Distributed Target Tracking under Partial Feedback using Lyapunov-based Deep Neural Networks

Distributed target tracking in multi-agent networks plays a critical role in cooperative sensing and autonomous navigation. However, it faces significant challenges in highly dynamic and adversarial setups. This study aims to enhance the resilience of decentralized target tracking algorithms against measurement faults and cyber–physical threats, especially false data injection attacks. We propose a consensus-based estimation algorithm that integrates a nearly constant velocity model with saturation-based filtering to suppress impulsive measurement variations and promote robust, distributed state estimation. To counteract adversarial conditions, we incorporate a dynamic false data injection detection and isolation mechanism that uses innovation thresholds to identify and disregard suspicious measurements before they can degrade the global estimate. The effectiveness of the proposed algorithms is demonstrated through a series of simulation-based case studies under both benign and adversarial conditions. The results show that increased network connectivity and higher consensus iteration rates improve estimation accuracy and convergence speed, while properly tuned saturation filters achieve a practical balance between fault suppression and accurate estimation. Furthermore, under localized, coordinated, and transient false data injection attacks, the detection mechanism successfully identifies compromised agents and prevents their data from corrupting the distributed global estimate. Overall, this study illustrates that the proposed algorithm provides a simplified fault-tolerant solution that significantly enhances the accuracy and resilience of distributed target tracking without imposing excessive communication or computational burdens.

This paper addresses the distributed and coordinated target tracking and collision avoidance using multiple nonholonomic mobile agents whose dynamics are subject to uncertainties and disturbances. A cascaded control architecture is proposed, which consists of a virtual “simulator” and a local tracking controller. The simulators exchange their uncertainty-free states over the network and achieve flocking, while avoiding collisions, using the information from their neighbors. The local tracking law, which consists of an outer-loop guidance law and an inner-loop L1 adaptive control law, solves the tracking problem with respect to the state of the virtual simulator in the presence of plant uncertainties. The guaranteed transient performance of the L1 adaptive controller is essential towards resolving the unavoidable coupling between the communication topology and the system dynamics. Extensive simulation results demonstrate the capability of the proposed algorithms to recover the desired flocking behavior. The proposed algorithms are implemented on an indoor multi-robot platform.

In distributed tracking, communication bandwidth is one of the most expensive resources when we require to send measurements to other locations for processing. Furthermore, bandwidth requirement increases when tracking in clutter is considered due to transmission of target as well as clutter measurements. This paper describes the tracking in clutter under bandwidth constraints. The main idea is that instead of sending all target and clutter measurements we combine them into a weighted sum and transmit the resultant measurement. A novel Bayesian filter is proposed utilising the received measurement information. We observe some loss of performance as compared to local tracker, however it is considerably small.

IEEE 802.15.4/ZigBee Wireless sensor networks are now becoming popular due to rapid increase in the number of very small, integrated low-powered sensors and mobile devices capable of gathering critical, real-time information for remote surveillance, environmental monitoring, distributed target tracking etc. ZigBee is the only IEEE standard uniquely designed for low-power, a low-cost, low-data rate based wireless technology network, that provides network security, and application support services operating on top of the IEEE 802.15.4 Medium Access Control (MAC) and Physical (PHY) Layer wireless standard[1]. The survey on IEEE 802.15.4/ZigBee sensor networks showed that the unreliability is the major limitation of such sensor networks, which is termed as MAC unreliability problem. The studies also highlighted that, this unreliability problem is due to the default MAC parameter settings suggested by the standard itself. Different solutions have come up to improve the reliability problem, such as setting a predefined value for parameters which is suitable only for static conditions, an adaptive technique for dynamic conditions based on mathematical model etc. In this proposed work, the impact of MAC parameters on packet delivery ratio and the effectiveness of ADAPT algorithm is analyzed for a ZigBee sensor network. A comparative study of ZigBee network with and without ADAPT is carried out based on simulated results obtained from NS2, which is an object oriented network simulating tool. As a modification, signature verification of each node on the sensor network is performed for security purposes.

Tracking multiple moving objects of interest (OOI) with multiple robot systems (MRS) has been addressed by active sensing that maintains a shared belief of OOIs and plans the motion of robots to maximize the information quality. Mobility of robots enables the behavior of pursuing better visibility, which is constrained by sensor field of view (FoV) and occlusion objects. We first extend prior work to detect, maintain and share occlusion information explicitly, allowing us to generate occlusion-aware planning even if à priori semantic occlusion information is unavailable. The efficacy of active sensing approaches is often evaluated according to estimation error and information gain metrics. However, these metrics do not directly explain the level of cooperative behavior engendered by the active sensing algorithms. Next, we extract different emergent cooperative behaviors that stem from the same underlying algorithms but manifest differently under differing scenarios. In particular, we highlight and demonstrate three emergent behavior patterns in active sensing MRS: (i) Change of tracking responsibility between agents when tracking trajectories with divergent directions or due to a re-allocation of the resource among heterogeneous agents; (ii) Awareness of occlusions to a trajectory and temporal leave-and-return of the sensing agent; (iii) Sharing of local occlusion objects in MRS that subsequently improves the awareness of occlusion.

Distributed target tracking via UWSNs in the presence of multipath interference

Multi-rate stochastic [formula omitted] filtering for networked multi-sensor fusion

The role of feedback in learning a vernier discrimination task

Fires determine vegetation patterns, impact human societies, and are a part of complex feedbacks into the global climate system. Empirical and process-based models differ in their scale and mechanistic assumptions, giving divergent predictions of fire drivers and extent. Although humans have historically used and managed fires, the current role of anthropogenic drivers of fires remains less quantified. Whereas patterns in fire–climate interactions are consistent across the globe, fire–human–vegetation relationships vary strongly by region. Taking a data-driven approach, we use an artificial neural network to learn region-specific relationships between fire and its socio-environmental drivers across the globe. As a result, our models achieve higher predictability as compared to many state-of-the-art fire models, with global spatial correlation of 0.92, monthly temporal correlation of 0.76, interannual correlation of 0.69, and grid-cell level correlation of 0.60, between predicted and observed burned area. Given the current socio-anthropogenic conditions, Equatorial Asia, southern Africa, and Australia show a strong sensitivity of burned area to temperature whereas northern Africa shows a strong negative sensitivity. Overall, forests and shrublands show a stronger sensitivity of burned area to temperature compared to savannas, potentially weakening their status as carbon sinks under future climate-change scenarios.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

Video hyperlinking represents a classical example of multimodal problems. Common approaches to such problems are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. A particular architecture, bidirectional symmetrical deep neural networks, have been proven to yield improved multimodal embeddings over classical autoencoders, while also being able to perform crossmodal translation. In this work, we focus firstly at evaluating good single-modal continuous representations both for textual and for visual information. Word2Vec and paragraph vectors are evaluated for representing collections of words, such as parts of automatic transcripts and multiple visual concepts, while different deep convolutional neural networks are evaluated for directly embedding visual information, avoiding the creation of visual concepts. Secondly, we evaluate methods for multimodal fusion and crossmodal translation, with different single-modal pairs, in the task of video hyperlinking. Bidirectional (symmetrical) deep neural networks were shown to successfully tackle downsides of multimodal autoencoders and yield a superior multimodal representation. In this work, we extensively tests them in different settings, with different single-modal representations, within the context of video-hyperlinking. Our novel bidirectional symmetrical deep neural networks are compared to classical autoencoders and are shown to yield significantly improved multimodal embeddings that significantly (alpha=0.0001) outperform multimodal embeddings obtained by deep autoencoders with an absolute improvement in precision at 10 of 14.1% when embedding visual concepts and automatic transcripts and an absolute improvement of 4.3% when embedding automatic transcripts with features obtained with very deep convolutional neural networks, yielding 80% of precision at 10.

This paper presented an adaptive control method for WECS with variable speed and variable pitch. To gain zero steady tracking error and reject the gust disturbance, the linearized state equation was extended by introducing a extra state variable. The eigenvalues of the extended system equation were shifted to a pre-specified vertical strip to achieve satisfied the dynamic performance (damping). For practical implementation, the design method only uses partial output feedback. RBF neural network was used to approximate the nonlinear mapping relation between stable state operating point and the output feedback gain. For demonstrating the effectiveness of the system performance enhance, simulation results are used to show that the proposed controller gives significant improvement in the steady performance, dynamic performance and rejecting disturbance in WECS.

This topic mainly aimed at the dynamic simulation of some actual problems. The research is suitable for the dynamic system of modeling artificial model and learning algorithm. First it summarizes the existing network simulation model of dynamic system and network delay unit. All the feedback network and part of the feedback network model, the network topology is given and used for system simulation. The method of simulation learning algorithm and simulation instance. And then established the time-varying input and output process neural networks and network model of two kinds of discrete process neural network for its properties are analyzed and proved that the concrete learning algorithm is deduced. Finally combined with the actual problem, time-varying input and output process neural network is given in the application of system identification.

Experimental validation of saliency maps for understanding deep neural networks for weld penetration prediction

In this study, the deep multi-layered group method of data handling (GMDH)-type neural network algorithm using revised heuristic self-organization method is proposed and applied to medical image diagnosis of liver cancer. The deep GMDH-type neural network can automatically organize the deep neural network architecture which has many hidden layers. The structural parameters such as the number of hidden layers, the number of neurons in hidden layers and useful input variables are automatically selected to minimize prediction error criterion defined as Akaike’s information criterion (AIC) or prediction sum of squares (PSS). The architecture of the deep neural network is automatically organized using the revised heuristic self-organization method which is a type of the evolutionary computation. This new neural network algorithm is applied to the medical image diagnosis of the liver cancer and the recognition results are compared with the conventional 3-layered sigmoid function neural network.