Search Results (14,639)

The Internet of Things (IoT) has transformed multiple industries, providing significant potential for automation, efficiency, and enhanced decision-making. The incorporation of IoT and data analytics in smart grid represents a groundbreaking opportunity for the energy sector, delivering substantial advantages in efficiency, sustainability, and customer empowerment. This integration enables smart grids to autonomously monitor energy flows and adjust to fluctuations in energy demand and supply in a flexible and real-time fashion. Statistical analytics, as a fundamental component of data analytics, provides the necessary tools and techniques to uncover patterns, trends, and insights within datasets. Nevertheless, it is crucial to address privacy and security issues to fully maximize the potential of data analytics in smart grids. This paper makes several significant contributions to the literature on secure, privacy-aware aggregation schemes in smart grids. First, we introduce a Fog-enabled Secure Data Analytics Operations (FESDAO) scheme which offers a distributed architecture incorporating robust security features such as secure aggregation, authentication, fault tolerance and resilience against insider threats. The scheme achieves privacy during data aggregation through a modified Boneh-Goh-Nissim cryptographic scheme along with other mechanisms. Second, FESDAO also supports statistical analytics on metering data at the cloud control center and fog node levels. FESDAO ensures reliable aggregation and accurate data analytical results, even in scenarios where smart meters fail to report data, thereby preserving both analytical operation computation accuracy and latency. We further provide comprehensive security analyses to demonstrate that the proposed approach effectively supports data privacy, source authentication, fault tolerance, and resilience against false data injection and replay attacks. Lastly, we offer thorough performance evaluations to illustrate the efficiency of the suggested scheme in comparison to current state-of-the-art schemes, considering encryption, computation, aggregation, decryption, and communication costs. Moreover, a detailed security analysis has been conducted to verify the scheme’s resistance against insider collusion attacks, replay attack, and false data injection (FDI) attack. Full article

Multi-modal image segmentation is a key task in various fields such as urban planning, infrastructure monitoring, and environmental analysis. However, it remains challenging due to complex scenes, varying object scales, and the integration of heterogeneous data sources (such as RGB, depth maps, and infrared). To address these challenges, we proposed a novel multi-modal segmentation framework, DyFuseNet, which features dynamic adaptive windows and cross-scale feature fusion capabilities. This framework consists of three key components: (1) Dynamic Window Module (DWM), which uses dynamic partitioning and continuous position bias to adaptively adjust window sizes, thereby improving the representation of irregular and fine-grained objects; (2) Scale Context Attention (SCA), a hierarchical mechanism that associates local details with global semantics in a coarse-to-fine manner, enhancing segmentation accuracy in low-texture or occluded regions; and (3) Hierarchical Adaptive Fusion Architecture (HAFA), which aligns and fuses features from multiple modalities through shallow synchronization and deep channel attention, effectively balancing complementarity and redundancy. Evaluated on benchmark datasets (such as ISPRS Vaihingen and Potsdam), DyFuseNet achieved state-of-the-art performance, with mean Intersection over Union (mIoU) scores of 80.20% and 80.65%, surpassing MFTransNet by 1.71% and 1.57%, respectively. The model also demonstrated strong robustness in challenging scenes (such as building edges and shadowed objects), achieving an average F1 score of 85% while maintaining high efficiency (26.19 GFLOPs, 30.09 FPS), making it suitable for real-time deployment. This work presents a practical, versatile, and computationally efficient solution for multi-modal image analysis, with potential applications beyond remote sensing, including smart monitoring, industrial inspection, and multi-source data fusion tasks. Full article

Unmanned aerial vehicle (UAV) imagery provides an efficient approach for monitoring cotton defoliation and boll-opening rates. Deep learning, particularly convolutional neural networks (CNNs), has been widely applied in image processing and agricultural monitoring, achieving strong performance in tasks such as disease detection, weed recognition, and yield prediction. However, existing models often suffer from heavy computational costs and slow inference speed, limiting their real-time deployment in agricultural fields. To address this challenge, we propose a lightweight cotton maturity recognition model, RTCMNet (Real-time Cotton Monitoring Network). By incorporating a multi-scale convolutional attention (MSCA) module and an efficient feature fusion strategy, RTCMNet achieves high accuracy with substantially reduced computational complexity. A UAV dataset was constructed using images collected in Xinjiang, and the proposed model was benchmarked against several state-of-the-art networks. Experimental results demonstrate that RTCMNet achieves 0.96 and 0.92 accuracy on defoliation rate and boll-opening rate classification tasks, respectively. Meanwhile, it contains only 0.35 M parameters—94% fewer than DenseNet121—and only requires an inference time of 33 ms, representing a 97% reduction compared to DenseNet121. Field tests further confirm its real-time performance and robustness on UAV platforms. Overall, RTCMNet provides an efficient and low-cost solution for UAV-based cotton maturity monitoring, supporting the advancement of precision agriculture. Full article

Visible Light Positioning (VLP) has emerged as a pivotal technology for industrial Internet of Things (IoT) and smart logistics, offering high accuracy, immunity to electromagnetic interference, and cost-effectiveness. However, fluctuations in signal gain caused by target motion significantly degrade the positioning accuracy of current VLP systems. Conventional approaches face intrinsic limitations: propagation-model-based techniques rely on static assumptions, fingerprint-based approaches are highly sensitive to dynamic parameter variations, and although CNN/LSTM-based models achieve high accuracy under static conditions, their inability to capture long-term temporal dependencies leads to unstable performance in dynamic scenarios. To overcome these challenges, we propose a novel dynamic VLP algorithm that incorporates a Spatio-Temporal Feature Information Network (STFI-Net) for joint localization and orientation estimation of moving targets. The proposed method integrates a two-layer convolutional block for spatial feature extraction and employs modern Temporal Convolutional Networks (TCNs) with dilated convolutions to capture multi-scale temporal dependencies in dynamic environments. Experimental results demonstrate that the STFI-Net-based system enhances positioning accuracy by over 26% compared to state-of-the-art methods while maintaining robustness in the face of complex motion patterns and environmental variations. This work introduces a novel framework for deep learning-enabled dynamic VLP systems, providing more efficient, accurate, and scalable solutions for indoor positioning. Full article

Lane detection is one of the key technologies for local map construction, and it is also a challenging task in intelligent driving, where various computer vision-based methods have been applied to address this issue. However, these methods often suffer from redundancy issues due to the sparse and narrow structure of the lane lines, and full generalization to lane detection needs more effort. To solve these problems, we propose a stepwise positive guidance strategy that utilizes the visually presented lane structure characteristics, which are inspired by the reference points in the DETR-Family methods. This strategy guides the network detection from the reference points to the reference lanes, improving the accuracy of the detection process. Moreover, we propose a new multi-scale feature fusion strategy that directly performs feature fusion on high-quality proposals. This approach differs from traditional object detection models using the Feature Pyramid Network (FPN). It fully uses the sparsity of lanes and reduces the network’s redundant computation. We proposed ProposalLaneNet, which takes full advantage of the lanes’ structure and sparse distribution characteristics. Significant improvements in speed and accuracy have been achieved by our method, enabling it to reach the state-of-the-art performance on the popular datasets CULane and TuSimple. Our method can be used as a new detection paradigm for lane detection. Full article

Coded-Aperture Snapshot Spectral Imaging (CASSI) systems acquire 3D spatial–spectral information on dynamic targets by converting 3D hyperspectral images (HSIs) into 2D compressed measurements. Various end-to-end networks have been proposed for HSI reconstruction from these measurements. However, these methods have not explored the frequency-domain information of HSIs. This research presents the spatial/spectral-frequency adaptive network (SSFAN) for CASSI image reconstruction. A frequency-division transformation (FDT) decomposes HSIs into distinct Fourier frequency components, enabling multiscale feature extraction in the frequency domain. The proposed dual-branch architecture consists of a spatial–spectral module (SSM) to preserve spatial–spectral consistency and a frequency division module (FDM) to model inter-frequency dependencies. Channel compression/expansion modules are integrated into the FDM to balance computational efficiency and reconstruction quality. Frequency-division loss supervises feature learning across divided frequency channels. Ablation experiments validate the contributions of each network module. Furthermore, comparison experiments on synthetic and real CASSI datasets demonstrate that SSFAN outperforms state-of-the-art end-to-end methods in reconstruction performance. Full article

The HIV-1 epidemic continues to challenge global public health, especially in sub-Saharan Africa. The rise in drug-resistant viruses, particularly pan-resistant strains, threatens treatment effectiveness, hindering progress toward UNAIDS viral suppression goals. This is critical in low-to-middle income countries (LMICs) like Zimbabwe, where treatment options and access to drug resistance testing are limited. This cross-sectional study analyzed 102 genotypes from patients with HIV-1 RNA ≥ 1000 copies/mL after at least 6 months on a dolutegravir (DTG)-based ART. HIV-1 genotyping and drug resistance interpretation were performed using the Stanford HIV Drug Resistance Database. Overall, 62% of genotypes harbored at least one drug resistance mutation, with 27% showing integrase strand transfer inhibitor (INSTI)-associated mutations. High-level resistance to DTG and cabotegravir was found in 14% and 23% of integrase sequences, respectively, primarily driven by G118R and E138K/T mutations. Pan-resistance was observed in 18% of complete genotypes, with one case of four class resistance. These results highlight the emergence of INSTI resistance in LMICs. The study underscores the urgent need for enhanced HIV drug resistance testing, continuous surveillance, and strategic optimization of ART regimens in resource-constrained settings to ensure effective HIV management. Full article

Infrared object detection is an important prerequisite for small unmanned aerial vehicle (UAV) swarm countermeasures. Owing to the limited imaging area and texture features of small UAV targets, accurate infrared detection of UAV swarm targets is challenging. In this paper, the GM-DETR is proposed for the detection of densely distributed small UAV swarm targets in infrared scenarios. Specifically, high-level and low-level features are fused by the Fine-Grained Context-Aware Fusion module, which augments texture features in the fused feature map. Furthermore, a Supervised Sampling and Sparsification module is proposed as an explicit guiding mechanism, which assists the GM-DETR to focus on high-quality queries according to the confidence value. The Geometric Relation Encoder is introduced to encode geometric relation among queries, which makes up for the information loss caused by query serialization. In the second stage of the GM-DETR, a long-term memory mechanism is introduced to make UAV detection more stable and distinguishable in motion blur scenes. In the decoder, the self-attention mechanism is improved by introducing memory blocks as additional decoding information, which enhances the robustness of the GM-DETR. In addition, we constructed a small UAV swarm dataset, UAV Swarm Dataset (USD), which comprises 7000 infrared images of low-altitude UAV swarms, as another contribution. The experimental results on the USD show that the GM-DETR outperforms other state-of-the-arts detectors and obtains the best scores (90.6 on AP${}_{75}$ and 63.8 on AP${}_{\mathit{S}}$), which demonstrates the effectiveness of the GM-DETR in detecting small UAV targets. The good performance of the GM-DETR on the Drone Vehicle dataset also demonstrates the superiority of the proposed modules in detecting small targets. Full article

The deployment of airborne hyperspectral sensors has expanded rapidly, driven by their ability to capture spectral information beyond the visual range and to reveal objects that remain obscured in conventional imaging. In scenarios where prior target signatures are unavailable, anomaly detection provides an effective alternative by identifying deviations from the spectral background. However, real-world reconnaissance and monitoring missions frequently take place in complex and dynamic environments, requiring anomaly detectors to demonstrate robustness and adaptability. These requirements have rarely been met in current research, as evaluations are still predominantly based on small, context-restricted datasets, offering only limited insights into detector performance under varying conditions. To address this gap, we propose a context-adaptive hyperspectral sensor and perception management (hSPM) architecture that integrates sensor context extraction, band selection, and detector management into a single adaptive processing pipeline. The architecture is systematically evaluated on a new, large-scale airborne hyperspectral dataset comprising more than 1100 annotated samples from two diverse test environments, which we publicly release to support future research. Comparative experiments against state-of-the-art anomaly detectors demonstrate that conventional methods often lack robustness and efficiency, while hSPM consistently achieves superior detection accuracy and faster processing. Depending on evaluation conditions, hSPM improves anomaly detection performance by 28–204% while reducing computation time by 70–99%. These results highlight the advantages of adaptive sensor processing architectures and underscore the importance of large, openly available datasets for advancing robust airborne hyperspectral anomaly detection. Full article

Self-supervised monocular depth estimation from oblique UAV videos is crucial for enabling autonomous navigation and large-scale mapping. However, existing self-supervised monocular depth estimation methods face key challenges in UAV oblique video scenarios: depth discontinuity from geometric distortion under complex viewing angles, and spatial ambiguity in weakly textured regions. These challenges highlight the need for models that combine global reasoning with geometric awareness. Accordingly, we propose RMTDepth, a self-supervised monocular depth estimation framework for UAV imagery. RMTDepth integrates an enhanced Retentive Vision Transformer (RMT) backbone, introducing explicit spatial priors via a Manhattan distance-driven spatial decay matrix for efficient long-range geometric modeling, and embeds a neural window fully-connected CRF (NeW CRFs) module in the decoder to refine depth edges by optimizing pairwise relationships within local windows. To mitigate noise in COLMAP-generated depth for real-world UAV datasets, we constructed a high-fidelity UE4/AirSim simulation environment, which generated a large-scale precise depth dataset (UAV SIM Dataset) to validate robustness. Comprehensive experiments against seven state-of-the-art methods across UAVID Germany, UAVID China, and UAV SIM datasets demonstrate that our model achieves SOTA performance in most scenarios. Full article

In recent years, numerous constrained multi-objective evolutionary algorithms (CMOEAs) have been proposed to tackle constrained multi-objective optimization problems (CMOPs). However, most of them still struggle to achieve a good balance among convergence, diversity, and feasibility. To address this issue, we develop an adaptive constraint-boundary learning-based two-stage dual-population evolutionary algorithm for CMOPs, referred to as CL-TDEA. The evolutionary process of CL-TDEA is divided into two stages. In the first stage, two populations cooperate weakly through environmental selection to enhance the exploration ability of CL-TDEA under constraints. In particular, the auxiliary population employs an adaptive constraint-boundary learning mechanism to learn the constraint boundary, which in turn enables the main population to more effectively explore the constrained search space and cross infeasible regions. In the second stage, the cooperation between the two populations drives the search toward the complete constrained Pareto front (CPF) through mating selection. Here, the auxiliary population provides additional guidance to the main population, helping it escape locally feasible but suboptimal regions by means of the proposed cascaded multi-criteria hierarchical ranking strategy. Extensive experiments on 54 test problems from four benchmark suites and three real-world applications demonstrate that the proposed CL-TDEA exhibits superior performance and stronger competitiveness compared with several state-of-the-art methods. Full article

Hybrid AC/DC microgrids have emerged as a promising solution for integrating diverse renewable energy sources, enhancing efficiency, and strengthening resilience in modern power systems. However, existing control schemes exhibit critical shortcomings that limit their practical effectiveness. Traditional linear controllers, designed around nominal operating points, often fail to maintain stability under large load and generation fluctuations. Optimization-based methods are highly sensitive to model inaccuracies and parameter uncertainties, reducing their reliability in dynamic environments. Intelligent approaches, such as fuzzy logic and ML-based controllers, provide adaptability but suffer from high computational demands, limited interpretability, and challenges in real-time deployment. These limitations highlight the need for robust control strategies that can guarantee reliable operation despite disturbances, uncertainties, and varying operating conditions. Numerical performance indices demonstrate that the reviewed robust control strategies outperform conventional linear, optimization-based, and intelligent controllers in terms of system stability, voltage and current regulation, and dynamic response. This paper provides a comprehensive review of recent robust control strategies for hybrid AC/DC microgrids, systematically categorizing classical model-based, intelligent, and adaptive approaches. Key research gaps are identified, including the lack of unified benchmarking, limited experimental validation, and challenges in integrating decentralized frameworks. Unlike prior surveys that broadly cover microgrid types, this work focuses exclusively on hybrid AC/DC systems, emphasizing hierarchical control architectures and outlining future directions for scalable and certifiable robust controllers. Also, comparative results demonstrate that state of the art robust controllers—including H∞-based, sliding mode, and hybrid intelligent controllers—can achieve performance improvements for metrics such as voltage overshoot, frequency settling time, and THD compared to conventional PID and droop controllers. By synthesizing recent advancements and identifying critical research gaps, this work lays the groundwork for developing robust control strategies capable of ensuring stability and adaptability in future hybrid AC/DC microgrids. Full article

To address the computational efficiency challenges in two-dimensional (2D) direction-of-arrival (DOA) estimation, a two-stage framework integrating the Nyström approximation with subspace decomposition techniques is proposed in this paper. The methodology strategically integrates the Nyström approximation with subspace decomposition techniques to bridge the critical performance–complexity trade-off inherent in high-resolution parameter estimation scenarios. In the first stage, the Nyström method is applied to approximate the signal subspace while simultaneously enabling construction of a reduced rank covariance matrix, which effectively reduces the computational complexity compared with eigenvalue decomposition (EVD) or singular value decomposition (SVD). This innovative approach efficiently derives two distinct signal subspaces that closely approximate those obtained from the full-dimensional covariance matrix but at substantially reduced computational cost. The second stage employs a sophisticated subspace-based estimation technique that leverages the principal singular vectors associated with these approximated subspaces. This process incorporates an iterative refinement mechanism to accurately resolve the paired azimuth and elevation angles comprising the 2D DOA solution. With the use of the Nyström approximation and reduced rank framework, the entire DOA estimation process completely circumvents traditional EVD/SVD operations. This elimination constitutes the core mechanism enabling substantial computational savings without compromising estimation accuracy. Comprehensive numerical simulations rigorously demonstrate that the proposed framework maintains performance competitive with conventional high-complexity estimators while achieving significant complexity reduction. The evaluation benchmarks the method against multiple state-of-the-art DOA estimation techniques across diverse operational scenarios, confirming both its efficacy and robustness under varying signal conditions. Full article

Inertial Measurement Units (IMUs), which embed several sensors (accelerometers, gyroscopes, magnetometers) are employed by musicians and performers to control sound, music, or lighting on stage. In particular, wireless IMU systems in the performing arts require particular attention due to strict requirements regarding streaming sample rate, latency, power consumption, and programmability. This article presents a review of systems developed in this context at IRCAM as well as in other laboratories and companies, highlighting specificities in terms of sensing, communication, performance, digital processing, and usage. Although basic IMUs are now widely integrated into IoT systems and smartphones, the availability of complete commercial wireless systems that meet the constraints of the performing arts remains limited. For this reason, a review of systems used in performing Arts provides exemplary use cases that may also be relevant to other applications. Full article

Recent developments in next-generation sequencing technology have led to the creation of extensive, open-source protein databases consisting of hundreds of millions of sequences. To render these sequences applicable in biomedical applications, they must be meticulously annotated by wet lab testing or extracting them from existing literature. Over the last few years, researchers have developed numerous automatic annotation systems, particularly deep learning models based on machine learning and artificial intelligence, to address this issue. In this work, we propose a transformer-based fusion model capable of predicting Gene Ontology (GO) terms from full-scale protein sequences, achieving state-of-the-art accuracy compared to other contemporary machine learning annotation systems. The approach performs particularly well on clustered split datasets, which comprise training and testing samples originating from distinct distributions that are structurally diverse. This demonstrates that the model is able to understand both short and long term dependencies within the protein’s structure and can capture sequence features that are predictive of the various GO terms. Furthermore, the technique is lightweight and less computationally expensive compared to the benchmark methods, while at the same time unaffected by sequence length, rendering it appropriate for diverse applications with varying sequence lengths. Full article