Recent advancements in ambient assisted living (AAL) technologies leverage machine learning (ML) and deep learning (DL) for improved emergency response and preventive care. This research introduces a multi-modal system with an advanced vision-language model (VLM) to enhance detection capabilities in AAL settings. Using DL, the system interprets scenes to generate captions, answer visual questions, and facilitate commonsense reasoning. An interactive chatbot with a large language model (LLM) and text-to-speech and speech-to-text capabilities enables real-time assessments of abnormal behavior. The system uses prompt engineering to refine anomaly detection without extensive retraining. It autonomously dispatches ambulances and generates alerts. Qualitative analysis confirms high usability among study participants, while quantitative assessments show a detection accuracy of 93.44 %, a recall rate of 95 %, and a specificity rate of 88.88 %. User interactions further enhance accuracy to 100%. This multi-modal system improves emergency recognition and response, providing caregivers with actionable insights in real time.

Injuries and sudden health crises at home demand rapid medical response. We present a lightweight framework that integrates the PrismerZ vision-language model with a key-frame selection algorithm and a multimodal retrieval system to recognize emergencies from video data. The approach combines image captioning and visual question answering with efficient storage and search of embeddings to support healthcare professionals. Evaluated on the Kinetics benchmark (86.5 % image captioning accuracy, 92.5 % visual question answering accuracy) and on a self-collected dataset of emergency scenarios (85.8 % image captioning accuracy, 87.5 % visual question answering accuracy), the system operated within seconds on an embedded edge device. By uniting anomaly detection and multimedia retrieval, the framework extends human activity recognition toward actionable emergency detection in home environments.

Abstract This study explores the application of deep learning in forecasting electricity consumption. Initially, we assess the performance of standard neural networks, such as convolutional neural networks (CNN) and long short‐term memory (LSTM), along with basic methods like ARIMA and random forest, on a univariate electricity consumption data set. Subsequently, we develop hybrid models for a comprehensive multivariate data set created by merging weather and electricity data. These hybrid models demonstrate superior performance compared to individual models on the univariate data set. Our main contribution is the introduction of a novel hybrid data fusion model. This model integrates a single‐model approach for univariate data, a hybrid model for multivariate data, and a linear regression model that processes the outputs from both. Our hybrid fusion model achieved an RMSE value of 0.0871 on the Chicago data set, outperforming other models such as Random Forest (0.2351), ARIMA (0.2184), CNN (0.1802), LSTM + LSTM (0.1496), and CNN + LSTM (0.1587). Additionally, our model surpassed the performance of our base transformer model. Furthermore, combining the best‐performing transformer model, with a Gaussian Process model resulted in further improvement in performance. The Transformer + Gaussian model achieved an RMSE of 0.0768, compared with 0.0781 for the single transformer model. Similar trends were observed in the Pittsburgh and IHEC data sets.

In industrial applications, Human Pose Estimation (HPE) is crucial for enhancing both automation and human-computer interaction. This study investigates the impact of synthetic data on HPE model efficacy, particularly examining the performance of the YOLOv8 algorithm. Using Nvidia Omniverse Isaac Sim, we created a synthetic dataset called ISAAC, designed for various complex scenarios. This tool was chosen for its ability to simulate highly realistic and intricate industrial contexts with advanced physics and AI capabilities. The inclusion of this synthetic dataset significantly enhances model accuracy, evidenced by up to a 19% increase in mean Average Precision (mAP) at an Intersection over Union (IoU) of 0.5, and a 12% improvement across the 0.5-0.95 IoU range compared to traditional datasets. These results highlight the substantial advantages of synthetic data in training more accurate and robust HPE models, advocating for the integration of innovative data solutions in the field of computer vision.

Human Activity Recognition (HAR) has emerged as a crucial assistive technology in elderly healthcare, providing caregivers with the ability to monitor and assist in daily activities. HAR is typically conducted through the analysis of data obtained from various types of sensors, including body, object, and ambient sensors. This study focused specifically on utilizing data from internal sensors to recognize activities such as walking, ascending/descending stairs, sitting, standing, and falling. Data was gathered from smartphones, and all HAR models were tested using real-time data collected from Wireless Multimedia Sensor Networks (WMSNs). To perform activity recognition, neural network algorithms such as CNN and LSTM, along with traditional machine learning classification algorithms such as SVM, KNN, and Random Forest Classifier were employed. Additionally, dimension reduction techniques are utilized to decrease the number of features, thus reducing computational time and energy consumption. Furthermore, transfer learning was employed with different scenarios to improve accuracy. Finally, all functions were implemented and compared in two different WMSN architectures. The results enabled us to identify the most efficient and accurate methods for HAR utilizing data from internal sensors. This research has the potential to enhance the quality of life for the elderly and provide caregivers with the necessary tools to provide better care.

Brain-Computer Interface (BCI) systems have a great impact on improving people’s lives. One of the popular BCI implementations is the Event-Related Potential (ERP)-based spelling system which decodes electroencephalogram (EEG) signals to identify a target character. The effectiveness of BCI systems highly depends on the single trial decoding accuracy; however, the EEG signals are contaminated with diverse artifacts which leads to a poor signal-to-noise ratio. Therefore, various filtering algorithms (e.g., FFT, CSP, Laplacian, PCA) have been applied to find the optimal subset of feature spaces in the temporal and spatial domains. These preprocessing steps could efficiently discard the artifacts and have shown superior performance with typical linear classifiers. However, there is a risk that the informative subspace can be also eliminated by the unsupervised learning process, and this algorithm is not proper to be employed in the end-to-end deep-learning architectures where all modules are differentiable. This study aims to propose a generalized deep neural network model by denoising the ERP signals and initializing the Convolutional Neural Network (CNN) model parameters based on the autoencoder. Proposed CNN models indicate - 98.2% spelling performance and - 91.5% single trial accuracy which outperformed the state-of-the-art CNN models.

With improvements in the area of Internet of Things (IoT), surveillance systems have recently become more accessible. At the same time, optimizing the energy requirements of smart sensors, especially for data transmission, has always been very important and the energy efficiency of IoT systems has been the subject of numerous studies. For environmental monitoring scenarios, it is possible to extract more accurate information using smart multimedia sensors. However, multimedia data transmission is an expensive operation. In this study, a novel hierarchical approach is presented for the detection of forest fires. The proposed framework introduces a new approach in which multimedia and scalar sensors are used hierarchically to minimize the transmission of visual data. A lightweight deep learning model is also developed for devices at the edge of the network to improve detection accuracy and reduce the traffic between the edge devices and the sink. The framework is evaluated using a real testbed, network simulations, and 10-fold cross-validation in terms of energy efficiency and detection accuracy. Based on the results of our experiments, the validation accuracy of the proposed system is 98.28%, and the energy saving is 29.94%. The proposed deep learning model’s validation accuracy is very close to the accuracy of the best performing architectures when the existing studies and lightweight architectures are considered. In terms of suitability for edge computing, the proposed approach is superior to the existing ones with reduced computational requirements and model size.

This study presents data preprocessing and imputation techniques for creating a model from medical sensor data. We aim to solve the problem of creating a framework to diagnose heart diseases with an incomplete and dirty data, which is common with medical data. The medical dataset is often incomplete and dirty due to its small size, imbalance and many missing, false, inaccurate data. In this study, we utilize the synthetic minority oversampling technique with the combination of Tomek links to increase the size and eliminate the imbalance of the dataset. We performed a number of experiments and measurements on the Cleveland dataset and conducted a comparative study of various prediction models with recent algorithms in the literature. In order to process additional data from Budapest, Zurich and Basel, we apply the technique of semi-supervised pseudo-labelling, which means that the model has been trained on unlabeled data and combined with labelled data by predicting unlabeled values and making them pseudo-labelled. Then, the same algorithm that we used for Cleveland dataset was applied for the entire dataset. As the main classifier, Fuzzy Random Forest technique was implemented. The final accuracy of the approach proposed in this study is 93.4%, with the specificity and sensitivity values of 96.92% and 89.99%, respectively, which is superior to previous models included in the literature.

Although the semantic understanding of multimedia content is immediate for humans, it is far from it for a computer. This problem is commonly called the semantic gap and is one of the major problems in multimedia retrieval. Therefore, to achieve better retrieval performance, low-level content features must be associated with semantic features effectively. In this study, we focus on the retrieval of multimedia data by combining semantic information with data content in an attempt to effectively solve the semantic gap problem. The main idea behind the combining content and concept descriptors of multimedia data is to represent the content information with the semantic information together by adding content descriptor as a new dimension to our index structure. This new dimension is constructed using a fuzzy cluster algorithm called Array Index. Thus, a new index structure which supports multimedia data querying, including fuzzy querying, is presented in this paper. The construction and query algorithms of this proposed index structure are explained throughout this paper. Experiments show that our new index structure is better than an index mechanism that stores content and concept descriptors in separate structures when the size of the data is large.

Effective data routing is one of the crucial themes for energy-efficient communication in wireless sensor networks (WSN). In the WSN research domain, fuzzy approaches are in most cases superior to well-defined methodologies, especially where boundaries between clusters are unclear. For this reason, a significant number of studies have recently proposed fuzzy-based solutions for the problems encountered in WSNs. Rule-based fuzzy systems are part of these widespread fuzzy-based solutions that often involve some field experts for identification and derivation of fuzzy rules as well as fuzzy membership functions; thus, a considerable amount of time is devoted to the realization of the final system. Nevertheless, it is almost impossible or not feasible to realize a fuzzy system with an optimality property. In this study, we utilize the modified clonal selection algorithm (CLONALG-M) to improve the performance of rule-based fuzzy routing algorithms. Although previous studies have been devoted to fuzzy optimization in general, to the best of our knowledge, improving the efficiency of rule-based fuzzy routing algorithms has not yet been considered. For this reason, CLONALG-M is applied to determine the approximate form of the output membership functions that improve the overall performance of fuzzy routing algorithms, whose rule base and shapes of membership functions are initially known. Experimental analysis and evaluations of the approach used in this study are performed on selected fuzzy rule-based routing algorithms and the obtained results verify that our approach performs and scales well to improve fuzzy routing performance.

Managing a large volume of multimedia data containing various modalities such as visual, audio, and text reveals the necessity for efficient methods for modeling, processing, storing, and retrieving complex data. In this paper, we propose a fusion-based approach at the query level to improve query retrieval performance of multimedia data. We discuss various flexible query types including the combination of content as well as concept-based queries that provide users with the ability to efficiently perform multimodal querying. We have carried out a number of experiments on a video database to show the efficiency of our approach for various types of queries. Our experimental results show that our query-level fusion approach presents a notable improvement in retrieval performance especially for the concept-based queries.

This study proposes a two-tier distributed fuzzy logic based protocol (TTDFP) to improve the efficiency of data aggregation operations in multihop wireless sensor networks (WSNs). Clustering is utilized for efficient aggregation requirements in terms of consumed energy. In a clustered network, member (leaf) nodes transmit obtained data to cluster-heads (CHs) and CHs relay received packets to the base station. In multihop wireless networks, this CH-generated transmission occurs over other CHs. Due to the adoption of a multihop topology, hotspots and/or energy-hole problems may arise. This article proposes a TTDFP to extend the lifespan of multihop WSNs by taking the efficiency of clustering and routing phases jointly into account. TTDFP is a distribution-adaptive protocol that runs and scales sensor network applications efficiently. Additionally, along with the two-tier fuzzy logic based protocol, we utilize an optimization framework to tune the parameters used in the fuzzy clustering tier in order to optimize the performance of a given WSN. This paper also includes performance comparisons and experimental evaluations with the selected state-of-the-art algorithms. The experimental results reveal that TTDFP performs better than any other protocols under the same network setup considering metrics used for comparing energy-efficiency and network lifespan of the protocols.

Multimedia data, particularly digital videos, which contain various modalities (visual, audio, and text) are complex and time consuming to model, process, and retrieve. Therefore, efficient methods are required for retrieval of such complex data. In this paper, we propose a multimodal query level fusion approach using a fuzzy cluster-based learning method to improve the retrieval performance of multimedia data. Experimental results on a real dataset demonstrate that employing fuzzy clustering achieves notable improvement in the concept-based query retrieval performance.

Wireless Sensor Networks (WSNs) facilitate efficient data gathering requirements occurring in indoor and outdoor environments. A great deal of WSNs operates by sensing the area-of-interest (AOI) and transmitting the obtained data to a sink/(s). The transmitted data is then utilized in decision making processes. In this regard, security of raw and relayed data is both crucial and susceptible to malicious attempts targeting the task of the network which occurs on the wireless transmission medium. A node, when compromised, may deliberately forward data packets selectively. When this happens, nodes adjacent to the malicious nodes cannot identify the malevolent node and mitigate the effects of the attacks. In this study, we introduce a fuzzy path selection approach that efficiently mitigates single selective forwarding attacks in WSNs. Performance of our proposed approach and its evaluations are simulated and obtained. Our experimental results show that our approach is an effective solution to serve as a defense mechanism in terms of the efficiency metrics, such as Half of the Nodes Alive (HNA), Total Remaining Energy (TRE), and Packet Drop Ratio (PDR).

Considering simultaneous wireless information and power transfer (SWIPT), we study a multiple-input- single-output (MISO) secrecy channel which consists of a multi-antenna trans- mitter and a cooperative jammer (CJ), multiple multi-antenna energy receivers (ERs), i.e., potential eavesdroppers, and multiple single-antenna co-located receivers (CRs). Both transmitter and CJ send the intend signal with artificial noise (AN) and jamming signal to interfere with the ERs. All receivers (CRs and ERs) adopt a power splitter to decode information and harvest power simultaneously. We exploit AN and CJ to facilitate efficient wireless energy transfer and secure transmission. Our aim is to maximize the minimum harvested energy among all ERs and CRs subject to the total power constraints at the transmitter and CJ while guaranteeing the minimum secrecy rate for each CR above its requirement. By incorporating norm-bounded channel uncertainty model, we propose a joint design of robust secure transmission. The original problem is solved by a two- step approach. In the first step, the proposed problem is reformulated as a sequence of semidefinite programs (SDPs). In the second step, the proposed problem can be handled by one-dimensional search to attain the optimal solution. Simulation results indicate that the performance of the proposed scheme outperforms that of separated AN-aided or CJ-aided scheme.

Feature encoding is a crucial step in BOW image representation. The standard BOW model assigns each image feature to the nearest visual-word without making a distinction between the features that are assigned to the same words. This hard feature assignment leads to high quantization errors and degrades the learning capacity of the classifiers in image classification. We propose a fuzzy feature encoding approach to overcome the uncertainty problem in BOW through assigning each image feature to the visual-words with some membership degrees. We employ two classification techniques, Naive Bayesian and SVM, to evaluate the effect of the fuzzy assignment in image classification. Experiments conducted on image datasets show that fuzzy feature encoding significantly improves the classification accuracy.

This paper introduces a new distributed fuzzy network clustering approach that specifically targets surveillance applications of wireless sensor networks. Surveillance domain heavily consists of multimedia applications which require heavy energy consumption. Moreover, in sensor networks, positioned nodes can be relocated either by users or external events which becomes crucial if the domain and existing resources include uncertainties. In this study, a distributed fuzzy clustering approach is introduced and then experimentally evaluated. The obtained results on the effect of fuzzy processing in heterogeneous sensor networks are presented.

The bag-of-words (BOW) has become a popular image representation model with successful implementations in visual analysis. Although the original model has been improved in several ways, the utilization of the Fuzzy Set Theory in BOW has not been investigated thoroughly. This paper presents a fuzzy feature encoding approach to address the problems associated with the hard and soft assignments of image features to the visual-words. Our encoding method assigns each image feature to only the first and second closest words in the codebook to overcome the word-uncertainty problem. Moreover, we introduce a new word-weighting scheme for image categories based on image histograms. Experiments conducted on some image datasets show that both methods increase the BOW performance in content based image retrieval.

In most applications of Underwater Acoustic Sensor Networks, network connectivity is required for data exchange, data aggregation and relaying the data to a surface station. However, such connectivity can be lost due to failure of some sensor nodes which creates disruptions to the network operations. In this paper, we present two algorithms, namely BMR and DURA, which can detect network partitioning due to such node failures and re-establish network connectivity through controlled depth adjustment of nodes in a distributed manner. The idea is to first identify whether the failure of each node will cause partitioning or not based on localized information. If partitioning is to occur as a result of the possible failure of a particular node, both BMR and DURA designates backup nodes to handle the recovery in the future. While DURA aims to localize the recovery process and minimize the movement overhead on the nodes, BMR strives to reduce the recovery completion time at the expense of increased movement overhead by employing a two-phase block movement. The performance of the proposed approaches is validated through extensive simulations. The results indicated that DURA can provide energy savings as much as a centralized exhaustive approach while BMR provided the fastest recovery time.

Surveillance Wireless Sensor Networks (SWSNs) are the result of abundant data gathering requirements occurring in Wireless Sensor Networks, specifically for surveillance reasons. Most SWSNs operate by sensing the environment and transmitting the acquired data to a sink in order to utilize it for decision making processes such as object detection, classification, localization, or event detection. In this respect, secure routing of acquired data is crucial since a decision making process is performed according to the received data. Although there are various other attack types targeting different layers of the protocol stack, in this study we primarily focus on routing attacks occurring in the network layer, highlight possible defense mechanisms with respect to each attack type, and present impacts of routing attacks on SWSNs.

Spatiotemporal data, in particular fuzzy and complex spatial objects representing geographic entities and relations, is a topic of great importance in geographic information systems and environmental data management systems. For database researchers, modeling and designing a database of fuzzy spatiotemporal data and querying such a database efficiently have been challenging issues due to complex spatial features and uncertainty involved. This paper presents an integrated approach to modeling, indexing, and efficiently querying spatiotemporal data related to fuzzy spatial and complex objects and spatial relations. As our case study, we design and implement a meteorological database application that involves fuzzy spatial and complex objects, and a spatiotemporal index structure, and supports various types of spatial queries including fuzzy spatiotemporal queries. Our implementation is based on an intelligent database system architecture that combines a fuzzy object-oriented database with a fuzzy knowledge base.

Local image features, which are robust to scale, view, and orientation changes in images, play a key factor in developing effective visual classification systems. However, there are two main limitations to exploit these features in image classification problems: 1) a large number of key-points are located during the feature detection process, and 2) most of the key-points arise in background regions, which do not contribute to the classification process. In order to decrease the inverse effects of these limitations , we propose a new codebook generation approach through employing a new clustering method that generates class-specific codebooks along with a novel feature selection method in the bag-of-words model. We evaluate the performance of different classification techniques including Naive Bayesian, k-NN, and SVM on distinctive features. Experiments conducted on PASCAL Visual Object Classification collections have shown that the class-specific codebooks along with distinctive image features can significantly improve the classification performances.

This paper introduces a distributed fault-tolerant topology control algorithm, called the Disjoint Path Vector (DPV), for heterogeneous wireless sensor networks composed of a large number of sensor nodes with limited energy and computing capability and several supernodes with unlimited energy resources. The DPV algorithm addresses the k-degree Anycast Topology Control problem where the main objective is to assign each sensor's transmission range such that each has at least k-vertex-disjoint paths to supernodes and the total power consumption is minimum. The resulting topologies are tolerant to k-1 node failures in the worst case. We prove the correctness of our approach by showing that topologies generated by DPV are guaranteed to satisfy k-vertex supernode connectivity. Our simulations show that the DPV algorithm achieves up to 4-fold reduction in total transmission power required in the network and 2-fold reduction in maximum transmission power required in a node compared to existing solutions.

This study is focused on a new approach for addressing the trade-off between accuracy and energy-efficiency of Wireless Multimedia Sensor Networks. Although a number of previous studies have focused on various special topics in Wireless Multimedia Sensor Networks in detail, to best of our knowledge, none presents a fuzzy multi-modal data fusion system, which is light-weight and provides a high accuracy ratio. Especially, multi-modal data fusion targeting surveillance applications make it inevitable to work within a multi-level hierarchical framework. In this study, we primarily focus on accuracy and efficiency by utilizing such a framework. In order to evaluate the performance of the proposed framework, a set of experiments is conducted and obtained results are presented.

Environmental sounds (ES) have different characteristics, such as unstructured nature and typically noise-like and flat spectrums, which make recognition task difficult compared to speech or music sounds. Here, we perform an exhaustive feature and classifier analysis for the recognition of considerably similar ES categories and propose a best representative feature to yield higher recognition accuracy. In the experiments, thirteen (13) ES categories, namely emergency alarm, car horn, gun, explosion, automobile, helicopter, water, wind, rain, applause, crowd, and laughter are detected and tested based on eleven (11) audio features (MPEG-7 family, ZCR, MFCC, and combinations) by using the HMM and SVM classifiers. Extensive experiments have been conducted to demonstrate the effectiveness of these joint features for ES classification. Our experiments show that, the joint feature set ASFCS-H (Audio Spectrum Flatness, Centroid, Spread, and Audio Harmonicity) is the best representative feature set with an average F-measure value of 80.6%.

Recent increase in the use of video-based applications has revealed the need for extracting the content in videos. Raw data and low-level features alone are not sufficient to fulfill the user 's needs; that is, a deeper understanding of the content at the semantic level is required. Currently, manual techniques, which are inefficient, subjective and costly in time and limit the querying capabilities, are being used to bridge the gap between low-level representative features and high-level semantic content. Here, we propose a semantic content extraction system that allows the user to query and retrieve objects, events, and concepts that are extracted automatically. We introduce an ontology-based fuzzy video semantic content model that uses spatial/temporal relations in event and concept definitions. This metaontology definition provides a wide-domain applicable rule construction standard that allows the user to construct an ontology for a given domain. In addition to domain ontologies, we use additional rule definitions (without using ontology) to lower spatial relation computation cost and to be able to define some complex situations more effectively. The proposed framework has been fully implemented and tested on three different domains. We have obtained satisfactory precision and recall rates for object, event and concept extraction.

Support Vector Machines (SVMs) have been extensively used for visual object classification to bridge the semantic gap between the low level features and high level concepts. SVM treats each training input equally during the construction of its decision surface which results in poor learning machines if training data include outliers. In this paper, a novel fuzzy visual object classification approach utilizing Self-Organizing Maps (SOMs) in SVM is proposed. The experimental results show the effectiveness of the proposed Fuzzy SVM compared to the traditional SVM.

Object classification from video frames has become more challenging in the context of Wireless Multimedia Sensor Networks (WMSNs). This is mainly due to the fact that these networks are severely resource constrained in terms of the deployed camera sensors. The resources refer to battery, processor, memory and storage of the camera sensor. Limited resources mandates the need for efficient classification techniques in terms of energy consumption, space usage and processing power. In this paper, we propose an efficient yet accurate classification algorithm for WMSNs using a genetic algorithm-based classifier. The efficiency of the algorithm is achieved by extracting two simple but effective features of the objects from the video frames, namely shape of the minimum bounding box of the object and the speed of the object in the monitored region. The accuracy of the classification, on the other hand, is provided through using a genetic algorithm whose space/memory requirements are minimal. The training of this genetic algorithm based classifier is done offline and it is stored at each camera in advance to perform online classification during surveillance missions. The experiments indicate that a promising classification accuracy can be achieved without introducing a major energy and storage overhead on camera sensors.

Despite the extensive number of studies for multimodal information fusion, the issue of determining the optimal modalities has not been adequately addressed yet. In this study, a RELIEF-based multimodal feature selection approach (RELIEF-RDR) is proposed. The original RELIEF algorithm is extended for weaknesses in three major issues; multi-labeled data, noise and class-specific feature selection. To overcome these weaknesses, discrimination based weighting mechanism of RELIEF is supported with two additional concepts; representation and reliability capabilities of features, without an increase in computational complexity. These capabilities of features are exploited by using the statistics on dissimilarities of training instances. The experiments conducted on TRECVID 2007 dataset validated the superiority of RELIEF-RDR over RELIEF.

The content-based classification and retrieval of real-world audio clips is one of the challenging tasks in multimedia information retrieval. Although the problem has been well studied in the last two decades, most of the current retrieval systems cannot provide flexible querying of audio clips due to the mixed-type form (e.g., speech over music and speech over environmental sound) of audio information in real world. We present here a complete, scalable, and extensible content-based classification and retrieval system for mixed-type audio clips. The system gives users an opportunity for flexible querying of audio data semantically by providing four alternative ways, namely, querying by mixed-type audio classes, querying by domain-based fuzzy classes, querying by temporal information and temporal relationships, and querying by example (QBE). In order to reduce the retrieval time, a hash-based indexing technique is introduced. Two kinds of experiments were conducted on the audio tracks of the TRECVID news broadcasts to evaluate the performance of the proposed system. The results obtained from our experiments demonstrate that the Audio Spectrum Flatness feature in MPEG-7 standard performs better in music audio samples compared to other kinds of audio samples and the system is robust under different conditions. © 2011 Wiley Periodicals, Inc.

In order to gather information more efficiently, wireless sensor networks (WSNs) are partitioned into clusters. The most of the proposed clustering algorithms do not consider the location of the base station. This situation causes hot spots problem in multi-hop WSNs. Unequal clustering mechanisms, which are designed by considering the base station location, solve this problem. In this paper, we introduce a fuzzy unequal clustering algorithm (EAUCF) which aims to prolong the lifetime of WSNs. EAUCF adjusts the cluster-head radius considering the residual energy and the distance to the base station parameters of the sensor nodes. This helps decreasing the intra-cluster work of the sensor nodes which are closer to the base station or have lower battery level. We utilize fuzzy logic for handling the uncertainties in cluster-head radius estimation. We compare our algorithm with some popular algorithms in literature, namely LEACH, CHEF and EEUC, according to First Node Dies (FND), Half of the Nodes Alive (HNA) and energy-efficiency metrics. Our simulation results show that EAUCF performs better than the other algorithms in most of the cases. Therefore, EAUCF is a stable and energy-efficient clustering algorithm to be utilized in any real time WSN application.

With the advances in technology, low cost and low footprint sensors are being used more and more commonly. Especially for military applications wireless sensor networks (WSN) have become an attractive solution as they have great use for avoiding deadly danger in combat. For military applications, classification of a target in a battlefield plays an important role. A wireless sensor node has the ability to sense the raw signal data in battlefield, extract the feature vectors from sensed signal and produce a local classification result using a classifier. Although only one sensor is sufficient to produce a classification result, decision fusion of the local classification results for a number of sensor nodes improves classification accuracy. In our approach, we propose fuzzy decision fusion methods for single target classification in a WSN environment. Our proposed fusion algorithms use fuzzy logic for selecting the most appropriate sensor nodes to be used for classification. Our algorithms provide better classification accuracy over some popular decision fusion algorithms.

This study presents a new comprehensive framework for semantic content extraction from raw video, storage of the extracted data and retrieval of the stored data. Objects, spatial relations between objects, events and temporal relations between events, which are considered as semantic contents of the video, are extracted automatically to a certain extend with the developed approach. Extraction process is supported by manual annotation when automatic extraction is not satisfactory. The extracted information is stored in an intelligent fuzzy object-oriented database in which the database is enhanced with a fuzzy knowledge-based system. Domain specific deduction rules can be defined to derive new information about semantic contents of the video. The database is also supported by an access structure to increase retrieval efficiency. The proposed framework is capable of handling uncertain data arising from annotation process or video nature.

Video texts are known to constitute an important source of information for semantic summaries of video archives. In this study, we propose a fully automated architecture for semantic annotation and later retrieval of Turkish news videos based on the corresponding video texts. At the core of the architecture is a named entity recognizer, the output of which on video texts is used as semantic annotations for the corresponding videos. The architecture also comprises components for news story segmentation, sliding text recognition, and video retrieval in addition to a news video database. The news story segmentation module makes use of the audio waveforms of the raw video files to detect the boundaries of individual news stories. The sliding text recognizer is then executed on the video segments corresponding to these news stories to extract their texts. The texts are then fed into the named entity recognizer for Turkish news texts to extract the named entities which are to be used as semantic annotations or index terms for the retrieval of these news videos. Finally, the retrieval interface of the overall architecture enables access to the annotated videos and video segments through boolean queries formed by using the previously extracted named entities. This study is significant for its proposing the first fully automated architecture for the semantic annotation and retrieval of Turkish news video archives.

Within the scope of information retrieval, efficient similarity search in large document or multimedia collections is a critical task. In this paper, we present a rigorous comparison of three different approaches to the image retrieval problem, including cluster-based indexing, distance-based indexing, and multidimensional scaling methods. The time and accuracy trade-offs for each of these methods are demonstrated on a large Corel image database. Similarity of images is obtained via a feature-based similarity measure using four MPEG-7 low-level descriptors. We show that an optimization of feature contributions to the distance measure can identify irrelevant features and is necessary to obtain the maximum accuracy. We further show that using multidimensional scaling can achieve comparable accuracy, while speeding-up the query times significantly by allowing the use of spatial access methods.

This study presents IDE_A-ITCP, a Turkish nationwide Information Technologies Certificate Program, which is based on synchronous and asynchronous communication methods over the Internet, offered by cooperation of the Middle East Technical University Computer Engineering Department and Continuing Education Center. This online certificate program started in May 1998 and is still active with its 13th group of participants. The program includes eight fundamental courses of the Computer Engineering Department curriculum and is comprised of four semesters spanning nine months. The main aim of this program is to train the participants in the IT field to meet the demands in the field of computer technologies in Turkey. In the present study, the history, infrastructure, and educational aspects of IDE_A are discussed in detail.

Advances in wireless multimedia sensor networks (WMSNs) stimulated interest in designing lightweight solutions in terms of processing and energy consumption for traditional problems due to severe resources constraints on camera sensors. Finding the exact object location is one of such traditional problems which has been well studied in the past. However, the proposed solutions mostly involve complex processing with multiple cameras and thus cannot be applied to surveillance applications which need to be deployed for extended periods. In this paper, we propose an object localization scheme for WMSNs which can be run on a single camera sensor by only using the sensor's location information. Our approach first extracts the detected object using frame differencing. To reduce the processing cost of this operation, each frame size is reduced with some video pre-processing. The location of the object can then be estimated using the distance of the object to the camera and camera/frame size properties. In addition to being energy-efficient, since a single camera sensor is involved, the required time for localization is reduced immensely as opposed to approaches which involve multiple camera sensors. Our experiments indicates that a promising accuracy can be achieved in determining the exact object location without introducing a major energy overhead.

The size of multimedia data is increasing fast due to the abundance of multimedia applications. Modeling the semantics of the data effectively is crucial for proper management of it. In this paper, we present a fuzzy conceptual data model for multimedia data which is also generic in the sense that it can be adapted to all multimedia domains. The model takes an object-oriented approach and it handles fuzziness at different representation levels where fuzziness is inherent in multimedia applications and should be properly modeled. The proposed model also has the nice feature of representing the structural hierarchy of multimedia data as well as the spatial and temporal relations of the data. The model is applied to the news video domain and implemented as a fuzzy multimedia database system where it turns out to be effective in representing the domain and thereby provides an evidence for the general applicability of the model. The model is accompanied by an automatic multimedia annotation scheme which makes use of information extraction techniques on the corresponding multimedia texts.

Similar to verse and chorus sections that appear as repetitive structures in musical audio, key-concept (or topic) of some speech recordings (e.g., presentations, lectures, etc.) may also repeat itself over the time. Hence, accurate detection of these repetitions may be helpful to the success of automatic speech summarization. Based on this motivation, we consider the applicability of music structural analysis methods to speech summary generation. Our method transforms a 1-D time-domain speech signal to a 2-D image representation, namely (dis)similarity matrix and detects possible repetitions within the matrix by using proper computer vision techniques. In addition, the method does not transcribe speech signal into words, phrases, or sentences. Hence, it can be generalized as speech-to-speech summarization method, in which summarization results are presented by speech instead of text. Furthermore, the method does not need a prior knowledge about the language or grammar of speech signal. Experiments show that, our method can capture the main theme of speech signals compared to the ideal transcription sections defined by experts and computational analysis shows our proposed method has a good performance.

Knowledge intensive applications require an intelligent environment, which can perform deductions in response to user queries or events that occur inside or outside of the applications. For that, we propose a fuzzy active object-oriented database for modeling knowledge intensive applications. In that, we incorporate fuzziness within the event, condition and action parts of an active rule. We consider deductive rules as special cases of active rules so that deductive queries are handled using abstract kind of events. We also introduce a model for fuzzy inferencing of fuzzy active rules where we develop a model for scenario concept. We use a Fuzzy Petri Net model for fuzzy rule-based inference.

A fuzzy object-oriented data model is a fuzzy logic-based extension to an object-oriented database model that permits uncertain data to be explicitly represented. The fuzzy object-oriented database (FOOD) model is one of the proposed models in the literature to handle uncertainty in object-oriented databases. Several kinds of fuzziness are dealt with in the FOOD model, including fuzziness at attribute level and between object and class and between class and superclass relations. The traditional index structures do not allow efficient access to both crisp and fuzzy objects for fuzzy object-oriented databases since they are not efficient enough in processing both crisp and fuzzy queries. In this study, we propose a new index structure, namely a FOOD index (FI), to deal with different kinds of fuzziness in fuzzy object-oriented databases and to support multidimensional indexing. In this paper, we describe this proposed index structure and show how it supports various types of flexible queries, and evaluate its performance for exact, range, and fuzzy queries.

Over the years database management systems have evolved to include spatially referenced data. Because spatial data are complex and have a number of unique constraints (i.e., spatial components and uncertain properties), spatial database systems can be effective only if the spatial data are properly handled at the physical level. Therefore, it is important to develop an effective spatial and aspatial indexing technique to facilitate flexible spatial and/or aspatial querying for such databases. For this purpose we introduce an indexing approach to use (fuzzy) spatial and (fuzzy) aspatial data. We use a number of spatial index structures, such as Multilevel Grid File (MLGF), G-tree, R-tree, and R*-tree, for fuzzy spatial databases and compare the performances of these structures for various flexible queries. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 805–826, 2007.

Real-world information including subjective opinions and judgments need imprecise data to be modeled for representation and querying in databases. The Extensible Markup Language (XML) has become a de-facto standard for data modeling and exchange in recent years. Efforts on modeling imprecision and representing such data in XML have not been fully developed. In this paper, an XML based fuzzy data representation and querying system is presented. Complex and imprecise data are represented using a fuzzy extension of XML. The representation forms the basis for a system which enables fuzzy querying on XML documents using XQuery, a XML query language. The system also enables restructuring of XML Schemas through merging of elements of the XML documents. By using this feature of the system, application specific XML Schema and XML documents can be generated from the existing documents.

We present a novel algorithm for structural analysis of audio to detect repetitive patterns that are suitable for content-based audio information retrieval systems, since repetitive patterns can provide valuable information about the content of audio, such as a chorus or a concept. The Audio Spectrum Flatness (ASF) feature of the MPEG-7 standard, although not having been considered as much as other feature types, has been utilized and evaluated as the underlying feature set. Expressive summaries are chosen as the longest patterns by the k-means clustering algorithm. Proposed approach is evaluated on a test bed consisting of popular song and speech clips based on the ASF feature. The well known Mel Frequency Cepstral Coefficients (MFCCs) are also considered in the experiments for the evaluation of features. Experiments show that, all the repetitive patterns and their locations are obtained with the accuracy of 93% and 78% for music and speech, respectively.

For many knowledge-intensive applications, it is important to develop an environment that permits flexible modeling and fuzzy querying of complex data and knowledge including uncertainty. With such an environment, one can have intelligent retrieval of information and knowledge, which has become a critical requirement for those applications. In this paper, we introduce a fuzzy knowledge-based (FKB) system along with the model and the inference mechanism. The inference mechanism is based on the extension of the Rete algorithm to handle fuzziness using a similarity-based approach. The proposed FKB system is used in the intelligent fuzzy object-oriented database (IFOOD) environment, in which a fuzzy object-oriented database is used to handle large scale of complex data while the FKB system is used to handle knowledge of the application domain. Both the fuzzy object-oriented database system and the fuzzy knowledge-based system are based on the object-oriented concepts to eliminate data type mismatches. The aim of this paper is mainly to introduce the FKB system of the IFOOD environment.

Knowledge intensive applications require an intelligent environment which can perform deductions due to user queries or events that occur inside or outside the environment. In this study, we propose a fuzzy active object-oriented database for modelling knowledge intensive applications. Our approach integrates fuzzy, active and deductive rules with database objects, so that the system gains intelligent behaviour, which provides the objects to perceive dynamic occurrences and answer user queries. In this way, the objects can produce new knowledge and keep themselves in a consistent, stable, and up to-date state.

Database systems can be effective only if the data are properly handled at the physical level. Therefore, it is important to develop an effective spatial and aspatial indexing technique to facilitate flexible spatial and/or aspatial querying for spatial databases. In this study we adapt a number of spatial index structures, such as multilevel grid file (MLGF), G-tree, R-tree, and R*-tree, for fuzzy spatial databases and compare the performances of these structures for various flexible queries.

Fuzzy relational database models generalize the classical relational database model by allowing uncertain and imprecise information to be represented and manipulated. In this article, we introduce fuzzy extensions of the normal forms for the similarity-based fuzzy relational database model. Within this framework of fuzzy data representation, similarity, conformance of tuples, the concept of fuzzy functional dependencies, and partial fuzzy functional dependencies are utilized to define the fuzzy key notion, transitive closures, and the fuzzy normal forms. Algorithms for dependency preserving and lossless join decompositions of fuzzy relations are also given. We include examples to show how normalization, dependency preserving, and lossless join decomposition based on the fuzzy functional dependencies of fuzzy relation are done and applied to some real-life applications. (C) 2004 Wiley Periodicals, Inc.

Next generation information system applications require powerful and intelligent information management that necessitates an efficient interaction between database and knowledge base technologies. It is also important for these applications to incorporate uncertainty in data objects, in integrity constraints, and/or in application. In this study, we propose an intelligent object-oriented database architecture, FOOD, which permits the flexible modeling and querying of complex data and knowledge including uncertainty with powerful retrieval capability.

Due to the ubiquity of space-related and time-related information, the ability of a database system to deal with both spatial and temporal phenomenon facts in a spatiotemporal applications is highly desired. However, uncertain and fuzzy information in these applications highly increases the complexity of database modeling. In this paper we introduce a semantic data modeling approach for spatiotemporal database applications. We specifically focus on various aspects of spatial and temporal database issues and uncertainty and fuzziness in various abstract levels. The semantic data model that we introduce in this paper utilizes unified modeling language (UML) for handling spatiotemporal information, uncertainty, and fuzziness especially at the conceptual level of database design. An environmental information system (EIS) application is used to illustrate our modeling approach and extension made to UML. By incorporating uncertainty and fuzziness into the semantic data model of a spatiotemporal EIS database application, one can handle pollution summary, analysis, and even pollution predictions, in addition to the other common uses of a database system. © 2001 John Wiley & Sons, Inc.

Many new-generation database applications demand intelligent information management necessitating efficient interactions between database & knowledge bases and the users. In this study we discuss evaluation of imprecise queries in an intelligent object-oriented database environment, WOOD. A flexible query evaluation mechanism, capable of handling different data types including complex and imprecise data and knowledge is presented and key language issues are addressed. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Trends in databases leading to complex objects present opportunities for representing imprecision and uncertainty that were difficult to integrate cohesively in simpler database models. In fact, one can begin at the conceptual level with a model that allows uncertainty assumptions and then transform those assumptions into a logical model having the necessary semantic foundations upon which to base a meaningful query language. Here we provide such a constructive approach beginning with the ExIFO model for expression of the conceptual design then show how the conceptual design is transformed into the logical design (for which we utilize the extended NF/sup 2/ logical database model). The steps are straightforward, unambiguous, and preserve the relevant information, including information concerning uncertainty.

An important research trend in databases is to handle different types of uncertainty at conceptual level. The trend of incorporating complex objects in databases presents opportunities for representing imprecision and uncertainty that were difficult to integrate cohesively in simple database models. We introduce a conceptual data model by extending ExIFO to handle both complex and uncertain, mainly fuzzy, objects and classes.

This paper first introduces a new definition for the conformance of tuples existing in a similarity-based fuzzy database relation. Then the formal definitions of fuzzy functional and multivalued dependencies are given on the basis of the conformance values presented here. These dependencies are defined to represent relationships between domains of the same relation that exist. The definitions of the fuzzy dependencies presented in this study allow a sound and complete set of inference rules. In this paper, we include examples to demonstrate how the integrity constraints imposed by these dependencies are enforced whenever a tuple is to be inserted or to be modified in a fuzzy database relation. © 1998 John Wiley & Sons, Inc.

In database environment, it is necessary to represent complex and uncertain information at conceptual level and then transform the conceptual schema into the logical one for ultimate implementation. It is also important to verify the conceptual schema with respect to the constraints imposed on the schema definition. In this paper we primarily focus on the verification and transformation of the conceptual schema. For the purpose of verification of the conceptual schema represented by the ExIFO data model (the extension of the IFO data model), we introduce a number of invariants. We also describe the transformation algorithm for mapping the conceptual specification into a logical database schema represented with the extended NF 2 database model. The system that we describe in this paper is implemented and it can test whether the given ExIFO specification is valid and transforms the conceptual specification into the logical schema. The transformation algorithm is computationally efficient and preserves the knowledge represented with verified conceptual schema.