This paper investigates a novel spectral-efficient design for a multi-Unmanned Aerial Vehicle (UAV) system assisted by Reconfigurable Intelligent Surfaces (RIS) within the emerging Integrated Sensing and Communication (ISAC) framework. The proposed system leverages uplink Non-Orthogonal Multiple Access (NOMA) and RIS-enhanced multi-UAV collaboration to jointly serve mobile users and perform target sensing. A hierarchical double-timescale solution is introduced, combining an adaptive Affinity Propagation Clustering (APC) approach for long-term UAV deployment and user-target association, with a short-term iterative algorithm for optimizing user transmit power, UAV beamforming, and RIS phase shifts. To tackle the non-convex optimization problem, a solution is proposed, leveraging Lagrangian dual transform, fractional programming, and minorization methods. Simulation results validate the effectiveness of the proposed approach, demonstrating significant improvements in both communication data rates and sensing information rates compared to existing benchmarks.

Decentralized Federated Learning (DFL) is recognized as a key paradigm for training models in resource-constrained, privacy-sensitive Internet of Things (IoT) environments. However, its real-world deployment is hindered by device heterogeneity, limited resources, and unpredictable node trustworthiness. To address these challenges, an innovative framework, namely Reinforcement Learning-driven Utility-based Decentralized Hierarchical Federated Learning (RL-UDHFL), is proposed, in which Reinforcement Learning (RL) is leveraged for adaptive optimization across three tiers: edge, coordination, and global aggregation. At the edge, participants are selected through an RL-Driven Participant Selection mechanism (RL-AUDPS), based on a utility function that accounts for computational resources, energy, data quality, and reputation. At the coordination level, self-tuning adaptive clustering is applied and a trust-aware gossip protocol is employed to enable robust inter-cluster communication. At the global level, reputation-based weighting is utilized and on-the-fly anomaly detection is performed to ensure model integrity. Through extensive simulations, it is demonstrated that RL-UDHFL achieves a model accuracy of 98%, surpassing hierarchical benchmarks such as HAFedRL (93.5%) and T-FedHA (92%). This superior performance is attributed to the framework’s capability to balance high accuracy, efficient resource utilization, and system reliability, thereby providing a scalable and robust blueprint for deploying sustainable and trustworthy learning systems in complex IoT applications.

This paper investigates energy-efficient federated learning (FL) in multiple-input multiple-output (MIMO) edge-enabled Internet of Things (IoT) networks, where user equipments (UEs) are enabled with simultaneous wireless information and power transfer (SWIPT) capabilities. To jointly optimize communication and computation resources, a hierarchical optimization framework is proposed to minimize the total effective energy consumption per global FL round, while satisfying latency, power, frequency, power-splitting, and local accuracy constraints. By exploiting the time-scale separation between wireless resource allocation and learning accuracy adaptation, the resulting non-convex problem is decomposed into a short-term convexified subproblem for communication and computation resource optimization, solved via successive convex approximation (SCA), and a long-term subproblem for local accuracy updates, addressed using coordinate descent (CD). The proposed algorithm ensures convergence to a stationary solution with polynomial complexity, achieving significant computational savings compared to exhaustive search. Simulation results verify that the proposed framework achieves substantial energy consumption reduction and faster convergence compared with the benchmark schemes. Furthermore, results demonstrate that increasing the base station (BS) antenna array or the energy harvesting efficiency enhances the network sustainability and scalability of FL for energy-constrained IoT devices.

Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks, despite demonstrations of significant merits such as improved robustness and resilience to unseen or out-of-distribution inputs over their non-Bayesian counterparts. Although, Deep ensemble methods (Seligmann et al. 2024; Lakshminarayanan, Pritzel, and Blundell 2017) have proven to be highly effective for Bayesian deep learning, their practical application is hindered by substantial computational cost. In this study, we introduce an innovative framework to mitigate the computational burden of ensemble Bayesian deep learning. We explore a more feasible alternative, inspired by the recent success of low-rank adapters, we introduce Bayesian Low-Rank LeArning (Bella). We show, i) Bella achieves a dramatic reduction in the number of trainable parameters required to approximate a Bayesian posterior; and ii) it not only maintains, but in some instances, surpasses the performance–in accuracy and out-of-distribution generalisation–of conventional Bayesian learning methods and non-Bayesian baselines. Our extensive empirical evaluation in large-scale tasks such as ImageNet, CAMELYON17, DomainNet, VQA with CLIP, LLaVA demonstrate the effectiveness and versatility of Bella in building highly scalable and practical Bayesian deep models for real-world applications.

Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature. In contrast, mask-based models leverage bidirectional context, enabling richer dependency modeling. However, they often assume token independence during prediction, which undermines the modeling of sequential dependencies. Additionally, the corruption of sequences through masking or absorption can introduce unnatural distortions, complicating the learning process. To address these issues, we propose Bidirectional Autoregressive Diffusion (BAD), a novel approach that unifies the strengths of autoregressive and mask-based generative models. BAD utilizes a permutation-based corruption technique that preserves the natural sequence structure while enforcing causal dependencies through randomized ordering, enabling the effective capture of both sequential and bidirectional relationships. Comprehensive experiments show that BAD outperforms autoregressive and mask-based models in text-to-motion generation, suggesting a novel pre-training strategy for sequence modeling. The codebase for BAD is available on https://github.com/RohollahHS/BAD.

Lung cancer diagnosis remains a critical challenge in personalized medicine, demanding novel approaches for efficient and accurate prediction. In this context, we propose the Spatially Optimized Lung Volume Evidence (SOLVE) framework, which is a novel lung malignancy prediction model developed by integrating principles from brain-inspired evidence accumulation and retina-inspired data processing. SOLVE introduces spatial scale optimization in Computed Tomography (CT) scan analysis, integrating evidence accumulation concepts to enhance decision-making. Mimicking the retina’s ability to process images across various spatial scales, SOLVE applies a series of filters and progressively captures features from coarse to fine details within each CT slice that may not be apparent when analyzed at a single resolution. Such an approach allows for a more discriminating feature representation, improving the richness of available information for analysis and reducing the reliance on large datasets. Addressing the challenge of limited medical image resources, SOLVE effectively decreases computational complexity via the use of its evidence-based mechanism. Through experiments conducted on an in-house dataset of 114 subjects, SOLVE demonstrated a marked improvement in prediction accuracy, outperforming traditional methods with far less training data.

Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC). However, the variability in polyp characteristics and the presence of artifacts in colonoscopy images and videos pose significant challenges for accurate and efficient polyp detection and segmentation. This paper presents a novel approach to polyp segmentation by integrating the Segment Anything Model (SAM 2) with the YOLOv8 model. Our method leverages YOLOv8’s bounding box predictions to autonomously generate input prompts for SAM 2, thereby reducing the need for manual annotations. We conducted exhaustive tests on five benchmark colonoscopy image datasets and two colonoscopy video datasets, demonstrating that our method exceeds state-of-the-art models in both image and video segmentation tasks. Notably, our approach achieves high segmentation accuracy using only bounding box annotations, significantly reducing annotation time and effort. This advancement holds promise for enhancing the efficiency and scalability of polyp detection in clinical settings https://github.com/sajjad-sh33/YOLO_SAM2.

Using massive datasets, foundation models are large-scale, pre-trained models that perform a wide range of tasks. These models have shown consistently improved results with the introduction of new methods. It is crucial to analyze how these trends impact the medical field and determine whether these advancements can drive meaningful change. This study investigates the application of recent state-of-the-art foundation models—DINOv2, MAE, VMamba, CoCa, SAM2, and AIMv2—for medical image classification. We explore their effectiveness on datasets including CBIS-DDSM for mammography, ISIC2019 for skin lesions, APTOS2019 for diabetic retinopathy, and CHEXPERT for chest radiographs. By fine-tuning these models and evaluating their configurations, we aim to understand the potential of these advancements in medical image classification. The results indicate that these advanced models significantly enhance classification outcomes, demonstrating robust performance despite limited labeled data. Based on our results, AIMv2, DI-NOv2, and SAM2 models outperformed others, demonstrating that progress in natural domain training has positively impacted the medical domain and improved classification outcomes. Our code is publicly available at https://github.com/sajjad-sh33/Medical-Transfer-Learning.

Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammograms is essential for early detection, driving a surge of interest in Artificial Intelligence (AI)-powered CAD models. While state-of-the-art multi-view mammogram classification models are largely based on Transformer architectures, their computational complexity scales quadratically with the number of image patches, highlighting the need for more efficient alternatives. To address this challenge, we propose Mammo-Mamba, a novel framework that integrates Selective State-Space Models (SSMs), transformer-based attention, and expert-driven feature refinement into a unified architecture. Mammo-Mamba extends the MambaVision backbone by introducing the Sequential Mixture of Experts (SeqMoE) mechanism through its customized SecMamba block. The SecMamba is a modified MambaVision block that enhances representation learning in high-resolution mammographic images by enabling content-adaptive feature refinement. These blocks are integrated into the deeper stages of MambaVision, allowing the model to progressively adjust feature emphasis through dynamic expert gating, effectively mitigating the limitations of traditional Transformer models. Evaluated on the CBIS-DDSM benchmark dataset, Mammo-Mamba achieves superior classification performance across all key metrics while maintaining computational efficiency.

Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence metric, its effectiveness can be limited, particularly in biased scenarios. Extending existing approaches like the Pseudo Label Probability Difference (PLPD), we introduce ETAGE, a refined TTA method that integrates entropy minimization with gradient norms and PLPD, to enhance sample selection and adaptation. Our method prioritizes samples that are less likely to cause instability by combining high entropy with high gradient norms out of adaptation, thus avoiding the overfitting to noise often observed in previous methods. Extensive experiments on CIFAR-10-C and CIFAR-100-C datasets demonstrate that our approach outperforms existing TTA techniques, particularly in challenging and biased scenarios, leading to more robust and consistent model performance across diverse test scenarios. The codebase for ETAGE is available on https://github.com/afsharshamsi/ETAGE.

Casting defects pose a significant challenge in the manufacturing industry, leading to material waste, production inefficiencies, and compromised product quality. While deep learning models have shown promise in automating defect detection, their effectiveness is often constrained by domain shifts and variability in real-world data distributions. In this work, we propose Bayesian Test-Time Adaptation (BTTA), a novel framework designed to enhance the robustness and adaptability of machine learning models in such dynamic environments. Unlike traditional Test-Time Adaptation (TTA) methods, our approach employs gradient-guided diversification with Stein Variational Gradient Descent (SVGD) to explore diverse optimization paths. Experimental results on benchmark datasets, including CIFAR-10-C , Casting Defects , and GDXray , demonstrate significant performance improvements across key metrics. Notably, the framework achieves an average accuracy improvement of 2-3% under severe corruption levels and excels in cross-domain generalization, highlighting its ability to handle diverse and unseen defect categories. This dynamic adaptability not only addresses the limitations of static models but also offers a practical and cost-effective solution for real-time defect detection in industrial settings. Our study underscores the potential of BTTA to transform quality assurance processes, ensuring reliable performance across varying operational conditions without the need for extensive retraining or large annotated datasets. The codebase for BTTA is available on: https://github.com/afsharshamsi/GradSurgery .

Federated Learning (FL) is a decentralized approach that allows for collaborative training of Machine Learning (ML) models across multiple local nodes, ensuring data privacy and security while leveraging diverse datasets. Conventional FL, however, is susceptible to gradient inversion attacks, restrictively enforces a uniform architecture on local models, and suffers from model heterogeneity (model drift) due to non-IID local datasets. To mitigate some of these challenges, the new paradigm of Federated Knowledge Distillation (FKD) has emerged. FKD is developed based on the concept of Knowledge Distillation (KD), which involves extraction and transfer of a large and well-trained teacher model’s knowledge to lightweight student models. FKD, however, still faces the model drift issue. Intuitively speaking, not all knowledge is universally beneficial due to the inherent diversity of data among local nodes. This calls for innovative mechanisms to evaluate the relevance and effectiveness of each client’s knowledge for others, to prevent propagation of adverse knowledge. In this context, the paper proposes Effective Knowledge Fusion (KnFu) algorithm that evaluates knowledge of local models to only fuse semantic neighbors’ effective knowledge for each client. The KnFu is a personalized effective knowledge fusion scheme for each client, that analyzes effectiveness of different local models’ knowledge prior to the aggregation phase. In this context, closeness of clients’ knowledge is measured by estimating the class distributions of local datasets based on the transmitted localized knowledge. Comprehensive experiments were performed on MNIST and CIFAR10 datasets. KnFu outperforms its FL-based, FKD-based, and local training baselines in scenarios where the clients have small datasets with intermediate degree of heterogeneity. KnFu’s source code is accessible throught the following link: https://github.com/jamal94sm/KnFu-Effective-Knowledge-Fusion.git.

Drawing inspiration from the primate brain’s intriguing evidence accumulation process, and guided by models from cognitive psychology and neuroscience, the paper introduces the NYCTALE framework, a neuro-inspired and evidence accumulation-based Transformer architecture. The proposed neuro-inspired NYCTALE offers a novel pathway in the domain of Personalized Medicine (PM) for lung cancer diagnosis. In nature, Nyctales are small owls known for their nocturnal behavior, hunting primarily during the darkness of night. The NYCTALE operates in a similarly vigilant manner, i.e., processing data in an evidence-based fashion and making predictions dynamically/adaptively. Distinct from conventional Computed Tomography (CT)-based Deep Learning (DL) models, the NYCTALE performs predictions only when sufficient amount of evidence is accumulated. In other words, instead of processing all or a pre-defined subset of CT slices, for each person, slices are provided one at a time. The NYCTALE framework then computes an evidence vector associated with contribution of each new CT image. A decision is made once the total accumulated evidence surpasses a specific threshold. Preliminary experimental analyses conducted using a challenging in-house dataset comprising 114 subjects. The results are noteworthy, suggesting that NYCTALE outperforms the benchmark accuracy even with approximately $60 \%$ less training data on this demanding and small dataset.

Coded/uncoded content placement in Mobile Edge Caching (MEC) has evolved as an efficient solution to meet the significant growth of global mobile data traffic by boosting the content diversity in the storage of caching nodes. To meet the dynamic nature of the historical request pattern of multimedia contents, the main focus of recent researches has been shifted to develop data-driven and real-time caching schemes. In this regard and with the assumption that users’ preferences remain unchanged over a short horizon, the Top-K popular contents. These contents refer to the most requested content in the upcoming period. Most existing data-driven popularity prediction models, however, are not suitable for the coded/uncoded content placement frameworks. On the one hand, in coded/uncoded content placement, in addition to classifying contents into two groups, i.e., popular and non-popular, the probability of content request is required to identify which content should be stored partially/completely, where this information is not provided by existing data-driven popularity prediction models. On the other hand, the assumption that users’ preferences remain unchanged over a short horizon only works for content with a smooth request pattern. To tackle these challenges, we develop a Multiple-model (hybrid) Transformer-based Edge Caching (MTEC) framework with higher generalization ability, suitable for various types of content with different time-varying behavior, that can be adapted with coded/uncoded content placement frameworks. In this work, we consider Top-K content as the output of the 1st Stage of the proposed MTEC framework, which includes both popular and mediocre content. Simulation results corroborate the effectiveness of the proposed MTEC caching framework in comparison to its counterparts in terms of the cache-hit ratio, classification accuracy, and the transferred byte volume.

Mobile-edge caching (MEC) integrated with deep neural networks (DNNs) is an innovative technology with significant potential for the future generation of wireless networks, resulting in a considerable reduction in users’ latency. The mobile-edge caching (MEC) network’s effectiveness, however, heavily relies on its capacity to predict and dynamically update the storage of caching nodes with the most popular contents. To be effective, a DNN-based popularity prediction model needs to have the ability to understand the historical request patterns of content, including their temporal and spatial correlations. Existing state-of-the-art time-series DNN models capture the latter by simultaneously inputting the sequential request patterns of multiple contents to the network, considerably increasing the size of the input sample. This motivates us to address this challenge by proposing a DNN-based popularity prediction framework based on the idea of contrasting input samples against each other, designed for the unmanned aerial vehicle (UAV)-aided MEC networks. Referred to as the contrastive learning-based survival analysis (CLSA), the proposed architecture consists of a self-supervised contrastive learning (CL) model, where the temporal information of sequential requests is learned using a long short-term memory (LSTM) network as the encoder of the CL architecture. Followed by a survival analysis (SA) network, the output of the proposed CLSA architecture is probabilities for each content’s future popularity, which are then sorted in descending order to identify the Top-$K$popular contents. Based on the simulation results, the proposed CLSA architecture outperforms its counterparts across the classification accuracy and cache-hit ratio.

The widespread deployment of information and communication technologies in smart power distribution networks (SPDNs) exposes them to cyber threats. Among different types of cyber-attacks in such ICT-based SPDNs, load-altering attacks (LAAs) against high-wattage devices have received significant attention in recent years. In this context, this article proposes a data-driven detection model tailored for identifying and localizing LAAs in SPDNs. In this pursuit, first, the graph structure of an SPDN, which is obtained from the grid topology, and node features, i.e., measurements of the load's power, are fed to a graph attention network (GAT), and the spatial correlations among the nodes are captured. Alongside, the temporal correlations are captured using a long short-term memory model trained based on the graph representation obtained from the GAT. These spatial and temporal correlations are used by prediction and reconstruction models, i.e., a fully connected neural network and an auto-encoder. Finally, based on the error of the prediction and reconstruction blocks, an attack score for each load is calculated, and the compromised loads are detected and localized. To evaluate the performance of the proposed model, a co-simulation framework, which simulates the power system and emulates the communication network using real industrial protocols, i.e., IEC 60870-5-104, has been developed. The robustness of the model's performance against noisy data and non-attack outliers is confirmed with respect to different noise levels and data outliers. Also, the developed model's superior performance over existing models is demonstrated through various LAA scenarios applied to the IEEE 33- and the 123-Bus benchmarks.

In this article, we address the problem of delay-causing time synchronization (DC-TS) attacks against wide-area damping controllers (WADCs). To enhance smart grid stability against such threats, we present a realistic and secure design procedure for WADCs. To this end, we follow a methodology that utilizes the state-space model of the entire grid to design a periodic observer-based event-triggered controller by formulating the problem as a set of linear matrix inequalities, solved by the looped-Lyapunov functional (LLF) technique. The event-triggered scheme applied in this design procedure improves communication efficiency. Plus, the periodic sampled-data approach makes the design better suited to the operational reality of digital systems and their constraints. As such, the contributions of this work include developing an event-triggered mechanism to reduce unnecessary data transmissions, applying LLF for less conservative stability analysis, and utilizing the Guardian map theorem and Rekasius substitution to assess the WADCs resilience under DC-TS attacks. We conducted extensive simulations on the Kundur two-area and New England 39-bus systems to validate our approach. These simulations, along with comparisons to existing methods and tests on the RT-Lab real-time platform, demonstrate the superior performance of our WADC in maintaining grid stability and improving damping under considered attacks.

Mobile Edge Caching (MEC) is a revolutionary technology for the Sixth Generation (6G) of wireless networks with the promise to significantly reduce users’ latency via offering storage capacities at the edge of the network. The efficiency of the MEC network, however, critically depends on its ability to dynamically predict/update the storage of caching nodes with the top-K popular contents. Conventional statistical caching schemes are not robust to the time-variant nature of the underlying pattern of content requests, resulting in a surge of interest in using Deep Neural Networks (DNNs) for time-series popularity prediction in MEC networks. However, existing DNN models within the context of MEC fail to simultaneously capture both temporal correlations of historical request patterns and the dependencies between multiple contents. This necessitates an urgent quest to develop and design a new and innovative popularity prediction architecture to tackle this critical challenge. The paper addresses this gap by proposing a novel hybrid caching framework based on the attention mechanism. Referred to as the parallel Vision Transformers with Cross Attention (ViT-CAT) Fusion, the proposed architecture consists of two parallel ViT networks, one for collecting temporal correlation, and the other for capturing dependencies between different contents. Followed by a Cross Attention (CA) module as the Fusion Center (FC), the proposed ViT-CAT is capable of learning the mutual information between temporal and spatial correlations, as well, resulting in improving the classification accuracy, and decreasing the model’s complexity about 8 times. Based on the simulation results, the proposed ViT-CAT architecture outperforms its counterparts across the classification accuracy, complexity, and cache-hit ratio.

The paper proposes a novel hybrid discovery Radiomics framework that simultaneously integrates temporal and spatial features extracted from non-thin chest Computed Tomography (CT) slices to predict Lung Adenocarcinoma (LUAC) malignancy with minimum expert involvement. Lung cancer is the leading cause of mortality from cancer worldwide and has various histologic types, among which LUAC has recently been the most prevalent. LUACs are classified as pre-invasive, minimally invasive, and invasive adenocarcinomas. Timely and accurate knowledge of the lung nodules malignancy leads to a proper treatment plan and reduces the risk of unnecessary or late surgeries. Currently, chest CT scan is the primary imaging modality to assess and predict the invasiveness of LUACs. However, the radiologists’ analysis based on CT images is subjective and suffers from a low accuracy compared to the ground truth pathological reviews provided after surgical resections. The proposed hybrid framework, referred to as the CAET-SWin, consists of two parallel paths: (i) The Convolutional Auto-Encoder (CAE) Transformer path that extracts and captures informative features related to inter-slice relations via a modified Transformer architecture, and; (ii) The Shifted Window (SWin) Transformer path, which is a hierarchical vision transformer that extracts nodules’ related spatial features from a volumetric CT scan. Extracted temporal (from the CAET path) and spatial (from the SWin path) are then fused through a fusion path to classify LUACs. Experimental results on our in-house dataset of 114 pathologically proven SubSolid Nodules (SSNs) demonstrate that the CAET-SWin significantly improves reliability of the invasiveness prediction task while achieving an accuracy of 82.65%, sensitivity of 83.66%, and specificity of 81.66% using 10-fold cross-validation.

Development of advance surface Electromyogram (sEMG)-based Human-Machine Interface (HMI) systems is of paramount importance to pave the way towards emergence of futuristic Cyber-Physical-Human (CPH) worlds. In this context, the main focus of recent literature was on development of different Deep Neural Network (DNN)-based architectures that perform Hand Gesture Recognition (HGR) at a macroscopic level (i.e., directly from sEMG signals). At the same time, advancements in acquisition of High-Density sEMG signals (HD-sEMG) have resulted in a surge of significant interest on sEMG decomposition techniques to extract microscopic neural drive information. However, due to complexities of sEMG decomposition and added computational overhead, HGR at microscopic level is less explored than its aforementioned macroscopic-level, DNN-based counterparts. In this regard, we propose the HYDRA-HGR framework, which is a hybrid model for HGR that simultaneously extracts a set of temporal and spatial features through its two independent Vision Transformer (ViT)-based parallel architectures (the so called Macro and Micro paths). The Macro Path is trained directly on the pre-processed HD-sEMG signals, while the Micro path is fed with the p-to-p values of the extracted Motor Unit Action Potentials (MUAPs) of each source. Extracted features at macroscopic and microscopic levels are then coupled via a Fully Connected (FC) fusion layer for final gesture classification. We evaluate the proposed hybrid HYDRA-HGR framework through a recently released HD-sEMG dataset, and show that it significantly outperforms its stand-alone counterparts. The proposed HYDRA-HGR framework achieves average accuracy of 94.86% for the 250 ms window size, which is 5.52 % and 8.22 % higher than that of the Macro and Micro paths, respectively.

The paper is motivated by the importance of the Smart Cities (SC) concept for future management of global urbanization. Among all Internet of Things (IoT)-based communication technologies, Blue-tooth Low Energy (BLE) plays a vital role in city-wide decision making and services. Extreme fluctuations of the Received Signal Strength Indicator (RSSI), however, prevent this technology from being a reliable solution with acceptable accuracy in the dynamic indoor tracking/localization approaches for ever-changing SC environments. The latest version of the BLE v.5.1 introduced a better possibility for tracking users by utilizing the direction finding approaches based on the Angle of Arrival (AoA), which is more reliable. There are still some fundamental issues remaining to be addressed. Existing works mainly focus on implementing stand-alone models overlooking potentials fusion strategies. The paper addresses this gap and proposes a novel Reinforcement Learning (RL)-based information fusion framework (RL-IFF) by coupling AoA with RSSI-based particle filtering and Inertial Measurement Unit (IMU)-based Pedestrian Dead Reckoning (PDR) frameworks. The proposed RL-IFF solution is evaluated through a comprehensive set of experiments illustrating superior performance compared to its counterparts.

Advancements in Biological Signal Processing (BSP) and Machine-Learning (ML) models have paved the path for development of novel immersive Human-Machine Interfaces (HMI). In this context, there has been a surge of significant interest in Hand Gesture Recognition (HGR) utilizing Surface-Electromyogram (sEMG) signals. This is due to its unique potential for decoding wearable data to interpret human intent for immersion in Mixed Reality (MR) environments. To achieve the highest possible accuracy, complicated and heavy-weighted Deep Neural Networks (DNNs) are typically developed, which restricts their practical application in low-power and resource-constrained wearable systems. In this work, we propose a light-weight hybrid architecture (HDCAM) based on Convolutional Neural Network (CNN) and attention mechanism to effectively extract local and global representations of the input. The proposed HDCAM model with 58, 441 parameters reached a new state-of-the-art (SOTA) performance with 82.91% and 81.28% accuracy on window sizes of 300 ms and 200 ms for classifying 17 hand gestures. The number of parameters to train the proposed HDCAM architecture is 18.87× less than its previous SOTA counterpart.

Given the recent surge of significant interest in implementing intelligent hand gesture recognition methods in human-machine interface systems, a wide variety of Deep Neural Networks (DNNs) have been proposed in the literature. In this paper, we introduce a novel and compact Spiking Neural Network (SNN) model for hand gesture recognition using High-Density surface Electromyogram (HD-sEMG) signals. Capitalizing on their ability to extract spatiotemporal features of HD-sEMG signals along with their proven strength in imitating human brain's neural activity using event-driven data processing, we used SNNs as the main building block of our proposed hand gesture recognition model. We show that our proposed model can efficiently differentiate 14 hand movements by considering each sample of the HD-sEMG data as a single time step for the SNN architecture. Moreover, we show that the proposed SNN model does not require huge pre-processing, spike encoding and feature extraction tasks and works effectively on Min-Max normalized continuous-value sEMG signals. We evaluate our SNN model using a 5-fold cross-validation scheme and categorize different participants based on the range of classification accuracy we obtained for them. The following results are acquired by segmenting HD-sEMG signals into windows of size 62.5ms with no overlap. The proposed method led to 6 out of 19 subjects achieving average classification accuracy of ≥ 80% with maximum accuracy of 98% associated with 3rdsession of the sEMG dataset as the test set.

Recently, as a consequence of the coronavirus disease (COVID-19) pandemic, dependence on contact tracing (CT) models has significantly increased to prevent the spread of this highly contagious virus and be prepared for the potential future ones. Since the spreading probability of the novel coronavirus in indoor environments is much higher than that of the outdoors, there is an urgent and unmet quest to develop/design efficient, autonomous, trustworthy, and secure indoor CT solutions. Despite such an urgency, this field is still in its infancy. This article addresses this gap and proposes the trustworthy blockchain-enabled system for an indoor CT (TB-ICT) framework. The TB-ICT framework is proposed to protect privacy and integrity of the underlying CT data from unauthorized access. More specifically, it is a fully distributed and innovative blockchain platform exploiting the proposed dynamic Proof-of-Work (dPoW) credit-based consensus algorithm coupled with randomized hash window (W-Hash) and dynamic Proof-of-Credit (dPoC) mechanisms to differentiate between honest and dishonest nodes. The TB-ICT not only provides a decentralization in data replication but also quantifies the node’s behavior based on its underlying credit-based mechanism. For achieving a high localization performance, we capitalize on the availability of Internet of Things (IoT) indoor localization infrastructures, and develop a data-driven localization model based on bluetooth low-energy (BLE) sensor measurements. The simulation results show that the proposed TB-ICT prevents the COVID-19 from spreading by the implementation of a highly accurate CT model while improving the users’ privacy and security.

Abstract Skin cancer, primarily resulting from the abnormal growth of skin cells, is among the most common cancer types. In recent decades, the incidence of skin cancer cases worldwide has risen significantly (one in every three newly diagnosed cancer cases is a skin cancer). Such an increase can be attributed to changes in our social and lifestyle habits coupled with devastating man-made alterations to the global ecosystem. Despite such a notable increase, diagnosis of skin cancer is still challenging, which becomes critical as its early detection is crucial for increasing the overall survival rate. This calls for advancements of innovative computer-aided systems to assist medical experts with their decision making. In this context, there has been a recent surge of interest in machine learning (ML), in particular, deep neural networks (DNNs), to provide complementary assistance to expert physicians. While DNNs have a high processing capacity far beyond that of human experts, their outputs are deterministic, i.e., providing estimates without prediction confidence. Therefore, it is of paramount importance to develop DNNs with uncertainty-awareness to provide confidence in their predictions. Monte Carlo dropout (MCD) is vastly used for uncertainty quantification; however, MCD suffers from overconfidence and being miss calibrated. In this paper, we use MCD algorithm to develop an uncertainty-aware DNN that assigns high predictive entropy to erroneous predictions and enable the model to optimize the hyper-parameters during training, which leads to more accurate uncertainty quantification. We use two synthetic (two moons and blobs) and a real dataset (skin cancer) to validate our algorithm. Our experiments on these datasets prove effectiveness of our approach in quantifying reliable uncertainty. Our method achieved 85.65 ± 0.18 prediction accuracy, 83.03 ± 0.25 uncertainty accuracy, and 1.93 ± 0.3 expected calibration error outperforming vanilla MCD and MCD with loss enhanced based on predicted entropy.

Ultra-Wideband (UWB) is one of the key technolo-gies empowering the Internet of Thing (IoT) concept to per-form reliable, energy-efficient, and highly accurate monitoring, screening, and localization in indoor environments. Performance of UWB-based localization systems, however, can significantly degrade because of Non Line of Sight (NLoS) connections between a mobile user and UWB beacons. To mitigate the destructive effects of NLoS connections, we target development of a Reinforcement Learning (RL) anchor selection framework that can efficiently cope with the dynamic nature of indoor environments. Existing RL models in this context, however, lack the ability to generalize well to be used in a new setting. Moreover, it takes a long time for the conventional RL models to reach the optimal policy. To tackle these challenges, we propose the Jump-start RL-based Uwb NOde selection (JUNO) framework, which performs real-time location predictions without relying on complex NLoS identification/mitigation methods. The effectiveness of the proposed JUNO framework is evaluated in term of the location error, where the mobile user moves randomly through an ultra-dense indoor environment with a high chance of establishing NLoS connections. Simulation results corroborate the effectiveness of the proposed framework in comparison to its state-of-the-art counterparts.

A long-standing challenge of deep learning models involves how to handle noisy labels, especially in applications where human lives are at stake. Adoption of the data Shapley Value (SV), a cooperative game-theoretic approach, is an intelligent valuation solution to tackle the issue of noisy labels. Data SV can be used together with a learning model and an evaluation metric to validate each training point’s contribution to the model’s performance. The SV of a data point, however, is not unique and depends on the learning model, the evaluation metric, and other data points collaborating in the training game. However, effects of utilizing different evaluation metrics for computation of the SV, detecting the noisy labels, and measuring the data points’ importance has not yet been thoroughly investigated. In this context, we performed a series of comparative analyses to assess SV’s capabilities to detect noisy input labels when measured by different evaluation metrics. Our experiments on COVID-19-infected of CT images illustrate that although the data SV can effectively identify noisy labels, adoption of different evaluation metric can significantly influence its ability to identify noisy labels from different data classes. Specifically, we demonstrate that the SV greatly depends on the associated evaluation metric.

Advances in biosignal signal processing and machine learning, in particular Deep Neural Networks (DNNs), have paved the way for the development of innovative Human-Machine Interfaces for decoding the human intent and controlling artificial limbs. DNN models have shown promising results with respect to other algorithms for decoding muscle electrical activity, especially for recognition of hand gestures. Such data-driven models, however, have been challenged by their need for a large number of trainable parameters and their structural complexity. Here we propose the novel Temporal Convolutions-based Hand Gesture Recognition architecture (TC-HGR) to reduce this computational burden. With this approach, we classified 17 hand gestures via surface Electromyogram (sEMG) signals by the adoption of attention mechanisms and temporal convolutions. The proposed method led to 81.65% and 80.72% classification accuracy for window sizes of 300 ms and 200 ms, respectively. The number of parameters to train the proposed TC-HGR architecture is 11.9 times less than that of its state-of-the-art counterpart.

As a consequence of the COVID-19 pandemic, the demand for telecommunication for remote learning/working and telemedicine has significantly increased. Mobile Edge Caching (MEC) in the 6G networks has been evolved as an efficient solution to meet the phenomenal growth of the global mobile data traffic by bringing multimedia content closer to the users. Although massive connectivity enabled by MEC networks will significantly increase the quality of communications, there are several key challenges ahead. The limited storage of edge nodes, the large size of multimedia content, and the time-variant users’ preferences make it critical to efficiently and dynamically predict the popularity of content to store the most upcoming requested ones before being requested. Recent advancements in Deep Neural Networks (DNNs) have drawn much research attention to predict the content popularity in proactive caching schemes. Existing DNN models in this context, however, suffer from long-term dependencies, computational complexity, and unsuitability for parallel computing. To tackle these challenges, we propose an edge caching framework incorporated with the attention-based Vision Transformer (ViT) neural network, referred to as the Transformer-based Edge (TEDGE) caching, which to the best of our knowledge, is being studied for the first time. Moreover, the TEDGE caching framework requires no data pre-processing and additional contextual information. Simulation results corroborate the effectiveness of the proposed TEDGE caching framework in comparison to its counterparts.

Recently, as a consequence of the COVID-19 pandemic, dependence on telecommunication for remote learning/working and telemedicine has significantly increased. In this context, preserving high Quality of Service (QoS) and maintaining low-latency communication are of paramount importance. In cellular networks, the incorporation of unmanned aerial vehicles (UAVs) can result in enhanced connectivity for outdoor users due to the high probability of establishing Line of Sight (LoS) links. The UAV’s limited battery life and its signal attenuation in indoor areas, however, make it inefficient to manage users’ requests in indoor environments. Referred to as the cluster-centric and coded UAV-aided femtocaching (CCUF) framework, the network’s coverage in both indoor and outdoor environments increases by considering a two-phase clustering framework for Femto access points (FAPs)’ formation and UAVs’ deployment. Our first objective is to increase the content diversity. In this context, we propose a coded content placement in a cluster-centric cellular network, which is integrated with the coordinated multipoint (CoMP) approach to mitigate the intercell interference in edge areas. Then, we compute, experimentally, the number of coded contents to be stored in each caching node to increase the cache-hit-ratio, signal-to-interference-plus-noise ratio (SINR), and cache diversity and decrease the users’ access delay and cache redundancy for different content popularity profiles. Capitalizing on clustering, our second objective is to assign the best caching node to indoor/outdoor users for managing their requests. In this regard, we define the movement speed of ground users as the decision metric of the transmission scheme for serving outdoor users’ requests to avoid frequent handovers between FAPs and increase the battery life of UAVs. Simulation results illustrate that the proposed CCUF implementation increases the cache-hit-ratio, SINR, and cache diversity and decrease the users’ access delay, cache redundancy, and UAVs’ energy consumption.

This article proposes a resilient framework for optimized consensus using a dynamic event-triggering (DET) scheme, where the multiagent system (MAS) is subject to denial-of-service (DoS) attacks. When initiated by an adversary, DoS blocks the local and neighboring communication channels in the network. A distributed DET scheme is utilized to limit transmissions between the neighboring agents. A novel convex optimization approach is proposed that simultaneously co-designs all unknown control and DET parameters. The optimization is based on the weighted sum approach and increases the interevent interval for a predefined consensus convergence rate. In the presence of DoS, the proposed co-design framework is beneficial in two ways: 1) the desired level of resilience to DoS is included as a given (desired) input and 2) the upper bound for guaranteed resilience associated with the proposed co-design approach is less conservative (larger) compared to those obtained from other analytical solutions. A structured tradeoff between relevant features of the MAS, namely, the consensus convergence rate, frequency of event triggerings, and level of resilience to DoS attacks, is established. Simulations based on nonholonomic mobile robots quantify the effectiveness of the proposed implementation.

There has been a recent surge of interest on smart phone-based indoor localization due to the urgent need for real-time, accurate, and scalable indoor positioning solutions independent of any proprietary sensors/modules. Existing Inertial Measurement Unit (IMU)-based approaches, typically, use statistical and error prone heading and step length estimation techniques rendering them impractical for robust, real-time and accurate indoor positioning. In this regard, the paper takes one step forward to transfer offline IMU-based models to online positioning frameworks. More specifically, inspired by prominent advances in sequential Signal Processing (SP) and Natural Language Processing (NLP) techniques, two near real-time dynamic windowing mechanisms are proposed based on a two stage Long Short-Term Memory (LSTM) localization architecture. The two underlying LSTM architectures are trained with 2100 Action Units (AU). Compared to the traditional LSTM-based positioning approaches suffering from either high tensor computation requirements or low accuracy preventing them for real-time deployment, the proposed Online Dynamic Windowing (ODW) assisted two stage LSTM models can perform localization in a real-time fashion. Performance evaluations based on a real Pedestrian Dead Reckoning (PDR) dataset shows that the proposed model can achieve exceptional classification accuracy of 97.9% and 95.5% for the two underlying LSTMs.

Bluetooth Low Energy (BLE) is one of the key technologies empowering the Internet of Things (IoT) for indoor positioning. In this regard, Angle of Arrival (AoA) localization is one of the most reliable techniques because of its low estimation error. BLE-based AoA localization, however, is in its infancy as only recently direction-finding feature is introduced to the BLE specification. Furthermore, AoA-based approaches are prone to noise, multi-path, and path-loss effects. The paper proposes an efficient Convolutional Neural Network (CNN)-based indoor localization framework to tackle these issues specific to BLE-based settings. We consider indoor environments without presence of Line of Sight (LoS) links affected by Additive White Gaussian Noise (AWGN) with different Signal to Noise Ratios (SNRs) and Rayleigh fading channel. Moreover, by assuming a 3-D indoor environment, the destructive effect of the elevation angle of the incident signal is considered on the position estimation. The effectiveness of the proposed CNN-AoA framework is evaluated via an experimental testbed, where In-phase/Quadrature (I/Q) samples, modulated by Gaussian Frequency Shift Keying (GFSK), are collected by four BLE beacons. Simulation results corroborate effectiveness of the proposed CNN-based AoA technique to track mobile agents with high accuracy in the presence of noise and Rayleigh fading channel.

The global outbreak of the novel corona virus (COVID-19) disease has drastically impacted the world and led to one of the most challenging crisis across the globe since World War II. The early diagnosis and isolation of COVID-19 positive cases are considered as crucial steps towards preventing the spread of the disease and flattening the epidemic curve. Chest Computed Tomography (CT) scan is a highly sensitive, rapid, and accurate diagnostic technique that can complement Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Recently, deep learning-based models, mostly based on Convolutional Neural Networks (CNN), have shown promising diagnostic results. CNNs, however, are incapable of capturing spatial relations between image instances and require large datasets. Capsule Networks, on the other hand, can capture spatial relations, require smaller datasets, and have considerably fewer parameters. In this paper, a Capsule network framework, referred to as the "CT-CAPS", is presented to automatically extract distinctive features of chest CT scans. These features, which are extracted from the layer before the final capsule layer, are then leveraged to differentiate COVID-19 from Non-COVID cases. The experiments on our in-house dataset of 307 patients show the state-of-the-art performance with the accuracy of 90.8%, sensitivity of 94.5%, and specificity of 86.0%.

This work is motivated by the recent advancements of Deep Neural Networks (DNNs) for myoelectric prosthesis control. In this regard, hand gesture recognition via surface Electromyogram (sEMG) signals has shown a high potential for improving the performance of myoelectric control prostheses. Although the recent researches in hand gesture recognition with DNNs have achieved promising results, they are still in their infancy. The recent literature uses traditional supervised learning methods that usually have poor performance if a small amount of data is available or requires adaptation to a changing task. Therefore, in this work, we develop a novel hand gesture recognition framework based on the formulation of FewShot Learning (FSL) to infer the required output given only one or a few numbers of training examples. Thus in this paper, we proposed a new architecture (named as FHGR which refers to "Few-shot Hand Gesture Recognition") that learns the mapping using a small number of data and quickly adapts to a new user/gesture by combing its prior experience. The proposed approach led to 83.99% classification accuracy on new repetitions with few-shot observations, 76.39% accuracy on new subjects with few-shot observations, and 72.19% accuracy on new gestures with few-shot observations.

The paper is motivated by the importance of the Smart Cities (SC) concept for future management of global urbanization and energy consumption. Multi-agent Reinforcement Learning (RL) is an efficient solution to utilize large amount of sensory data provided by the Internet of Things (IoT) infrastructure of the SCs for city-wide decision making and managing demand response. Conventional ModelFree (MF) and Model-Based (MB) RL algorithms, however, use a fixed reward model to learn the value function rendering their application challenging for ever changing SC environments. Successor Representations (SR)-based techniques are attractive alternatives that address this issue by learning the expected discounted future state occupancy, referred to as the SR, and the immediate reward of each state. SR-based approaches are, however, mainly developed for single agent scenarios and have not yet been extended to multi-agent settings. The paper addresses this gap and proposes the Multi-Agent Adaptive Kalman Filtering-based Successor Representation (MAKF-SR) framework. The proposed framework can adapt quickly to the changes in a multi-agent environment faster than the MF methods and with a lower computational cost compared to MB algorithms. The proposed MAKF-SR is evaluated through a comprehensive set of experiments illustrating superior performance compared to its counterparts.

The unprecedented COVID-19 pandemic has been remarkably impacting the world and influencing a broad aspect of people’s lives since its first emergence in late 2019. The highly contagious nature of the COVID-19 has raised the necessity of developing deep learning-based diagnostic tools to identify the infected cases in the early stages. Recently, we proposed a fully-automated framework based on Capsule Networks, referred to as the CT-CAPS, to distinguish COVID-19 infection from normal and Community Acquired Pneumonia (CAP) cases using chest Computed Tomography (CT) scans. Although CT scans can provide a comprehensive illustration of the lung abnormalities, COVID-19 lung manifestations highly overlap with the CAP findings making their identification challenging even for experienced radiologists. Here, the CT-CAPS is augmented with a wide range of clinical/demographic data, including patients’ gender, age, weight and symptoms. More specifically, we propose a hybrid deep learning model that utilizes both clinical/demographic data and CT scans to classify COVID-19 and non-COVID cases using a Random Forest Classifier. The proposed hybrid model specifies the most important predictive factors increasing the explainability of the model. The experimental results show that the proposed hybrid model improves the CT-CAPS performance, achieving accuracy of 90.8%, sensitivity of 94.5% and specificity of 86.0%.

Accelerating Magnetic Resonance Imaging (MRI) acquisition process is a critical and challenging medical imaging problem as basic reconstructions obtained from the undersampled k-space often exhibit blur or aliasing effects. Despite its significance and recent advancements in the field of deep neural networks (DNNs), development of deep learning-based MRI reconstruction algorithms is not yet flourished due to unavailability of public and large datasets. The recently introduced large-scale fastMRI dataset is posed to change this state of affairs, however, existing DNN solutions developed based on fastMRI require learning a large number of parameters rendering their practical application limited due to the strict low-latency requirements of real-time MRI acquisition. In this paper, we aim to address this drawback and target reducing the computational cost associated with single-coil reconstruction task. More specifically, the paper proposes a novel deep model referred to as the SepUnet architecture achieving significant reduction in the required number of parameters while maintaining high accuracy. Performance of the proposed SepUnet architecture is evaluated based on the official test dataset from fastMRI illustrating accuracy improvement in comparison to its published counterparts while requiring significantly reduced number of trainable parameters (i.e., the SepUnet architecture is much faster and lighter than its counterparts).

Given the data-hungry nature of Wireless Multimedia Sensor Networks (WMSNs) due to the need for near real-time processing of a large number of multimedia data, it is of significant practical importance to design/develop energy-efficient routing protocols to extend the WMSN’s collective lifetime. In this regard and to jointly utilize potential benefits that can be achieved by coupling clustering and image compression, the paper proposes a novel routing methodology referred to as the Energy Efficient Cluster-based Image Transmission (EECIT) scheme. In the proposed EECIT scheme, the multimedia-based sensor network is divided into different clusters depending on the node’s density, in which one node is adaptively assigned as the Cluster Head (CH). A key novelty of the proposed EECIT lies in the routing stage where ranking sensor nodes is performed via a new metric named Fair Selection (FS) coefficient, which is designed by considering a combination of mean-deviation and the number of times that nodes involve in routing. As a consequence of the fair distribution of energy consumption across the network, the network’s lifetime increases.

Referred to as the RQ-CEASE, this article proposes a resilient framework for quantized, event-triggered (ET), sampled-data, average consensus in multiagent systems subject to denial of service (DoS) attacks. The DoS attacks typically attempt to block the measurement and communication channels in the network. Two different ET approaches are considered in RQ-CEASE based on whether the ET threshold is dependent or independent of the state dynamics. For each approach, we analytically derive operating conditions (bounds) for the sampling period and ET design parameter guaranteeing the input-to-state stability (ISS) of the network under DoS attacks. In addition, upper bounds for duration and frequency of DoS attacks are derived within which the network remains operational. For each approach, the maximum possible error from the average consensus value is derived. The resilience of the two RQ-CEASE approaches to DoS attacks, as well as their steady-state consensus error, and transmission savings are compared both analytically and using simulations.

With expected widespread implementation of 5G networks and 5G Internet of Things (IoT), indoor localization is expected to become of even further importance. Although Global Positioning System (GPS) ensures efficient outdoor localization, generally speaking, indoor localization systems fail to provide the same level of efficiency. In this regard, there has been recent widespread attention to Angle of Arrival (AoA) with the application on Switch Antenna Array (SAA), as an efficient indoor localization method due to its potential in determining location with low estimation error. The AoA, however, suffers from several issues including being sensitive to multipath effects, noise, fluctuations of received signal, and frequency/phase shifts. To tackle these issues, the paper proposes a set of signal processing and information fusion methods by integration of Nonlinear Least Square (NLS) curve fitting, Kalman Filter (KF), and Gaussian Filter (GF) to boost the accuracy rate of estimated angle. The proposed fusion framework is evaluated based on a real Bluetooth Low Energy (BLE) dataset and results illustrate significant potentials in terms of improving overall BLE-based achievable accuracy in angle detection.

There has been a recent surge of interest on development of news-oriented Deep Neural Network (DNN) architectures to predict stock trend movements. Limited focus is, however, devoted to reliability fusing different available information resources. In this regard, this paper proposes a Noisy Deep Stock Movement Prediction Fusion framework (ND-SMPF) for stock price movement prediction. The proposed ND-SMPF predictive framework uses information fusion to combine twitter data with extended horizon market historical prices to boost the accuracy of the stock movement prediction task. More specifically, Noisy Bi-directional Gated Recurrent Unit (NBGRU) is utilized coupled with a Hybrid Attention Network (HAN) to extract news level temporal information. A two level attention layer is used to identify relevant words with highest correlation and effects on the stock trends, which are then fused with historical price data to perform the prediction task. A real dataset is incorporated to evaluate performance of the proposed ND-SMPF framework, which illustrates superior performance in comparison to its recently developed counterparts.

Predicting death in lung cancer patients before initiating treatment is of paramount importance as this may guide decision-making towards more aggressive or combination of different types of treatment. In this work, we propose a Multi-scale Deep learning-based Radiomics model, referred to as "MDR-SURV" that exploits the information from positron emission tomography/computed tomography (PET/CT) images, combined with other clinical factors, to predict the overall survival (OS). Deep learning-based radiomics has the advantage of learning what features to extract, on its own. Furthermore, it does not require the exact segmentation of the tumor. The proposed MDR-SURV, which is a multi-scale framework, incorporates the tumor region and its surroundings, from different scales, and can extract both local and global tumor features. PET/CT images of 132 lung cancer patients who underwent stereotactic body radiotherapy (SBRT) were used to predict OS with the proposed model. Our results show that the MDR-SURV model outperforms its single-scale counterparts in predicting OS. Furthermore, the proposed MDR-SURV model achieves significantly high concordance index (C-index) of 73% in predicting the OS, which is noticeably higher than the results reported in existing literature.

With recent breakthroughs in signal processing, communication and networking systems, we are more and more surrounded by smart connected devices empowered by the Internet of Thing (IoT). Bluetooth Low Energy (BLE) is considered as the main-stream technology to perform identification and localization/tracking in IoT applications. Indoor localization applications within smart cities, typically, start by observing messages transmitted by BLE beacons and then utilization of Received Signal Strength Indicator (RSSI) to provide location estimates. RSSI signals are, however, prone to significant fluctuations. The main challenge is that multipath fading and drastic fluctuations in the indoor environment result in complex non-Gaussian RSSI measurements, necessitating the need to smooth RSSIs for development of BLE-based localization applications. In contrary to existing solutions, where RSSIs are assumed to have normal statistical properties, in this paper, a Gaussian Sum Filter (GSF) approach is designed to more realistically model the non-Gaussian nature of RSSIs. To maintain acceptable computational load, the number of components in the GSF is collapsed into a single Gaussian term with a novel Wasserstein Distance (WD)-Based Gaussian Mixture Reduction (GMR) algorithm. The simulation results based on real collected RSSI signals confirm the success of the proposed WD-based GSF framework compared to its conventional counterparts.

Capitalizing on the goal of addressing identified shortcomings of recent solutions developed for recognition tasks via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the XceptionTime architecture. The proposed innovative XceptionTime architecture is designed by integration of depthwise separable convolutions, adaptive average pooling, and a novel no-linear normalization technique. At the hearth of the proposed architecture is several XceptionTime modules concatenated in series fashion designed to captures both temporal and spatial information-bearing contents of the sparse multichannel sEMG signals without the need for data augmentation and manual design of feature extraction. In addition to instruction of the new XceptionTime module, by integration of adaptive average pooling, instead of fully connected layers, and utilization of a novel non-linear normalization approach, the proposed architecture is less prone to overfitting, more robust to temporal translation of the input, and more importantly is independent from the input window size, i.e., there is no need to change/reconfigure the architecture by changing the size of the input sequence. Finally, by utilizing the depthwise separable convolutions, the XceptionTime network has far less parameters resulting in less complex network.

Smart grid is susceptance to a variety of cyber attacks, among which False Data Injection Attacks (FDIA) are shown to be of significantly disruptive nature. Complex, distributed, and interconnected aspects of smart grids make detection of stealthy FDIAs with high accuracy significantly challenging. To address this issue, the paper proposes an innovative Adaptive Multi-Level Features Classification for Stealthy FDIA Detection (AMLFC-SFD) based on the Alternating Current (AC) state estimation. More specifically, we focus on maintaining a trade-off between the accuracy rate of detection and its associated computational complexity by utilizing two different Support Vector Machine (SVM)-based classifiers, in which the number of features as the input of the classifier depends on the strength of the underlying attack. In this regard, we divide potential FDI attacks in smart grids into three decision regions, including strong, moderate, and weak attacks and obtain the most accurate Kernel to separate measurements. To evaluate the proposed AMLFC-SFD framework, comprehensive numerical experiments are performed based on the IEEE 30-bus system. Results illustrate that with a lower number of features a reasonably high detection accuracy can be achieved, leading to a considerably less run time, which is of paramount importance for practical implementation.

Angle of Arrival (AoA) approach with applications to Bluetooth Low Energy (BLE) has been recognized as an effective indoor localization method because of its ability for position determination with low estimation error. However, there are several issues including Carrier Frequency Offset (CFO), multipath effect, Inter-Symbol Interference (ISI), noise, and phase shifting faced by the AoA. To tackle these issues, we first highlight the wireless signal model in BLE standard and formulate the transmitted signal, wireless channel model, and the signal received by Linear Antenna Array (LAA). In addition, the paper introduces a novel fusion processing technique to eliminate the destructive impact of the wireless channel on the received signal, which leads to accurate angle detection following precise position estimation. The effectiveness of the proposed fusion processing method is evaluated through an experimental testbed in the presence of noise and Rayleigh fading channel. Based on the simulation results, the proposed processing approach illustrates significant improvements in the angle detection and path tracking in companion to its counterparts.

It is recognized that system trustworthiness is a hyperstructure embodied by the structural, behavioral, and system dimensions with a set of coherent attributes. We explore a theoretical framework of tripartite trustworthiness that can be applied to real-world autonomous systems. We present a formal study of the essences and mathematical models of system trustworthiness and their quantitative measurements in the contexts of autonomous and mission-critical intelligent systems where humans and machines interact in a hybrid environment.

Convolutional neural networks (CNNs), which have been the state-of-the-art in many image-related applications, are prone to losing important spatial information between image instances. Capsule networks (CapsNets), on the other hand, are capable of leveraging such information through their routing by agreement process, making them powerful architectures for small datasets, such as medical imaging ones. Within the domain of medical imaging problems, brain tumor classification is of paramount importance, due to the deadly nature of this cancer and the consequences of the tumor misclassification. In our recent works, we showed potentials of developing CapsNet architecture for the task of brain tumor type classification. Similar to other deep learning models, however, CapsNets do not capture prediction uncertainty (coming from the uncertainty in the model weights, which is significantly important in keeping the human experts in the loop, by returning the uncertain samples. In this paper, we propose a Bayesian CapsNet framework, referred to as the BayesCap, that can provide not only the mean predictions, but also entropy as a measure of prediction uncertainty. Results show that filtering out the uncertain predictions can improve the accuracy, confirming that returning the uncertain predictions is an appropriate strategy for improving interpretability of the network.

The paper investigates resilient conditions for the event-triggered average consensus problem under denial of service (DoS) attack and uncertainty in the network. To reach average consensus in the multiagent system, each node communicates with its neighbouring nodes only if an event-triggering condition is satisfied. In the presence of the DoS attack, no information can be communicated within the network. In addition to DoS, the information being transmitted through the communication channels is perturbed due to uncertainty in the nominally designed edge weights of the network. Using the Lyapunov theorem, we analytically determine the maximum allowable duration and frequency for the DoS attack and maximum network uncertainty for which the exponential event-triggered consensus convergence stays preserved. The practicability of the proposed event-triggering scheme is studied by proving the Zeno-behaviour exclusion. The performance of the implementation is quantified through simulations in different scenarios.

According to official statistics, cancer is considered as the second leading cause of human fatalities. Among different types of cancer, brain tumor is seen as one of the deadliest forms due to its aggressive nature, heterogeneous characteristics, and low relative survival rate. Determining the type of brain tumor has significant impact on the treatment choice and patient's survival. Human-centered diagnosis is typically error-prone and unreliable resulting in a recent surge of interest to automatize this process using convolutional neural networks (CNNs). CNNs, however, fail to fully utilize spatial relations, which is particularly harmful for tumor classification, as the relation between the tumor and its surrounding tissue is a critical indicator of the tumor's type. In our recent work, we have incorporated newly developed CapsNets to overcome this shortcoming. CapsNets are, however, highly sensitive to the miscellaneous image background. The paper addresses this gap. The main contribution is to equip CapsNet with access to the tumor surrounding tissues, without distracting it from the main target. A modified CapsNet architecture is, therefore, proposed for brain tumor classification, which takes the tumor coarse boundaries as extra inputs within its pipeline to increase the CapsNet's focus. The proposed approach noticeably outperforms its counterparts.

The paper proposes a Hybrid Deep Neural Network (HDNN) framework for remaining useful life (RUL) estimation for prognostic health management applications. The proposed HDNN framework is the first hybrid model designed for RUL estimation that integrates two deep learning architectures simultaneously and in a parallel fashion. More specifically, in contrary to the majority of existing data-driven prognostic approaches for RUL estimation, which are developed based on a single deep model and can hardly maintain satisfactory generalization performance across various prognostic scenarios, the proposed HDNN framework consists of two parallel paths (one based on Long Short Term Memory (LSTM) and one based on convolutional neural networks (CNN)) followed by a fully connected multilayer fusion neural network, which acts as the fusion center combining the outputs of the two paths to form the target RUL. The proposed HDNN framework is tested on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. Our comprehensive experiments and comparisons with several recently proposed RUL estimation methodologies developed based on the same data-sets show that the proposed HDNN framework significantly outperforms all its counterparts in the complicated prognostic scenarios with increased number of operating conditions and fault modes.

The paper proposes a novel distributed, sampled-data, event-triggered algorithm with quantized information exchange for average consensus (Q-CEASE) in multi-agent/multi-sensor networks. Q-CEASE communicates quantized information with its neighbouring nodes only if a discretized event-triggering condition is satisfied. Both design and implementation of Q-CEASE are distributed and do not require a fusion center. The design stage determines its operating region in terms of the sampling period and transmission thresholds for the constituent nodes. A minimum exponential rate for consensus convergence is guaranteed using the Lyapunov stability theorem. The performance of the Q-CEASE algorithm is quantified through Monte-Carlo simulations on randomized networks.

Recent advancements in signal processing and communication systems have resulted in evolution of an intriguing concept referred to as Internet of Things (IoT). By embracing the IoT evolution, there has been a surge of recent interest in localization/tracking within indoor environments based on Bluetooth Low Energy (BLE) technology. The basic motive behind BLE-enabled IoT applications is to provide advanced residential and enterprise solutions in an energy efficient and reliable fashion. Although recently different state estimation (SE) methodologies, ranging from Kalman filters, Particle filters, to multiple-modal solutions, have been utilized for BLE-based indoor localization, there is a need for ever more accurate and real-time algorithms. The main challenge here is that multipath fading and drastic fluctuations in the indoor environment result in complex non-linear, non-Gaussian estimation problems. The paper focuses on an alternative solution to the existing filtering techniques and introduces/discusses incorporation of the Belief Condensation Filter (BCF) for localization via BLE-enabled beacons. The BCF is a member of the universal approximation family of densities with performance bound achieving accuracy and efficiency in sequential SE and Bayesian tracking. It is a resilient filter in harsh environments where nonlinearities and non-Gaussian noise profiles persist, as seen in such applications as Indoor Localization.

Brain tumor, which is one of the deadliest cancers, can have several types, based on different characteristics of the tumor. Determining the exact category of this cancer is of significant importance, because it directly affects the treatment options and patient's survival. Although experts' judgment remains the gold standard for brain tumor classification, human-centered decision is time-consuming and error prone. Radiomics, referring to the extraction of features from medical images with the ultimate goal of cancer prediction/classification, can automatize the tumor classification task, having the promise of providing more accurate and time-effective decision. Hand-crafted Radiomics, which is the most common Radiomics analysis, needs a prior knowledge on the types of features to extract, which is not always available, leading to an increased surge of interest toward deep learning-based Radiomics. Although deep learning-based Radiomics does not need a prior knowledge, its practical application is limited by the low explainablity of the deep learning networks. In this work, the interpretability of Capsule networks, which have shown promising results in brain tumor classification, is explored. Outcomes show that the Radiomics features extracted by Capsule networks can not only distinguish between the tumor types, but also show considerable correlation with hand-crafted features, which are more acceptable and reliable from a physician's point of view.

With the rapid emergence of Internet of Things (IoT), we are more and more surrounded by smart connected devices with integrated sensing, processing, and communication capabilities. Bluetooth Low Energy (BLE), referred to as Bluetooth Smart, is considered as the main-stream technology to perform identification and localization/tracking in IoT applications. While single-model BLE-based tracking has been investigated from different aspects, application of multi-model (hybrid) solutions are still in their infancy. In this regard, the letter proposes a novel BLE-based tracking framework, referred to as the STUPEFY, which incorporates set-valued information within box particle filtering context. More specifically, the proposed multiple-model STUPEFY framework consists of three integrated modules, i.e., an intriguing Smoothing Module based on Kalman filtering to reduce the Received Signal Strength Indicator (RSSI) fluctuations and facilitate comparison of Gaussian models of the RSSI values in distribution with the learned ones; A learning-based model (Coordination Module) utilized in an intuitive fashion to provide/construct a coarse estimate of the target's location together with the smallest axes-aligned box containing the ellipsoid associated with each zone's learned RSSI distribution, and; A novel set-valued box particle filtering (SBPF) approach (Micro-Localization Module). The proposed STUPEFY framework is evaluated based on real BLE datasets and results illustrate significant potentials in terms of improving overall BLE-based achievable tracking accuracy.

This paper proposes a distributed guaranteed-performance event-triggered average consensus (GP-ETAC) algorithm for multi-agent/sensor networks. The proposed GP-ETAC approach is distributed and event-triggered in the sense that the agents selectively limit their transmissions to local neighbourhoods when certain triggering conditions are satisfied. Using the Lyapunov stability theorem, a novel cost function is optimized to compute consensus design parameters (namely, the overall control gain and local event-triggering thresholds). The proposed cost function provides a structured trade-off between the number of local transmissions and the rate of consensus convergence. The performance of the GP-ETAC approach is evaluated through Monte-Carlo simulations.

This paper proposes a robust distributed event-triggered approach for consensus in linear multi-agent systems (MAS) with uncertain network topologies. To achieve consensus, each agent transmits its information only when a certain event-triggering condition is fulfilled. The connection weights in the network are uncertain and hence the information received by each agent is unreliable. In such an uncertain topology, the objective is to co-design robust consensus parameters (namely, the state transmission threshold and local control gains) that collectively ensure an exponential rate for consensus convergence. An objective function incorporating the transmission load and control effort is minimized to compute the design parameters. Numerical simulations quantify the effectiveness of the proposed event-triggered consensus approach in a second-order MAS.

The paper is motivated by recent advancements and developments in large, distributed, autonomous, and self-aware systems such as autonomous vehicles and vehicle-to-everything (V2X) technologies, where bandwidth, security, privacy, and/or power considerations limit the number of information transfers between neighbouring agents. In this regard, we propose an event-triggered distributed state estimation via diffusion strategies (ET/DPF), which is a systematic and intuitively pleasing distributed state estimation algorithm that jointly incorporates point and set-valued measurements within the particle filtering framework. In the absence of a measurement form a neighbouring node (i.e., having a set-valued measurement), each local agent/node evaluates the probability that the unknown measurement belongs to the event-triggering set based on its particles which is then used to update the corresponding particle weights. In our Monte Carlo simulations, the proposed ET/DPF outperforms its counterparts in environments with limited bandwidth or/and intermittent connectivity.

Tremor extraction techniques are considered as the central component of several rehabilitative and compensatory robotic technologies, and the accuracy of such filters can directly affect the performance of the aforementioned technologies. Motivated by this fact, the paper proposes an adaptive estimation framework, referred to as Multiple Adaptive Reduced-order Kalman filtering (KFE-BMFLC), for extraction of pathological hand tremors. The proposed KFE-BMFLC framework is designed with the goal of improving the performance of an existing state-of-the-art filtering technique, i.e. Enhanced Band-limited Fourier Linear Combiner (E-BMFLC), which has shown a promising potential in extracting involuntary hand motions but uses embedded least mean square (LMS) estimation approach. The proposed technique is capable of reducing the computational overhead in comparison to that of the conventional BMFLC technique, while increasing the estimation accuracy.

The paper is motivated by recent urgency to design continuous and cuff-less blood pressure (BP) monitoring solutions to prevent, detect, and treat the hypertension. In this regard, we propose a novel wavelet-based feature extraction algorithm coupled with an adaptive and multiple-model Kalman filtering framework (referred to as the WAKE-BPAT), which provides accurate and dynamic BP estimates by extraction and fusion ofdifferent pulse arrival time(PAT) features. In particular, a wavelet transform and histogram analysis-based robust and high-accurate R-peak detection algorithm is proposed without incorporation of any pre-defined thresholds. This in combination with high-quality photoplethysmogram (PPG) characteristic points obtained from signal recordings of a recently developed PPG device (Gen-1), are used for BP estimation, which is modeled as a hybrid state-space model with structural uncertainties to fuse different PAT features in an adaptive fashion. Our experimental evaluations based on a real data set collected via Gen-1 device confirms the superiority of the proposed WAKE-BPAT framework in comparison to its counterparts.

The ability to discriminate and classify different tasks is a crucial requirement for any Electroencephalogram (EEG) based Brain computer Interface (BCI). However, the intra and inter subject variability in the brain signal patterns is a bottleneck for developing general BCI systems and needs to be tackled. To address this issue, recently filter banks are deployed to extract frequency specific features, which are then fused at the classification step. On the other hand, some works deploy optimization techniques to design (extract) subject-specific filters (features). While both approaches have reached compromising results, there is still a huge gap between the performance of the techniques and that of humans. In this regard, we propose a Bayesian framework to simultaneously optimize a number of filter banks and spatial filters according to the patterns of brain activity for each subject. Referred to as the Bayesian double band spectro-spatial filter optimization (B2B-SSFO), the proposed method aims at combining the advantages of the two aforementioned approaches, and consists of two bandpass filters providing frequency specific features for each subject. The proposed framework is evaluated on dataset 2b from BCI Competition IV. The proposed B2B-SSFO approach outperforms its counterparts and introduces a robust framework for motor imagery studies.

Brain tumor is considered as one of the deadliest and most common form of cancer both in children and in adults. Consequently, determining the correct type of brain tumor in early stages is of significant importance to devise a precise treatment plan and predict patient's response to the adopted treatment. In this regard, there has been a recent surge of interest in designing Convolutional Neural Networks (CNNs) for the problem of brain tumor type classification. However, CNNs typically require large amount of training data and can not properly handle input transformations. Capsule networks (referred to as CapsNets) are brand new machine learning architectures proposed very recently to overcome these shortcomings of CNNs, and posed to revolutionize deep learning solutions. Of particular interest to this work is that Capsule networks are robust to rotation and affine transformation, and require far less training data, which is the case for processing medical image datasets including brain Magnetic Resonance Imaging (MRI) images. In this paper, we focus to achieve the following four objectives: (i) Adopt and incorporate CapsNets for the problem of brain tumor classification to design an improved architecture which maximizes the accuracy of the classification problem at hand; (ii) Investigate the over-fitting problem of CapsNets based on a real set of MRI images; (iii) Explore whether or not CapsNets are capable of providing better fit for the whole brain images or just the segmented tumor, and; (iv) Develop a visualization paradigm for the output of the CapsNet to better explain the learned features. Our results show that the proposed approach can successfully overcome CNNs for the brain tumor classification problem.

The paper is motivated by the fact that brain cancer is one of the deadliest cancers and its detection in early stages is of paramount importance. In this regard, tumor 3D shape reconstruction from magnetic resonance (MR) or computed tomography (CT) scans provides critical information, which can not be interpreted from 2D images. However, CT and MR images have low resolution in z direction compared to their resolution in x and y directions, therefore, 3D reconstructed shapes are of low quality. In this paper, we propose to use convolutional auto-encoders (CAEs) to address this drawback, and develop a convolutional autoencoder-based inter-slice interpolation (CARISI) framework. Although deep nets have been used very recently for brain tumor segmentation, to the best of our knowledge, this is the first attempt to use CAEs for 3D reconstruction of brain tumor. The proposed CARISI framework consists of several encoding and decoding components, which can handle rapid changes in tumor shape without the need for supervision of an expert. Our experiments based on a real data-set consisting of 3064 segmented brain tumor images indicate that the proposed CARISI framework outperforms its counterpart and has the potential to significantly improve the overall quality of the reconstructed shapes.

This letter proposes a novel ternary-event-based particle filtering (TEB-PF) framework by introducing the ternary-event-triggering mechanism coupled with a non-Gaussian fusion strategy that jointly incorporates point-valued, quantized, and set-valued measurements. In contrast to the existing binary-event-triggering solutions, the TEB-PF is a distributed state estimation architecture where the remote sensor communicates its measurements to the estimator, residing at the fusion centre, in a ternary-event-based fashion, i.e., holds on to its observation during idle epochs, transfers quantized ones during the transitional epochs, and only communicates raw observations during event epochs. Due to joint utilization of quantized and set-valued measurements in addition to the point-valued ones, the proposed TEB-PF simultaneously reduces the communication overhead, in comparison to its binary triggering counterparts, while also improving the estimation accuracy specially in low communication rates.

The paper is motivated by recent surge of interest in utilization of a large number of sensor nodes in cyber-physical systems (CPSs) and the critical importance of managing sensor's restricted resources. In this regard, we propose a multi-sensor and open-loop estimation algorithm with an information-based triggering mechanism. In the open-loop topology considered in this paper, each sensor transfers its measurements to the fusion centre (FC) only in occurrence of specific events (asynchronously). Events are identified using the information-based triggering mechanism without incorporation of a feedback from the FC and/or implementation of a local filter at the sensor level. We propose a multi-sensor triggering approach based on the projection of each local observation into the state-space which corresponds to the achievable gain in the sensor's information state vector. The simulation results show that the proposed multi-sensor information-based triggering mechanism closely follows its full-rate estimation counterpart.

Based on the theory of linear matrix inequalities (LMI), this paper proposes an event-based distributed consensus algorithm for linear multi-agent/sensor networks that are heterogeneous. The proposed scheme is event-based in the sense that each agent transmits its information to its neighbouring nodes only under predefined circumstances. Ensuring the stability of the closed-loop system, the Lyapunov theorem is utilized to compute design parameters (heterogeneous controller gains and transmission threshold) used in the proposed consensus algorithm. Numerical simulations demonstrate a performance gain in the convergence time and a reduction in the number of data transmissions with the proposed approach.

Image denoising methods have been rapidly advanced in past few years. Image denoising is a challenging process of suppressing unwanted noise components from an image while retaining image details as mush as possible. Motivated by the recent advances in graph signal processing, in this paper, we address image denoising and enhancement problems from a new graph-based viewpoint. In particular, non-local similar patches of each color channel are grouped into a block for which a graph-based framework is proposed to construct a novel dictionary. The proposed graph-based sparse coding results in removing unwanted high frequency noise from the image. In addition and to further improve the contrast level of the image, a novel enhancement method is proposed based on iterative graph filtering. Simulations are conducted to evaluate the performance of the proposed color image denoising and enhancement method and to compare it with that of the other existing methods. The proposed method is shown to provide significantly improved visual quality for denoised images as well as higher peak signal-to-noise-ratio values as compared to other existing methods.

Modeling and representation of multiple tasks from brain signals is a crucial task in Electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs). The motivation of this work comes from the need for a BCI system, intended to operate in real world scenarios, to discriminate multiple tasks and activities simultaneously. In this regard, the paper proposes a novel multi-class EEG-based BCI system via utilization of error correcting output coding (ECOC) classifiers. To best of our knowledge, the ECOC classifiers have not ever been applied to the EEG classification problems. In the ECOC method, the classification problem is modeled as communication over a noisy channel where the miss-classification error is corrected by error correcting techniques borrowed from information theory. In this work, we propose to utilize a modified version of the ECOC classifiers adopted to EEG classification problems which deploys ternary class codewords. Therefore, we analyze more combinations of the classes and greater number of classifiers vote for the final result. The proposed classifier is coupled with a Bayesian framework to compute the optimized spatio-spectral filters to extract the most discriminative feature sets of different classes. The proposed framework is applied to a motor imagery classification problem and evaluated over BCI Competition IV-2a dataset where the results indicate a noticeable enhancement over other methods developed for multi-class EEG classification.

The paper proposes an on-line distributed implementation of the particle filter (DPF) for applications, where the sensing and consensus time scales are the same. We are motivated by state estimation problems in large, geographically-distributed agent/sensor networks, where bandwidth constraints limit the number of information transfers between neighbouring nodes. As an alternative to consensus strategies often used by the DPF, we propose a diffusive framework to eliminate the need of running the consensus step. In our Monte Carlo simulations, the proposed diffusion based DPF (D/DPF) outperforms the state-of-the-art consensus based DPF approaches in environments with limited bandwidth or/and intermittent connectivity.

Motivated by application of complex-valued signal processing techniques in statistical pattern recognition, classification, and Gaussian mixture (GM) modeling, this paper derives analytical expressions for computing the Bhattacharyya coefficient/distance (BC/BD) between two improper complex-valued Gaussian distributions. The BC/BD is one of the most widely used statistical measures for evaluating class separability in classification problems, feature extraction in pattern recognition, and for GM reduction (GMR) purposes. The BC provides an upper bound on the Bayes error, which is commonly known as the best criterion to evaluate feature sets. Although the computation of the BC/BD between real-valued signals is a well-known result, it has not yet been extended to the case of improper complex-valued Gaussian densities. This paper addresses this gap. We analyze the role of the pseudocovariance matrix, which characterizes the noncircularity of the signal, and show that it carries critical second-order statistical information for computing the BC/BD. We derive upper and lower bounds on the BD in terms of the eigenvalues of the covariance and pseudocovariance matrices of the underlying densities. The theoretical bounds are then used to introduce the concept of β -dominance in the context of statistical distance measures. The BC is pseudometric, since it fails to satisfy the triangle inequality. Using the Matusita distance (a full-metric variant of the BC), we propose an intuitively pleasing indirect distance measure for comparing two general GMs. Finally, we investigate the application of the proposed BC/BD measures for GMR purposes and develop two BC-based GMR algorithms.

The letter considers a multi-sensor state estimation problem configured in a decentralized architecture where local complex statistics are communicated to the central processing unit for fusion instead of the raw observations. Naive adaptation of the augmented complex statistics to develop a decentralized state estimation algorithm results in increased local computations, and introduces extensive communication overhead, making it practically unattractive. The letter proposes a structure-induced complex Kalman filter framework with reduced communication overhead. In order to further reduce the local computations, the letter proposes a non-circularity criterion which allows each node to examine the non-circularity of its local observations. A local sensor node disregards its extra second-order statistical information when the non-circularity coefficient is small. In cases where the local observations are highly non-circular, an intuitively pleasing circularization approach is proposed to avoid computation and communication of the pseudo-covariance matrices. Simulation results indicate that the proposed structured-induced complex Kalman filter (SCKF) provides significant performance improvements over its traditional counterparts.

Motivated by application of Gaussian sum filters (GSF) and multiple model adaptive estimation (MMAE) approaches in scenarios where assumption of proper (circular) Gaussian signals is not valid, the letter proposes a novel complex-valued Gaussian sum filter (C/GSF) for non-linear filtering of non-Gaussian/non-circular measurement noise. Although the literature on recursive state estimation using GSF is rich, its complex-valued counterpart which incorporates the full second-order statistics of the system and can cope with non-Gaussian/non-circular measurements, has not yet been investigated in the literature. The paper addresses this gap. The C/GSF is a computationally attractive adaptive filter where the number of non-circular Gaussian components is controlled utilizing a modified Bayesian learning technique which is used to collapse the resulting non-Gaussian sum mixture into an equivalent complex-valued Gaussian term. Simulation results indicate that the C/GSF provides significant performance improvement over its traditional counterparts.

The paper develops a fusion-based, reduced order, distributed implementation of the unscented particle filter (FR/DUPF) for state estimation in complex nonlinear electric power grids (EPG). Based on partitioning the overall EPG system into nsublocalized but dynamically coupled subsystems, the near-optimal FR/DUPF provides a computational saving of up to a factor of nsubover the centralized particle filter. In our Monte Carlo simulations of the IEEE 14-bus test system, the FR/DUPF state estimates are close to the actual values and virtually indistinguishable from the centralized particle filter.

Motivated by the problem of distributed signal processing in sensor networks, the paper considers the general problem of state estimation in geographically dispersed systems with nonlinear dynamics operating in an uncertain environment with communication constraints. Distributed particle filter implementations used as nonlinear state estimators introduce an additional consensus step, which must converge to achieve consistent values for local estimators' statistics in between two consecutive filter iterations. The number of consensus iterations per consensus run is high such that the consensus step may not converge in between two filter iterations especially in networks with intermittent connectivity. To reduce the consensus liability, we propose a consensus plus innovation based distributed implementation of the unscented particle filter (CI/DUPF), which extends the linear consensus and innovation framework to nonlinear distributed estimation. The CI/DUPF does not require the consensus step to converge and is suited for environments with intermittent connectivity. In our Monte Carlo simulations, the performance of the CI/DUPF follows that of its centralized counterpart even with a limited number of consensus iterations per consensus run.

The posterior Cramέr Rao lower bound (PCRLB) has recently been proposed as an effective selection criteria for sensor resource management in large, geographically distributed sensor networks. Existing algorithms (in particular the decentralized approaches with no central fusion centre) designed for computing the PCRLB are based on raw observations resulting in significant communication overhead from the sensor nodes to the associated local processing nodes. The paper derives distributive computational techniques for determining the PCRLB for quantized sensor networks configured using decentralized architectures. We refer to the distributed computation of the PCRLB as dPCRLB. The main contribution of the paper is extending the dPCRLB algorithm [1] to quantized observations that leads to significant savings in the communication overhead over its counterparts that use raw observations. In our Monte Carlo simulations, we show that the proposed dPCRLB closely follows the centralized bound based on quantized observations. As expected, there is potential performance loss with quantization as is illustrated by the difference between the dPCRLBs computed using raw and quantized observations. The drop in the estimator's performance is, however, compensated for with an increase in the number of quantization levels associated with the observation quantizer.

Motivated by the problem of adaptive resource management in decentralized sensor networks, the paper derives an algorithm for the distributed computation of the conditional posterior Cramér-Rao lower bound (PCRLB) for nonlinear tracking applications as an alternative to the non-conditional (conventional) PCRLB. Using the proposed conditional bound, a decentralized adaptive sensor-selection algorithm is then developed with the objective of dynamically activating a subset of observation nodes to optimize the network's performance. Our Monte Carlo simulations verify the superiority of the proposed decentralized PCRLB based sensor selection approach in bearing only tracking applications over its conventional counterparts.

The paper considers the problem of performing distributed particle filtering in intermittently connected networks with nonlinear state dynamics. In the context of large, geographically-distributed sensor networks, communication delays affect the convergence of the consensus algorithms used to derive the global state estimate from local estimates. We propose a non-linear fusion rule that relaxes the condition of requiring convergence of the consensus step between two successive iterations of the localized particle filters, thereby, allowing the consensus step to catch up with the localized filters in case of communication delays. Our Monte Carlo simulations illustrate the ability of the modified consensus/fusion based distributed implementation of the particle filter (MCF/DPF) to successfully handle intermittence in the network connectivity.

Motivated by the decentralized adaptive resource management problems, the letter derives recursive expressions for online computation of the conditional decentralized posterior Cramér-Rao lower bound (PCRLB). Compared to the non-conditional PCRLB, the conditional PCRLB is a function of the past history of observations made and, therefore, a more accurate representation of the estimator's performance and, consequently, a better criteria for sensor selection. Previous algorithms to compute the conditional PCRLB are limited to centralized architectures. The letter addresses this gap. Our simulations verify the optimality of the conditional dPCRLB by comparing it with the centralized conditional PCRLB in bearing-only tracking applications.

In sensor networks deployed over large-scale, multidimensional physical systems with limited spatial observability, reduced-order, distributed estimation is a practical alternative to centralized estimation. For such reduced-order systems, centralized computation of the posterior Cramér Rao lower bound (CRLB) is not possible as the global estimate of the entire state vector is not accessible at a single processing node. We derive the distributed PCRLB (dPCRLB) implementations encompassing both linear and nonlinear reduced-order dynamical systems and verify their optimality through Monte Carlo simulations.

A constrained sufficient statistic based distributed implementation of the particle filter (CSS/DPF) is proposed for angle/bearing-only tracking (BOT) applications. The CSS/DPF runs localized particle filters at each sensor node and computes the global sufficient statistics (GSS) of the overall system as a function (summation) of the local sufficient statistics (LSS). The CSS/DPF is, therefore, a two stage procedure: (i) First, the means of LSS at local nodes are computed by running average consensus algorithms to derive the GSS, and; (ii) Each node then updates its localized particle filter using the modified GSS. Simulation results show that the CSS/DPF is near-optimal with its performance almost identical to that of the centralized particle filter. The number of average consensus runs in the CSS/DPF are reduced by an order of magnitude of the dimension of the state vector, thereby, reducing the communication complexity and bandwidth requirement of the distributed implementation.

Recent developments in nonlinear dynamics and the theory of chaos have shown deterministic chaotic property of EEGs. Such evidences made the researchers try to take advantage of the chaotic behavior in artificial neural networks. According to the natural selection theory a good problem-solver should have two main properties: The ability of emerging various solutions for problem and existence of a rule (or intelligence) to guide this evolution and variety to become close to the goal. In this paper we used a chaotic node with logistic map to make the ability of emerging various solutions. In order to intelligently control the evolution of chaotic nodes we designed a rule by using NDRAM. The performance of proposed chaotic neural network is about 80% whereas the performance of NDRAM is about 40% in the same condition.