Search Results (42)

Federated learning (FL) has emerged as a powerful approach for privacy-preserving model training in autonomous vehicle networks, where real-world deployments rely on multiple roadside units (RSUs) serving heterogeneous clients with intermittent connectivity. While most research focuses on single-server or hierarchical cloud-based FL, multi-server FL can alleviate the communication bottlenecks of traditional setups. To this end, we propose an edge-based, multi-server FL (MS-FL) framework that combines performance-driven aggregation at each server—including statistical weighting of peer updates and outlier mitigation—with an application layer handover protocol that preserves model updates when vehicles move between RSU coverage areas. We evaluate MS-FL on both MNIST and GTSRB benchmarks under shard- and Dirichlet-based non-IID splits, comparing it against single-server FL and a two-layer edge-plus-cloud baseline. Over multiple communication rounds, MS-FL with the Statistical Performance-Aware Aggregation method and Dynamic Weighted Averaging Aggregation achieved up to a 20-percentage-point improvement in accuracy and consistent gains in precision, recall, and F1-score (95% confidence), while matching the low latency of edge-only schemes and avoiding the extra model transfer delays of cloud-based aggregation. These results demonstrate that coordinated cooperation among servers based on model quality and seamless handovers can accelerate convergence, mitigate data heterogeneity, and deliver robust, privacy-aware learning in connected vehicle environments. Full article

When faced with diverse types of image tampering and image quality degradation in real-world scenarios, traditional image tampering localization methods often struggle to balance boundary accuracy and robustness. To address these issues, this paper proposes a symmetric guided dual-branch image tampering localization network—FENet (Fusion-Enhanced Network)—that integrates adaptive feature fusion and edge attention mechanisms. This method is based on a structurally symmetric dual-branch architecture, which extracts RGB semantic features and SRM noise residual information to comprehensively capture the fine-grained differences in tampered regions at the visual and statistical levels. To effectively fuse different features, this paper designs a self-calibrating fusion module (SCF), which introduces a content-aware dynamic weighting mechanism to adaptively adjust the importance of different feature branches, thereby enhancing the discriminative power and expressiveness of the fused features. Furthermore, considering that image tampering often involves abnormal changes in edge structures, we further propose an edge-aware coordinate attention mechanism (ECAM). By jointly modeling spatial position information and edge-guided information, the model is guided to focus more precisely on potential tampering boundaries, thereby enhancing its boundary detection and localization capabilities. Experiments on public datasets such as Columbia, CASIA, and NIST16 demonstrate that FENet achieves significantly better results than existing methods. We also analyze the model’s performance under various image quality conditions, such as JPEG compression and Gaussian blur, demonstrating its robustness in real-world scenarios. Experiments in Facebook, Weibo, and WeChat scenarios show that our method achieves average F1 scores that are 2.8%, 3%, and 5.6% higher than those of existing state-of-the-art methods, respectively. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

Smart cities necessitate ultra-secure and scalable communication frameworks to manage billions of interconnected IoT devices, particularly in the face of the emerging quantum computing threats. This paper proposes the QESIF, a novel Quantum-Enhanced Secure IoT Framework that integrates Quantum Key Distribution (QKD) with classical IoT infrastructures via a hybrid protocol stack and a quantum-aware intrusion detection system (Q-IDS). The QESIF achieves high resilience against eavesdropping by monitoring quantum bit error rate (QBER) and leveraging entropy-weighted key generation. The simulation results, conducted using datasets TON IoT, Edge-IIoTset, and Bot-IoT, demonstrate the effectiveness of the QESIF. The framework records an average QBER of 0.0103 under clean channels and discards over 95% of the compromised keys in adversarial settings. It achieves Attack Detection Rates (ADRs) of 98.1%, 98.7%, and 98.3% across the three datasets, outperforming the baselines by 4–9%. Moreover, the QESIF delivers the lowest average latency of 20.3 ms and the highest throughput of 868 kbit/s in clean scenarios while maintaining energy efficiency with 13.4 mJ per session. Full article

With the increasing significance of deep-sea resource development, Forward-Looking Sonar (FLS) has become an essential technology for real-time environmental mapping and navigation in deep-sea mining vehicles (DSMV). However, FLS images often suffer from a limited field of view, uneven imaging, and complex noise sources, making single-frame images insufficient for providing continuous and complete environmental awareness. Existing mosaicking methods typically rely on external sensors or controlled laboratory conditions, often failing to account for the high levels of uncertainty and error inherent in real deep-sea environments. Consequently, their performance during sea trials tends to be unsatisfactory. To address these challenges, this study introduces a robust FLS image mosaicking framework that functions without additional sensor input. The framework explicitly models the noise characteristics of sonar images captured in deep-sea environments and integrates bidirectional cyclic consistency filtering with a soft-weighted feature refinement strategy during the feature-matching stage. For image fusion, a radial adaptive fusion algorithm with a protective frame is proposed to improve edge transitions and preserve structural consistency in the resulting panoramic image. The experimental results demonstrate that the proposed framework achieves high robustness and accuracy under real deep-sea conditions, effectively supporting DSMV tasks such as path planning, obstacle avoidance, and simultaneous localization and mapping (SLAM), thus enabling reliable perceptual capabilities for intelligent underwater operations. Full article

Situation awareness (SA) involves analyzing sensory data, such as audio signals, to identify anomalies. While acoustic features are widely used in audio analysis, existing methods face critical limitations; they often overlook the relevance of SA audio segments, failing to capture the complex relational patterns in audio data that are essential for SA. In this study, we first propose a graph neural network (GNN) with an attention mechanism that models SA audio features through graph structures, capturing both node attributes and their relationships for richer representations than traditional methods. Our analysis identifies suitable audio feature combinations and graph constructions for SA tasks. Building on this, we introduce a situation awareness gated-attention GNN (SAGA-GNN), which dynamically filters irrelevant nodes through max-relevance neighbor sampling to reduce redundant connections, and a learnable edge gated-attention mechanism that suppresses noise while amplifying critical events. The proposed method employs sigmoid-activated attention weights conditioned on both node features and temporal relationships, enabling adaptive node emphasizing for different acoustic environments. Experiments reveal that the proposed graph-based audio features demonstrate superior representation capacity compared to traditional methods. Additionally, both proposed graph-based methods outperform existing approaches. Specifically, owing to the combination of graph-based audio features and dynamic selection of audio nodes based on gated-attention, SAGA-GNN achieved superior results on two real datasets. This work underscores the importance and potential value of graph-based audio features and attention mechanism-based GNNs, particularly in situational awareness applications. Full article

Federated learning enables privacy-preserving model training across distributed clients, yet real-world deployments face statistical, system, and behavioral heterogeneity, which degrades performance and increases vulnerability to adversarial clients. Existing incentive mechanisms often neglect participant credibility, leading to unfair rewards and reduced robustness. To address these issues, we propose a Trust-Aware Incentive Mechanism (TAIM), which evaluates client reliability through a multi-dimensional trust model incorporating participation frequency, gradient consistency, and contribution effectiveness. A trust-weighted reward allocation is formulated via a Stackelberg game, and a confidence-based soft filtering algorithm is introduced to mitigate the impact of unreliable updates. Experiments on FEMNIST, CIFAR-10, and Sent140 demonstrate that TAIM improves accuracy by up to 4.1%, reduces performance degradation under adaptive attacks by over 35%, and ensures fairer incentive distribution with a Gini coefficient below 0.3. TAIM offers a robust and equitable FL framework suitable for heterogeneous edge environments. Full article

With the demand for workflow processing driven by edge computing in the Internet of Things (IoT) and cloud computing growing at an exponential rate, task scheduling in heterogeneous distributed systems has become a key challenge to meet real-time constraints in resource-constrained environments. Existing studies now attempt to achieve the best balance in terms of time constraints, energy efficiency, and system reliability in Dynamic Voltage and Frequency Scaling environments. This study proposes a two-stage collaborative optimization strategy. With the help of an innovative algorithm design and theoretical analysis, the multi-objective optimization challenges mentioned above are systematically solved. First, based on a reliability-constrained model, we propose a topology-aware dynamic priority scheduling algorithm (EAWRS). This algorithm constructs a node priority function by incorporating in-degree/out-degree weighting factors and critical path analysis to enable multi-objective optimization. Second, to address the time-varying reliability characteristics introduced by DVFS, we propose a Fibonacci search-based dynamic frequency scaling algorithm (SEFFA). This algorithm effectively reduces energy consumption while ensuring task reliability, achieving sub-optimal processor energy adjustment. The collaborative mechanism of EAWRS and SEFFA has well solved the dynamic scheduling challenge based on DAG in heterogeneous multi-core processor systems in the Internet of Things environment. Experimental evaluations conducted at various scales show that, compared with the three most advanced scheduling algorithms, the proposed strategy reduces energy consumption by an average of 14.56% (up to 58.44% under high-reliability constraints) and shortens the makespan by 2.58–56.44% while strictly meeting reliability requirements. Full article

Background/Objectives: Alzheimer’s disease (AD) is the leading cause of dementia and is characterized by progressive neurodegeneration, resulting in cognitive impairment and structural brain changes. Although no curative treatment exists, pharmacological therapies like cholinesterase inhibitors and NMDA receptor antagonists may deliver symptomatic relief and modestly delay disease progression. Structural magnetic resonance imaging (sMRI) is a commonly utilized modality for the diagnosis of brain neurological diseases and may indicate abnormalities. However, improving the recognition of discriminative characteristics is the primary difficulty in diagnosis utilizing sMRI. Methods: To tackle this problem, the Fuzzy Optimized Attention Network with Multi-Instance Deep Learning (FOA-MIDL) system is presented for the prodromal phase of mild cognitive impairment (MCI) and the initial detection of AD. Results: An attention technique to estimate the weight of every case is presented: the fuzzy salp swarm algorithm (FSSA). The swarming actions of salps in oceans serve as the inspiration for the FSSA. When moving, the nutrient gradients influence the movement of leading salps during global search exploration, while the followers fully explore their local environment to adjust the classifiers’ parameters. To balance the relative contributions of every patch and produce a global distinct weighted image for the entire brain framework, the attention multi-instance learning (MIL) pooling procedure is developed. Attention-aware global classifiers are presented to improve the understanding of the integral characteristics and form judgments for AD-related categorization. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarker, and Lifestyle Flagship Study on Ageing (AIBL) provided the two datasets (ADNI and AIBL) utilized in this work. Conclusions: Compared to many cutting-edge techniques, the findings demonstrate that the FOA-MIDL system may determine discriminative pathological areas and offer improved classification efficacy in terms of sensitivity (SEN), specificity (SPE), and accuracy. Full article

Artificial intelligence of things (AIoT) has become a pivotal enabler of precision agriculture by supporting real-time, data-driven decision-making at the edge. Deep learning (DL) models are central to this paradigm, offering powerful capabilities for analyzing environmental and climatic data in a range of agricultural applications. However, deploying these models on edge devices remains challenging due to constraints in memory, computation, and energy. Existing model compression techniques predominantly target large-scale 2D architectures, with limited attention to one-dimensional (1D) models such as gated recurrent units (GRUs), which are commonly employed for processing sequential sensor data. To address this gap, we propose a novel three-stage coarse-to-fine compression framework, termed SUQ-3 (Structured, Unstructured Pruning, and Quantization), designed to optimize 1D DL models for efficient edge deployment in AIoT applications. The SUQ-3 framework sequentially integrates (1) structured pruning with an $M\times N$ sparsity pattern to induce hardware-friendly, coarse-grained sparsity; (2) unstructured pruning to eliminate low-magnitude weights for fine-grained compression; and (3) quantization, applied post quantization-aware training (QAT), to support low-precision inference with minimal accuracy loss. We validate the proposed SUQ-3 by compressing a GRU-based crop recommendation model trained on environmental and climatic data from an agricultural dataset. Experimental results show a model size reduction of approximately 85% and an 80% improvement in inference latency while preserving high predictive accuracy (F1 score: 0.97 vs. baseline: 0.9837). Notably, when deployed on a mobile edge device using TensorFlow Lite, the SUQ-3 model achieved an estimated energy consumption of 1.18 μJ per inference, representing a 74.4% reduction compared with the baseline and demonstrating its potential for sustainable low-power AI deployment in agricultural environments. Although demonstrated in an agricultural AIoT use case, the generality and modularity of SUQ-3 make it applicable to a broad range of DL models across domains requiring efficient edge intelligence. Full article

Due to the construction damage of high-density polyethylene film (HDPE) during the early stages of landfill construction and missed or faulty welding, this paper proposes a method based on the synchronous characteristic temperature differences between defective and intact areas of HDPE film. An image feature-edge-picking algorithm was used to detect various defects. First, under the action of a continuous heat source, infrared images of different types of defects on the surface of HDPE films were collected, and we recorded the temperature of different areas on the film surface. We also analyzed the changes in the temperatures of the complete and defect areas over time and extracted the temperature characteristic curves. Second, the contour characteristics of hidden defects in the weld area were analyzed. The image with the most substantial temperature difference resolution was selected and preliminary noise reduction was performed. Further enhancement of the edges was carried out using the guided image-filtering (GIF) algorithm, which was improved by using the edge-aware weighting in weighted guided image filtering (WGIF) and the weighted aggregation mechanism in weighted aggregated guided image filtering (WAGIF). Finally, the Canny operator was used to detect the edges of the processed images to recognize the contour of the welding defect. The best pixel image was extracted, the pixel comparison relationship was used to quantitatively detect the defect size of the HDPE film and the error between the image defect size and the actual size was analyzed. The experimental results show that the model could identify the surface defects on HDPE film during construction and could obtain the approximate outline and size of the hidden defects in the welding area. Full article

Crack segmentation is essential for structural health monitoring and infrastructure maintenance, playing a crucial role in early damage detection and safety risk reduction. Traditional methods, including digital image processing techniques have limitations in complex environments. Deep learning-based methods have shown potential, but still face challenges, such as poor generalization with limited samples, insufficient extraction of fine-grained features, feature loss during upsampling, and inadequate capture of crack edge details. This study proposes SECrackSeg, a high-accuracy crack segmentation network that integrates an improved UNet architecture, Segment Anything Model 2 (SAM2), MI-Upsampling, and an Edge-Aware Attention mechanism. The key innovations include: (1) using a SAM2 S-Adapter with a frozen backbone to enhance generalization in low-data scenarios; (2) employing a Multi-Scale Dilated Convolution (MSDC) module to promote multi-scale feature fusion; (3) introducing MI-Upsampling to reduce feature loss during upsampling; and (4) implementing an Edge-Aware Attention mechanism to improve crack edge segmentation precision. Additionally, a custom loss function incorporating weighted binary cross-entropy and weighted IoU loss is utilized to emphasize challenging pixels. This function also applies Multi-Granularity Supervision by optimizing segmentation outputs at three different resolution levels, ensuring better feature consistency and improved model robustness across varying image scales. Experimental results show that SECrackSeg achieves higher precision, recall, F1-score, and mIoU scores on the CFD, Crack500, and DeepCrack datasets compared to state-of-the-art models, demonstrating its excellent performance in fine-grained feature recognition, edge segmentation, and robustness. Full article

Edge-computing applications demand ultra-low-power architectures for both feature extraction and classification tasks. In this manuscript, a Keyword Spotting (KWS) system tailored for energy-constrained portable environments is proposed. A 16-channel analog filter bank is employed for audio feature extraction, followed by a digital Gated Recurrent Unit (GRU) classifier. The filter bank is behaviorally modeled, making use of second-order band-pass transfer functions, simulating the analog front-end (AFE) processing. To enable efficient deployment, the GRU classifier is trained using a Learned Step Size (LSQ) and Look-Up Table (LUT)-aware quantization method. The resulting quantized model, with 4-bit weights and 8-bit activation functions (W4A8), achieves 91.35% accuracy across 12 classes, including 10 keywords from the Google Speech Command Dataset v2 (GSCDv2), with less than 1% degradation compared to its full-precision counterpart. The model is estimated to require only 34.8 kB of memory and 62,400 multiply–accumulate (MAC) operations per inference in real-time settings. Furthermore, the robustness of the AFE against noise and analog impairments is evaluated by injecting Gaussian noise and perturbing the filter parameters (center frequency and quality factor) in the test data, respectively. The obtained results confirm a strong classification performance even under degraded circuit-level conditions, supporting the suitability of the proposed system for ultra-low-power, noise-resilient edge applications. Full article

Object detection in remote sensing images has gained prominence alongside advancements in sensor technology and earth observation systems. Although current detection frameworks demonstrate remarkable achievements in natural imagery analysis, their performance degrades when applied to remote imaging scenarios due to two inherent limitations: (1) complex background interference, which causes object features to be easily obscured by noise, leading to reduced detection accuracy; (2) the variation in object scales leads to a decrease in the model’s generalization ability. To address these issues, we propose a progressive semantic-aware fusion network (ProSAF-Net). First, we design a shallow detail aggregation module (SDAM), which adaptively integrates features across different channels and scales in the early Neck stage through dynamically adjusted fusion weights, fully exploiting shallow detail information to refine object edge and texture representation. Second, to effectively integrate shallow detail information and high-level semantic abstractions, we propose a deep semantic fusion module (DSFM), which employs a progressive feature fusion mechanism to incrementally integrate deep semantic information, strengthening the global representation of objects while effectively complementing the rich shallow details extracted by SDAM, enhancing the model’s capability in distinguishing objects and refining spatial localization. Furthermore, we develop a spatial context-aware module (SCAM) to fully exploit both global and local contextual information, effectively distinguishing foreground from background and suppressing interference, thus improving detection robustness. Finally, we propose auxiliary dynamic loss (ADL), which adaptively adjusts loss weights based on object scales and utilizes supplementary anchor priors to expedite parameter convergence during coordinate regression, thereby improving the model’s positioning accuracy for targets. Extensive experiments on the RSOD, DIOR, and NWPU VHR-10 datasets demonstrate that our method outperforms other state-of-the-art methods. Full article

Fumigation effectively manages pests, yet manual spraying poses long-term health risks to operators, making autonomous fumigation robots safer and more efficient. Path planning is a crucial aspect of deploying autonomous robots; it primarily focuses on minimizing energy consumption and maximizing operational time. The Payload and Energy-aware Tactical Allocation Loop (PETAL) algorithm integrates a genetic algorithm to search for waypoint permutations, applies a 2-OPT (two-edge exchange) local search to refine those routes, and leverages an energy cost function that reflects payload weight changes during spraying. This combined strategy minimizes travel distance and reduces energy consumption across extended fumigation missions. To evaluate its effectiveness, a comparative study was performed between PETAL and prominent algorithms such as A*, a hybrid Dijkstra with A*, random search, and a greedy distance-first approach, using both randomly generated environments and a real-time map from an actual deployment site. The PETAL algorithm consistently performed better than baseline algorithms in simulations, demonstrating significant savings in energy usage and distance traveled. On a randomly generated map, the PETAL algorithm achieved 6.05% higher energy efficiency and 23.58% shorter travel distance than the baseline path-planning algorithm. It achieved 15.69% and 31.66% in energy efficiency and distance traveled saved on a real-time map, respectively. Such improvements can diminish operator exposure, extend mission durations, and foster safer, more efficient urban pest control. Full article