Embedded sensor systems operating in heterogeneous and evolving environments face critical challenges in detecting rare or novel anomalies under strict power, communication, and supervision constraints. To address these limitations, we propose a dual-model framework that combines stochastic modeling and geometric analysis for unsupervised anomaly detection. First, we model the evolution of sensor derived feature vectors as multivariate Brownian motion trajectories, capturing both the temporal and statistical dynamics of nominal actions. This parametric representation provides interpretable descriptors, such as drift and covariance, which characterize the average direction and variability of feature evolution over time, respectively. Second, we introduce a non-parametric decision layer based on kernel density estimation and convex hulls, enabling the identification of anomalies as trajectories that traverse low-density regions or exit the geometric envelope of previously observed behaviors. This dual statistical–geometric perspective allows for real-time, unsupervised detection of anomalies without requiring labeled data or static assumptions. The proposed framework is lightweight, adaptable to multiple sensing modalities, and suitable for embedded deployment.

Deep learning applications in fault diagnosis face two critical challenges. First, a significant distribution gap between source domain training data and target domain samples with unknown noise patterns. Second, labeled fault data remain scarce in practice. These issues hinder the practical deployment. This paper presents a Cross-View Consistency Network (CVC-Net) to tackle these problems through noise-generalization capabilities. The method learns robust features from limited source domain data. It maintains diagnostic accuracy with unknown noise data, without prior knowledge of target noise characteristics. CVC-Net processes temporal waveforms and Gramian Angular Field representations through specialized encoders, exploiting their asymmetric noise sensitivities. A cross-view consistency mechanism extracts fault patterns across modalities. The method integrates fault-aware prototype learning for enhanced discrimination with limited labels and employs adaptive fusion that weights view contributions based on cross-view prediction. Experimental validation shows that CVC-Net is effective in challenging scenarios. When tested on target domain with unknown noise types, CVC-Net maintains reliable performance, effectively handling noise patterns not present during source domain training. Under limited-label conditions, it outperforms existing methods in diagnostic performance.

Given a query sentence, text-to-image person retrieval aims to identify matched pedestrian images from a large gallery. Most of the existing methods are designed for the unified domain setting, which is operated under the assumption that the training and test data are drawn from the same distribution. However, this assumption is difficult to guarantee in real application scenes, as data is often collected from various surveillance scenarios. To this end, in this paper, we introduce the concept of single-source domain generalization into the context of text-to-image person retrieval and propose a novel task called single-source domain generalizable text-to-image person retrieval (SSDG-TIPR). This task is applicable in real-world scenarios but poses significant challenges due to the limitation of accessible training data. Intuitively, a trained model is the most familiar with the domain on which it was trained, that is, the source domain. Therefore, to handle this SSDG-TIPR task, we propose a new method to infinitely close astray features from unseen target domains to the source domain, namely, to take it home (TIME), allowing the model to handle the features in a familiar manner. The proposed TIME method comprises three main modules: the Domain Astray Leading (DAL) module, the Domain Invariant Feature Extract (DIFE) module and the Domain Home Taking (DoT) module. We evaluated TIME on 3 benchmark datasets, namely CUHK-PEDES, ICFG-PEDES and RSTPReid, and demonstrated its superior performance on 10 SSDG-TIPR sub-tasks as well as on 3 conventional TIPR sub-tasks, establishing a new state-of-the-art in both settings.

In industrial quality control, detecting anomalies in visual textures is essential for ensuring product quality and operational efficiency. Early identification of defects prevents faulty items from reaching consumers, reduces waste, and maintains high standards of production. Numerous unsupervised anomaly detection methods heavily depend on the integration of multiple layers from various pretrained models, a selection often made through empirical means. We propose SingleNet, an innovative knowledge distillation approach tailored for fast unsupervised texture anomaly detection, using a single layer from a compact pretrained model. Contrary to the previous knowledge distillation approaches, our network leverages fast Fourier convolutions (FFC) to reconstruct a degraded version of the teacher extracted features. At test time, we employed a frequency-aware filtering mechanism to reduce reconstruction artifacts caused by discrepancies between teacher and student architectures. Empirical results demonstrate the efficacy of our approach, attaining state-of-the-art performance across evaluated datasets coupled with expedited high-speed inference.

Robotic arm target grasping by vision support is a commonly used method in grasping tasks and is usually used for multi-target complex scenes. Where vision support is generally used to identify the targets and to get their positions, categories and sizes. Most robotic arm grasping tasks using target recognition methods as visual inspection ignore the relationship between target objects such as the occlusion problem between objects. This limits the targets to be grasped and makes the crawling task inefficient. We propose Grasping with Occlusion-Aware aLly (GOAL) method based on binocular stereo-vision. Firstly, occlusion relationships in the view are directly inferred and targets are segmented as well as localized. Subsequently, multi-target grasping pose estimation is performed to obtain effective grasping positions. Ultimately, validation is conducted on a high-resolution dataset using the EPSON robotic arm. Note to Practitioners—This research significantly advances the field by addressing occlusion challenges in robotic grasping, offering effective methods, a valuable dataset, and practical insights. The proposed Grasping with Occlusion-Aware aLly (GOAL) method was validated on a high-resolution dataset using the EPSON robotic arm, showcasing its applicability and efficiency in real-world scenarios. This work provides valuable contributions to practitioners in the field of robotic manipulation and grasping tasks.

Noncontrastive self-supervised learning methods offer an effective alternative to contrastive approaches by avoiding the need for negative samples to avoid representation collapse. Noncontrastive learning methods explicitly or implicitly optimize the representation space, yet they often require large representation dimensions, leading to dimensional inefficiency. To provide negative samples, contrastive learning methods often require large batch sizes, thus regarded as sample inefficient, while noncontrastive learning methods require large representation dimensions, thus regarded as dimension inefficient. Although we have some understanding of the noncontrastive learning method, theoretical analysis of such phenomenon still remains largely unexplored. We present a theoretical analysis of the dimensional need for noncontrastive learning. We investigate the transfer between upstream representation learning and downstream tasks' performance, demonstrating how noncontrastive methods implicitly increase interclass distances within the representation space and how the distance affects the model performance of evaluation performance. We prove that the performance of noncontrastive methods is affected by the output dimension and the number of latent classes, and illustrate why performance degrades significantly when the output dimension is substantially smaller than the number of latent classes. We demonstrate our findings through experiments on image classification experiments, and enrich the verification in audio, graph and text modalities. We also perform empirical evaluation for image models on extensive detection and segmentation tasks beyond classification that show satisfactory correspondence to our theorem.

Text-based person retrieval is the process of searching a massive visual resource library for images of a particular pedestrian, based on a textual query. Existing approaches often suffer from a problem of color (CLR) over-reliance, which can result in a suboptimal person retrieval performance by distracting the model from other important visual cues such as texture and structure information. To handle this problem, we propose a novel framework to Excavate All-round Information Beyond Color for the task of text-based person retrieval, which is therefore termed EAIBC. The EAIBC architecture includes four branches, namely an RGB branch, a grayscale (GRS) branch, a high-frequency (HFQ) branch, and a CLR branch. Furthermore, we introduce a mutual learning (ML) mechanism to facilitate communication and learning among the branches, enabling them to take full advantage of all-round information in an effective and balanced manner. We evaluate the proposed method on three benchmark datasets, including CUHK-PEDES, ICFG-PEDES, and RSTPReid. The experimental results demonstrate that EAIBC significantly outperforms existing methods and achieves state-of-the-art (SOTA) performance in supervised, weakly supervised, and cross-domain settings.

Industrial sensors capture critical information for intelligent manufacturing maintenance. To promote equipment upgrading and manufacturing processes, intelligent decisions, and information learning play an important role. Although deep learning methods historically obtain excellent results, there is always a tradeoff between fine-tuning existing networks or designing models from scratch for sensor data processing. In this article, we propose the multihead attention self-supervised (MAS) representation model, which is a self-supervised learning-based sensor feature extraction network. To the best of our knowledge, this is the first time a self-supervised contrastive learning method using positive samples that represent multidimensional industry sensor data is being used for anomaly detection. We review alternative data augmentation methods proposed for better-representing sensor sequence data. We use this insight to design a new structure that adapts to the temporal characteristics of the application. We apply our method to a real-world water circulation system that uses a variety of industrial sensors. The effectiveness of the proposed MAS methods is demonstrated.

This paper aims to generalize the well-known list-mode maximum likelihood expectation maximization (LM-MLEM) algorithm to reconstruct 3D Compton images from multi-view data. The main originality resides in developing a new list-mode data space and the associated probabilistic framework enabling parallax improvement for compact Compton cameras. To further improve the accuracy of 3D image reconstruction, we carry out a data preprocessing based on the spectra of total energy and incidence angle of photon on absorber to select significant Compton events in consideration. Numerous numerical results on real datasets confirm the outperformance of the generalized LM-MLEM algorithm in the localization of radioactive sources.

Modeling the spatiotemporal relationship (STR) of traffic data is important yet challenging for existing graph networks. These methods usually capture features separately in temporal and spatial dimensions or represent the spatiotemporal data by adopting multiple local spatial-temporal graphs. The first kind of method mentioned above is difficult to capture potential temporal-spatial relationships, while the other is limited for long-term feature extraction due to its local receptive field. To handle these issues, the Synchronous Spatio-Temporal grAph Transformer (S2TAT) network is proposed for efficiently modeling the traffic data. The contributions of our method include the following: 1) the nonlocal STR can be synchronously modeled by our integrated attention mechanism and graph convolution in the proposed S2TAT block; 2) the timewise graph convolution and multihead mechanism designed can handle the heterogeneity of data; and 3) we introduce a novel attention-based strategy in the output module, being able to capture more valuable historical information to overcome the shortcoming of conventional average aggregation. Extensive experiments are conducted on PeMS datasets that demonstrate the efficacy of the S2TAT by achieving a top-one accuracy but less computational cost by comparing with the state of the art.

Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two intractable distributions. In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs. Particularly, we lead a decoupled EBLVM consisting of a marginal energy-based distribution and a structural posterior to handle the difficulties when learning deep EBLVMs on images. By choosing a symmetric KL divergence in the lower level of our framework, a compact BiDVL for visual tasks can be obtained. Our model achieves impressive image generation performance over related works. It also demonstrates the significant capacity of testing image reconstruction and out-of-distribution detection.

The automated conveyor system, as the core component in the modern manufacturing world, has gained lots of attention from researchers. To optimize the operation of the conveyor system, range-inspection control (RIC) has been considered an efficient strategy to bring this conventional technology to an intelligent level. Various algorithms have been put into use to achieve optimal control. However, the current methodologies are only focusing on control optimization, not scaled into the smart manufacturing framework. The schema of alignment and corporation between the physical and virtual spaces for the system remains an important problem. Therefore, the work in this article aims for an effective framework of implementation between the physical and virtual stations in an automated conveyor system. Since increasingly more application scenarios rely on the digital twin (DT) technology to realize the integration of physical and virtual systems, we proposed the DT automated conveyor system (DT-ACS) that constructs the road map to implement the RIC-based conveyor system under the background of a smart factory. Besides, profit-sharing-based deep Q-networks (PDQNs) have been proposed to cope with the RIC optimization problem. The robustness and efficiency of the proposed PDQN were evaluated via sets of experiments. The discussion and conclusion are presented at last accordingly.Note to Practitioners—This article aims to propose a strategy of control optimization for conveyor-based manufacturing systems under the digital twin (DT) framework. The conveyor system can be flexible to control the running flows to avoid overloading workstations. Due to the complex environment in the production line, the range that is able to be inspected and the capacity of the reserve area can be considerably diverse among the workstations. To maximally evaluate our framework, we set a comparatively complex environment for the experiments. Nevertheless, to obtain practically ideal performance under other circumstances, the parameters should be precisely tested and fine-tuned with simulation in advance.

Crowd counting is a valuable technology for extremely dense scenes in the transportation. Existing methods generally have higher-order inconsistencies between ground truth density maps and generated density maps. To address this issue, we incorporate an attentional discriminator to take charge of checking the density map between the generator and the ground truth. Thus, a Cascaded Attentional Generative Adversarial Network (CACrowdGAN) is proposed that enables the attentional-driven discriminator to distinguish implausible density maps and simultaneously to guide the generator to deliver fine-grained high quality density maps. The proposed CACrowdGAN consists of two components: an attentional generator and a cascaded attentional discriminator. The attentional generator has an attention module and a density module. The attention module is developed for the generator to focus on the crowd regions of the input images, while the density module is used to provide the attentional input of the discriminator. In addition, a cascaded attentional discriminator is proposed to synthesize attentional-driven fine-grained details at different crowd regions of the input image and compute a per-pixel fine-grained loss for training generator. The proposed CACrowdGAN achieves the state-of-the-art performance on five popular crowd counting datasets (ShanghaiTech, WorldEXPO’10, UCSD, UCF_CC_50 and UCF_QNRF), which demonstrates the effectiveness and robustness of the proposed approach in the complex scenes.

In this paper, we propose a novel method for irregularity detection. Previous researches solve this problem as a One-Class Classification (OCC) task where they train a reference model on all of the available samples. Then, they consider a test sample as an anomaly if it has a diversion from the reference model. Generative Adversarial Networks (GANs) have achieved the most promising results for OCC while implementing and training such networks, especially for the OCC task, is a cumbersome and computationally expensive procedure. To cope with the mentioned challenges, we present a simple but effective method to solve the irregularity detection as a binary classification task in order to make the implementation easier along with improving the detection performance. We learn two deep neural networks (generator and discriminator) in a GAN-style setting on merely the normal samples. During training, the generator gradually becomes an expert to generate samples which are similar to the normal ones. In the training phase, when the generator fails to produce normal data (in the early stages of learning and also prior to the complete convergence), it can be considered as an irregularity generator. In this way, we simultaneously generate the irregular samples. Afterward, we train a binary classifier on the generated anomalous samples along with the normal instances in order to be capable of detecting irregularities. The proposed framework applies to different related applications of outlier and anomaly detection in images and videos, respectively. The results confirm that our proposed method is superior to the baseline and state-of-the-art solutions.

Summary At present, human action recognition is a challenging and complex task in the field of computer vision. The combination of CNN and RNN is a common and effective network structure for this task. Especially, we use 3DCNN in CNN part and ConvLSTM in RNN part. We divide the video into multiple temporal segments by average and compress each segment into one feature map by pooling layer. Adding the pooling layer, dropout layer, and batch normalization layer into ConvLSTM is our groundbreaking work. We test our model on KTH, UCF‐11, and HMDB51 datasets and achieve a high accuracy of action recognition.

Generating action proposals in untrimmed videos is a challenging task, since video sequences usually contain lots of irrelevant contents and the duration of an action instance is arbitrary. The quality of action proposals is key to action detection performance. The previous methods mainly rely on sliding windows or anchor boxes to cover all ground-truth actions, but this is infeasible and computationally inefficient. To this end, this article proposes a RecapNet-a novel framework for generating action proposal, by mimicking the human cognitive process of understanding video content. Specifically, this RecapNet includes a residual causal convolution module to build a short memory of the past events, based on which the joint probability actionness density ranking mechanism is designed to retrieve the action proposals. The RecapNet can handle videos with arbitrary length and more important, a video sequence will need to be processed only in one single pass in order to generate all action proposals. The experiments show that the proposed RecapNet outperforms the state of the art under all metrics on the benchmark THUMOS14 and ActivityNet-1.3 datasets. The code is available publicly at https://github.com/tianwangbuaa/RecapNet.

Matching manually cropped pedestrian images between queries and candidates, termed as person re-identification, has achieved significant progress with deep convolutional neural networks. Recently, a topic called ‘person search’ is proposed for the end-to-end application of re-identification technologies. It integrates object detection and person re-identification and aims to both locate and match pedestrians on a gallery of raw images. However, the design and implementation of such kind of hybrid network are difficult and computationally consuming in real practical situations. In order to fasten the design and ease the implementation, this paper proposes a deep-frozen transfer learning framework, named FT-MDnet, to extract re-identification features from a pre-trained detection network in two steps. First, using a channel-wise attention mechanism, a network called adaptive transfer learning network (ATLnet) is used to convert the sharing data of the underlying detection network to a re-identification feature map. Then, a multi-branch feature representation network called multiple descriptor network (MDnet) is proposed to extract re-identification features from the re-identification feature map. Our proposed solution has been verified on different types of mainstream detection networks, including YOLOv3, YOLOv4, Mask RCNN, and CenterNet. The experimental results show that our solution outperforms all other person search solutions by a large margin. It proves that the feature representations of detection networks are highly compatible with re-identification, and the proposed framework effectively extracts these features out. To encourage further research, we have made our framework open source.

Soft computing is facing a rapid evolution thanks to the development of artificial intelligence especially the deep learning. With video surveillance technologies of soft computing, such as image processing, computer vision, and pattern recognition combined with cloud computing, the construction of smart cities could be maintained and greatly enhanced. In this article, we focus on the online detection of action start task in video understanding and analysis, which is critical to the multimedia security in smart cities. We propose a novel model to tackle this problem and achieves state-of-the-art results on the benchmark THUMOS14 data set.

Recent advancements in avionics and electronics systems led to the increased use of Unmanned Aerial Vehicles (UAVs) in several military and civilian missions. One of the main advantages that makes UAVs attractive is their ability to reach remote regions that are inaccessible to human operators, i.e. provide new aerial perspective in visual surveillance. Autonomous visual surveillance systems require real time anomalies detection. However, there are many difficulties associated with automatic anomalies detection by an UAV, as there is a lack in the proposed contributions describing abnormal events detection in videos recorded by a drone. In this paper, we propose an anomaly detection approach in a surveillance mission where videos are acquired by an UAV. We combine deep features extracted using a pretrained Convolutional Neural Network (CNN) with an unsupervised classification method, namely One Class Support Vector Machine (OCSVM). The quantitative results obtained on the used dataset show that our proposed method achieves good results in comparison to existing technique with an Area Under Curve (AUC) of 0.93.

Person re-identification is one of the indispensable elements for visual surveillance. It assigns consistent labeling for the same person within the field of view of the same camera or even across multiple cameras. While handcrafted feature extraction is certainly one way of approaching this problem, in many cases, these features are becoming more and more complex. Besides, training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. This paper explores the following three main strategies for solving the person re-identification problem: (i) using handcrafted features, (ii) using transfer learning based on a pre-trained deep CNN (trained for object categorization) and (iii) training a deep CNN from scratch. Our experiments consistently demonstrated that: (1) The handcrafted features may still have favorable characteristics and benefits especially in cases where the learning database is not sufficient to train a deep network. (2) A fully trained Siamese CNN outperforms handcrafted approaches and the combination of pre-trained CNN with different re-identification processes. (3) Moreover, our experiments demonstrated that pre-trained features and handcrafted features perform equally well. These experiments have also revealed the most discriminative parts in the human body.

Anomalies detection in video footage is a daunting task treated with many challenges in crowded scenes. In this paper, we propose an efficient method based on deep learning and handcrafted spatio-temporal feature extraction for anomaly detection using a pre-trained CNN (convolution neural network) and HOF (Histogram of Optical Flow) features. Abnormal motion is picked by relative thresholding. One-class SVM is trained with spatial features for robust classification of abnormal shapes. Moreover, a decision function is applied to correct the false alarms and the miss detections. Our method has a high performance in terms of speed and accuracy. It achieved anomaly detection with good efficiency in challenging datasets and reduced computational complexity compared to state-of-the-art methods.

International audience

In this paper, we propose a Deep Neural Network model based on WiFi-fingerprinting to improve the accuracy of zone location in a multi-building, multi-floor indoor environment. The proposed model is presented as a Stacked AutoEncoder (SAE) to allow efficient reduction of the feature space in order to achieve robust and precise classification. The multi-label classification is used to simplify and reduce the complexity of the learning classification task during the training phase. To achieve a hierarchical classification, we applied an argmax function on the multi-label output to convert the multi-label classification into multi-class classification ones to estimate the building, the floor and the zone identifier. Experimental results show that the proposed model achieves an accuracy of 100% for building, 99.66% for floor and 83.47% for zone location with a test time that does not exceed 10.21s.

Occupants' thermal comfort assessment is becoming a crucial research topic since it aims not only at improving indoor thermal comfort but also to save energy in both commercial and residential buildings. Hence, it makes buildings more sustainable. Predicted Mean Vote (PMV) model is considered as the most recognized in thermal comfort standards and was widely used to estimate thermal sensation of occupants. However, few works are dealing with the assessment and control of occupants' thermal comfort in real time and most of them do not provide mechanisms to improve occupants' comfort in case of detecting indoor thermal discomfort. In this paper, we propose ThermCont a novel machine learning based tool to predict and control occupants' thermal comfort through the PMV model, in real time. Our tool uses multiple linear regression algorithm and is based on findings from a one-year longitudinal case study of occupants' thermal comfort in office building. Moreover, we also propose a new genetic algorithm based scheme to optimize parameters values of thermal comfort, when observing occupants' thermal discomfort, and hence to improve the indoor thermal comfort. The experimental results show the efficiency of ThermCont in terms of prediction accuracy and time complexity when compared to other machine learning algorithms, in addition to its ability to control and improve occupants' thermal comfort in real time.

Unmanned Aerial Vehicles (UAVs) have known much popularity for dangerous missions for human operators or for applications which do not need human intervention (such as monitoring and surveillance of physical infrastructures and interest areas). They operate in frequency bands (IEEE L-Band, IEEE S-Band, and ISM band) shared with other users. Accordingly, these frequency bands have become overcrowded and UAVs may face the issue of spectrum scarcity. Furthermore, there are particular difficulties associated with aeronautical communication links. Cognitive radio (CR) has emerged as a promising strategy for resolving the problems caused by scarce spectrum. It checks the spectrum availability and allows the adjustment of the transmission parameters. The aim is to opportunistically use spectral bands with minimum interference to applications or other users. In this paper, we present a centralized CR based frequency allocation scheme for UAV-Ground Control Station (GCS) communication in surveillance applications within an urban environment. In the proposed model, the GCS monitors and allocates available WiMAX frequencies using CR and Software Defined Radio (SDR). If no WiMAX frequency is available at a given time, the Wi-Fi will be used. Therefore in the worst case, our approach will have the same performance as when the Wi-Fi is only used for UAV-GCS communication.

In recent years, a large number of researchers investigate the conception of systems that use a unique Unmanned Ariel Vehicles (UAV) or multiple independent UAVs to conduct civil or military missions, with minimal human intervention. In this paper we focus on using multiple UAVs to cooperatively monitor a crowded area. Communication in such UAVs network is an ongoing project. Due to the lack of proper communication standards and rules, designing a reliable communication model is essential for: (i) multi-UAV coordination, (ii) efficient bandwidth sharing according to data priority and urgency and (iii) avoiding useless transmission of the same data by multiple UAVs. To address the above challenges, we propose a centralized data-oriented communication architecture for crowd surveillance allocations using an UAV fleet. The Ground Control Station (GCS) is used as a central coordinator to manage bandwidth usage for the UAV fleet in its coverage area. To allow UAVs to send priority messages urgently to the GCS, we define two classes of urgent messages: critical state and important result. The class of the data as well as other relevant information about the detected event will be used by the GCS to authorize or not UAV data transmission and hence to optimize the bandwidth usage efficiency.

The use of Unmanned Aerial Vehicles (UAVs) has evolved and increased recently both in civilian and military operations. In this research, we investigate the coverage of a given area using an autonomous UAV network and maintaining connectivity during the patrol; UAVs are equipped with an image and radio sensors, whose goal is to monitor a given area. Covering means that every position in the area should be covered at least by one UAV and connectivity consists to maintain the communication between UAVs and the base station during the patrol for better collaboration. Due to the communication range limit of UAVs, connectivity may then be needed to find inter-UAVs routing paths to satisfy the communication between UAVs and the base station.The problem is formulated and tested successfully, using the Solver CPLEX, as an integer linear programming model to solve it optimally. Computational experiments are generated on different grid sizes and multiple sensor ranges.

Security surveillance is critical to social harmony and people's peaceful life. It has a great impact on strengthening social stability and life safeguarding. Detecting anomaly timely, effectively and efficiently in video surveillance remains challenging. This paper proposes a new approach, called S2-VAE, for anomaly detection from video data. The S2-VAE consists of two proposed neural networks: a Stacked Fully Connected Variational AutoEncoder (SF-VAE) and a Skip Convolutional VAE (SC-VAE). The SF-VAE is a shallow generative network to obtain a model like Gaussian mixture to fit the distribution of the actual data. The SC-VAE, as a key component of S2-VAE, is a deep generative network to take advantages of CNN, VAE and skip connections. Both SF-VAE and SC-VAE are efficient and effective generative networks and they can achieve better performance for detecting both local abnormal events and global abnormal events. The proposed S2-VAE is evaluated using four public datasets. The experimental results show that the S2-VAE outperforms the state-of-the-art algorithms. The code is available publicly at https://github.com/tianwangbuaa/.

Indoor thermal comfort monitoring is becoming a crucial research topic to improve not only the occupants' comfort but also the energy consumption, and thus the building sustainability. Existing works focus on real time thermal comfort assessment of people that are performing some activities and able to answer a questionnaire. However, few works deal with thermal comfort for people with physical disabilities which may have different thermal requirements from those without physical disability, due to the disability itself. Furthermore, the remote and constant monitoring amenities are not established yet, properly. To overcome this, Internet of Things (IoT) can be used, which would introduce more flexibility to monitor residential building of these population from anywhere. As a first step, we aim to provide remote availability of thermal comfort information from A.P.E.I buildings of Troyes city11A.P.E.I stands for Association des Parents d'Enfants Inadapts, is an association of parents of in-adapted children and people with physical disabilities., located in east of France, in order to enable remote monitoring and assessment of thermal comfort in these residential buildings. To do so, a complete IoT architecture is proposed. This architecture is based on sensor devices and permits to collect data, to be transferred and processed in the Cloud infrastructure for an adequate decision-making. Moreover, we optimize sensors deployment in addition to the data collection process while ensuring high data collection accuracy. Numerical results show the efficiency and the reliability of our schemes.

Internet of Things (IoT) is an emerging paradigm that aims at making objects in the world to be connected through Internet. IPv6 over Low-power Wireless Personal Area Networks (6LoWPAN) is considered as one of the common protocol stack suite for IoT applications. The 6LoWPAN network is implemented on the top of IEEE 802.15.4 standard in order to alleviate the challenges of connecting resource constrained objects to the Internet. In such a network, nodes are competing to send their sensed data as high as possible in a selfish way. However, high network data traffic degrades network performance and quality of service aspects, e.g., data sending rate, network latency and reliability and energy consumption. In this paper, we formulate the sending rate adjustments as a non-cooperative game where each node is modeled as a player in the game and demands high data sending rate in a selfish way. The basic idea of our scheme is to adjust the data sending rate according to the preferences of nodes to send high data rate, the quality of data in terms of similarity and nodes priorities in the targeted IoT application. We then prove the existence and uniqueness of Nash equilibrium before computing the optimal sending rate using Lagrange multipliers and KarushKuhnTucker (KKT) conditions. We called our game-based scheme ThingsGame. We validate and evaluate ThingsGame scheme in the IoT operating system Contiki OS using Cooja simulator. Simulation results show that ThingsGame improves significantly network performance in terms of overall throughput, energy consumption, number of lost packets, as compared to the Selfish way scheme.

Keeping a safe city against security breaches and acts of violence is something critical. In a smart video-surveillance system, multi-shot human re-identification is a major challenge because of the large variations in a human's appearance caused by different types of noise such as occlusion, viewpoint and illumination variations. In this paper, we propose a model based-on the analysis of all the video surveillance data extracted from camera networks by exploiting the performance of the space-time covariance descriptor. This model not only deals with one video frame as the majority of models, but also considers all the extracted groups of pictures to implicitly encode the described pedestrian in motion by the integration of time parameter with the appearance features such as color, gradient and LBP, and the clustering step. The experiments conducted on PRID dataset showed the importance of video surveillance data analytics in recognition rates.

The need to locate objects and to be situated in the space, whether inside or outside, has long been the focus of a substantial amount of research. Especially in Wireless Sensor Networks, indoor localization has become an important issue in many fields of applications. In this paper, we propose an indoor location solution based on Support Vector Machine (SVM). SVM is a class of learning algorithms defined to resolve discrimination and regression problems. In fact, with many works, it turned out that it is very difficult to properly locate a target with only the RSSI measurements. Thus, the idea is to use multi-class SVM with RSSI measurements to propose a zoning localization approach. The performed experiments using different datasets, collected from two real world environments in both a hospital and a laboratory building, and the comparison with Artificial Neural Networks (ANN) confirm the effectiveness of our SVM-based localization proposal. Experimental results show that the system achieves a correct classification rate of around 90% with misclassification is in rooms where there is no wall separating them.

This paper proposes a new Bayesian strategy for the smooth estimation of altimetric parameters. The altimetric signal is assumed to be corrupted by a thermal and speckle noise distributed according to an independent and non-identically Gaussian distribution. We introduce a prior enforcing a smooth temporal evolution of the altimetric parameters which improves their physical interpretation. The posterior distribution of the resulting model is optimized using a gradient descent algorithm which allows us to compute the maximum a posteriori estimator of the unknown model parameters. This algorithm has a low computational cost that is suitable for real-time applications. The proposed Bayesian strategy and the corresponding estimation algorithm are evaluated using both synthetic and real data associated with conventional and delay/Doppler altimetry. The analysis of real Jason-2 and CryoSat-2 waveforms shows an improvement in parameter estimation when compared to state-of-the-art estimation algorithms.

Wireless sensor networks (WSNs) are important platforms for collecting environmental data and monitoring phenomena. So, outlier detection process is a necessary step in building sensor network systems to assure data quality for perfect decision making. Over the last few years Kernel Principal Component Analysis (KPCA) is considered as a natural nonlinear generalization of PCA, which extracts nonlinear structure from the data. Wireless sensor networks had been deployed in the real world to collect large amounts of raw sensed data. Then, the key challenge is to extract high level knowledge from such raw data. So, the accuracy of sensor readings is without a doubt one of the most important measures to evaluate the quality of a sensor and its network. For this case, the task amounts to create a useful model based on KPCA to recognize data as normal or outliers. However, KPCA based reconstruction error (RE) has found several applications in outlier detection but is not perfect to detect outlier. Within this setting, we propose Kernel Principal Component Analysis based Mahalanobis kernel as a new outlier detection method using mahalanobis distance to implicitly calculate the mapping of the data points in the feature space so that we can separate outlier points from normal pattern of data distribution. The use of KPCA based mahalanobis kernel on real word data obtained from three real datasets are reported showing that the proposed method performs better in finding outliers in wireless sensor networks when compared to the original RE based variant and the One-Class SVM detection approach.

State-of-the-art methods for articulated human pose estimation are based on pictorial structures model (PS). Most of these methods predict the pose directly in part-based models and only consider rigid parts guided by human anatomy. In this paper, we propose a new framework for human pose estimation which is composed of two stages: pre-estimation and estimation. The first stage includes three steps: upper body detection, upper body categorization, and model selection. In the second stage, a new upper body category based multiple mixture parts (MMP) model is proposed. We present quantitative results demonstrating that our model significantly improves the accuracy of the pose estimation.

In intelligent video surveillance systems, tracking people in non overlapping camera networks is a major challenge. To deal with the change of illumination, occlusion, change of view, etc., it is essential to seek the most robust object descriptor invariant during changes. By exploiting the performance of covariance descriptor, we propose a spatio-temporal covariance descriptor. This descriptor deals not only one picture as the majority of descriptors, but also considers groups of pictures to implicitly encode the described object motion by the integration of time parameter. The experiments conducted on “CAVIAR4REID” database showed these improvements. The person recognition rate in the first rank is improved by more than 10% compared to other descriptors.

In this paper, we propose a semiparametric regression model that relates the received signal strength indicators (RSSIs) to the distances separating stationary sensors and moving sensors in a wireless sensor network. This model combines the well-known log-distance theoretical propagation model with a nonlinear fluctuation term, estimated within the framework of kernel-based machines. This leads to a more robust propagation model. A fully comprehensive study of the choices of parameters is provided, and a comparison to state-of-the-art models using real and simulated data is given as well.

The aim of this paper is to detect abnormal events in video streams, a challenging but important subject in video surveillance. We propose a novel algorithm to address this problem. The algorithm is based on an image descriptor and a nonlinear classification method. We introduce a histogram of optical flow orientation as a descriptor encoding the moving information of each video frame. The nonlinear one-class support vector machine classification algorithm, following a learning period characterizing the normal behavior of training frames, detects abnormal events in the current frame. Further, a fast version of the detection algorithm is designed by fusing the optical flow computation with a background subtraction step. We finally apply the method to detect abnormal events on several benchmark data sets, and show promising results.

This paper considers the localization problem of sensors in mobile wireless sensor networks. It proposes a combined localization technique, using both fingerprinting and accelerometer information. The proposed approach consists of two phases. In the first one, a power map is constructed over the surveillance area. In the second phase, nodes are localized and a first position estimate is computed using the constructed power map. A second estimate is also given using accelerometer information. Both estimates are then combined using interval analysis, solutions being boxes including the real positions of the nodes. Simulation results show that the combined method improves the positioning performance, compared to methods based only on fingerprinting or accelerometer information.

In this paper, we propose an algorithm to detect abnormal events based on video streams. The algorithm is based on histograms of the orientation of optical flow descriptor and one-class SVM classifier. We introduce grids of Histograms of the Orientation of Optical Flow (HOFs) as the descriptors for motion information of the monolithic video frame. The one-class SVM, after a learning period characterizing normal behaviors, detects the abnormal events in the current frame. Extensive testing on benchmark dataset corroborates the effectiveness of the proposed detection method.

In mobile sensor networks, it is important to manage the mobility of the nodes in order to improve the performances of the network. This paper addresses the problem of single target tracking in controlled mobility sensor networks. The proposed method consists of estimating the current position of a single target. Estimated positions are then used to predict the following location of the target. Once an area of interest is defined, the proposed approach consists of moving the mobile nodes in order to cover it in an optimal way. It thus defines a strategy for choosing the set of new sensors locations. Each node is then assigned one position within the set in the way to minimize the total traveled distance by the nodes. While the estimation and the prediction phases are performed using the interval theory, relocating nodes employs the ant colony optimization algorithm. Simulations results corroborate the efficiency of the proposed method compared to the target tracking methods considered for networks with static nodes.

Abstract The key impediments to a successful wireless sensor network (WSN) application are the energy and the longevity constraints of sensor nodes. Therefore, two signal processing oriented cluster management strategies, the proactive and the reactive cluster management, are proposed to efficiently deal with these constraints. The former strategy is designed for heterogeneous WSNs, where sensors are organized in a static clustering architecture. A non‐myopic cluster activation rule is realized to reduce the number of hand‐off operations between clusters, while maintaining desired estimation accuracy. The proactive strategy minimizes the hardware expenditure and the total energy consumption. On the other hand, the main concern of the reactive strategy is to maximize the network longevity of homogeneous WSNs. A Dijkstra‐like algorithm is proposed to dynamically form active cluster based on the relation between the predictive target distribution and the candidate sensors, considering both the energy efficiency and the data relevance. By evenly distributing the energy expenditure over the whole network, the objective of maximizing the network longevity is achieved. The simulations evaluate and compare the two proposed strategies in terms of tracking accuracy, energy consumption and execution time. Copyright © 2010 John Wiley & Sons, Ltd.

This paper studies a variational Bayesian unmixing algorithm for hyperspectral images based on the standard linear mixing model. Each pixel of the image is modeled as a linear combination of endmembers whose corresponding fractions or abundances are estimated by a Bayesian algorithm. This approach requires to define prior distributions for the parameters of interest and the related hyperparameters. After defining appropriate priors for the abundances (uniform priors on the interval (0,1)), the joint posterior distribution of the model parameters and hyperparameters is derived. The complexity of this distribution is handled by using variational methods that allow the joint distribution of the unknown parameters and hyperparameter to be approximated. Simulation results conducted on synthetic and real data show similar performances than those obtained with a previously published unmixing algorithm based on Markov chain Monte Carlo methods, with a significantly reduced computational cost.

This work presents the problem of target tracking and relay localization in wireless sensor networks (WSN) based on quantized proximity sensors. Thus, we use the quantized variational filtering (QVF) in order to estimate jointly the target position and the relay location. Recently, variational filtering has been proved to be suitable to the communication constraints of WSN. However, this problem has been proposed only for binary sensor networks neglecting the information relevance of sensor measurements and the transmission energy consumption. At each sampling instant, the adaptive scheme provides the estimates of the target position and the relay location by using the QVF algorithm. The efficiency of the proposed method is validated by simulation results in target tracking for wireless sensor networks.

Due to the limited energy supplies of nodes in wireless sensor networks (WSN), optimizing their design under energy constraints, reducing their communication costs are of paramount importance. To this goal and in order to efficiently solve the problem of target tracking in WSN with quantized measurements, we propose to jointly estimate the target position and select the optimal communication path between the cluster head (CH) and the slave sensors. Firstly, we select the optimal communication path between the candidate sensor and the CH. Then, we estimate the target position using Quantized Variational Filtering (QVF) algorithm. The optimal communication path is selected as well as the highest signal-to-noise ratio (SNR) at the CH. The efficiency of the proposed method is validated by extensive simulations in target tracking for wireless sensor networks.

In this article, we propose an original approach for self-localization in mobile sensor networks. The proposed approach is developed for low-anchors density networks. Based on intervals theory, the presented method is an online technique yielding a bounded-cumulative error. The estimation of the positions of mobile sensors is performed using multi-hop observation model added to an a priori mobility model. One of the contributions of this paper is that it uses the measurements of all types of sensors, including those that do not have GPS, denoted non-anchor nodes. Compared to the existing localization techniques, this method leads to a higher accuracy with a low computational cost.

This paper addresses multiple target tracking (MTT) in wireless sensor networks (WSN) where the nonlinear observed system is assumed to progress according to a probabilistic state space model. In this paper, we propose to improve the use of the quantized variational filtering (QVF) by optimally quantizing the data collected by the sensors and estimating the channel attenuation between sensors. Our proposed technique is intended to jointly estimate the multiple target positions by using the Hybrid QVF and Sequential Monte Carlo-based approach to data association (SMCDA) algorithm, optimize the number of quantization bits per observation and estimate the fading channel coefficient. The adaptive quantization is achieved by maximizing the predicted Fisher information and the fading channel coefficient is estimated by maximizing the a posteriori distribution. The simulation results show that the adaptive quantization algorithm, outperforms both the centralized quantized particle filter (QPF) and the VF algorithm based on binary sensors (BVF).

We consider the problem of quantized target tracking in wireless sensor networks (WSN) where the observed system is assumed to evolve according to a probabilistic state space model. We propose to improve the use of the quantized variational filtering (QVF) by jointly estimating the target position and selecting the best sensors that participate in data association. In fact, the QVF has been shown to be adapted to the communication constraints of sensor networks. Its efficiency relies on the fact that the online update of the filtering distribution and its compression are executed simultaneously. Firstly, we select the best sensor that provides satisfied data of the target and balances the energy level among all sensors and minimum node density in a local cluster. Then, we estimate the target position using the QVF algorithm. The best candidate sensors are obtained by maximizing the mutual information function under energy constraints. The efficiency of the proposed method is validated by simulation results in target tracking for wireless sensor networks.

The prime motivation of our work is to balance the inherent trade-off between the resource consumption and the accuracy of the target tracking in wireless sensor networks. Toward this objective, the study goes through three phases. First, a cluster-based scheme is exploited. At every sampling instant, only one cluster of sensors that located in the proximity of the target is activated, whereas the other sensors are inactive. To activate the most appropriate cluster, we propose a nonmyopic rule, which is based on not only the target state prediction but also its future tendency. Second, the variational filtering algorithm is capable of precise tracking even in the highly nonlinear case. Furthermore, since the measurement incorporation and the approximation of the filtering distribution are jointly performed by variational calculus, an effective and lossless compression is achieved. The intercluster information exchange is thus reduced to one single Gaussian statistic, dramatically cutting down the resource consumption. Third, a binary proximity observation model is employed by the activated slave sensors to reduce the energy consumption and to minimize the intracluster communication. Finally, the effectiveness of the proposed approach is evaluated and compared with the state-of-the-art algorithms in terms of tracking accuracy, internode communication, and computation complexity.

In this paper, we propose a distributed learning strategy in wireless sensor networks. Taking advantage of recent developments on kernel-based machine learning, we consider a new sparsification criterion for online learning. As opposed to previously derived criteria, it is based on the estimated error and is therefore is well suited for tracking the evolution of systems over time. We also derive a gradient descent algorithm, and we demonstrate its relevance to estimate the dynamic evolution of temperature in a given region.

This paper presents a new method for analysis of center of pressure (COP) signals using empirical mode decomposition (EMD). The EMD decomposes a COP signal into a finite set of band-limited signals termed as intrinsic mode functions (IMFs). Thereafter, a signal processing technique used in continuous chaotic modeling is used to investigate the difference between experimental conditions on the summed IMFs. This method is used to detect the degree of variability from a second-order difference plot, which is quantified using a Central Tendency Measure (CTM). Seventeen subjects were tested under eyes open (EO) and eyes closed (EC) conditions, with different vibration frequencies applied for the EC condition in order to provide additional sensory perturbation. This study has demonstrated an effective way to differentiate vibration frequencies by combining EMD and second-order difference (SOD) plots.

In this paper, a data-driven extension of the variational algorithm is proposed. Based on a few selected sensors, target tracking is performed distributively without any information about the observation model. Tracking under such conditions is possible if one exploits the information collected from extra inter-sensor RSSI measurements. The target tracking problem is formulated as a kernel matrix completion problem. A probabilistic kernel regression is then proposed that yields a Gaussian likelihood function. The likelihood is used to derive an efficient and accelerated version of the variational filter without resorting to Monte Carlo integration. The proposed data-driven algorithm is, by construction, robust to observation model deviations and adapted to non-stationary environments.

Resource limitations in wireless sensor networks have put stringent constraints on distributed signal processing. In this paper, we propose a cluster-based decentralized variational filtering algorithm with minimum resource allocation for simultaneous sensor localization and target tracking. At each sampling instant, only one cluster of sensors is activated according to the prediction of the target state. Slave sensors employ a binary proximity observation model to reduce energy consumption and minimize communication cost. Based on the binary measurements between sensors and the target, activated sensors and target location estimates are interdependently improved. By adopting the variational method, the inter-cluster information exchange is reduced to one single Gaussian statistic, further minimizing resource consumption in the network. Since the measurement incorporation and the approximation of the filtering distribution are jointly performed by variational calculus, an effective and lossless compression is achieved compared to the classical particle filtering. Effectiveness of the proposed approach is evaluated in terms of tracking accuracy and localization precision.

This paper presents a solution to the problem of target tracking within a sensor network. This is based on modeling the target dynamics as a Markov process, and is reformulated as nonlinear filtering. When the target motion is a diffusion process, the optimal filtering involves a resolution of the backward Kolmogorov equation. Since an explicit solution for this partial differential equation does not exist in general, we recover the filtering by an alternative Monte-Carlo approach.

In this paper, we introduce a collaborative minimum mean squared error (MMSE) interference canceler in MIMO relay networks. The proposed receiver architecture is characterized by the integration of the generalized minimum residual method (GMRES) for symbol detection. In this scheme, the GMRES method detects the transmitted symbols by solving iteratively a linear system representing the MMSE interference canceler without matrix inversion. The relay-destination channels are assumed to be orthogonal. We evaluate the instantaneous capacity of the equivalent MIMO relay network equipped with K parallel relay nodes for TDMA and MC-CDMA modes, using the assumption that the source node does not communicate directly with the destination node. In order to evaluate the system performances, the bit error rate (BER) is evaluated with respect to the number of relay nodes K and the signal to noise ratio (SNR) measured at the destination.

Over the past few years, wireless sensor networks received tremendous attention for monitoring physical phenomena, such as the temperature field in a given region. Applying conventional kernel regression methods for functional learning such as support vector machines is inappropriate for sensor networks, since the order of the resulting model and its computational complexity scales badly with the number of available sensors, which tends to be large. In order to circumvent this drawback, we propose in this paper a reduced-order model approach. To this end, we take advantage of recent developments in sparse representation literature, and show the natural link between reducing the model order and the topology of the deployed sensors. To learn this model, we derive a gradient descent scheme and show its efficiency for wireless sensor networks. We illustrate the proposed approach through simulations involving the estimation of a spatial temperature distribution.

In this contribution, we propose an original algorithm for self-localization in mobile ad-hoc networks. The proposed technique, based on interval analysis, is suited to the limited computational and memory resources of mobile nodes. The incertitude about the estimated position of each node is propagated in an interval form. The propagation is based on a state space model and formulated by a constraints satisfaction problem. Observations errors as well as anchor nodes imperfections are taken into account in a simple and computational-consistent way. A simple Waltz algorithm is then applied in order to contract the solution, yielding a guaranteed and robust online estimation of the mobile node position. Simulation results on mobile node group trajectories corroborate the efficiency of the proposed technique and show that it compares favorably to particle filtering methods.

Several methods of measuring entropy of time series have been developed and applied on physiological signals in order to distinguish data sets according to their underlying nonlinear dynamics. These methods are not well adapted for studying the time series in different scales, in the presence of dominant local trends and low-frequency components. In this letter, intrinsic mode entropy (IMEn) is proposed as an entropy measure over multiple oscillation levels. Robustness to local trends is ensured with this new measure, enabling an efficient characterization of the underlying nonlinear dynamics of the time series considered. IMEn is obtained by computing the Sample Entropy (SampEn) of the cumulative sums of the intrinsic mode functions extracted by the empirical mode decomposition method. An example of an application of IMEn is then presented, with the method able to successfully discriminate between two groups of subjects (elderly versus control) for signals of postural stability

In this contribution, we propose an efficient collaborative strategy for online change detection, in a distributed sensor network. The collaborative strategy ensures the efficiency and the robustness of the data processing, while limiting the required communication bandwidth. The observed systems are assumed to have each a finite set of states, including the abrupt change behavior. For each discrete state, an observed system is assumed to evolve according to a linear state-space model. An efficient Rao-Blackwellized collaborative particle filter (RB-CPF) is proposed to estimate the a posteriori probability of the discrete states of the observed systems. The Rao-Blackwellization procedure combines a sequential Monte Carlo filter with a bank of distributed Kalman filters. Only sufficient statistics are communicated between smart nodes. The spatio-temporal selection of the leader node and its collaborators is based on a trade-off between error propagation, communication constraints and information content complementarity of distributed data.

In this contribution, we propose a Bayesian sampling solution to the problem of noisy blind separation of generalized hyperbolic (GH) signals. GH models, introduced by Barndorff-Nielsen in 1977, represent a parametric family able to cover a wide range of real signal distributions. The alternative construction of these distributions as a normal mean-variance (continuous) mixture leads to an efficient implementation of the MCMC method applied to source separation. The incomplete data structure of the GH distribution is indeed compatible with the hidden variable nature of the source separation problem. Our algorithm involves hyperparameters estimation as well. Therefore, it can be used, independently, to fit the parameters of the GH distribution to real data.