory, Perceptual Theory of On line Handwriting Segmentation, where handwriting is defined as a sequence of elementary and perceptual codes. In fact, the theory analyzes the written script and tries to learn the handwriting visual codes features in order to generate new ones via the generated perceptual sequences. To get this classification we try to apply the Beta-elliptic model, fuzzy detector and also genetic algorithms in order to get the EPCs (Elementary Perceptual Codes) and GPCs (Global Perceptual Codes) that composed the script. So, we will present our Android application M-PerTOHS for segmentation of handwriting.

In this paper, we treat the supervised data classification, while using the fuzzy random forests that combine the hardiness of the decision trees, the power of the random selection that increases the diversity of the trees in the forest as well as the flexibility of the fuzzy logic for noise. We will be interested in the construction of a forest of fuzzy decision trees. Our system is validated on nine standard classification benchmarks from UCI repository and have the specificity to control some data, to reduce the rate of mistakes and to put in evidence more of hardiness and more of interoperability.

When dealing with real world data; noise, complexity, dimensionality, uncertainty and irrelevance can lead to low performance and insignificant judgment. Fuzzy logic is a powerful tool for controlling conflicting attributes which can have similar effects and close meanings. In this paper, an interval type-2 fuzzy feature selection is presented as a new approach for removing irrelevant features and reducing complexity. We demonstrate how can Feature Selection be joined with Interval Type-2 Fuzzy Logic for keeping significant features and hence reducing time complexity. The proposed method is compared with some other approaches. The results show that the number of attributes is proportionally small.

Two systems of eyes and hand gestures recognition are used to control mobile devices. Based on a real-time video streaming captured from the device's camera, the first system recognizes the motion of user's eyes and the second one detects the static hand gestures. To avoid any confusion between natural and intentional movements we developed a system to fuse the decision coming from eyes and hands gesture recognition systems. The phase of fusion was based on decision tree approach. We conducted a study on 5 volunteers and the results that our system is robust and competitive.

Security and surveillance are vital issues in today’s world. The recent acts of terrorism have highlighted the urgent need for efficient surveillance. There is indeed a need for an automated system for video surveillance which can detect identity and activity of person. In this article, we propose a new paradigm to recognize an aggressive human behavior such as boxing action. Our proposed system for human activity detection includes the use of a fusion between Spatio Temporal Interest Point (STIP) and Histogram of Oriented Gradient (HoG) features. The novel feature called Spatio Temporal Histogram Oriented Gradient (STHOG). To evaluate the robustness of our proposed paradigm with a local application of HoG technique on STIP points, we made experiments on KTH human action dataset based on Multi Class Support Vector Machines classification. The proposed scheme outperforms basic descriptors like HoG and STIP to achieve 82.26% us an accuracy value of classification rate.

This paper highlights a new method for online Arabic handwriting recognition based on graphemes segmentation. The main contribution of our work is to explore the utility of Beta-elliptic model in segmentation and features extraction for online handwriting recognition. Indeed, our method consists in decomposing the input signal into continuous part called graphemes based on Beta-Elliptical model, and classify them according to their position in the pseudo-word. The segmented graphemes are then described by the combination of geometric features and trajectory shape modeling. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results using the benchmarking ADAB Database show the performance of the proposed method.

To control the state of horses in the born, breeders needs a monitoring system with a surveillance camera that can identify and distinguish between horses. We proposed in [5] a method of horse’s identification at a distance using the frontal facial biometric modality. Due to the change of views, the face recognition becomes more difficult. In this paper, the number of images used in our THoDBRL’2015 database (Tunisian Horses DataBase of Regim Lab) is augmented by adding other images of other views. Thus, we used front, right and left profile face’s view. Moreover, we suggested an approach for multiview face recognition. First, we proposed to use the Gabor filter for face characterization. Next, due to the augmentation of the number of images, and the large number of Gabor features, we proposed to test the Deep Neural Network with the auto-encoder to obtain the more pertinent features and to reduce the size of features vector. Finally, we performed the proposed approach on our THoDBRL’2015 database and we used the linear SVM for classification.

This article is focused in developing an improved cluster ensemble method based cluster forests. Cluster forests (CF) is considered as a version of clustering inspired from Random Forests (RF) in the context of clustering for massive data. It aggregates intermediate Fuzzy C-Means (FCM) clustering results via spectral clustering since pseudo-clustering results are presented in the spectral space in order to classify these data sets in the multidimensional data space. One of the main advantages is the use of FCM, which allows building fuzzy membership to all partitions of the datasets due to the fuzzy logic whereas the classical algorithms as K-means permitted to build just hard partitions. In the first place, we ameliorate the CF clustering algorithm with the integration of fuzzy FCM and we compare it with other existing clustering methods. In the second place, we compare K-means and FCM clustering methods with the agglomerative hierarchical clustering (HAC) and other theory presented methods using data benchmarks from UCI repository.

On the light of the remarkable audio-visual effect on modern life, and the massive use of new technologies (smartphones, tablets ...), the image has been given a great importance in the field of communication. Actually, it has become the most effective, attractive and suitable means of communication for transmitting information between different people. Of all the various parts of information that can be extracted from the image, our focus will be particularly on the text. Actually, since its detection and recognition in a natural image is a major problem in many applications, the text has drawn the attention of a great number of researchers in recent years. In this paper, we present a framework for text detection and recognition from natural images for mobile devices.

Text detection in natural scenes holds great importance in the field of research and still remains a challenge and an important task because of size, various fonts, line orientation, different illumination conditions, weak characters and complex backgrounds in image. The contribution of our proposed method is to filtering out complex backgrounds by combining three strategies. These are enhancing the edge candidate detection in HSV space color, then using MSER candidate detection to get different masks applied in HSV space color as well as gray color. After that, we opt for the Stroke Width Transform (SWT) and heuristic filtering. Such strategies are followed so as to maximize the capacity of zones text pixels candidates and distinguish between text boxes and the rest of the image. The non-text components are filtered by classifying the characters candidates based on Support Vector Machines (SVM) using Histogram of Oriented Gradients (HOG) features. Finally we apply boundary box localization after a stage of word grouping where false positives are eliminated by geometrical properties of text blocks. The proposed method has been evaluated on ICDAR 2013 scene text detection competition dataset and the encouraging experiments results demonstrate the robustness of our method.

In recent years, growing attention has been paid to recognizing text in natural scenes images. Scene Character recognition (SCR) is an important step in automatizing the process of reading text in natural scenes. In this paper, we propose a new system which deals with SCR problem. This system is based on a novel Bag of Features (BoF)-based model which use supervised dictionary learning in BoF framework using sparse neural networks models. Thus, in the learning dictionary step, we use a strategy based on neural network model combined with supervised fine-tuning. This technique provide more accuracy and more concise visual dictionary, if we compare it to the most used unsupervised dictionary learning technique like sparse coding. To evaluate our system, we test our proposed method on two English scene character benchmark datasets, i.e, Chars74K and ICDAR2003, and we propose a database of Arabic characters, called ARASTI. Experimental results show the efficiency of this framework for English and Arabic SCR recognition.

Human Action Recognition methods have prospered during the last decade. They seek to automatically analyze ongoing activities in different camera views by using machine-learning algorithms in video sequences. Various human action recognition methods match local features and global features using action class labels in which abundant visual spatio-temporal information can hardly be generalized. To overcome this problem, we propose a novel notion of mid-level representations to construct a discriminative and informative semantic concept for human action recognition. This work introduces a mid-level representation based on the Optical Flow (OF) method, Hu and Zernike moment together. First we extract from each video, Uhand Uvmotion vectors by forming motions curvatures. Second, we determine the Hu moment and Zernike that serve as the feature vector of an action. Our method was tested and evaluated through a classification of the KTH and Weizmann datasets, with an Artificial Neural Network classifier (ANN). The results prove the accuracy of the suggested approach.

This work is concerned with the existence and uniqueness of pseudo almost-periodic solution for a class of impulsive recurrent neural network networks with mixed delays. Some criteria are established to prove the asymptotic stability of the equilibrium point. Tow illustrative an example with numerical simulations are given to show the validity of the main results.

Echo State Networks ESNs are specific kind of recurrent networks providing a black box modeling of dynamic non-linear problems. Their architecture is distinguished by a randomly recurrent hidden infra-structure called dynamic reservoir. Coming up with an efficient reservoir structure depends mainly on selecting the right parameters including the number of neurons and connectivity rate within it. Despite expertise and repeatedly tests, the optimal reservoir topology is hard to be determined in advance. Topology evolving can provide a potential way to define a suitable reservoir according to the problem to be modeled. This last can be mono- or multi-constrained. Throughout this paper, a mono-objective as well as a multi-objective particle swarm optimizations are applied to ESN to provide a set of optimal reservoir architectures. Both accuracy and complexity of the network are considered as objectives to be optimized during the evolution process. These approaches are tested on various benchmarks such as NARMA and Lorenz time series.

The online writer identification is a required component in many applications of Computer vision and Pattern Recognition. The offline writer identification is more developed in literature due to the use of traditional system based on Image Processing. There is a lack of works done in the case of online writer identification. In this paper, we propose a novel method to text independent writer identification from online handwriting. Our proposed method is based on the use of Beta-elliptic model that computes efficiently on real time writing movements in online handwriting by involving simultaneously its both profile entities: the Beta impulses and the elliptic arcs. The information provided by the feature extraction is used in a Deep Neural Network as classifier. The obtained results show that the proposed online writer identification method is worth to receive further exploration in capturing the writer's individual. The use of the Deep Neural Network provides more robustness to identification of writers.

This paper introduces a novel approach for secure navigation of wheelchairs. The approach is based on a combination of robotic road train based navigation and Cloud Computing technologies. The navigation strategy is inspired from elephants. Marching trunk to tail, each wheelchair in a platoon takes cues from the wheelchair just in front of it. The leader of navigation is a person. The cloud computing technologies are used to share wheelchairs positions and to send notifications to caregiver. The role of the caregiver is to lead navigation and to watch in real time the navigation progress and to control the system navigation when problems occur. To improve tracking process, two approaches of obstacle detection and avoidance were developed. Some experimental results are given in the paper to demonstrate the feasibility and performance of the developed system.

Optimization process occurs in many aspects and areas of everyday life. However, the big use of the internet in recent years caused a complex management of large quantities of data that are stored in many different data sources and optimization attend the domain of big data to optimize multi and dynamic data that stored in a complex dataset including all types of transactions in the data sources. So, the diversity of data stored in different data sources caused a complexity to access the information and user find a problem to present the same real world object from different sources in a clear and complementary one representation. Therefore, the high complexity of the representation of a target concept “object” that provided from different data sources, the dynamic feature selection problem based big data fusion present as a solution and a novel approach that will be applicable to solve a dynamic multi-objective optimization feature selection problem (MOOP) based on Multi-Objective Particle Swarm Optimization (MOPSO). This paper carried out on the state-of-the-art of the research done to present an overview of static and dynamic optimization in literature approach, then to define an overview of big data and to present an idea about the future work that will be able to solve the dynamic feature selection based on big data fusion with MOPSO.

Palmprint identification is a popular biometric technology used for personal characterization. Traditional palmprint recognition methods are mostly based on acquisition devices with contact, and this, may affect their user friendliness. In this paper, a toucheless palmprint identification method based on Scale Invariant Feature Transform (SIFT) descriptors and sparse representation method is proposed, in order to extract palmprint features of left and right palms. The fusion scheme is performed at rank level using Support Vector Machines (SVM) classifier and probability distribution to generate the final identity of a person. Experiments evaluated on CASIA palmprint database and a proposed toucheless REST (REgim Sfax Tunisia) hand database, report promising performances which are competitive to other existing palmprint identification methods.

This work is interested to show the importance of possibility theory in multi-criteria decision making (MCDM). Thus, we apply some intuitionistic fuzzy possibility measures from literature to the MCDM method using intuitionistic fuzzy sets (IFSs). These measures are applied to a decision matrix after being transformed with intuitionistic aggregation operators. The results are compared to previous one and concluding remarks are drawn.

In this paper we proposed a writer adaptation system based on an adaptation module that is a plug-in for any writer-independent handwriting recognition systems. The adaptation module is a radial basis function neural network (RBF-NN) that is built using an incremental learning algorithm named GALTM-AM algorithm (Growing-Adjustment with Long-Term Memory). GALTM-AM train a new given data with some LTM data to suppress the interference. Therefore, we design two procedures to manage the LTM data. The first is produce and store. The second is retrieve and learn. This new learning algorithm is evaluated by the adaptation of a writer-independent handwriting recognition system. Moreover, the results using a benchmark database named LaViola prove the efficiency of the proposed GALTM-AM. Performance comparison of GALTM-AM algorithm over the existing approaches is presented.

The automated evolutionary design of an optimal hierarchical fuzzy system combined with the use of Interval Type-2 Fuzzy Systems and the Beta basis function is considered in this study. The resulted proposed system is named the Hierarchical interval Type-2 Beta Fuzzy System (HT2BFS). For the learning process, two main optimizations steps are considered. The first one executes the structure learning of the HT2BFS by the Extended Genetic Programming (EGP) algorithm allowing the generation of an optimal architecture. In the second step, the Opposite-based Particle Swarm Optimization (OPSO) algorithm is employed for the adjustment of parameters existing in the best obtained architecture. The two optimization algorithms are interleaved until an optimal HT2BFS is generated. Experiments on some time-series forecasting problems were performed and prove the effectiveness of the proposed system.

AS-PSO-2Opt is a new enhancement of the AS-PSO method. In the classical AS-PSO, the Ant heuristic is used to optimize the tour length of a Traveling Salesman Problem, TSP, and PSO is applied to optimize three parameters of ACO, (α, β, ρ). The AS-PSO-2Opt consider a post processing resuming path redundancy, helping to improve local solutions and to decrease the probability of falling in local minimum. Applied to TSP, the method allowed retrieving a valuable path solution and a set of fitted parameters for ACO. The performance of the AS-PSO-2Opt is tested on nine different TSP test benches. Experimental results based on a statistical analysis showed that the new proposal performs better than key state of art methods using Genetic algorithm, Neural Network and ACO algorithm. The AS-PSO-2Opt performs better than close related methods such as PSO-ACO-3Opt [9] and ACO with ABC [19] for various test benches.

This paper describes a method for extracting relevant tokens of entity from semi-structured administrative documents. This method is used for mislabeling correction by employing the entity tokens physically close in a document. Firstly, the entities are labeled. Secondly, each entity is modeled by a tokens structure graph in which the nodes represent the tokens and the arcs represent the distances. A clustering algorithm is then applied to incrementally concatenate the relevant tokens of entities and ignore the noisy parts. The obtained results with a dataset of real invoices are reported in experimental section.

Information fusion is a research domain that strives to establish theories that exploit and analyze the data retrieved from multiple sources. Generally, these fusion theories try to combine these data for a classification task and to make the decision efficiently. The possibility theory is one of the most known in the information fusion domain. So, the possibility distribution estimation step represents the key element of success of the fusion process based on possibilistic reasoning. In the framework of the possibility theory, we will concentrate to study the conditional possibilities distributions existing in the literature. Therefore, in this paper, we propose to present a comparative study of the different existing conditional possibilities to fuse numerical information. For this fact, we have evaluated each conditional possibility definition on 15 benchmark databases in order to deduct the best one. Thus, the experiments results provide insights that can help the researchers in the fusion information to increase the performance of its fusion/classification systems by the choosing of the most appropriate conditional possibility distribution.

Assessing E-commerce web sites quality is essential not only to have recommendations for improvement but also to make comparisons with competitors. In this paper, the aim is to know the best criteria for the evaluation and obtain a weight for them using fuzzy Analytic Network Process (fuzzy ANP). The subjective judgments of the decision maker are expressed by fuzzy numbers. The decision making problem is solved by making fuzzy pairwise comparisons and a feedback between the criteria.

Online Feature Selection (OFS) is an important technique in pattern recognition and machine learning. Our challenge is how to enhance the classification performance in real contexts where the large-scale training data arrive sequentially with a big number of features. The major problem is how to choose the best accurate and efficient state-of-the art OFS method that can select the relevant features or if we do a combination between these methods can we improve the classification performance? In this paper, we propose a framework of OFS using the characteristics of multi-agent systems (MAS) to overcome this challenge. We propose firstly a new OFS model; Agent-Learner based OFS (ALOFS) which represents each agent in our MAS. ALOFS is a generalization of first-order and second-order online learning methods based feature selection. Secondly, we propose the Multi Agent-Learner based OFS (MALOFS) system which is our MAS. MALOFS uses two levels of selection: the first level aims to select the more confident learners and the second level has as object to select the relevant features using a proposed negotiation method (MANOFS). MALOFS is applicable to different domains successfully and achieves highly accuracy with some real world applications.

Recently crowded cities are having an increasing need for an advanced parking management system to help drivers to locate the vacant and available parking places in real time. In this study, the authors propose a novel multi agent parking lots management system based on vision approach to detect and localise the vacant parking places at a city level and to provide drivers with relevant information in real time. The elaboration of a multi agent approach for parking places modelling enable the cooperation between different agents in order to improve the results of the proposed system and to detect different cases of anomalies and abnormal situations that can be caused by the drivers, such as the cases where parked cars affect the state of more than one place or when a car blocks the access to parking lots.

Super‐resolution (SR) task has become an important research area due to the rapidly growing interest for high quality images in various computer vision and pattern recognition applications. This has led to the emergence of various SR approaches. According to the number of input images, two kinds of approaches could be distinguished: single or multi‐input based approaches. Certainly, processing multiple inputs could lead to an interesting output, but this is not the case mainly for textual image processing. This study focuses on single image‐based approaches. Most of the existing methods have been successfully applied on natural images. Nevertheless, their direct application on textual images is not enough efficient due to the specificities that distinguish these particular images from natural images. Therefore, SR approaches especially suited for textual images are proposed in the literature. Previous overviews of SR methods have been concentrated on natural images application with no real application on the textual ones. Thus, this study aims to tackle this lack by surveying methods that are mainly designed for enhancing low‐resolution textual images. The authors further criticise these methods and discuss areas which promise improvements in such task. To the best of the authors’ knowledge, this survey is the first investigation in the literature.

Many engineering processes use custom Android kernel to perform specific tasks. These applications often rely on extensive manual intervention and expert skills to modify existing files or add new libraries. In this paper, we describe a novel system for customizing and adding new features to Android system with one click. Use of this integration framework reduces turnaround time, reduces likelihood of errors, and high level knowledge to establish a properly modification of Android OS. The modular architecture allows the addition of custom modules with minimal effort. Preliminary experimental results on real world Android devices show the feasibility of the approach and encourage further research activities. To illustrate the effectiveness of The framework described here, we used it to implement a telepresence robot.

Human hand is a physiological biometric trait employed in order to characterize and identify an individual. It is considered as one of the most popular biometric technologies especially in forensic applications, due to its high users acceptance compared to other biometric technologies. In this paper, we propose a new hand biometric system for personal identity verification, combining two local features at matching score level. Indeed, these features are represented by SIFT (Scale Invariant Feature Transform) descriptors and geometrical measurements of the hand. Our experiments are evaluated using Bogazici University Hand database containing 1926 left hand images acquired from 642 subjects and showed promising results which are comparable with other approaches.

This paper introduces a novel approach for secure navigation of wheelchairs. The approach is based on a combination of robotic road train based navigation and Cloud Computing technologies. The navigation strategy is inspired from elephants. Marching trunk to tail, each wheelchair in a platoon takes cues from the wheelchair just in front of it. The wheelchair also communicates directly with the leader in order to anticipate any turns or braking action. The cloud computing technologies are used to perform shared computations and remote teleoperation by a caregiver. Caregivers are persons connected through cloud interfaces. Their role is to watch in real time the navigation progress and to control the system navigation when problems occur. Some experimental results are given in the paper to demonstrate the feasibility and performance of the developed system.

In this paper, a Multi-Objective Extended Genetic Programming (MOEGP) algorithm is developed to evolve the structure of the Hierarchical Flexible Beta Fuzzy System (HFBFS). The proposed algorithm allows finding the best representation of the hierarchical fuzzy system while trying to attain the desired balance of accuracy/interpretability. Furthermore, the free parameters (Beta membership functions and the consequent parts of rules) encoded in the best structure are tuned by applying the hybrid Bacterial Foraging Optimization Algorithm (the hybrid BFOA). The proposed methodology interleaves both MOEGP and the hybrid BFOA for the structure and the parameter optimization respectively until a satisfactory HFBFS is found. The performance of the approach is evaluated using several classification datasets with low and high input dimensions. Results prove the superiority of our method as compared with other existing works.

Intuitionistic fuzzy sets (IFSs) are used in methods of multi-criteria decision making. Some techniques are used in each method to use intuitionistic fuzzy information. Therefore, crisp methods can be changed to use IFSs information. The latter are used in Technique for order performance by similarity to ideal solution (TOPSIS), Analytic Hierarchy Process (AHP) and in VIKOR. We apply These methods in Human Capital Indicators (HCI) [1] and we compare them to distinguish differences between used techniques.

In MCDM problems some criteria (attributes) having different importance are used to determine a best alternative from many. Thus, different weight methods exist in literature to evaluate the importance of each criteria. In this work TOPSIS, multi-criteria decision making (MCDM) method is applied using crisp data set with different techniques of weight proposed in literature. Therefore, intuitionistic fuzzy TOPSIS is applied on intuitionistic fuzzy data set (IFS) using methods of weights existing in literature. The latter are intuitionistic generalization of crisp weights. We propose to extend two methods of weight computation, the Standard Deviation (SD) and the preference selection index (PSI) to intuitionistic fuzzy sets. Obtained results are compared to assess the impact of methods of weight in the result of decision making methods.

Character classification is the most important step in automatizing the process of reading text in natural scenes. The detection and the recognition of characters, needed in the end-to-end system, depend mainly on the robustness of the character classifier. Furthermore, Arabic characters classification need specific framework to deal with problems of their complexity and their diversity. In our work, we choose to use local feature representations since local features represent an efficient tool for dealing with problems of variability of size and color of text and problems of camera-based images. Adapting the Bag of Feature (BoF) technique to represent local features was extremely used in recent years. However, the BoF method removes the spatial information of local descriptors, which restricts the descriptive power for image representation. To solve this problem, we use Spatial Pyramid Matching (SPM). For the feature representation step, we choose to use sparse coding of Sift features. In this paper, we present a robust classification framework for Arabic Scene Text Characters (STC). Our architecture is based on the use of an adopted BoF model using SPM method and sparse coding to represent features. To evaluate our system, we propose a database of Arabic characters, called ARASTEC, since there aren't any such previous databases. Experimental results show the efficiency of this framework for Arabic STC recognition.

Current issues on textual image magnification have been focused on noise-free low-resolution images. Nevertheless, real circumstances are far from these assumptions and existing systems are generally confronted with noisy images; limiting thus the efficiency of the magnification process. The scope of this study is to propose a joint denoising and magnification system based on sparse coding to tackle such a problem. The underlying idea suggests the representation of an image patch by a linear combination of few elements from a suitable dictionary. The proposed system uses both online and offline learned dictionaries that are selected adaptively for each image patch of the input Low-Resolution (LR) noisy image to generate its corresponding noise-free High-Resolution (HR) version. In fact, the online learned dictionaries are trained on a clustered dataset of the image patches selected from the input image and used for the denoising purpose in order to take benefit of the non-local self-similarity assumption in textual images. For the offline learned dictionaries, they are trained on an external LR/HR image patch pair dataset and employed for the magnification purpose. The performance of the proposed system is evaluated visually and quantitatively on different LR noisy textual images and promising results are achieved when compared with other existing systems and conventional approaches dealing with such kind of images.

The major issue of researchers in ANN field is the optimization of the training process including time cost and NN structure. In response to the long training time, Multi-Agent architecture of feed forward Flexible Neural Tree model (MAFNT) is introduced for parallelizing the NN training. Moreover, looking for the best topology of NN, for a given problem, accounts for the large feasible solutions provided. Agents manage different NN structures simultaneously for optimization using Evolutionary Computation algorithms. However, different agents need communications to produce cooperative work and to reach the near-optimum solution. For that, a negotiation process is designed for the multi-agent system. It distributes tasks and organizes the message traffic between agents. They followed negotiation strategy to ensure interactions between themselves, overcoming the difference of NN structures. This model was evaluated through real problem classification datasets. Compared to some existing classifiers, MAFNT shows better performance respecting NN structure complexity and classification rate.

Personal wireless communication and digital multimedia information devices become widely available and extensively used. These devices require more and more developed video codecs. Hence, several video coding standards motivate developers to innovate and improve them. The block of Motion Estimation (ME) is an important module in all recent video coders. This paper presents REGIM Video Coding (REGIM-VC) as a new video coding technique. REGIM-VC proposes an efficient motion estimation algorithm based on block matching. The proposed algorithm purpose is to improve the compression performance by applying new Motion Estimation techniques. For this reason, it reduces the search points number in Motion Estimation block of video codec. Consequently, it saves significantly the bit-rate and the computational time.

In this paper we propose a new Hybrid Bat Algorithm to solve the traveling salesman problem (TSP) that has attracted many researchers applying exact and metaheuristic methods trying to solve it. The new proposed method is based on the basics of Bat Algorithm (BA) recently proposed as a new bio-inspired meta-heuristic algorithm. Accordingly, we use the concepts of Swap Operator (SO) and Swap Sequence (SS) to redefine respectively BA position and velocity operators for TSP. Additionally, based on ordered crossover and 3-Opt algorithm, we propose to redefine the Bat's local search method. We compare our algorithm to other state of the art methods from the literature by using benchmark datasets of symmetric TSP from TSPLIB library in order to test its effectiveness. Based on the recorded experiments our method outperforms most of the compared methods.

The data fusion architecture has an important role in the efficiency of the processed information and the significance of the made decision at the output level. For this reason, we choose to concentrate this paper on architectures of systems working on information fusion. This will allow scientists to have an idea about which architecture is more suitable to their application, and in which step one can work in order to modify the information fusion process or to ameliorate a given framework.

This work presents theoretical research on the global exponential synchronization of second-order RNNs with mixed delays. Basing on the Halanay inequality lemma and the Lyapunov stability method, several assumptions are proposed to guarantee the synchronization of two RNNs systems. Finally, we propose a numerical example to show the presented exponential synchronization curve.

In this paper a new approach to video event detection is presented. This approach is based on HOG/HOF features optimized by an auto-associative neural network models for feature reduction and an incremental SVM model for event classification. This auto-associative neural network models are frequently used to reduce the size of feature vectors. In our approach, each event is modeled by a set of states, and each state is represented by a learning model containing a positive class (event) and a negative class (non-event). Experiments on real video sequences have shown encouraging results.

Human hand is a physiological biometric trait employed in order to characterize and identify a person. It is considered as one of the most popular biometric technologies especially in forensic applications, due to its high users acceptance compared to other biometric technologies. In this paper, we propose a hand biometric system for personal identity verification, fusing multiple features of the hand at matching score level. In fact, shape and texture are extracted from hand, fingers and palmprint in order to represent the hand image of each person. In the feature extraction strategy, the scale Invariant Feature Transform (SIFT) is extracted from the hand image to describe local invariant features of the hands contour and also extracted from fingers images. In the other hand, Gabor filters are extracted from palmprint images to describe the texture of the hand. The main advantage of these two descriptors (SIFT and Gabor) is that features extracted are invariant to rotation, translation, scale and lighting changes. Personal verification was performed by fusing similarity scores achieved from the hand shape, the fingers and the palmprint. Experimental results show good performances (EER=1.95%) in hand verification using a database containing 230 different subjects.

This paper proposes an automatic text-independent online Arabic writer identification system. The main contribution of our system is to explore the utility of Beta-elliptic model in features extraction for online writer identification, due to the rich output of Beta-elliptic model in terms of graphical, kinematical and biometrical data. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results on ADAB Database show the performance of the proposed system in online Arabic writer identification task.

In this paper, we try to analyze drowsiness which is a major factor in many traffic accidents due to the clear decline in the attention and recognition of danger drivers. The object of this work is to develop an automatic method to evaluate the drowsiness stage by analysis of EEG signals records. The absolute band power of the EEG signal was computed by taking the Fast Fourier Transform (FFT) of the time series signal. Finally, the algorithm developed in this work has been improved on eight samples from the Physionet sleep-EDF database.

The mobile human-computer interaction is aiming to facilitate communication with the mobile devices. The hand gesture recognition is considered as the most important alternative that can be deployed because it is natural, intuitive and easy to use. In this paper, we proposed our system of static hand gesture recognition to control mobile devices based only on a real time video streaming capture from the front-facing camera of the device. Our proposed system is based on the skin colour algorithm and face subtraction to detect hand area. The features derived from contour extraction, convex hull detection, convexity defects extraction and the palm center detection are used on SVM classifier for the recognition step. This system, running on an Android tablet, achieves 96,8% of recognition rate that proves the robustness of our system. We applied the parallelism techniques to ensure the respect of real time constraint and realise a 23 fps.

This paper is a tentative to describe the basics of dynamic optimization using swarm & evolutionary methods. Computational intelligence methods based on swarming, collaborative computing and related techniques showed their potentials at solving classical static problems; for dynamic problems new paradigms needs to be established, this concerns the methods, the test benches and the performance evaluation processes. A review of the key population based computational techniques is performed prior to set some perspective guidelines on how to handle the multi-objective dynamic problems using these technique.

In this paper, we provide an improvement of the circuit implementation of a one-layer recurrent neural network for support vector machine learning in pattern classification and regression. Our goal is to reduce the complexity of this architecture. Numerical example with graphical illustration is given to illuminate our main results.

This paper describes a novel bio-inspired metaheuristic named ASClass for data clustering problem. The particular principles used for the design of this strategy are inspired by the foraging behavior observed in ant colony. In this technique, an ant colony optimization algorithm is used to search a closed tour of minimal length connecting n objects in database. The process of building path-object is inspired by the collective weaving observed in social spiders.

This paper presents the principal phase of extraction and recognition of the basic emotions in the Arabic speech applied to five emotional states were taken into effect; neutral, sadness, fear, anger and happiness. Emotional speech database REGIM_TES [1] was created and evaluated to provide all practical experiences of extraction. The selected descriptors in our study are; Pitch of voice, Energy, MFCCs, Formant, LPC and the spectrogram. Descriptors showed the importance of the Arabic language on the physiological events and the influence of culture on emotional behavior. A comparative study between the kernel functions has enabled us to promote the RBF kernel SVMs multiclass classifier [15] performing the classification phase.

In this paper we proposed a new deep neural network architecture which is composed from a radial basis function neural network (RBF NN) followed by two auto-encoders and softmax classifier and we presented some comparison between this architecture and other architecture on numeral recognition applications. We gave also a review about RBF and sparse auto-encoder neural networks in the literature. First we defined neural networks and their different type's especially radial basis function neural networks (RBF NN) due to their specificity. Second we focused on auto-encoders and sparse coding then we moved to sparse auto-encoders and finally we demonstrated the effectiveness of our deep architecture by showing our experimental results and some comparisons.

This paper presents a comprehensive experimental study on face recognition to prove that holistic approaches are more robust than geometric and local approaches in order to address the problem of which method holistic or geometric can assist to face recognition. This work is done based on the motivation to integrate soft biometric traits into face recognition systems using same computing. A bag of features extraction and classification combined with each other to find the most appropriate technique that can enhance face recognition task. The experimental study shows that the texture information is discriminant in facial images representation, Gabor filter is more useful than Local Binary Pattern, a space dimensionality reduction using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) is very interesting to increase recognition rates. The fusion between Gabor, PCA or LDA and Multi class Support Vector Machines (SVM) ranks top the list of all other combinations.These techniques will be performed later to integrate soft biometrics.

Multiple Criteria Decision Making (MCDM) is widely used in everyday life especially to make decisions between conflicted criteria. In this paper, MCDM is explored in the Web domain that plays a major role in the modern society. A web site can provide or not users' needs. Assess the quality of web sites requires a list of criteria and sub-criteria, they depend also on web site category. So, to qualify criteria versus others it is important to resort to Multi-Criteria decision Making method. Weighing criteria, ranking web sites or other purposes of assessment can be resolved by MCDM. This paper identifies and discusses some methods and techniques in this area; it proposes also a comparative study between them and concludes with some findings discussions and future issues.

Feature selection is an important technique in machine learning and pattern classification. Most existing studies of feature selection are using the batch learning methods. Such methods are not appropriate for real-world applications especially when data arrive sequentially. Recently, this problem is addressed by some feature selection techniques using online learning. Despite the advantages in efficiency of online feature selection methods, they are not always accurate enough when handling real world data. In this paper, we address this limitation by the integration of automated negotiation process. We present a novel method based on negotiation theory for online feature selection (ANOFS) and demonstrate its application to several public datasets.

Interlinking multimedia resources (video, photo, music, etc) with Linked Open Data will enrich multimedia content and make it connected to the web of linked Data. Especially, DBpedia which represents the central interlinking hub for the emerging Web of Data. Currently, the Web of interlinked data sources around DBpedia covers several domains as companies, people, music, films, drugs, books, geographic information and scientific publications. This paper presents a system that enrich video program with linked open data. We detail the proposed architecture, and we focus on the interlinking process, the encountered problems and the adopted process to address to this problem.

Text detection from images in natural scene is one of the most active research areas. It still remains a challenge for researchers because of the complexity of the image in the wild specifically their background. The state of the text presents also different problems of localization such as size, font, color and orientation. This paper presents a new method based on the location of the concentration areas of text candidates in first step. This step allows a mask is applied, the major objective is to filter the maximum the complex background. We use Otsu technique and edge enhancement by pyramid image in different scales. The second step is to fine detection of candidate characters by maximally stable extremal regions (MSER) based on the luminance that gives more meaning to information merged with enhanced edges and connected to surpass the limits of MSER. Then non-text components are filtered out by the character candidate classification based on DTW using SIFT and HOG features. The false positives are eliminated by geometrical properties of text blocks. Finally we apply boundary box localization after a stage of word grouping. The proposed method has been evaluated on ICDAR 2013 scene text detection competition dataset and the encouraging experiments results can be compared with the latest published algorithms.

The road traffic becomes more complex to manage because of the high dynamics of traffic flow and the rise of travel time when the number of vehicles augments in the road networks. Hence, the shortest itinerary based on route length (as provided by GPS navigators) cannot be the best solution nowadays. The application of type-2 Fuzzy Logic is regarded as an effective way for transportation engineering to prevent the problem of ambiguity and uncertainty of road perceptions. In this paper, we propose a hierarchical type-2 Fuzzy Logic System to evaluate itinerary by integrating contextual factors influencing the route choice like speed and road work information.

Nowadays the emergence of mobile devises and Cloud Computing can change the culture of healthcare from direct care services into Mobile Cloud computing (MCC) services. For that, the application targeted at mobile devices becoming copious with others systems in healthcare sector. Consequently, we assume that this technology have a potential effect in healthcare domain. MCC offers new kinds of services and facilities medical tasks. In this regard, we have tried to propose a new mobile medical web service system. The proposed system called Medical Mobile Cloud Multi Agent System (2MCMAS) is a hybrid system which integrates MCC and Multi Agent System in healthcare in order to make efficiency care.

In this paper we introduce the Interval type-2 Beta fuzzy set as a membership function in a Fuzzy Logic System (FLS). First order derivatives of type-1 and type-2 Beta functions were developed for designing fuzzy logic systems based on given input-output pairs. Then, the steepest descent algorithm is used to train Beta fuzzy basis functions to obtain the final fuzzy system. The performance of the proposed model of Beta fuzzy logic system is evaluated using the benchmark of Forecasting of Time-Series and is compared to fuzzy systems using Gaussian membership functions as a popular example of shapes.

Echo state networks (ESNs) fulfill considerable promises for topology fine-tuning in supervised training. However the randomness of the setting of ESN weights initialization affects badly the learning performance. On the other side, Particle Swarm Optimization (PSO) has proven its efficiency as an optimization tool to puzzle out optimal solutions in complex space. In this work, we present an ESN architecture to which we associate a PSO algorithm to pre-train the weights within the network layers. A random distribution of the weights matrices is firstly performed. Then, these weights are pre-trained in order to fit the application requirements. Once optimized, they are re-injected into the ESN model which, in its turn, undergoes a training process followed by a test phase. A comparison between the network performances before and after optimization process is performed. Empirical results show a reduction of learning errors in the case of PSO use.

Horses recognition is an important task especially for horses' trainers. It is necessary in this case to identify each horse to be distinguished. All methods used for identification are invasive and threaten the well-being of horses like Tatto and Freeze branding. So, for this reason we aim to create a human method of identification using the facial biometric modality. We tested the Gabor and LBP features for face characterization and the Euclidian and Mahcosine distance for classification. We performed our approaches on our database "THoFDRL'2015 database: Horses Face Database of REGIM Lab" and we used only horses' faces in front view. These faces are considered for experimentation. The recognition rate is 95.74%. This result maintains the success of our approach in horse recognition.

The goal of our project is to explore the already installed video surveillance cameras in the cities to provide an intelligent vision based approach for vacant parking lots detection and drivers' guidance. Our system should be able to treat huge number of parking stations in the town and to supply a real time information about the vacancies and their locations. The concept of distributed and extensible system is dominant in our case, so the need to the adoption of a Multi Agent implementation to ensure the interoperability, the autonomy, and the ability to take initiative and to interact with the external environment. In this paper we will present a general architecture of a Multi Agent Parking Lots Management system based on vision techniques dedicated to cover multiple parking stations at a city level. We will also demonstrate the importance of the elaboration of multi agent approach at this level to benefit from the cooperation and negotiation between agents in order to ameliorate the results of the already existent approaches.

This paper presents a multi-robot system for an intelligent wheelchair. This system creates maps of the environment using SLAM (Simultaneous Localization And Mapping) algorithm and partially updates this maps around the planned trajectory after fixing the target by the user. Temporary obstacles like humans, animals, closed doors ... Are not considered in the updating process. An object recognition block is developed to classify detected objects before adding them to the map. Some experimental results are given in the paper to demonstrate the feasibility and performance of the developed system.

Providing a semantic access to video data requires the development of concept detectors. However, semantic concepts detection is a hard task due to the large intra-class and the small inter-class variability of content. Moreover, semantic concepts co-occur together in various contexts and their occurrence may vary from one to another. Thus, it is interesting to exploit this knowledge in order to achieve satisfactory performances. In this paper we present a generic semantic video indexing scheme, called SVI_REGIMVid. It is based on three levels of analysis. The first level (level1) focuses on low-level processing such as video shot boundary/key-frame detection, annotation tools, key-points detection and visual features extraction tools. The second level (level2) aims to build the semantic models for supervised learning of concepts/contexts. The third level (level3) enriches the semantic interpretation of concepts/contexts by exploiting fuzzy knowledge. The obtained experimental results are promising for a semantic concept/context detection process.

In this paper, a PSO-based update memory for Improved Harmony Search (PSOUM-IHS) algorithm is proposed to learn the parameters of Flexible Beta Basis Function Neural Tree (FBBFNT) model. These parameters are the Beta parameters of each flexible node and the connected weights of the network. Furthermore, the FBBFNT's structure is generated and optimized by the Extended Genetic Programming (EGP) algorithm. The combination of the PSOUM-IHS and EGP in the same algorithm is so used to evolve the FBBFNT model. The performance of the proposed evolving neural network is evaluated for nonlinear systems of prediction and identification and then compared with those of related models.

In this paper, we present an integrated system able to localize multi-oriented handwritten annotations in scanned documents. Unlike previous single methods which limit colors or types of annotations to be extracted, the proposed method attempts to extract annotations by fusing three feature extraction techniques based on internal and external shape analysis. Our method consists of two processes: 1) a coarse segmentation process which divides the scanned document into text and non-text regions. 2) A fine segmentation process which consists of three steps: a feature extraction process, a classification process and a majority voting process which identifies the segmented regions as machine-printed or handwritten annotations. We find that our adaptive method outperform all individual methods. Experimental results on a set of 301 annotated scanned documents are reported.

This paper provides an overview on a new evolutionary approach based on an intelligent multi-agent architecture to design Beta fuzzy systems (BFSs). The Methodology consists of two processes, a learning process using a clustering technique for the automated design of an initial Beta fuzzy system, and a multi-agent tuning process based on Particle Swarm Optimization algorithm to deal with the optimization of membership functions parameters and rule base. In this approach, dynamic agents use communication and interaction concepts to generate high-performance fuzzy systems. Experiments on several data sets were performed to show the effectiveness of the proposed method in terms of accuracy and convergence speed.

In this paper, we propose, a semi-automatic approach for the identification of Regions Of Interest (ROI) of the kidneys (healthy and diseased) on dynamic scintigraphic images. The triggering of the method depend on the intervention of an expert, such as a specialist in nuclear medicine. Our contribution is made obvious here through referring to the adaptive threshold relying on the calculation of the gradients histogram and thus accurately detecting the places of the region of interest. The adaptive threshold will be the average of the histogram of the matrix of the calculated gradients. This approach was tested on dynamic scintigraphic images acquired clinically and satisfactory results are obtained.

In this paper, we apply the Beta Basis Function Neural Network (BBFNN) trained with cuckoo search (CS) for time series predictions. The cuckoo search algorithm optimizes the network parameters. In order to evaluate the effectiveness of the proposed method, we have carried out some experiments on four data sets: Mackey Glass, Lorenz attractor, Henon map and Box-Jenkins. We give also simulation examples to compare the effectiveness of the model with the other known methods in the literature. The results show that the CS-BBFNN model produces a better generalization performance.

This paper describes a process of converting raw Global Positioning System (GPS) data to a routable road map. In fact, it is a large scale database collected from thousands of vehicles circulating on Tunisian public roads. Moreover, the paper contains the architecture used to collect GPS data from these vehicles using GPRS connection and all the steps until getting the road traces. The data flow is composed of many steps which are: Collecting data which consists of extracting National Marine Electronics Association(NMEA) sentences; Filtering raw GPS nodes to eliminate outliers and noise caused by several sources of errors; Clustering step, in which we used two methods partitional (k-means)and hierarchical (agglomerative)clustering techniques. We compare them and we choose the most suitable for our work. In fact, K-means algorithm is carried out in order to partition data and facilitate handling the big data sets; Generating a Tunisian map network from our database and map-matching it with Google maps in order to make a comparison between them.

In this paper, query sound-by-example video retrieval framework based on audio concepts is presented. First, audio stream extracted from movies in the database is set into orientation clusters using an unsupervised segmentation technique. Audio signals admit a new proposed particular pretreatment process to distinguish audio concepts. This is used for indexing the video data. Second, the query asked by the user, in sound signal form, is treated. Finally, a specific retrieval function is used to obtain video shot containing the sound of query. Objective evaluation reached 89% retrieval performance.

Autonomous MultiRobot Systems are developing useful capabilities in several fields of applications as surveillance, exploration and space cleaning. Moreover, important features are of robotics' environments like avoid collision and planning should be handled. Furthermore, the distributed planning approaches, considered as MultiAgent planning, can be thought as a specialization of distributed problem solving. Therefore, this paper started by propounds a review on some planning approaches for MultiRobot Systems and describes the subsumption architecture of the mobile robot control in the MultiRobot system by highlighting the lowest level which is the obstacle avoidance using the soft computing technique. We present also in this research a simulation of MultiRobot for parallel spaces cleaning.

The amount of circulating data on the internet has witnessed a considerable increase during the last decades. A web site is the main source that provides users' needs. However, some of the existing web sites are not well intentioned by users. Many studies have treated the problem of assessing the web sites' quality of different categories such as ecommerce, education, entertainment, health, etc. The problematic implies a multiple criteria decision making (MCDM) due to the multiple conflicting criteria for assessment. Existing methods are mainly based on making a hierarchy to divide high level criteria, sub-level criteria and alternatives. There is no standard until now that defines important criteria for evaluation. Indeed, this paper presents a process of collecting and extracting data from a list of studies according to a Systematic Literature Review (SLR) method. In fact, it is necessary to know frequent criteria used in the literature for establishing the task of assessment. This paper proposes also a determination of an association rules' set extracted from a set of criteria by applying an Apriori method.

The writer adaptation arisen with the appearance and the excessive use of Handheld devices. These devices are conceived to be used in diverse user settings which can be stationary or mobile. Most of the works tackle the writer adaptation in the "sitting at a desk" environment, nevertheless we notice a lack of contributions in the multi-environment context. In this paper we present a multi-environment writer adaptation technique to improve accuracy of writer-independent recognition system. Our system is based on adaptation module (AM) which can greatly decrease error accuracy without changing the writer-independent system. The (AM) is built using IGAAM which is an incremental learning algorithm. First, we test the performance of the IGA-AM on Laviola dataset against GA-AM algorithm for writer adaptation. Second, we test the recognition accuracy by taking into account the writing style change proportionally to environment changes. Thus the system contains as much adaptation module as handled environments. In this paper we consider two stationary environments that are sitting at a desk and standing. Finally, results on multi environment dataset (REGIM-MEnv) are presented.

Sparse coding has shown to be an effective technique in solving various reconstruction tasks such as denoising, in painting, and resolution enhancement of natural images. In this paper, we explore the use of this technique specifically to deal with low-resolution and degraded textual images. Firstly, we propose a sparse coding based resolution enhancement approach to recover a textual image with higher resolution than the input low-resolution one. It is based on the use of multiple coupled dictionaries which are learned from a clustered training low-resolution/high-resolution patch-pair database. A reconstruction scheme is then suggested in order to adaptively select the appropriate dictionaries that are useful for better recovering each local patch. This approach can be applied for the magnification of both printed and handwritten characters. Secondly, we propose to integrate the magnification in a restoration framework specifically to denoise and reconstruct at the same time degraded characters. The performances of these propositions are evaluated on various types of degraded printed and handwritten textual images where loss of details and background noise exist. Promising results are achieved when compared with results of other existing approaches.

Nowadays, the number of mobile applications based on image registration and recognition is increasing. Most interesting applications include mobile translator which can read text characters in the real world and translates it into the native language instantaneously. In this context, we aim to recognize characters in natural scenes by computing significant points so called key points or features/interest points in the image. So, it will be important to compare and evaluate features descriptors in terms of matching accuracy and processing time in a particular context of natural scene images. In this paper, we were interested on comparing the efficiency of the binary features as alternatives to the traditional SIFT and SURF in matching Arabic characters descended from natural scenes. We demonstrate that the binary descriptor ORB yields not only to similar results in terms of matching characters performance that the famous SIFT but also to faster computation suitable for mobile applications.

Sparse coding is widely known as a methodology where an input signal can be sparsely represented from a suitable dictionary. It was successfully applied on a wide range of applications like the textual image Super-Resolution. Nevertheless, its complexity limits enormously its application. Looking for a reduced computational complexity, a coupled dictionary learning approach is proposed to generate dual dictionaries representing coupled feature spaces. Under this approach, we optimize the training of a first dictionary for the high-resolution image space and then a second dictionary is simply deduced from the latter for the low-resolution image space. In contrast with the classical dictionary learning approaches, the proposed approach allows a noticeable speedup and a major simplification of the coupled dictionary learning phase both in terms of algorithm architecture and computational complexity. Furthermore, the resolution enhancement results achieved by applying the proposed approach on poorly resolved textual images lead to image quality improvements.

Multi-Agent System (MAS) is a very active field that ensures global coherence between agents' interactions in a distributed way and implicit global control. Under the awareness of its power, the application of MAS was no more limited to very specific problems, but to almost application area: optimization, neural network, robotics, fuzzy system, etc. In the other side, a complex system of Artificial Neural Network called Flexible Beta Basis Function Neural Tree (FBBFNT) has reached a great level in the prediction search domain. In the purpose of enlarging the application of the algorithm to complex applications of the real problems, a new architecture of MAS was designed and applied to the FBBFNT process. This new multi-agent system based on communications and negotiations allowed the resolution of more complex prediction problems and the acceleration of the global convergence speed.

In this paper, the universal approximation propriety is proved for the Flexible Beta Basis Function Neural Tree (FBBFNT) model. This model is a tree-encoding method for designing Beta basis function neural network. The performance of FBBFNT is evaluated for benchmark problems drawn from time series approximation area and is compared with other methods in the literature.

This paper discuss the oscillations of high-Order type recurrent delayed neural networks. Various creteria are used to prove the existence and uniqueness of pseudo almost periodic solution in a suitable convex domain. Our method is based on constructing suitable Lyapunov functionals and the well-known Banach contraction mapping principle. Banach fixed point, pseudo almost-periodic functions, high order recurrent neural network.

Hand shape biometry is among the most popular biometrics employed to characterize a person in forensic applications, due to its simplicity of use and acceptance of individuals. However, this modality presents weaknesses which may make system inaccurate. In fact, people from the same family or twins may have related hand features. Therefore, the performance of the hand verification process depends highly on the hand descriptors. In this paper, we propose a new approach for personal verification combining hand shape and palmprint features extracted using the Scale Invariant Feature Transform (SIFT). This transform was improved its high distinction and efficiency in many applications especially in object recognition and video tracking. Our experiments on IITD hand database demonstrate promising results by fusing at matching level score the hand shape and palmprint modalities. These results are comparable with similar bimodal identification methods.

Internet communication plays a considerable part in economic, financial and even politic domains.It is greatly influencing the politic revolution of many Arabic countries.That allows Internet communication to take more and more scale especially in an Arabic context.In this case, we notice that Internet communication is based on textual interchange using Arabic dialects more than Arabic language.However, few efforts were made for Arabic dialect processing particularly for aeb 1 language.In this case, we suggest building a standardized aeb Wordnet, which is a basic tool for Natural Language Processing (NLP) of aeb language.In this article, we present an extended Wordnet-LMF model acquired to aeb language specificities used to represent aeb Wordnet and we describe building steps.

Our works deals with the problem of Information Retrieval System (IRS) that integrates the human behaviour. This system must be able to recognize the degree of satisfaction of the user of the result found through its facial expression, its physiological state, its gestures and its voice. For this, we propose in this paper an algorithm for recognizing the emotional state of a user during a search session in order to issue the relevant documents that he needs. We present also, the architecture agent of the envisaged system.

The Event detection method from a video surveillance has received much attention in the image processing. In this paper, we present an overview of a new approach for event detection from video surveillance system based on incremental learning. In our approach, each event is modeled by a set of states, and each state is represented by a learning model containing a positive class (event) and a negative class (non-event). Experiments on real image sequences have shown encouraging results.

Aerial Video-Surveillance systems are being more and more used in security applications. The analysis and detection of abnormal behaviours in a aerial sequence has progressively drawn the attention in the field of public area security, since it allows filtering out a large number of useless information, which guarantees the high efficiency in the security protection, and save a lot of human and material resources. We present in this paper an intelligent video-surveillance framework for abnormal behaviour detection in aerial video surveillance. This framework is attended to be able to achieve real-time alarming, in public areas. This architecture takes into consideration four main challenges: behaviour understanding in public area, aerial video challenges, unstable video and contextual-based adaptability to recognize the active context of the scene.

Scintigraphic images are often characterized with much noise and a badly contrasted resolution which makes the perception of regions of interest very difficult. The renal quantification is how to define the regions of interests whose activities informs on the status of the renal function. In this context, the current study presents an intelligent system for the segmentation of renal regions in order to facilitate the process of quantification. The use of a multi-agent system based on the HOG3D descriptor combined with Fast Marching Method, has made our System of segmentation faster and more accurate. This automatic segmentation system is expected to assist physicians in both clinical diagnosis and educational training. Experiments and tests were developed on a database including 1800 images from 15 patients selected to obtain a variety of images. The results of the application of our method on several dynamic images are presented and discussed.

This paper investigates a Hybrid Naïve Possibilistic Classifier (HNPC) to detect the presence of heart disease from the heterogeneous data (numerical and categorical) of the Cleveland dataset. The proposed classifier stands for the hybridization of two versions of Naïve Possibilistic Classifier (NPC) which have been recently applied on numerical and categorical data, respectively. To estimate possibility beliefs from data, each one of these two versions calls the probability-possibility transformation method of Dubois et al. Later, two fusion steps are performed to make decision. In the first fusion, possibility values are combined within each classifier using the product and the minimum operators for numerical and categorical data, respectively. Then, these two rules are investigated in the second fusion step to combine possibilities assigned to each class. The obtained results show that the proposed HNPC outperforms the main classification techniques which have been used in recent related work.

In real robot applications, the task of designing a fuzzy logic controller is complex enough essentially because the presence of many forms of noise and uncertainties. The robot while navigating has to control many variables to get the best result at the end of the task: best smooth trajectory, the guarantee of arrive to goal, lowest time, etc. We present in this paper a novel Particle Swarm Optimization based adaptive learning Fuzzy Logic Controller design for a motion planning task. The membership functions of a fuzzy controller are tuned instantanously using particle swarm optimization technique. The proposed architecture presented good results which were demonstrated on the robot “iRobot Create”.

We propose in this paper an emotional recognition system based on physiological signals. We adopt the seven basic emotions that are: neutrality, joy, sadness, fear, anger, disgust and surprise. An experiment has been conducted to verify the feasibility of the proposed system. This experience has allowed us to acquire EEG signals and to create an emotional database. For this, we have used the Emotiv EPOC headset. Thereafter, we have chosen the fuzzy logic techniques to classify the EEG signals and to analyze the results.

For different reasons, many viewers like to watch a summary of films in less time than it takes to play. Traditionally, video films were analyzed manually to provide its summary; however this requires an important work time. Therefore, it is a necessity to propose a tool for summarization and video analysis automatically. Automatic video summarization has to extract all important moments in which viewers may be interested. All summarization criteria can be different from a video to another. In a different context with foregoing video summarization works, this paper present how the emotional dimensions issued from the real viewers can be considered as the important input to compute which part is most interesting in the total time of a film.

Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) algorithms have attracted the interest of researchers due to their simplicity, effectiveness and efficiency in solving real world optimization problems. Swarm-inspired optimization has recently become very popular. Both ACO and PSO are successfully applied in the Traveling Salesman Problem (TSP). Our approach consists in combining Fuzzy Logic with ACO (FACO - Fuzzy Ant Colony Optimization) and PSO (FPSO - Fuzzy Particle Swarm Optimization) for solving the TSP. Experimental results and comparative studies illustrate the importance of Fuzzy logic in reducing the time and the best length for the TSP problems considered.

This paper discusses the use of intelligent technology to solve the problem of grasp planning known as a difficult problem. The scope aims to find points of contact between a five-fingered hand and an object. In this paper, we applied a new hierarchical approach for distributed Multi-Objective Particles Swarms Optimization, based on dynamic subdivision of the population using Pareto fronts (pbMOPSO) for the optimization of the grasp planning problem. The problem is based on simultaneous optimization of two objectives functions. The first objective is to explore the space of skillful manipulation of a robot hand with five fingers and find the best configuration of the fingers by minimizing the distance between the center of mass of the object and the center of the contact polyhedron. The second evaluation function is to maximize another quality measure that is related to the angles defining a configuration of the hand. An experimental study done with the HandGrasp simulator has shown a better performance of our algorithm to solve the grasp planning problem.

In this paper, we introduce a new evolutionary methodology to design fuzzy inference systems. An innovative hybrid stages of learning method and tuning method, contains Subtractive clustering, Adaptive Neuro-Fuzzy Inference System (ANFIS) and particle swarm optimization (PSO), is developed to generate evolutional fuzzy modeling systems with high accuracy. For the purpose of illustration and validation of the approach, some data sets have been exploited. Empirical results illustrate that the proposed method is efficient.

This article introduces an improved version of the ant-clustering approach for image segmentation. An application of breast cancer magnetic resonance breas imaging has been chosen and the improved ant-based clustering approach has been applied to see their ability and accuracy to isolate the region of interest in the MRI images. The aim of the proposed ant-based clustering is to identify target objects through an The experimental results obtained, show that the modified ant-based clustering is superior to the classical ant-based clustering and the overall accuracy offered by the improved approach confirm that the effectiveness and performance is 98% in average.

Face recognition is a very popular biometric solution in the literature. Several solutions are presented to meet the needs of individual's verification or identification. There are three types of face recognition approaches: local, global and hybrid. In this paper, we proposed a local approach for face recognition based on combined features selection methods like Genetic algorithm, Gramdt Shmidt algorithm, mRmR features selection algorithm and naïve Bayesian classifier. Our proposed approach will be compared with some face recognition systems based on global features. A comparative study is given in this paper based on Recognition rates and Execution times. Our Face recognition system, which is based on naïve Bayesian classifier and tested on ORL face database, has showed 78.75% recognition rate and interesting execution times compared to global approaches.

Bio-inspired techniques and swarm intelligence are used to solve complex problems. In this paper, two new variants of AS-PSO (Ant Supervised by Particle Swarm optimization) meta-heuristic are proposed and applied to a classical travelling salesman benchmark problem. The new variants are Fuzzy-AS-PSO and Simplified AS-PSO (S-AS-PSO). AS-PSO is a hierarchical meta-heuristic based on the ant colony optimisation (ACO) and particle swarm optimization (PSO), in which ACO is the heuristic and PSO is the meta-heuristic. The paper reviews the initial formulation; and introduces a new focus as well as two new variants. AS-PSO is an adaptive heuristic, since the user is not asked to fit any parameter values. In AS-PSO, the ACO algorithm is in charge of the problem solving, while the PSO is managing the optimality of the ACO parameters. The Simplified AS-PSO, S-AS-PSO, is a variant that uses simplified PSO while in Fuzzy AS-PSO; the fuzzy PSO is used as a meta-heuristic. The paper also includes an application of the new AS-PSO variants to the travelling Salesman Problem (TSP) and is compared with the ACO results.

Distance learning has met an appearante evolution since some time ago. Thanks to the progress of Information Communication Technologies (ICT), a new approach appear in the last decades, which is a learning technique based on Television and called T-Learning. Indeed, the recent technological development of Television opens a wide range of services and features. Furthermore, social inclusion in learning environment and entertainment-based learning can produce an effective learning strategy. That's why this new technique can open new challenges for distance learning and smart TV. Our idea consists of the development of a new system for the improvement of TV program content. In this paper, we will define T-learning and present some T-learning works, and then we will present the different composant of the system proposed for the improvement of TV programs with extra learning contents.

Chemical compounds have a biological activity on animal genes; Mutagenicity and Carcinogenicity are examples of this activity. Both activities are similar except that mutagen compounds induce a heritable change in cells, while carcinogen compounds induce an unregulated growth process in cells. The relation between Mutagenicity and Carcinogenicity is not proved quantitatively yet. In this article, the relation between both activities is discovered based on the machine learning methodology. Feature selection techniques are applied to provide a well defined analysis of the highest discriminating descriptors of the mutagenic or carcinogenic compounds. Molecular charge appears to be a discriminating factor for Carcinogenicity, while Mutagenicity is characterized more by the branching and aromaticity/aliphaticity of the compounds. Electronegativity and Lipophilicity appears to be common factors for both activities. Further analysis and visualization are applied based on rough set and formal concept analysis to check the correlation among these descriptors and the ranges required for each descriptor.

This paper introduces the Generalized Eigen Cooccurrence Matrix (GECM) as a new feature to describe complex structures like images of handwritings for palaeographic expertise. It measures the spatial dependency between two features in the image. It generalizes the popular grey level cooccurrence Dependencies (SGLD) which uses the luminance for the two features. 2nd order statistics generate high dimensional feature space which must be reduced to overcome the curse of dimensionality. Haralick have described several descriptors suited for SGLD matrices that cannot be used in Generalized Cooccurrence. In our case, the cooccurrence matrices are not always symmetric and the contents of each matrice are different from the SGLD. We introduce the GECM which uses the eigen decomposition of the cooccurrence matrices to reduce the number of matrices and decrease the redundancy of spatial information instead to reduce the size of each matrix. We show the effectiveness of the GECM on palaeography application and writing comparison.

This paper describes the Arabic Recognition Competition: Multi-font Multi-size Digitally Represented Text held in the context of the 12th International Conference on Document Analysis and Recognition (ICDAR'2013), during August 25-28, 2013, Washington DC, United States of America. This competition has used the freely available Arabic Printed Text Image (APTI) database. A first edition took place in ICDAR'2011. In this edition, four groups with six systems are participating in the competition. The systems are compared using the recognition rates at character and word levels. The systems were tested in a blind manner using set 6 of APTI database. A short description of the participating groups, their systems, the experimental setup, and the observed results are presented.

This paper addresses the problem of generating a super-resolved version of a low-resolution textual image by using Sparse Coding (SC) which suggests that image patches can be sparsely represented from a suitable dictionary. In order to enhance the learning performance and improve the reconstruction ability, we propose in this paper a multiple learned dictionaries based clustered SC approach for single text image super resolution. For instance, a large High-Resolution/Low-Resolution (HR/LR) patch pair database is collected from a set of high quality character images and then partitioned into several clusters by performing an intelligent clustering algorithm. Two coupled HR/LR dictionaries are learned from each cluster. Based on SC principle, local patch of a LR image is represented from each LR dictionary generating multiple sparse representations of the same patch. The representation that minimizes the reconstruction error is retained and applied to generate a local HR patch from the corresponding HR dictionary. The performance of the proposed approach is evaluated and compared visually and quantitatively to other existing methods applied to text images. In addition, experimental results on character recognition illustrate that the proposed method outperforms the other methods, involved in this study, by providing better recognition rates.

In this paper, a new evolving artificial neural network using evolutionary computation is introduced. Based on the pre-defined Beta operator sets, this model called Flexible Beta Basis Function Neural Tree (FBBFNT), can be created and learned. The structure is developed using the Extended Immune Programming (EIP). The Beta parameters and connected weights are optimized using the Hybrid Bacterial Foraging Optimization algorithm. The performance of the proposed method is evaluated for nonlinear systems and compared with those of related methods.

This paper investigates a Naïve Bayes Style Possibilistic Classifier (NBSPC) to make decision from the categorical and subjective medical information included by the lymphography dataset of University of California Irvine (UCI). Main focus of the work is to improve the classification accuracy. NBSPC simultaneously relies on the structure of the Naïve Bayes classifier as a good classifier for categorical features, and on the possibility theory as an interesting framework to model and fuse subjective medical data. Possibilistic measures are estimated within the NBSPC using maximum likelihood estimation and then the probability-possibility transformation method of Dubois et al. Results show that the proposed classifier outperforms other classification techniques which have been already evaluated on the same data.

The adaptation module is a Radial Basis Function Neural Network (RBF-NN) that can be connected to the output of any recognition system and its aim is to examine the output of the writer-independent system and produce a more correct output vector close to the desired response. The proposed adaptation module is built using an incremental training named GA-AM algorithm (Growing-Adjustment Adaptation Module). Two adaptation strategies are applied : Growing and Adjustment. The growing criteria are based on the estimation of the significance of the new input and the significance of the nearest unit compared to the input. The adjustment consists of the update of two specific units (nearest and desired contributor) parameters using the standard LMS gradient descent to decrease the error at each time no new unit is allocated. This new training algorithm is evaluated by the adaptation of two handwriting recognition systems. The results, reported according to the cumulative error, show that the GA-AM algorithm leads to decreasing the classification error and to instantly adapting the recognition system to a specific user's handwriting. Performance comparison of GA-AM training algorithm with two other adaptation strategies, based on four writer-dependent datasets, are presented.

Page segmentation and classification is very important in document layout analysis system before it is presented to an OCR system or for any other subsequent processing steps. In this paper, we propose an accurate and suitably designed system for complex documents segmentation. This system is based on steerable pyramid transform. The features extracted from pyramid sub-bands serve to locate and classify regions into text (either machine printed or handwritten) and non-text (images, graphics, drawings or paintings) in some noise-infected, deformed, multilingual, multi-script document images. These documents contain tabular structures, logos, stamps, handwritten script blocks, photos etc. The encouraging and promising results obtained on 1,000 official complex document images data set are presented in this research paper.

Arabic and Latin language and script identification in machine printed and handwritten types present several difficulties because the Arabic (machine printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper an accurate and suitable designed system for language and script identification at word level which is based on steerable pyramid transform. The features extracted from pyramid sub bands serve to classify the scripts on only one script among the scripts to identify. The encouraging and promising results obtained are presented in this research paper.

This paper deals with the improvement of an on-line Arabic handwriting modeling system based on graphemes segmentation. The presented strategy consists in the integration of off-line features to assimilate and take up the handwriting style variation in a multi-writer context. The main contribution of the presented work consists in making off-line fuzzy template for each on-line segmented graphemes trajectory and the extraction of geometric moments invariants by using a method adapted to the irregular spatial sampling of their on-line trajectory. The experimental results prove the added value of the introduced features on the discriminative power of the developed handwriting modeling system.

The cultural heritage is full of important manuscript collections preserved in digital libraries. The need to annotate and enrich the scanned documents is claimed by some users to keep traces in the system for a further use. Moreover, the reuse of annotations could help other users to accomplish repetitive tasks in a semi-automatic way. One manuscript annotation technique is the word spotting. It is a process that seeks in a document for all the fragments that are similar to the one specified by the user. The main focus of this research work is to propose a solution integrating and encapsulating the word spotting algorithm in digital libraries. This solution involves, in particular, the specification and the implementation of an architecture to integrate the image processing tool using Restful Web services. The proposed prototype is tested on the ARMARIUS digital library. This library is one of the collaborative digital archiving models that stores ancient digitized manuscripts.

A neural network model for handwritten script generation is proposed, in which curvilinear velocity signals are approximated by the Beta profiles. For each Beta profile we associate an elliptic arc to fit the initial stroke in the trajectory domain. The network architecture consists of an input layer which uploads the set of Beta-elliptic characteristics as input, hidden layers and the output layer where script coordinates X(t) and Y(t) are estimated. A separate timing network prepares the input data. This latter involves the time-index starting time of each simple stroke for an appropriate handwriting movement signal. The experiments showed that the neural network model could be applied for the case of Latin handwriting scripts as well as Arabic handwriting scripts. New ways are proposed for the application of the neural network model such as: generation of complex handwriting movements, shape and character recognition.

To test the performance of handwriting on-line or offline recognition system, to measure and experimenting handwriting, to valid psychologist's laws, to compare and to make competitions between existing handwriting system, we must use databases. In this paper, we present the new dual handwriting database: "MAYASTROUN". The developed database contains a large lexicon of unconstrained cursive Arabic and Latin texts, words, characters, digits, mathematical expressions and signatures. The collected data contains more than 67825 and written by 355 writers. To facilitate experiments and research, this database offers four different extensions of each file and interactive software. The database architecture is described in details in this paper. The MAYASTROUN-database is available for the purpose to improve handwriting research filed.

Generally real data sets are naturally defined in a fuzzy context. Moreover, in real applications there is no sharp boundary between classes. Therefore, fuzzy clustering is better suited for complex real data sets to determine the best distribution. In this paper we present a new fuzzy learning approach called FMIG (Fuzzy Multilevel Interior Growing Self-Organizing Maps). It is a fuzzy version of MIGSOM (Multilevel Interior Growing Self-Organizing Maps). The main contribution of FMIG is to define a fuzzy process of mappings and take in account the fuzzy criterion of real datasets. This new algorithm is able to auto-organize the map perfectly due to the fuzzy training property of the nodes. Experiment study with synthetic and real world data sets is made to compare FMIG to the crisp MIGSOM and GSOM. Thus, our new method shows improvement in term of quantization error and topology preservation.

This paper presents an application of swarm intelligence technique namely Artificial Bee Colony (ABC) to design the design of the Beta Basis Function Neural Networks (BBFNN). The focus of this research is to investigate the new population metaheuristic to optimize the Beta neural networks parameters. The proposed algorithm is used for the prediction of benchmark problems. Simulation examples are also given to compare the effectiveness of the model with the other known methods in the literature. Empirical results reveal that the proposed ABC-BBFNN have impressive generalization ability.

This paper belongs to the field of communication and computer networks. Networks of low earth orbiting satellites are able to provide wireless connectivity to any part of the world while ensuring timely and better performance lower bit error rate. This type of technology has been growing interest towards the development of small satellites. Especially, when we talk about the execution of the service quality system, we must use some optimization techniques. However, these systems have the drawback of energy management which is the biggest problem to worry about. Therefore, optimization of the processing time and the effective implementation of information flow and storage on board must be discussed with respect to topology changes fast. In this paper we will discuss various routing algorithms of data used in small satellites and terrestrial networks. As a multiobjective problem, we try to solve the problem of routing data with multiobjective particle swarm optimization (MOPSO).

This paper is concerned with the existence and uniqueness of pseudo almost-periodic solutions to recurrent delayed neural networks. Several conditions guaranteeing the existence and uniqueness of such solutions are obtained in a suitable convex domain. Furthermore, several methods are applied to establish sufficient criteria for the globally exponential stability of this system. The approaches are based on constructing suitable Lyapunov functionals and the well-known Banach contraction mapping principle. Moreover, the attractivity and exponential stability of the pseudo almost-periodic solution are also considered for the system. A numerical example is given to illustrate the effectiveness of our results.

Video segmentation and tracking have been important and challenging issues for many video processing. A novel spatio-temporal video object segmentation and tracking algorithm is proposed in this paper. This algorithm is based on multi-agent system and active contour technique. The multi-agent system is composed of a set of supervisor and explorator agents. The agents are communicating and inspired in their conduct from active contour technique, more precisely the “Level Sets”. We used the DIMA platform to implement this algorithm. Experimental results indicate that the proposed algorithm is more robust than previous approaches.

Audio classification has been becoming very important in the field of multimedia researches dealing with audio processing and pattern recognition. Although major of them are focusing in “how”? Audio classifications should be semantic; the majority of them have neglected the importance of preprocessing step of environmental sound recognition, or using simply very classic sound classifiers. The originality of this paper is to construct a complete three modules process, acting dependently, with well defined functions. New method of acoustic sources separation are offered by our process, as well as, a sophisticated encapsulation of binary classifiers is used to promote environmental sound classification, leading to a real time audio concepts identifier. The main finding is that our system was able to recognize accuracy more than 90% of the introduced audio concepts.

Numerous similarity measures between intuitionistic fuzzy sets are proposed in literature using different approaches. In this paper, relationship between some existing intuitionistic fuzzy similarity and distance measures are investigated. These relations are paramount for the choice of a similarity or a distance measure and its application for any research topic.

The aim of this paper is to address the task of writer Identification of on-line handwriting. A new method for analytical on-line writer identification is proposed. However, although it is possible to measure the degree of handwriting irregularity thanks to the fractal dimension, the fractal analysis with a single exponent is not enough sufficient to characterize handwriting styles variation, instead, a continuous spectrum of exponents is necessary. In this purpose Multi-Fractal analysis was used to characterize styles of writing of writers. The main objective of this study is to explore the utility of this novel statistical tool for the purpose of distinguishing styles of on-line writings. Furthermore, a new method to estimate Multi-Fractal dimensions for on-line handwriting is presented and a procedure to find the most distinctive graphemes is elaborated. To evaluate our method, we have used the writings of 100 writers from the ADAB database. Our experimental results demonstrate the effectiveness of our proposed method and show a large capability of Multi-fractal features to characterize on-line handwriting styles.

Writer identification still remains as a challenge area in the field of off-line handwriting recognition because only an image of the handwriting is available. Consequently, some information on the dynamic of writing, which is valuable for identification of writer, is unavailable in the off-line approaches, contrary to the on-line approaches where temporal and spatial information for the handwriting is available. In this paper we present a new method for writer identification based on Multi-Fractal features for both types of presented approaches. This method consists to extract the multi-fractal dimensions from the images of Arabic words and the on-line signals for the same words. In order to enhance the performance of our writer identification system, we have combined both on-line and off-line approaches, taking the advantage it provides ADAB database, which allows to recover the on-line signal and image for the same handwriting. In this way, our work consists to take advantage of static and dynamic representations of handwriting, in order to identify the writer in realistic conditions. The tests are performed on the writing of 100 writers from the ADAB database. The obtained results show the effectiveness of the proposed writer identification system.

In this paper we designed an adaptation module (AM) with the objective to increase the performance of a recognition system for a new user or new writing style. The developed adaptation module is added after the recognition system, and its role is to examine the output of the independent system and produce a more correct output vector close to the desired response of the user. To achieve this end, we conceive an adaptation module based on Radial Basis Function Neural Network (RBF-NN) which is built using an incremental training algorithm. Two adaptation strategies are applied for adaptation module training: increase the number of new hidden units and adjust the parameters of the nearest unit (weights and location of center) using the standard descent gradient. This new architecture is evaluated by the adaptation of two recognition systems, one for digit recognition and one for alphanumeric character recognition. The results, reported according to the cumulative error, show that the adaptation module (AM) leads to decreasing the classification error and is capable of fast adaptation to the users handwriting. Moreover, results are compared with those carried out using the weights updating strategy of the nearest center apart from the addition of new units. In fact, the adaptation module decreases an average of 50% the error rate with standard recognition systems.

Arabic script presents a challenge complexity and variability for handwriting recognition. The first on line Arabic Database called ADAB is known as a standard benchmark in the ICDAR competition of 2009. This paper describes the Online Arabic handwriting recognition competition held at ICDAR 2011. 3 groups with 5 systems are participating in the competition. The systems were tested on known data (sets 1 to 4) and on two test datasets which are unknown to all participants (set 5 and set 6). The systems are compared on the most important characteristic of classification systems, the recognition rate. Additionally, the relative speed of every system was compared. A short description of the participating groups, their systems, the experimental setup, and the performed results are presented.

This paper describes the Arabic Recognition Competition: Multi-font Multi-size Digitally Represented Text held in the context of the 11$^{th}$ International Conference on Document Analysis and Recognition (ICDAR2011), during September 18-21, 2011, Beijing, China. This first competition used the freely available Arabic Printed Text Image (APTI) database. Several research groups have started using the APTI database and this year, 2 groups with 3 systems are participating in the competition. The systems are compared using the recognition rates at the character and word levels. The systems were tested on one test dataset which is unknown to all participants (set 6 of APTI database). The systems are compared on the most important characteristic of classification systems, the recognition rate. A short description of the participating groups, their systems, the experimental setup, and the observed results are presented.

The aim of this paper is to understand the importance of modeling the dynamic of industrial systems using Recurrent Neural Network (RNN) and report the results obtained by training the RNN on a textile process to identify the relationship between yarn color and fabric color. The importance of RNN can be highlighted by the fact that the information about the underlying dynamics of such systems is not available. The dynamics can only be observed with the help of certain measurable variables. In this context, Recurrent Neural Network based approach is a powerful tool with promising results. In conventional Neural Network based approaches, periodic training is required. The time between retraining is still an open issue.

Femtocells are an inexpensive solution to address weak indoor cellular coverage. Femtocells increase network coverage, offloaded macro cell sites, and provide high data rate services in a cost-effective manner. However, several aspects of this new technology are ambiguous or not defined in standard, such as QoS architecture, bandwidth request management and subscribers flows priority. This paper provides a new QoS management scheme for WiMAX Femtocell Access Point (WFAP). Our proposal offers three key features: prioritize femtocell's owner traffics; guarantee's the QoS for the different connections of each user, better resources management. We validate our assumptions through simulations and numerical analysis. Results show the effectiveness of our solution in public and private access methods.

In this paper, a novel learning algorithm of wavelet networks based on the Fast Wavelet Transform (FWT) is proposed. It has many advantages compared to other algorithms, in which we solve the problem in previous works, when the weights of the hidden layer to the output layer are determined by applying the back propagation algorithm or by direct solution which requires to compute the matrix inversion, this may cause intensive computation when the learning data is too large. However, the new algorithm is realized by iterative application of FWT to compute the connection weights. Furthermore, we have extended the novel learning algorithm by using Levenberg–Marquardt method to optimize the learning functions. The experimental results have demonstrated that our model is remarkably more refreshing than some of the previously established models in terms of both speed and efficiency.

In this paper, we propose a new linguistic-based approach called the affixal approach for Arabic word and text image recognition. Most of the existing works in the field integrate the knowledge of the Arabic language in the recognition process in two ways: either in post-recognition using the language of dictionary (dictionary of words) to validate the word hypotheses suggested by the OCR or in the course of the recognition process (recognition directed by a lexicon) using a statistical model of the language (Hidden Markov Model or N-gram). The proposed approach uses the linguistic concepts of the vocabulary to direct and simplify the recognition process. The principal contribution of the proposed approach is to be able to categorize the word hypotheses in words that are either derived or not derived from roots and to characterize morphologically each word hypothesis in order to prepare the text hypotheses for later analyses (for example, syntactic analysis; to filter the sentence hypotheses).

Swarm-inspired optimization has become very popular in recent years. The multiple criteria nature of most real world problems has boosted research on multi-objective algorithms that can tackle such problems effectively, with the computational burden and colonies. Particle Swarm Optimization (PSO) and Ant colony Optimization (ACO) have attracted the interest of researchers due to its simplicity, effectiveness and efficiency in solving optimization problems. We use the notion of multi-objective Particle Swarm Optimization (MOPSO) for few methods; and we find in most of the results; more the number of the swarm increases more the accuracy of object is achieved with greater accuracy. Performance of the basic swarm for small problems with moderate dimensions and searching space is satisfactory.

This paper deals with an experiment which proves that wavelet networks are capable for 3D objects modeling. To prove this, we will propose a new structure of wavelet network founded on several mother wavelets families. This new structure is in some ways similar to the classic wavelet networks but it admits some originality. Actually, wavelet network basically uses dilations and translations versions of only one mother wavelet to construct the network. The proposed structure uses several mother wavelets, in order to maximize best wavelets selection probability. An algorithm to construct this structure is presented. First, 3D object model vertices and their corresponding normal values are used to create a training set. Then, an improved Orthogonal Least Squares method version is applied to optimize wavelet selection for every mother wavelet. Some simulation results will describe the proposed wavelet network performance employing several types of Polywogs as mother wavelets.

In this paper, we propose a strategy of multi-SVM incremental learning system based on Learn++ classifier for detection of predefined events in the video. This strategy is offline and fast in the sense that any new class of event can be learned by the system from very few examples. The extraction and synthesis of suitably video events are used for this purpose. The results showed that the performance of our system is improving gradually and progressively as we increase the number of such learning for each event. We then demonstrate the usefulness of the toolbox in the context of feature extraction, concepts/events learning and detection in large collection of video surveillance dataset.

Many methods for solving optimization problems, whether direct or indirect, rely upon gradient information and therefore may converge to a local optimum. Global optimization methods like Evolutionary algorithms, overcome this problem although these techniques are computationally expensive due to slow nature of the evolutionary process. In this work, a new concept is investigated to accelerate the differential evolution. The opposition-based DE uses the concept of opposite number to create a new population during the learning process to improve the convergence rate of generalization performance of the beta basis function neural network. The proposed algorithm uses the dichotomy research to determine the target solution. Detailed performance comparison of ODE-BBFNN with learning algorithm on benchmarks problems drawn from regression and time series prediction area. The results show that the ODE-BBFNN produces a better generalization performance.

A known difficulty of Arabic text recognition is in the large variability of printed representation from one font to the other. In this paper, we present a comparative study between two strategies for the recognition of multi-font Arabic text. The first strategy is to use a global recognition system working independently on all the fonts. The second strategy is to use a so-called cascade built from a font identification system followed by font-dependent systems. In order to reach a fair comparison, the feature extraction and the modeling algorithms based on HMMs are kept as similar as possible between both approaches. The evaluation is carried out on the large and publicly available APTI (Arabic Printed Text Image) database with 10 different fonts. The results are showing a clear advantage of performance for the cascading approach. However, the cascading system is more costly in terms of cpu and memory.

We present a comparative study between fuzzy similarity measures applied to shape recognition and Arabic sentences recognition described with fuzzy features. The objective is to demonstrate that the choice of a fuzzy similarity is important and can influence results in any research topic.

The aim of this work is to present a particular design technique of hierarchical fuzzy controllers. The method makes an easy way to control complex systems with an automatic low complicated design. It was based on the systems capability to generate output informations when exited outside any control instance. This fact helps constructing input-output learning and testing data. This type of fuzzy controller is made optimal by the use of hierarchical minimal association of input rule bases, learned fuzzy inferences and the configuration of aggregation processes. The proposed strategy of design with learned fuzzy rule bases guarantee an interpretable behavioral decomposition. The effect of the growth of fuzzy rules number in terms of the algorithmic complexity has been studied. This algorithm was tested on the stabilization of an inverted simple pendulum around a desired position.

This paper presents an intelligent hybrid system to support the planning for a mobile robot motion in unknown and dynamic environment. Called Fuzzy-MARCoPlan (Fuzzy-MultiAgent Remote Control motion Planning), this system optimizes the path by the introduction of sub-goals and through a multiagent cooperation based on fuzzy reasoning. In fact, we propose to agentify the surrounding zones of the robot; these zone agents compete for attracting the sub-goal. A planning agent, fortified with a fuzzy rule based system, decides on the best sub-goal to reach. Fuzzy-MARCoPlan is simulated and tested on several navigation environments which are generated randomly under the multiagent platform MadKit. These tests confirm the robustness of the proposed system in terms of path optimality in a dynamic environment. Moreover, the obtained results reinforce the advantage of a multiagent planning hybridized with fuzzy reasoning for mobile robot motion planning.

In this paper we present a new modeling approach for online Arabic handwriting which is based on fuzzy graphemes segmentation. In the literature, the result of the graphemes segmentation of a cursive writing not often reaches its optimum. This fact is due to the crisp aspect of the segmentation decision. In order to overcome this problem, we propose to introduce a fuzzy effect in this segmentation decision by overlapping the segmented graphemes in proportion to the confidence degrees associated with the detection of the particular points that separate them. The fuzzified boundary shapes of the extracted fuzzy graphemes are then modeled taking into account the coefficient of fuzzy membership of their points. The obtained results by using the ADAB database show an improvement of the recognition rate given by the fuzzy segmentation approach compared to the crisp one.

In this paper, we propose a new encoding system for On-line Arabic handwriting. To identify patterns, our human perceptual system is based on basic features called perceptual codes. Analysing handwriting, we notice the existence of elementary and global ones. Gathering the elementary perceptual codes in various constraints we obtain global ones, and to obtain different forms of handwriting, we proceed by combining them. So, we present a new approach to improve handwriting segmentation via perceptual encoding system. This system uses the fuzzy set theory to detect the elementary perceptual codes (EPCs) and the genetic algorithms for the global perceptual ones (GPCs). To validate our new approach, a large Arabic lexicon was developed containing words, alphabet and digits acquired by different writers on digitizing tablet, in addition to ADAB database set. The obtained results show successful representations of Arabic handwritten script via perceptual codes.

We analyze in this paper the impact of sub-models choice for automatic Arabic printed text recognition based on Hidden Markov Models (HMM). In our approach, sub-models correspond to characters shapes assembled to compose words models. One of the peculiarities of Arabic writing is to present various character shapes according to their position in the word. With 28 basic characters, there are over 120 different shapes. Ideally, there should be one sub model for each different shape. However, some shapes are less frequent than others and, as training databases are finite, the learning process leads to less reliable models for the infrequent shapes. We show in this paper that an optimal set of models has then to be found looking for the trade-off between having more models capturing the intricacies of shapes and grouping the models of similar shapes with other. We propose in this paper different sets of sub-models that have been evaluated using the Arabic Printed Text Image (APTI) Database freely available for the scientific community.

We present in this paper a new approach of online Arabic handwriting modeling based on the graphemes segmentation. This segmentation rests on the previous detection of baseline. It involves the detection of two types of topologically meaningful points: the backs of the valleys adjoining the baseline and the angular points. The stage of features extraction allows to model the shapes of segmented graphemes by relevant geometric parameters and to estimate their diacritics fuzzy affectation rates. The test results show a significant improvement in recognition rate with the introduction of new pertinent parameters.

This paper presents a new method for automatic text-line extraction from Arabic historical handwritten documents presenting an overlapping and multi-touching characters problems. Our approach is based on block covering analysis using unsupervised technique. This algorithm performs firstly a statistical block analysis which computes the optimal number of document decomposition into vertical strips. Then, our algorithm achieves a fuzzy base line detection using fuzzy C-means algorithm. Finally, blocks are assigned to its corresponding lines. Experiment results show that the proposed method achieves high accuracy about 95% for detecting text lines in Arabic historical handwritten document images written with different scripts.

In recent years, fractal and multi-fractal analysis have been widely applied in many domains, especially in the field of image processing. In this direction we present in this paper a novel method for Arabic text-dependent writer identification based on fractal and multi-fractal features; thus, from the images of Arabic words, we calculate their fractal dimensions by using the “Box-counting” method, then we calculate their multi-fractal dimensions by using the method of DLA (Diffusion Limited Aggregates). To evaluate our method, we used 50 writers of the ADAB database, each writer wrote 288 words (24 Tunisian cities repeated 12 times) with 2/3 of words are used for the learning phase and the rest is used for the identification. The results obtained by using knearest neighbor classifier, demonstrate the effectiveness of our proposed method.

We present in this paper a new approach for Arabic font recognition. Our proposal is to use a fixed-length sliding window for the feature extraction and to model feature distributions with Gaussian Mixture Models (GMMs). This approach presents a double advantage. First, we do not need to perform a priori segmentation into characters, which is a difficult task for arabic text. Second, we use versatile and powerful GMMs able to model finely distributions of features in large multi-dimensional input spaces. We report on the evaluation of our system on the APTI (Arabic Printed Text Image) database using 10 different fonts and 10 font sizes. Considering the variability of the different font shapes and the fact that our system is independent of the font size, the obtained results are convincing and compare well with competing systems.

Many methods for solving optimization problems, whether direct or indirect, rely upon gradient information and therefore may converge to a local optimum. Global optimization methods like Evolutionary algorithms, overcome this problem although these techniques are computationally expensive due to slow nature of the evolutionary process. In this work, a new concept is investigated to accelerate the particle swarm optimization. The opposition-based PSO uses the concept of opposite number to create a new population during the learning process to improve the convergence rate of generalization performance of the beta basis function neural network. The proposed algorithm uses the dichotomy research to determine the target solution. Detailed performance comparison of OPSO-BBFNN with learning algorithm on benchmarks problems drawn from regression and time series prediction area. The results show that the OPSO-BBFNN produces a better generalization performance.

Image classification is an important task in computer vision. In this paper, we propose a supervised method for image classification based on a fast beta wavelet networks (FBWN) model. First, the structure of the wavelet network is detailed. Then, to enhance the performance of wavelet networks, a novel learning algorithm based on the Fast Wavelet Transform (FWTLA) is proposed. It has many advantages compared to other algorithms, in which we solve the problem of the previous works, when the weights of the hidden layer to the output layer are determinate by applying the back propagation algorithm or by direct solution which requires to compute matrix inversion, this may be intensive computation when the learning data is too large. However, the new algorithm is realized by the iterative application of FWT to compute connection weights. In the simulation part, the proposed method is employed to classify images. Comparisons with classical wavelet network classifier are presented and discussed. Results of comparison have shown that the FBWN model performs better than the previously established model in the context of training run time and classification rate.

Self-Organizing Maps (SOM) are widely used for their ability to preserve the topology in the projection. However, this topology is not perfectly preserved due to the static structure of SOM. Therefore, we show in this paper a novel architecture of SOM which organizes itself over time. The proposed method called MIGSOM (Multilevel Interior Growing Self-Organizing Maps) is generated by a growth process which allows to adds nodes where it is necessary. The network start with a minimum number of nodes, then nodes will be added from the boundary as well as the interior of the network. The MIGSOM algorithm adds the interior nodes in a superior level of the map. As a result, the map can have three-Dimensional structure with multi-levels oriented maps. To improve the performance of the proposed algorithm, comparison of MIGSOM to the Kohonen feature Map (SOM) and the Growing Grid (GG) is made. Our experiment results demonstrate that the MIGSOM constructs better mappings than the classic SOM and GG, especially, in terms of data quantification and topology preservation.

Since swarm intelligence allows self-organization into an unfamiliar environment and adapting behaviors through simple individuals' interactions, we propose to realize a swarm multirobot organization with a fuzzy control. We introduce in this paper a fuzzy system for avoiding the collaboration stagnation and to improve the counter-ant algorithm (CAA). The robots' collaborative behavior is based on a hybrid approach combining the CAA and a fuzzy system learned by MAGAD-BFS (Multi-agent Genetic Algorithm for the Design of Beta Fuzzy System). A series of simulations enables us to discuss and validate both the effectiveness of the hybrid approach to the problem of environment exploration (i.e., for the purpose of cleaning an area) as well as the usefulness of MAGAD-BFS for learning the fuzzy knowledge base while tuning it and reducing its number of rules.

This paper introduces a new hierarchical architecture for multi-objective optimization. Based on the concept of Pareto dominance, the process of implementation of the algorithm consists of two stages. First, when executing a multiobjective Particle S warm Optimization (MOPSO), a ranking operator is applied to the population in a predefined iteration to build an initial archive Using ε-dominance. Second, several runs will be based on a dynamic number of sub-populations. Those populations, having a fixed size, are generated from the Pareto fronts witch are resulted from ranking operator. A comparative study with other algorithms existing in the literature has shown a better performance of our algorithm referring to some most used benchmarks.

Intelligent software based on agent technology emerges to improve system design, and to increase enterprise competitive position as well. The competitiveness is based on the cooperation. Thus, within this cooperation, conflicts may arise. Argumentation theory has become an important topic in the field of Multi-Agent Systems and especially in the negotiation problem. Moreover, research on trust and reputation is a recent discipline oriented to increase the reliability and performance of electronic communities. In this paper, first, an overview of a proposed model MAIS-E2(Multi Agent Information System for an Extended Enterprise) and a proposed argumentation based negotiation framework: Relationship-Role and Interest Based Negotiation (R2-IBN) framework is presented. Then, we focused mainly on the description of the proposed trust and reputation model. For that, we conduct an hybridization of approaches: fuzzy, mathematical and statistical.

In view of the high dynamicity of traffic flow and the polynomial increase in the number of vehicles on road networks, the route choice problem becomes more complex. A classical shortest path algorithm based only on road length is no longer relevant. We propose in this paper an adaptive vehicle guidance system instigated from the ants behavior, well known for its good adaptativity; this system allows adjusting intelligently and promptly the route choice according to the real-time changes in the road network situations, such as new congestions and jams. This method is implemented as a deliberative module of a vehicle ant agent in a collaborative multiagent system representing the entire road network. Series of simulations, under a multiagent platform, allow us to discuss the improvement of the global road traffic quality in terms of time, fluidity, and adaptativity.

In this paper we propose a method to generate gaits of a biped robot by a particle swarm optimization algorithm. The system generates angular positions for joints with an interpolate end segments positions to evaluate walking stability. The proposed PSO is adapted to generate angular position joints, Human walking stability criteria are used to check and validate the gaits. The experimental procedure includes a robot assembly and online test. Then an upper torso controller is introduced to correct walking stability and limits fall downs.

The last years witnessed a continued growth of the amount of data. The data analysis and exploration has become more and more difficult. So, it seems important to find means to visually represent this flood of data. Information visualization can help any user to get and understand information efficiently and implicate him/her in the data mining process thanks to our perception possibilities. The visualization domain proposes a large number of information visualization techniques which have been developed over the last decade to support the exploration of large data sets. In this paper, we propose a classification of information visualization techniques. We present also each technique, its advantages and disadvantages.

In this paper we present a comparison of intuitionistic fuzzy similarity measures applied to Arabic sentences recognition using an extract of the IFN/ENIT data set. Such comparison shows the importance of similarity measures choice for any field of research needing to match between patterns.

Recently type-2 Fuzzy logic systems (FLSs) have demonstrated their competence in treating vagueness in real world dynamic systems. But, in the last few years, new trends and theory in Fuzzy Logic have been appeared, proposing the geometric type-2 Fuzzy logic approach. The main idea of this approach was to model fuzzy logic sets using computational geometry providing by this more accurate results and better performance in treating vagueness. Throughout this paper, we study the effect of the geometric approach in robotic mobile issue. We propose two controllers: a geometric interval type-2 fuzzy logic local avoiding obstacles controller and a geometric interval type-2 fuzzy logic wall following controller. The obtained results are presented and are discussed. The geometric type-2 FLSs provide good results...

This paper describes the Online Arabic handwriting recognition competition held at ICDAR 2009. This first competition uses the ADAB-database with Arabic online handwritten words. This year, 3 groups with 7 systems are participating in the competition. The systems were tested on known data (sets 1 to 3) and on one test dataset which is unknown to all participants (set 4). The systems are compared on the most important characteristic of classification systems, the recognition rate. Additionally, the relative speed of the different systems were compared. A short description of the participating groups, their systems, the experimental setup, and the performed results are presented.

Arabic and Latin script identification in printed and handwritten nature present several difficulties because the Arabic (printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper an accurate and suitable designed system for script identification at word level which is based on steerable pyramid transform. The features extracted from pyramid sub bands serve to classify the scripts on only one script among the scripts to identify. The encouraging and promising results obtained are presented in this research paper.

In this paper, we propose an accurate and suitable designed system for complex documents segmentation. This system is based on steerable pyramid transform. The features extracted from pyramid sub bands serve to locate and classify regions into text and non text in some noise infected, deformed, multilingual, multi script document images. These documents contain tabular structures, logos, stamps, handwritten text blocks, photos etc. The encouraging and promising results obtained on 1000 official complex documents images data set are presented in this research paper.

In this paper we present a new method of baseline detection of online or offline short handwriting. This work is part of a large project for the edification of a dual online / offline Arabic handwriting recognition system. Compared to the existing approaches in the literature, this new method brings three specific novelties: First, the consideration of the agreement between the alignment of the points and their trajectory tangent directions for the detection of aligned points regroupings. Then, the consideration of a topologic characteristics specific to the used writing language, to value the pertinence of the pretender points regroupings to be recognized as baseline. Finally, we showed the aptitude of the algorithm to detect curved baseline.

This paper presents a new enhanced text extraction algorithm from degraded document images on the basis of the probabilistic models. The observed document image is considered as a mixture of Gaussian densities which represents the foreground and background document image components. The EM algorithm is introduced in order to estimate and improve the parameters of the mixtures of densities recursively. The initial parameters of the EM algorithm are estimated by the k-means clustering method. After the parameter estimation, the document image is partitioned into text and background classes by the means of ML approach. The performance of the proposed approach is evaluated on a variety of degraded documents comes from the collections of the National library of Tunisia.

In this paper we present a system of the off-line handwriting recognition. Our recognition system is based on temporal order restoration of the off-line trajectory. For this task we use a genetic algorithm (GA) to optimize the sequences of handwritten strokes. To benefit from dynamic informations we make a sampling operation by the consideration of trajectory curvatures. We proceed to calculate the curvilinear velocity signal and use the beta-elliptical modelling which is developed in on-line systems to calculate other characteristics. Our approach is validated by Hmm Tool Kit (HTK) recognition system using IFN/ENIT database.

In this paper, we present a new approach to the temporal order restoration of the off-line handwriting. After the pre-processing steps of the word image, a suitable algorithm makes it possible to segment its skeleton in three types of strokes. After that, we developed a genetic algorithm GA in order to optimize the best trajectory of these segments. The repetition of a segment will be studied in a secondary algorithm so that we do not disturb the GA operations. The techniques used in GA are the selection, crossover and the mutation. The fitness function value depends on right-left direction (direction of the Arab writing), the segments repetition and angular deviation on the crossing of the occlusion stroke. To validate our approach, we tested it on the on/off LMCA dual Arabic handwriting, the Latin IRONOFF and the off-line IFN/ENIT datasets.

This paper presents an off-line Arabic handwriting recognition system based on the selection of different state of the art features and the combination of multiple hidden Markov models classifiers. Beside the classical use of the off-line features, we add the use of on-line features and the combination of the developed systems. The designed recognizer is implemented using the HMM-Toolkit. In a first step, we use different features to make the classification and we compare the performance of single classifiers. In a second step, we proceed to the combination of the on-line and the off-line based systems using different combination methods. The system is evaluated using the IFN/ENIT database. The recognition rate is in maximum 63.90% for the individual systems. The combination of the on-line and the off-line systems allows to improve the system accuracy to 81.93% which exceeds the best result of the ICDAR 2005 competition.

In this paper, we propose a comparative study between the affixal approach and the analytical approach for off-line Arabic decomposable word recognition. The analytical approach is based on the modeling of alphabetical letters. The affixal approach is based on the modeling of the linguistic entity namely prefix, infix, suffix and root. The experimental results obtained by these two last approaches are presented on the basis of the printed decomposable word data set in mono-font nature by varying the character sizes. We achieve then our paper by the current improvements of our works concerning the Arabic multi-font, multi-style and multi-size word recognition.

We report on the creation of a database composed of images of Arabic Printed words. The purpose of this database is the large-scale benchmarking of open-vocabulary, multi-font, multi-size and multi-style text recognition systems in Arabic. The challenges that are addressed by the database are in the variability of the sizes, fonts and style used to generate the images. A focus is also given on low-resolution images where anti-aliasing is generating noise on the characters to recognize. The database is synthetically generated using a lexicon of 113psila284 words, 10 Arabic fonts, 10 font sizes and 4 font styles. The database contains 45psila313psila600 single word images totaling to more than 250 million characters. Ground truth annotation is provided for each image. The database is called APTI for Arabic Printed Text Images.

Mobile WiMAX is an emerging broadband wireless communication technology. The IEEE 802.16e standard for Mobile WiMAX, the enhanced version of the IEEE 802.16 standard with mobility support, defines that the implementation of hard handover is mandatory. However, the long interruption of hard handover is horrible for delay and packet loss sensitive real-time applications such as IPTV and VoIP. To solve this problem without many changes to 802.16e equipments, we propose some improvements at various stages of the handover, including the principle for selection of target base station depending on the type of traffic connection managed by subscriber station. Simulation results prove that the scheme accelerates handover process and make Real-time downlink data transmission interruption so brief that users will not perceive the interruption.

In this paper we propose an approach aiming to integrate human-computer interaction (HCI) aspects in decision support system (DSS) development. We propose an approach combining two methods: one issued from software engineering field (the rational unified process) and the other one from the HCI field (the U model). We have tested our approach in a DSS set up in the healthcare domain: the supervision of nosocomial infections in an intensive care unit.

This paper presents our contribution for the compression of images of old Arabic manuscripts. Our method of compression is based on the segmentation of the images in three blocks: text, graphics and background, then each block will undergo a different compression method. We present two parts: first, while developing a characteristic extractor based on the wavelet transform and statistical characteristics, we propose an algorithm of segmentation based on the classification of old documents images. Second, we present the education and the implementation of a compression method by using the wavelet transform. This method comprises three steps: the compression of the text blocks, the background blocks, and the graphics blocks.

This paper proposes and describes an effective utilization of the heuristic optimization. The focus of this research is on a hybrid method combining two heuristic optimization techniques; Differential evolution algorithms (DE) and particle swarm optimization (PSO), to train the beta basis function neural network (BBFNN). Denoted as PSO- DE, this hybrid technique incorporates concepts from DE and PSO and creates individuals in a new generation not only by crossover and mutation operations as found in DE but also by mechanisms of PSO. The results of various experimental studies using the Mackey time prediction have demonstrated the superiority of the hybrid PSO-DE approach over the other four search techniques in terms of solution quality and convergence rates.

This paper deals about text extraction from heterogeneous documents for categorizing documents and indexing tasks. The purpose of this work is to find similar text regions basing on their fonts. First text regions are extracted, and then font matching is performed using fractal descriptors. Experiments are done for both maps and ancient documents.

In this paper, we present a new design for an interactive information service based on on-line recognition of the handwriting and quick news stories browsing. A person communicates with server PC using PDA and Bluetooth headset technology in order to consult same key frame that represent a summaries of video news. The result of the server research will by returned to the PDA.

In this paper, we present multilingual automatic identification of Arabic and Latin in both handwritten and printed script. The proposed scheme is based, Firstly, on morphological transform of line text images, secondly on fractal analysis features of both (i): original texture of 2-D images, (ii): vertical and horizontal profile projection. We used two techniques to obtain only 12 features based on fractal multi-dimension. The proposed system has been tested for 1000 prototypes with various typefaces, scriptors styles and sizes. The accuracy discrimination rate is about of 96.64 % by using KNN, and 98.72 % by using RBF. Experimental results show the importance of the proposed approach.

Many methods for solving optimization problems, whether direct or indirect, rely upon gradient information and therefore may converge to a local optimum. Global optimization methods like evolutionary algorithms, overcome this problem. In this work it is investigated how to construct a quality BBF network for a specific application can be a time-consuming process as the system must select both a suitable set of inputs and a suitable BBF network structure. Evolutionary methodologies offer the potential to automate all or part of these steps. This study illustrates how a hybrid BBFN-PSO system can be constructed, and applies the system to a number of datasets. The utility of the resulting BBFNs on these optimization problems is assessed and the results from the BBFN-PSO hybrids are shown to be competitive against the best performance on these datasets using alternative optimization methodologies. The results show that within these classes of evolutionary methods, particle swarm optimization algorithms are very robust, effective and highly efficient in solving the studied class of optimization problems.

This paper aims at presenting different strategies for the construction of beta basis function (BBF) fuzzy neural network. These strategies lead to the determination of the network architecture by determining the structure of the hidden layer and parameters of its centers based on data structure. For that, we use self organizing maps (SOM) clustering to construct a mapped structure of the real training data. By analyzing this structure, we proceed to neuron selection. Data sets were also analyzed with the fuzzy c-means (FCM) clustering technique to generate fuzzy membership values presenting fuzzy outputs for our fuzzy neural model. We propose to estimate the parameters of beta basis function in order to obtain better data coverage. Experimental results show that the use of the proposed technique produces better results.

This paper describes an approximate algorithm for inference in dynamic possibilistic networks (DPNs). DPNs provide a succinct and expressive graphical language for representing sequential data and factoring joint possibility distributions and they are powerful models using only the concepts of random variables and conditional possibilities. The proposed algorithm, to perform inference in such networks, is an approximate one and it is based mainly on the standard Boyen-Koller (BK) algorithm well defined for dynamic probabilistic networks. The new possibilistic framework, proposed in this paper, is notable because it gives a counterpart of traditional probability framework, generally used to represent uncertainty in sequential data. The possibilistic BK algorithm is based on the junction tree technique where inference is done via an interface clusters that decrease the size of the dynamic network structured and amenable to a very simple form of inference. We present this algorithm in terms of two possibilistic conditioning; the product based and the min-based one.

Motion planning of mobile robots in unknown and dynamic environments is faced with a large amount of uncertainties. Such those uncertainties we find; the measurement noise, the membership function's translations, data uncertainties... In fact, the known type of fuzzy logic (FL), Type-1, gave some solutions. But, in the last few years, new trends and theory in FL have been appeared, proposing by thus the Type-2 Fuzzy Logic Systems (Type-2 FLSs) which can handle and minimize the effects of the cited uncertainties with a better performance. This paper deals with the design of an Interval Type-2 fuzzy logic controller for the navigation of mobile robots in unknown and dynamic environments. The obtained results are presented and are compared with the navigation using the Type-1 Fuzzy Logic system. The Type-2 FLSs provide very good results and outperform the correspondent Type-1 FLS.

In this article, we present initially arguments supporting the idea of the approximation of a cursive handwriting trajectory by arcs of ellipses. Then, we introduce a new strategy which improves the dynamic and geometrical features of the online handwritten trajectory modeling. We show that the curvilinear velocity can be rebuilt with the superposition of two components successively named the "Beta" model and the "Carrying" dragged component. After that, we integrated the geometrical characteristics as the arcs of ellipses for the layout modeling.

This paper presents the new system PRAAD for preprocessing and analysis of Arabic historical documents. It is composed of two important parts: pre-processing and analysis of ancient documents. After digitization, the color or greyscale ancient documents images are distorted by the presence of strong background artefacts such as scan optical blur and noise, show-through and bleed-through effects and spots. In order to preserve and exploit this cultural heritage documents, we intend to create efficient tool that achieves restoration, binarisation, and analyses the document layout. The developed tool is done by adapting our expertise in document image processing of Arabic ancient documents, printed or manuscripts. The different functions of PRAAD system are tested on a set of Arabic ancient documents from the national library and the National Archives of Tunisia.

Arabic and Latin script identification in printed and handwritten nature present several difficulties because the Arabic (printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper a strategy which is based on three decision levels where each level will have its own features vector and will consist in identifying only one script among the scripts to identify.

In this paper, we introduce a new variant of growing self-organizing maps (GSOM) based on Alahakoon's algorithm for SOM training; so called 2IBGSOM (interior and irregular boundaries growing self-organizing maps). It's dynamically evolving structure for SOM, which allocates map size and shape during the unsupervised training process. 2IBGSOM starts with a small number of initial nodes and generates new nodes from the boundary and the interior of the network. 2IBGSOM represents the structure of the training data as accurately as possible. Our proposed method was tested on real world databases and showed better performance than the classical SOM and the growing grid (GG) algorithms. Three criteria were used to compare the above algorithms with our proposed method; the quantization error; the topological error and the labeling error to have more accuracy on the produced structure. Results report that 2IBGSOM shows a very good capacity of estimation for the training data based on the three tested factors.

This article describes a kinematic theory, called the Bêta-elliptic model, for generating handwriting movements. The model consists of a sequential controller producing a curvilinear velocity approximated by Bêta profiles. This earlier interacts with a trajectory generator to provide elliptic strokes. As an application to our model, we consider a redundant seven degrees of freedom manipulator having a kinematic structure similar to that of a human arm. We treat to demonstrate how the Bêta-elliptic theory enables a simple motor program to generate complex curvilinear movements that have many of the properties that humans exhibit when they produce cursive script. Bêta-elliptic properties enable a simple control strategy to generate complex handwritten script if the hand model contains redundant degrees of freedom. Here, we restrict our analysis to a total of seven degrees of freedom from the shoulder to the wrist. The proposed controller launches transient commands to independent hand synergies at times when the hand begins to move. The Bêta-elliptic model transforms these synergy commands into smooth curvilinear velocity fitted by Bêta profiles among temporally overlapping synergetic units of trajectory approximated by elliptic strokes. In experiments, and at first sight, good phenomenological agreement with natural movement trajectories is found.

We propose a new feature selection method based on distributed genetic algorithms and bi-coded genes. This solution uses homogeneous and heterogeneous population strategies to minimize the complexity and to accelerate the algorithm convergence. The importance rate is computed for each feature measure to estimate the contribution of each feature in the finale selected vector. A new fitness function was proposed to take into consideration the recognition rate relatively to the size of the selected features subset. Two genetic codes are used to represent each member; a binary code to represent when the corresponding feature was selected or not; the second real code was used to estimate the importance rate of the selected feature or the selection probability for the non selected feature.

We develop a modified differential evolution algorithm that produces radial basis function neural network controllers for chaotic systems. This method requires few controlling variables. We examine the result of applying the proposed algorithm to time series prediction, which illustrates the effectiveness of this technique. We apply this algorithm to several computational and real systems including Mackey-Glass time series, the Lorenz attractor, and experimental data obtained from the Henon map. Our experiments indicate that the structural differences between our approach and the other methods existing in the bibliography particularly are well suited to modeling chaotic time series data.

Summary form only given. In this article, we present a new architecture of the intelligent tutoring system (ITS) and we suggest an original method, which allows recognizing the expression of the learner's face during exercise. It helps evaluate his affective state in an emotional system in order to distinguish his influence on his responses. Accordingly, we should first be able to detect his face, extract his important features translating the state of his expression (characteristical features: eyes and mouth,), then we should analyse their configuration and characteristics in order to recognize the expression, which describe and interpret it. Our architecture is based on the observation of the behaviour of the learner; detect engaging signs so as to detect affective responses, which can be the manifestation of feelings of interest, excitement and confusion. From the observation and the identification of the emotional state of the learner, the tutor can undertake actions which influences the quality of learning and its execution (important remarks may reduce the feeling of failure of the learner or avoid the risk of interrupting his work as soon as he feels bored). A scientific and especially emotional analysis is necessary to evaluate and help the learner during exercise.

Summary form only given. In this paper, we present a system of restoration of temporal order in the offline Arabic handwritten tracing. The word image, captured in level of gray from a scanner with a resolution of 300 dpi, passes by four stages of preprocessing: binarization, filtering, smoothing and elimination of the diacritical signs. A first algorithm calculates for every point of the contour a curvature function. The local maximas of this function correspond to the dominant points of the contour. The dominant points correspond to all angular variations on the contour (end of the stroke, cross point, branch point, pocket, buckle...). A sweep of a window of a dimension equal to the triple of the thickness, of the stroke permits to detect cross and branch points of features and a suitable algorithm permits to solve the problem of the temporal order in these ambiguous zones. Finally, another algorithm permits to detect the starting point and to follow the tracing in order to reconstitute the order in which it has been written. The system is improved by an algorithm that treats the particular cases concerning the starting point, the ambiguous zone analysis and the progression of the system at the time of the follow-up of the contour. Preliminary results obtained from our basis (50 words written by 2 people), are: detection of the point of departure: 96%; correct interpretation of ambiguous zones: 95%; and movement of pen (temporal order) recovered: 92%.

The majority of the studies conducted in scheduling real-time imprecise transactions mostly concentrate on flat transaction models. In this paper, we apply this technique to distributed real-time nested transaction models. We consider that nested transaction is a collection of both essential and non-essential subtransactions. We propose a real-time imprecise concurrency control protocol (ICCP) that resolves the conflicts in favor of the essential subtransactions. For the lending of data-item, we have used the PROMPT commit protocol, which causes intra-aborts cascade in nested environment. To alleviate this problem, we propose a S-PROMPT commit protocol: the borrowing subtransaction carries out a speculative execution by accessing both before and after-image (prepared-data) of the lending subtransaction. Simulations we have carried out show that by allowing better concurrency between transaction trees and between subtransactions on the same transaction tree and the speculative lending of data-item, the firm real-time performance of nested transactions are greatly increased.

We propose a new approach for Arabic word recognition called affixal approach. This approach is founded on morphological structure of Arabic vocabulary. A mechanism of decomposition-recognition is used in our approach and makes it possible to lead to a set of reliable solutions for each word. This mechanism tries to recognize word basic morphemes: prefix, infix, suffix and root contrary to existing approaches which are usually based on recognition of word entity by holistic approach, pseudo-word entity by pseudo-analytical approach or letter entity by analytical approach. In this paper, we will present limits of existing approaches for Arabic word recognition. We will expose then Arabic vocabulary structure. We will detail after affixal approach for Arabic decomposable vocabulary recognition with a word example. Lastly, we will expose experimental results obtained on a basis of 1000 words data set.

In this work, we present a new tool for the font optical recognition. This tool is based on the use of the fractal geometry. We used two techniques for obtaining two parameters, they allowed the extraction of the global textures characteristics. These characteristics are expressed in a parametric form. The vision aspect is held in consideration, since it makes it possible to differentiate one font of another. Experiments show the importance of the proposed approach.

We propose an evolutionary method for the design of Beta fuzzy systems (BFS). Classical training algorithms start with a predetermined number of fuzzy rules for fuzzy systems. Generally speaking, the fuzzy system created is either insufficient or over-complicated. This paper describes a hierarchical genetic learning model of the BFS. In order to examine the performance of the proposed algorithm, it is used for the identification of an induction machine fuzzy plant model. The results obtained have been encouraging.

This paper studies the dependence betweengeometry and kinematics in handwriting generationMovements. Based on a handwriting generationmodel developed earlier, movements parameters areextracted directly from on-line recording of velocityprofiles. These parameters, which reflect dynamicprocess, are found to be highly related to thegeometry of handwriting movements.The overall approach is based upon thehypothesis that complex human movements can besegmented into, basic and simple units. In otherwords, due to the intrinsic properties of theneuromuscular system involved in a rapid writingtask, there is a class of simple movements, hereaftercalled strokes. More complex movements are thusgenerated by the addition of the various strokesbelonging to such a class.

The use of artificial outputs generated by a classifier simulator has recently emerged as a new trend to provide an underlying evaluation of classifier combination methods. In this paper, we propose a new method for the artificial generation of classifier outputs based on additional parameters which provide sufficient diversity to simulate, for a problem of any number of classes and any type of output, any classifier performance. This is achieved through a two-step algorithm which first builds a confusion matrix according to desired behaviour and secondly generates, from this confusion matrix, outputs of any specified type. We provide the detailed algorithms and constraints to respect for the construction of the matrix and the generation of outputs. We illustrate on a small example the usefulness of the classifier simulator.

The problem of simultaneous approximations of a given function and its derivatives, has been addressed frequently in pure and applied mathematics. In pure mathematics, Bernstein polynomials get their importance from the fact that they provide simultaneous approximation of a function and its derivatives. In neural network theory, feedforward networks were shown to be universal approximators of an unknown function and its derivatives. In this paper, we consider fuzzy logic systems with the membership functions of each input variables are chosen as the translations and dilations of one appropriately fixed function. We prove, by a constructive proof based on discretization of the convolution operator, that under certain conditions made on the input variables membership functions, fuzzy logic systems of Sugeno type are universal approximators of a given function and its derivatives.

The aim of the work was the full design of a Beta fuzzy system for the modeling of nonlinear processes. We propose a hierarchical genetic algorithm with two nodes connected together. Each node is a real coded genetic algorithm allowing the migration of individuals between each other. These two algorithms are based on a Pittsburgh-style approach where each chromosome encodes a set of knowledge bases. Our main contribution results in the genetic representation wherein each individual is coded as a two-dimension matrix, the number of lines is equal to the number of input variables whereas four columns of the matrix represent one fuzzy rule. One distinguishing feature of this approach is that it gives a standard solution to building a fuzzy logic system and neural networks.

Proposes a multi-agent approach (MA) for genetic algorithms (GA) applied to the training of Beta basis function neural networks (BBFNN). This approach, called the multi-agent distributed genetic algorithm (MADGA) has two advantages. First, thanks to the GAs' efficiency, it allows us to design a suitable architecture for the Beta system. Second, it improves the GAs' convergence by reducing their temporal complexity thanks to distributed implementation of the MA system. Agents, which are managed dynamically, interact to provide an optimal solution in order to obtain the best neural network that is considered as a compromise between network performances and structures. For illustration and discussion, we used BBFNN training sets with two space dimensions.