• Systematic review of 373 Mel-based AEDC studies from 2020 to 2025. • Five Mel feature types analysed across four key parameters. • Jensen-Shannon divergence quantifies temporal parameter trends. • Domain-specific parameter patterns across four application areas. • Practical guidance for Mel parameter selection in AEDC systems. Acoustic Event Detection and Classification (AEDC) systems are artificial intelligence technologies widely used in modern audio-based monitoring and decision-support applications. These systems may operate independently or function as perceptual modules within intelligent decision-making frameworks and expert systems. AEDC has been applied in diverse domains, including security monitoring, healthcare diagnostics, environmental surveillance, and industrial maintenance. Although Mel-based features are extensively employed in both traditional machine learning and deep learning AEDC approaches, no comprehensive review has systematically analysed their usage patterns and parameter configurations. This systematic review examines 373 AEDC studies published between 2020 and 2025 that employ Mel-based feature extraction. Five principal feature types are analysed: Log Mel Spectrogram (237 studies), Mel Spectrogram (61 studies), Log Mel Band Energies (34 studies), Mel-Frequency Cepstral Coefficients (36 studies), and Mel Band Energies (5 studies). Four critical Mel-related parameters—number of Mel filters, frame length, overlap percentage, and window type—are evaluated to identify dominant configurations, feature-specific patterns, and temporal trends. Classification architectures are systematically mapped across studies to analyse the relationship between feature selection and model design. The results reveal substantial variability in parameter choices across feature types and application contexts, as well as dominant trends aligned with deep learning frameworks. The review further identifies methodological gaps and outlines research directions to improve the design, reporting, and optimisation of Mel-based AEDC systems.

Urban vehicle accidents highlight the need for intelligent systems that can process environmental acoustic signals and improve driver awareness. Traditional acoustic event detection and classification (AEDC) methods often struggle to perform effectively when multiple acoustic events overlap in frequency. This study presents a two-stage framework for detecting and classifying horn signals in urban driving scenarios. The first stage separates horn signals from background noise using Log-Mel spectrogram features and a bagging ensemble classifier. The second stage classifies detected horns into four categories (boat, car, train, truck) using VGGish features. Feature dimensionality is reduced by approximately 40% through minimum Redundancy Maximum Relevance (mRMR) selection without losing accuracy. A post-processing step based on the binomial probability distribution corrects errors across consecutive frames in both stages. The proposed system achieves a minimum F1 score of 0.82 before post-processing and 0.96 after post-processing across all horn classes. This represents more than a 15% improvement over recent deep learning approaches, while maintaining low computational demands through feature selection. The hybrid architecture makes AEDC practical for driver assistance systems in automotive environments with limited processing resources.

Abstract Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative condition in the brain that affects memory, thinking, and behaviour. To overcome this problem, which according to the World Health Organization, is on the rise, creating strategies is essential to identify and predict the disease in its early stages before clinical manifestation. In addition to cognitive and mental tests, neuroimaging is promising in this field, especially in assessing brain matter loss. Therefore, computer‐aided diagnosis systems have been imposed as fundamental tools to help imaging technicians as the diagnosis becomes less subjective and time‐consuming. Thus, machine learning and deep learning (DL) techniques have come into play. In recent years, articles addressing the topic of Alzheimer's diagnosis through DL models are increasingly popular, with an exponential increase from year to year with increasingly higher accuracy values. However, the disease classification remains a challenging and progressing issue, not only in distinguishing between healthy controls and AD patients but mainly in differentiating intermediate stages such as mild cognitive impairment. Therefore, there is a need to develop more valuable and innovative techniques. This article presents an up‐to‐date systematic review of deep models to detect AD and its intermediate phase by evaluating magnetic resonance images. The DL models chosen by different authors are analysed, as well as their approaches regarding the used dataset and the data pre‐processing and analysis techniques.

Abstract An autonomous vehicle can sense its environment and operate without human involvement. Its adequate management in an intelligent transportation system could significantly reduce traffic congestion and overall travel time in a network. Adaptive traffic signal controller (ATSC) based on multi‐agent systems using state‐action‐reward‐state‐action (SARSA ()) are well‐known state‐of‐the‐art models to manage autonomous vehicles within urban areas. However, this study found inefficient weights updating mechanisms of the conventional SARSA () models. Therefore, it proposes a Gaussian function to regulate the eligibility trace vector's decay mechanism effectively. On the other hand, an efficient understanding of the state of the traffic environment is crucial for an agent to take optimal actions. The conventional models feed the state values to the agents through the MinMax normalization technique, which sometimes shows less efficiency and robustness. So, this study suggests the MaxAbs scaled state values instead of MinMax to address the problem. Furthermore, the combination of the A‐star routing algorithm and proposed model demonstrated a good increase in performance relatively to the conventional SARSA ()‐based routing algorithms. The proposed model and the baselines were implemented in a microscopic traffic simulation environment using the SUMO package over a complex real‐world‐like ‐intersections network to evaluate their performance. The results showed a reduction of the vehicle's average total waiting time and total stops by a mean value of % and % compared to the considered baselines. Also, the A‐star combined with the proposed controller outperformed the conventional approaches by increasing the vehicle's average trip speed by %.

Abstract The detection of sound events has become increasingly important due to the development of signal processing methods, social media, and the need for automatic labeling methods in applications such as smart cities, navigation, and security systems. For example, in such applications, it is often important to detect sound events at different levels, such as the presence or absence of an event in the segment, or to specify the beginning and end of the sound event and its duration. This study proposes a method to reduce the feature dimensions of a Sound Event Detection (SED) system while maintaining the system’s efficiency. The proposed method, using Empirical Mode Decomposition (EMD), Intrinsic Mode Functions (IMFs), and extraction of locally regulated features from different IMFs of the signal, shows a promising performance relative to the conventional features of SED systems. In addition, the feature dimensions of the proposed method are much smaller than those of conventional methods. To prove the effectiveness of the proposed features in SED tasks, two segment-based approaches for event detection and sound activity detection were implemented using the suggested features, and their effectiveness was confirmed. Simulation results on the URBAN SED dataset showed that the proposed approach reduces the number of input features by more than 99% compared with state-of-the-art methods while maintaining accuracy. According to the obtained results, the proposed method is quite promising.

Accurate traffic state prediction is fundamental to Intelligent Transportation Systems, playing a critical role in optimising traffic management, improving mobility, and enhancing the efficiency of transportation networks. Traditional methods often rely on feature engineering, statistical time-series approaches, and non-parametric techniques to model the inherent complexities of traffic states, incorporating external factors such as weather conditions and accidents to refine predictions. However, the effectiveness of long-term traffic state prediction hinges on capturing spatial-temporal dependencies over extended periods. Current models face challenges in dealing with (i) high-dimensional traffic features, (ii) error accumulation for multi-step prediction, and (iii) robustness to external factors effectively. To address these challenges, this study proposes a novel model with a Dynamic Feature Embedding layer designed to transform complex data sequences into meaningful representations and a Deep Linear Projection network that refines these representations through non-linear transformations and gating mechanisms. These two features make the model more scalable when dealing with high-dimensional traffic features. The model also includes a Spatial-Temporal Positional Encoding layer to capture spatial-temporal relationships, masked multi-head attention-based encoder blocks, and a Residual Temporal Convolutional Network to process features and extract short- and long-term temporal patterns. Finally, a Time-Distributed Fully Connected Layer produces accurate traffic state predictions up to 24 timesteps into the future. The proposed architecture uses a direct strategy for multi-step modelling to help predict timesteps non-autoregressively and thus circumvents the error accumulation problem. The model was evaluated against state-of-the-art baselines using two benchmark datasets. Experimental results demonstrated the model's superiority, achieving up to 21.17% and 29.30% average improvements in Root Mean Squared Error and 3.56% and 32.80% improvements in Mean Absolute Error compared to the baselines, respectively. The Friedman Chi-Square statistical test further confirmed the significant performance difference between the proposed model and its counterparts. The adversarial perturbations and random sensor dropout tests demonstrated its good robustness. On top of that, it demonstrated good generalizability through extensive experiments. The model effectively mitigates error accumulation in multi-step predictions while maintaining computational efficiency, making it a promising solution for enhancing Intelligent Transportation Systems.

Acoustic monitoring of road traffic events is an indispensable element of Intelligent Transport Systems to increase their effectiveness. It aims to detect the temporal activity of sound events in road traffic auditory scenes and classify their occurrences. Current state-of-the-art algorithms have limitations in capturing long-range dependencies between different audio features to achieve robust performance. Additionally, these models suffer from external noise and variation in audio intensities. Therefore, this study proposes a spectrogram-specific transformer model employing a multi-head attention mechanism using the scaled product attention technique based onsoftmaxin combination with Temporal Convolutional Networks to overcome these difficulties with increased accuracy and robustness. It also proposes a unique preprocessing step and a Deep Linear Projection method to reduce the dimensions of the features before passing them to the learnable Positional Encoding layer. Rather than monophonic audio data samples, stereophonic Mel-spectrogram features are fed into the model, improving the model’s robustness to noise. State-of-the-art One-dimensional Convolutional Neural Networks and Long Short-term Memory models were used to compare the proposed model’s performance on two well-known datasets. The results demonstrated its superior performance by achieving an improvement in accuracy of 1.51 to 3.55% compared to the studied baselines.

Abstract Since digital media has become increasingly popular, video processing has expanded in recent years. Video processing systems require high levels of processing, which is one of the challenges in this field. Various approaches, such as hardware upgrades, algorithmic optimizations, and removing unnecessary information, have been suggested to solve this problem. This study proposes a video saliency map based method that identifies the critical parts of the video and improves the system’s overall performance. Using an image registration algorithm, the proposed method first removes the camera’s motion. Subsequently, each video frame’s color, edge, and gradient information are used to obtain a spatial saliency map. Combining spatial saliency with motion information derived from optical flow and color-based segmentation can produce a saliency map containing both motion and spatial data. A nonlinear function is suggested to properly combine the temporal and spatial saliency maps, which was optimized using a multi-objective genetic algorithm. The proposed saliency map method was added as a preprocessing step in several Human Action Recognition (HAR) systems based on deep learning, and its performance was evaluated. Furthermore, the proposed method was compared with similar methods based on saliency maps, and the superiority of the proposed method was confirmed. The results show that the proposed method can improve HAR efficiency by up to 6.5% relative to HAR methods with no preprocessing step and 3.9% compared to the HAR method containing a temporal saliency map.

Speech recognition aims to convert human speech into text and has applications in security, healthcare, commerce, automobiles, and technology, just to name a few. Inserting residual neural networks before recurrent neural network cells improves accuracy and cuts training time by a good margin. Furthermore, layer normalization instead of batch normalization is more effective in model training and performance enhancement. Also, the size of the datasets presents tremendous influences in achieving the best performance. Leveraging these tricks, this article proposes an automatic speech recognition model with a stacked five layers of customized Residual Convolution Neural Network and seven layers of Bi-Directional Gated Recurrent Units, including a logarithmic softmax for the model output. Each of them incorporates a learnable per-element affine parameter-based layer normalization technique. The training and testing of the new model were conducted on the LibriSpeech corpus and LJ Speech dataset. The experimental results demonstrate a character error rate (CER) of 4.7 and 3.61% on the two datasets, respectively, with only 33 million parameters without the requirement of any external language model.

Over the last decades, facing the blooming growth of technological progress, interest in digital devices such as computed tomography (CT) as well as magnetic resource imaging which emerged in the 1970s has continued to grow. Such medical data can be invested in numerous visual recognition applications. In this context, these data may be segmented to generate a precise 3D representation of an organ that may be visualized and manipulated to aid surgeons during surgical interventions. Notably, the segmentation process is performed manually through the use of image processing software. Within this framework, multiple outstanding approaches were elaborated. However, the latter proved to be inefficient and required human intervention to opt for the segmentation area appropriately. Over the last few years, automatic methods which are based on deep learning approaches have outperformed the state-of-the-art segmentation approaches due to the use of the relying on Convolutional Neural Networks. In this paper, a segmentation of preoperative patients CT scans based on deep learning architecture was carried out to determine the target organ’s shape. As a result, the segmented 2D CT images are used to generate the patient-specific biomechanical 3D model. To assess the efficiency and reliability of the proposed approach, the 3DIRCADb dataset was invested. The segmentation results were obtained through the implementation of a U-net architecture with good accuracy.

Hand tracking and gesture recognition are fundamental in a multitude of applications. Various sensors have been used for this purpose, however, all monocular vision systems face limitations caused by occlusions. Wearable equipment overcome said limitations, although deemed impractical in some cases. Using more than one sensor provides a way to overcome this problem, but necessitates more complicated designs. In this work, we aim to highlight contemporary methods used for hand tracking and gesture recognition by collecting publications of systems developed in the last decade, that employ contactless devices as RGB cameras, IR, and depth sensors, along with some preceding pillar works. Additionally, we briefly present common steps, techniques, and basic algorithms used during the process of developing modern hand tracking and gesture recognition systems and, finally, we derive the trend for the next future.

Diabetic Foot Ulcers (DFU) are lesions in the foot region caused by diabetes mellitus. It is essential to define the appropriate treatment in the early stages of the disease once late treatment may result in amputation. This article proposes an ensemble approach composed of five modified convolutional neural networks (CNNs) - VGG-16, VGG-19, Resnet-50, InceptionV3, and Densenet-201 - to classify DFU images. To define the parameters, we fine-tuned the CNNs, evaluated different configurations of fully connected layers, and used batch normalization and dropout operations. The modified CNNs were well suited to the problem; however, we observed that the union of the five CNNs significantly increased the success rates. We performed tests using 8,250 images with different resolution, contrast, color, and texture characteristics and included data augmentation operations to expand the training dataset. 5-fold cross-validation led to an average accuracy of 95.04%, resulting in a Kappa index greater than 91.85%, considered “Excellent”.

Proton therapy is a cancer therapy that is more expensive than classical radiotherapy but that is considered the gold standard in several situations. Since there is also a limited amount of delivering facilities for this techniques, it is fundamental to increase the number of treated patients over time. The objective of this work is to offer an insight on the problem of the optimization of the part of the delivery time of a treatment plan that relates to the movements of the system. We denote it as the Nozzle Travel Time Problem (NTTP), in analogy with the Leaf Travel Time Problem (LTTP) in classical radiotherapy. In particular this work: (i) describes a mathematical model for the delivery system and formalize the optimization problem for finding the optimal sequence of movements of the system (nozzle and bed) that satisfies the covering of the prescribed irradiation directions; (ii) provides an optimization pipeline that solves the problem for instances with an amount of irradiation directions much greater than those usually employed in the clinical practice; (iii) reports preliminary results about the effects of employing two different resolution strategies within the aforementioned pipeline, that rely on an exact Traveling Salesman Problem (TSP) solver, Concorde, and an efficient Vehicle Routing Problem (VRP) heuristic, VROOM.

With the emergence of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), three-dimensional images facilitate the generation of 3D models of a patient, providing a new practical and accurate assistance, particularly for surgical planning. These images can be manipulated to produce an accurate 3D representation of an organ. The reconstructed mesh can be used to generate and visualize a deformable model during surgical intervention using Augmented Reality (AR) technology. To obtain an efficient reconstruction, a segmentation of these medical images using deep learning architecture can be used to extract the target organ's properties. Many methods were proposed based on the captured pre-operative patient's CT scans. Generally, the segmentation process is done manually using image processing software. In this context several approaches were proposed, these methods are not efficient and need human interaction to select the segmentation area correctly. This work aims to develop a deep learning method using a Convolutional Neural Network (CNN) that captures the liver organ from a set of CT scans. Given preoperative patient-specific data (CT scans), the U-net architecture is implemented to detect the liver organ. As a result, the segmented 2D images are used to generate a 3D patient-specific liver model.

Augmented Reality (AR) technology offers innovative ways in order to visualize and manipulate a 3D model of an object by superimposing computer-generated images onto another object interactively. The ability to interact with digital and spatial information in real-time offers new opportunities to manipulate and process medical data easily and efficiently. During surgical interventions, surgeons face various challenges dealing with digital patient data. Several methods are used to visualize the operative areas, such as fluoroscopy and ultrasound techniques. These techniques have several limitations. Thus, the augmented reality technique could serve as a better alternative to project a three-dimensional model of the target organ into the surgeon's perspective and field of view to improve the accuracy and efficiency of the medical intervention intraoperatively. In this paper, a new AR method is proposed in order to visualize and simulate the biomechanical model of the liver organ during open hepatic surgery. In this regard, the 3D model based on the patient's preoperative CT scans is first reconstructed. Then, the reconstructed model is projected using the AR headset. After that, the biomechanical model is generated and prepared for the simulation. The proposed approach is validated using acquired CT scans of the human organ.

Abstract According to the World Alzheimer Report 2015, 46 million people are living with dementia in the world. The diagnosis of diseases helps doctors treating patients better. One of the signs of diseases is related to white matter, grey matter and cerebrospinal fluid. Therefore, the automatic segmentation of three tissues in brain imaging especially from magnetic resonance imaging (MRI) plays an important role in medical analysis. In this research, we proposed an effective approach to segment automatically these tissues in three-dimensional (3D) brain MRI. First, a deep learning model is used to segment the sure and unsure regions. In the unsure region, another deep learning model is used to classify each pixel. In the experiments, an adaptive U-net model is used to segment the sure and unsure regions, and the Local Convolutional Neural Network (CNN) model with multiple inputs is used to classify each pixel only in the unsure region. Our method was evaluated with a real image database, Internet Brain Segmentation Repository database, with 18 persons (IBSR 18) (https://www.nitrc.org/projects/ibsr) and compared with state of art methods being the results very promising.

Quantum computing has made rapid progress in many fields, especially in artificial intelligence. Quantum machine learning is introduced to enhance the training rate of machine learning algorithms and hence, to achieve enhanced accuracy. The integration of quantum computing with artificial intelligence is incorporated with quantum neural networks and quantum tensor flow. Quantum neural networks play a vital role in enhancement of quantum computing progress in techniques of artificial intelligence. The aim of this special issue is to depict the importance and advances of quantum computing in a variety of fields, especially artificial intelligence. In the article by Jiao,1 fault tolerance for design of digital comparators is examined. A coplanar quantum-dot cellular automata (QCA) based fault tolerance comparator is proposed in order to achieve good simulation results. QCA designer needs 63 cells of QCA of 0.8μ2 and it requires three clock cycles delay to complete the task. In the article by Dogra et al.,2 an algorithm named multi-level filtering based image fusion algorithm is proposed for fusion of image information from MRI and CT scan images into a single vector. In the first step, source images are processed with the help of a filter of rolling guidance and then the calculation of the detail layer is performed. After that, guidance is used with the same rolling filter for the calculation of the base layer for edge preservation at a higher level. At the next step, in order to remove noise and other artifacts, all detail layers are fused together using the Karhunen Loeve transform and all the base layers are combined together by using the principle of weighted superimposition. In the article by Umer et al.,3 a method for early detection of COVID-19 is proposed in order to minimize the mortality rate. This method has two different phases: in the first phase, the pre-trained models like AlexNet and MobileNet are used and from their last fully connected layers deep features are extracted and then these extracted feature vectors are concatenated. Applying a method of feature selection, such as principal component analysis (PCA), the best features are then selected and then those features are passed to k-nearest neighbors algorithm (KNN) and support vector machine (SVM) for classification. In the second phase, a model of quantum transfer learning is used where a pre-trained model ResNet-18 is used for the collection of deep features and then these features are given to a four-qubit quantum circuit for the purpose of training with tuned hyper parameters. The proposed method is tested on two X-ray image datasets which are publicly available. In the article by Das et al.,4 the prediction of the OS period in a brain tumor is performed using the rain forest framework. Different algorithms such as eXtreme Gradient Boosting (XGBoost), light gradient boosting machine, and SVMs are used to take radiomic features and the efficiency of prediction is dependent upon the tumor volume, which is segmented after taking multiple MRI images. The complete tumor and its sub-parts are extracted from MRI model modalities by using the U-Net++ deep model and these are stacked together for the extraction of deep features via a convolutional neural network. In order to achieve increased accuracy, features are reduced by using PCA and then for the prediction of the OS period, the reduced radiomic feature set is used. The prediction results are tested for survival groups in both cases: for two classes and for three classes. Experiments are performed on the dataset of BraTs 2017 for both two classes and three classes by using different types of classifiers. In order to have an enhanced accuracy, different methods of optimization like PCA and genetic algorithm are used for the fusion of feature sets. In the article by Lepcha et al.,5 a piecewise regression model is proposed for learning the images through the mapping of resolution images from low to high. This is performed by utilizing filtering of the domain transform and an optimized framework of weighted least squares. First, the weighted least mean square is used to coarsen the given input images to extract multiscale information by building multiscale decompositions for edge preservations for which recursive filtering is also applied. The patterns named as Hadamard from low resolution images are collected for the classification of high resolution and low resolution image features. Finally, a piecewise linear regression model is used to learn the relationship of mapping between the classes of high resolution and low resolution image features.

Abstract Human gait recognition (HGR) shows high importance in the area of video surveillance due to remote access and security threats. HGR is a technique commonly used for the identification of human style in daily life. However, many typical situations like change of clothes condition and variation in view angles degrade the system performance. Lately, different machine learning (ML) techniques have been introduced for video surveillance which gives promising results among which deep learning (DL) shows best performance in complex scenarios. In this article, an integrated framework is proposed for HGR using deep neural network and fuzzy entropy controlled skewness (FEcS) approach. The proposed technique works in two phases: In the first phase, deep convolutional neural network (DCNN) features are extracted by pre‐trained CNN models (VGG19 and AlexNet) and their information is mixed by parallel fusion approach. In the second phase, entropy and skewness vectors are calculated from fused feature vector (FV) to select best subsets of features by suggested FEcS approach. The best subsets of picked features are finally fed to multiple classifiers and finest one is chosen on the basis of accuracy value. The experiments were carried out on four well‐known datasets, namely, AVAMVG gait, CASIA A, B and C. The achieved accuracy of each dataset was 99.8, 99.7, 93.3 and 92.2%, respectively. Therefore, the obtained overall recognition results lead to conclude that the proposed system is very promising.

Traffic flow forecasting is an essential component of an intelligent transportation system to mitigate congestion. Recurrent neural networks, particularly gated recurrent units and long short-term memory, have been the state-of-the-art traffic flow forecasting models for the last few years. However, a more sophisticated and resilient model is necessary to effectively acquire long-range correlations in the time-series data sequence under analysis. The dominant performance of transformers by overcoming the drawbacks of recurrent neural networks in natural language processing might tackle this need and lead to successful time-series forecasting. This article presents a multi-head attention based transformer model for traffic flow forecasting with a comparative analysis between a gated recurrent unit and a long-short term memory-based model on PeMS dataset in this context. The model uses 5 heads with 5 identical layers of encoder and decoder and relies on Square Subsequent Masking techniques. The results demonstrate the promising performance of the transform-based model in predicting long-term traffic flow patterns effectively after feeding it with substantial amount of data. It also demonstrates its worthiness by increasing the mean squared errors and mean absolute percentage errors by (1.25−47.8)% and (32.4−83.8)%, respectively, concerning the current baselines.

Dermoscopic images are commonly used in the early diagnosis of skin lesions, and several computational systems have been proposed to analyze them. The segmentation of the lesions is a fundamental step in many of these systems. Therefore, a semi-automatic segmentation method is proposed here, which begins by building the superpixels of the image under analysis based on the zero parameter version of the simple linear iterative clustering (SLIC0) algorithm. Then, each superpixel is represented using a descriptor built by combining the grey-level co-occurrence matrix and Tamura texture features. Afterward, the gain ratios of the features are used to select the input for the semi-supervised seeded fuzzy C-means clustering algorithm. Hence, from a few specialist-selected superpixels, this clustering algorithm groups the built superpixels into lesion or background regions. Finally, the segmented image undergoes a post-processing step to eliminate sharp edges. The experiments were performed on 1380 images: 401 images from the PH2 and DermIS datasets, which were used to establish the parameters of the method, and 3,573 images from the ISIC 2016, ISIC 2017 and ISIC 2018 datasets were used for the analysis of the method’s performance. The findings suggest that, by manually identifying just a few of the generated superpixels, the method can achieve an average segmentation accuracy of 96.78%, which confirms its superiority to the ones in the literature.

Abstract Virtual Glove (VG) is a low-cost computer vision system that utilizes two orthogonal LEAP motion sensors to provide detailed 4D hand tracking in real–time. VG can find many applications in the field of human-system interaction, such as remote control of machines or tele-rehabilitation. An innovative and efficient data-integration strategy, based on the velocity calculation, for selecting data from one of the LEAPs at each time, is proposed for VG. The position of each joint of the hand model, when obscured to a LEAP, is guessed and tends to flicker. Since VG uses two LEAP sensors, two spatial representations are available each moment for each joint: the method consists of the selection of the one with the lower velocity at each time instant. Choosing the smoother trajectory leads to VG stabilization and precision optimization, reduces occlusions (parts of the hand or handling objects obscuring other hand parts) and/or, when both sensors are seeing the same joint, reduces the number of outliers produced by hardware instabilities. The strategy is experimentally evaluated, in terms of reduction of outliers with respect to a previously used data selection strategy on VG, and results are reported and discussed. In the future, an objective test set has to be imagined, designed, and realized, also with the help of an external precise positioning equipment, to allow also quantitative and objective evaluation of the gain in precision and, maybe, of the intrinsic limitations of the proposed strategy. Moreover, advanced Artificial Intelligence-based (AI-based) real-time data integration strategies, specific for VG, will be designed and tested on the resulting dataset.

Many critical aspects affect the correct operation of a Brain Computer Interface. The term ‘BCI-illiteracy’ describes the impossibility of using a BCI paradigm. At present, a universal solution does not exist and seeking innovative protocols to drive a BCI is mandatory. This work presents a meta-analytic review on recent advances in emotions recognition with the perspective of using emotions as voluntary, stimulus-independent, commands for BCIs. 60 papers, based on electroencephalography measurements, were selected to evaluate what emotions have been most recognised and what brain regions were activated by them. It was found that happiness, sadness, anger and calm were the most recognised emotions. Relevant discriminant locations for emotions recognition and for the particular case of discrete emotions recognition were identified in the temporal, frontal and parietal areas. The meta-analysis was mainly performed on stimulus-elicited emotions, due to the limited amount of literature about self-induced emotions. The obtained results represent a good starting point for the development of BCI driven by emotions and allow to: (1) ascertain that emotions are measurable and recognisable one from another (2) select a subset of most recognisable emotions and the corresponding active brain regions.

Dermoscopy is an imaging technique that has been widely used in the diagnosis of skin lesions. However, its accuracy largely depends on the dermatologist's experience; thus, computer-aided diagnosis techniques are required. In this paper, a novel approach based on a deformable model is proposed to handle the segmentation of skin lesions in dermoscopic images. The RGB color space is converted so that the color information contained in the images can be used effectively to differentiate normal skin and skin lesions; and the differences in the color channels are combined together to define the speed function and the stopping criterion of the deformable model. This novel approach is robust against the noise, and provides an effective and flexible segmentation. Two image databases were used to test the performance of the novel approach and the segmentation results obtained were satisfactory. Quantitative analysis on 250 dermoscopic images showed that the novel algorithm outperformed other state-of-the-art algorithms. Also, using comparative data, the reliability and the implementation issues of the approach are discussed in this paper.

In this paper, we show how to improve the Radial Basis Function Neural Networks effectiveness by using the Optimum-Path Forest clustering algorithm, since it computes the number of clusters on-the-fly, which can be very interesting for finding the Gaussians that cover the feature space. Some commonly used approaches for this task, such as the well-known fc-means, require the number of classes/clusters previous its performance. Although the number of classes is known in supervised applications, the real number of clusters is extremely hard to figure out, since one class may be represented by more than one cluster. Experiments over 9 datasets together with statistical analysis have shown the suitability of OPF clustering for the RBF training step.

Several standardized video coding algorithms use a well known discrete cosine transform (DCT) at the encoder to remove redundancy from video random processes. Its inverse, the IDCT is present at the decoder as well as at the encoder loop. The accuracy of this inverse transform, required to avoid large drift between the encoder and decoder, is defined in an IEEE standard which will be withdrawn from MPEG and ITU standardized codecs. Due to the huge number of computations required to compute the FDCT/IDCT (forward/inverse DCT) pair, reduction of their complexity is essential to speed up the video processing. In this paper, we propose a fast integer IDCT calculation method. Additionally, we insert it into the H.263 reference software in order to validate our proposed method. The testing results using two different video sequences, at QCIF and CIF resolutions, show similar PSNR average values between the reference H.263 and the proposed H.263 codec