Search Results (1,134)

Plant disease diagnosis in real-world agricultural environments is challenged by data scarcity, domain shift, privacy constraints, and limited edge-device resources. This paper proposes FMEL-FSDA, a Federated Multimodal Edge Learning framework with Few-Shot Domain Adaptation for robust field-based plant disease recognition. The framework integrates attention-based RGB–text feature fusion, privacy-preserving federated learning, rapid few-shot personalization, and uncertainty-aware inference within an edge-efficient architecture. Federated training enables collaborative learning across distributed farms without sharing raw data, while few-shot adaptation allows fast deployment to new regions using only 1–10 labeled samples per class. Experiments on the PlantWild in-the-wild dataset show that FMEL-FSDA outperforms centralized, federated, and few-shot baselines, achieving 93.78% accuracy, 93.33% F1-score, and 0.97 AUC. The model maintains strong performance under privacy mechanisms such as gradient perturbation and secure aggregation, reduces communication overhead by up to 4×, and supports low-latency edge inference. Uncertainty estimation and Grad-CAM-based explainability further enhance reliability by identifying low-confidence cases and highlighting disease-relevant regions. Overall, FMEL-FSDA offers a scalable, privacy-aware, and field-ready solution for intelligent plant disease diagnosis in precision agriculture. Full article

Substrates have become essential enabling materials for creating lightweight electronic components, particularly supporting advanced telecommunication technologies. This progress is driven by continuous advancements in novel substrate materials and cutting-edge fabrication techniques, pushing the limits of high-frequency device design. This paper explores both the challenges and breakthroughs in 5G mmWave substrate technology, focusing on recent developments in materials, device fabrication, and integration methods that enhance performance and provide an in-depth analysis of the importance of mmWave technology. This paper also highlights the key concerns in substrate design for researchers and academicians to accelerate the invention and commercialization of substrate designs in areas such as antenna engineering and integrated circuit technologies, as well as addressing key issues like scalability, thermal impact in flexible substrates, and AI-driven RSSI-aware beamforming and its implications. Likewise, since matters related to material losses and substrates’ fabrication constraints are increasingly severe at high frequencies, mmWave substrates need to be looked at; therefore, this paper details, as well, the particular issues related to mmWave propagation and manufacturing design processes for high-frequency devices. Aims at optimizing antenna and system reliability by employing advanced strategies and materials, as well as outlining the existing gaps that need clarification to augment 5G mmWave infrastructure and services. Full article

Indoor speech propagation causes minute vibrations in surrounding objects, enabling remote speech recovery through passive eavesdropping. Unlike traditional methods that rely on acoustic waves, passive eavesdropping uses object vibrations, making it difficult to defend against, even in soundproof environments. However, weak vibration signals and noise interference make speech recovery challenging. Existing studies mainly focus on deep learning for signal reconstruction, requiring large datasets and high computational power, which complicates real-time, on-device deployment. To address this, we propose a lightweight passive speech recovery system based on millimeter-wave radar. Without prior knowledge of object locations or numbers, the system can adaptively fuse multi-source signals for real-time speech reconstruction. To counteract the noise characteristics of millimeter-wave radar and the weak amplitude of vibration signals, we designed a set of low-complexity noise suppression and signal enhancement algorithms, ensuring efficient operation on edge devices. Experimental results demonstrate that in single-target scenarios, the proposed system achieved a Mel Cepstral Distortion (MCD) of 3.923 and a Word Error Rate (WER) of 12.9%. In multi-target scenarios, the SNR improved by 3.65 dB, MCD decreased by an average of 1.52, and WER decreased by an average of 15.83%, making the method effective and practical in complex acoustic environments. Full article

Long-term time series forecasting (LTSF) is critical for modern power systems, energy management, and grid planning. Yet virtually all existing forecasting models employ stationary activation functions that apply identical nonlinear mappings regardless of temporal context—a fundamental mismatch with real-world load data, which exhibits strongly regime-dependent dynamics such as summer demand peaks, winter heating patterns, and overnight low-load periods. We address this gap by proposing TC-KAN (Time-Conditioned Kolmogorov–Arnold Network), the first forecasting architecture to augment KAN activation functions with position-aware coefficient parameterisation. The core innovation replaces the static polynomial coefficients in standard KAN activations with position-conditioned coefficients produced by a lightweight positional-embedding MLP, providing additional learnable capacity beyond standard KAN while adding negligible parameter overhead. TC-KAN further integrates a dual-pathway processing block—combining depthwise convolution for local temporal pattern extraction with the time-conditioned KAN layer for enhanced nonlinear transformation—within a channel-independent framework with Reversible Instance Normalisation. Experiments were conducted on four standard ETT benchmark datasets and the high-dimensional Weather dataset. TC-KAN achieves superior or competitive accuracy in most configurations while requiring merely 51K parameters—approximately 40% of DLinear and ∼100× fewer than iTransformer. On ETTh2, TC-KAN reduces the mean squared error by up to 61.4% over DLinear, and matches the current state-of-the-art iTransformer on ETTm2 at a fraction of the computational cost. This extreme parameter reduction circumvents the steep memory bottlenecks endemic to massive Transformer models, positioning TC-KAN as a highly practical architecture tailored precisely for resource-constrained edge deployments—such as on-device load forecasting inside smart grid sensors and industrial IoT controllers. Full article

Wearable neurotechnology depends critically on continuous movement monitoring to characterize motor impairment and recovery in real-world settings. While joint torque serves as a clinically essential kinetic marker, estimating it directly on-device from inertial signals remains challenging due to stringent computational, memory, and energy constraints. Lightweight pipelines typically omit computationally expensive time–frequency processing; however, this omission degrades the observability of dynamics encoded in 1D IMU signals and diminishes the effectiveness of standard knowledge distillation strategies. To enable reliable on-device torque inference, we propose a Physically Guided Dual-Consistency Knowledge Distillation (PDC-KD) framework that explicitly integrates biomechanical priors into the learning process through two collaborative pathways: parameter-manifold alignment and physics-guided compensation. The student network receives guidance through Fisher-information-weighted parameter transfer, ensuring robust knowledge distillation despite significant model capacity mismatch. Furthermore, the framework incorporates a physics-guided regularization term that enforces dynamically consistent torque trajectories via a numerically stable Cholesky-parameterized constraint. Experiments demonstrate that the student model preserves teacher-level predictive accuracy while operating within the stringent resource constraints of edge devices (achieving a 98% parameter reduction, ∼2× faster inference, and ∼1 ms latency). Moreover, the proposed method yields torque estimates with enhanced dynamical consistency, providing an efficient biosignal-processing solution for wearable neurotechnology platforms demanding real-time movement analytics. Full article

Pitahaya (Hylocereus spp.) production is increasingly affected by climatic factors, as well as by phytopathogens and abiotic stress, leading to delays in agronomic interventions and reduced productivity. The objective was to design, implement, and validate a multimodal system (CARYPAR) that enables early disease detection and agile decision-making, characterized by low latency and reduced dependence on cloud connectivity. The methodology integrates climate reanalysis from NASA POWER, biophysical remote sensing variables derived from Sentinel-1/2, and proximal computer vision captured via mobile devices using a late fusion architecture and an optimized convolutional neural network, EfficientNet-V2B0, which discriminates between optimal and pathological conditions in vegetative tissues and fruit. The results of the experimental validation carried out in 160 georeferenced units achieved an overall accuracy of 80.0% and an F1 score of 0.8645 for Bad Fruit. The McNemar test and the operational agreement with agro-industrial experts yielded a Cohen’s Kappa index of κ = 0.6831, with an inference latency reduced to 22.00 ms. It is concluded that the multimodal integration of satellite bio-environmental data with edge computer vision achieves substantial agreement with agronomic expert judgment under heterogeneous field conditions (Cohen’s κ = 0.6831), supporting its role as a decision-support tool rather than a replacement for expert assessment. Therefore, its adoption can enhance real-time irrigation management and crop protection, while contributing to traceability and sustainable resource management in agricultural regions with limited connectivity. Full article

High-voltage bushings, the fault-prone key electrical components of transformers, are critical for real-time and high-accuracy fault monitoring and management. Intelligent fault detection via infrared images is plagued by low classification accuracy due to massive interference from similar tubular objects and small target characteristics. This study proposes a lightweight deep learning model, MTrip–YOLO, an improved YOLO11n integrated with Mamba-2 (Structured State Space Duality, SSD) and Triplet Attention, to achieve efficient fault monitoring in complex backgrounds. The training and validation dataset comprises open-source images, on-site data from a substation, and field-collected infrared images, categorized into four types: normal bushings, poor contact, oil shortage, and high dielectric loss faults. Mamba-2 captures the long-range global context of infrared features with its linear-complexity long-range modeling capability to enhance feature extraction, while Triplet Attention suppresses complex background radiation noise through cross-dimensional interaction without dimensionality reduction, enabling the model to focus on small targets and accurately classify bushings from morphologically similar strip-shaped objects. Experimental results show that MTrip–YOLO achieves a top mAP50 of 91.6% and a minimal parameter count of 1.9 M, outperforming Faster R-CNN, RT-DETR, and YOLO26n across all evaluated metrics and being potentially suitable for edge deployment on UAV-mounted or handheld infrared platforms, pending hardware validation on embedded computing devices. Ablation experiments verify the independent contributions of Mamba-2 (0.8027% mAP50 improvement) and Triplet Attention (0.89327% mAP50 improvement), with a synergistic effect from their combination. MTrip–YOLO provides a potential edge-deployable solution for high-voltage bushing fault monitoring, offering important application value for the intelligent operation and maintenance of substations. Full article

To address the challenge of balancing computational efficiency with fine-grained feature capture in complex field environments when using existing deep learning methods for tomato leaf disease detection, this paper proposes a novel lightweight classification model called Visual Mamba with Frequency-channel attention, Cross-layer attention and Salient feature suppression (VMamba-FCS). Based on the visual state-space model, this model integrates three collaborative enhancement mechanisms: a frequency-domain channel attention module, which improves the perception of disease-related textures by recalibrating features in the frequency domain; a cross-layer attention module, which promotes multi-scale feature fusion by integrating the semantic context of early layers; and a salient feature suppression module, which forces the network to learn more comprehensive discriminative features to improve robustness by suppressing overactivated feature regions during training. Experimental results on the real-world field dataset “Tomato-Village” demonstrate that VMamba-FCS achieves a classification accuracy of 93.62% and an inference speed of 126.5 frames per second (FPS) with only 1.20 M parameters, representing a 7.48% improvement in accuracy compared to the basic VMamba model. In the cross-dataset (PlantDoc) generalization test, VMamba-FCS significantly outperformed all comparison models with an accuracy of 71.3%, demonstrating its excellent domain adaptability and robustness. This work verifies the effectiveness of the multi-mechanism collaborative enhancement strategy in the state-space model architecture, providing a new lightweight solution for real-time and accurate agricultural disease detection on resource-constrained edge devices. Full article

Skeleton-based action recognition is a critical technology for intelligent sports analysis. Although the human skeletal structure exhibits inherent bilateral symmetry, sensor noise on resource-constrained edge devices frequently induces geometric distortion and topological asymmetry. Consequently, achieving a balance between high accuracy and real-time performance remains a significant challenge. To this end, we propose EMS-GCN, an Efficient Multi-scale Shift Graph Convolutional Network that integrates geometric priors. Specifically, we design a Gaussian kernel-driven topology refinement module to mitigate structural noise inherent in sensor data. By leveraging geometric symmetry and Gaussian distances among nodes, this module dynamically constrains graph topology learning, thereby effectively rectifying the structural asymmetry and ambiguity induced by noise. Furthermore, we construct a Multi-scale Shift Linear Attention (MSLA) module to replace computationally intensive temporal convolutions. Leveraging temporal shift invariance, this module captures multi-scale contexts via parameter-free shift operations. Furthermore, we introduce a linear temporal attention mechanism to model global temporal dependencies with linear complexity, effectively resolving the information asymmetry inherent in long-range interactions. Finally, EMS-GCN incorporates a dual-branch attention structure to adaptively calibrate feature responses. Extensive experiments demonstrate that our model maintains high recognition accuracy with only 0.56M parameters, representing a reduction of over 60% compared to mainstream baselines. These results validate the efficacy of leveraging geometric and temporal symmetries to enhance real-time sports analysis. Full article

With the proliferation of edge computing in IoT and smart security, there is a growing demand for large-scale encrypted traffic anomaly detection. However, the opaque nature of encrypted traffic makes it difficult for traditional detection methods to balance efficiency and accuracy. To address this challenge, this paper proposes FMTF, a Multi-Scale Feature Fusion method based on Federated Learning for encrypted traffic anomaly detection. FMTF constructs graph structures at three scales—spatial, statistical, and content—to comprehensively characterize traffic features. At the spatial scale, communication graphs are constructed based on host-to-host IP interactions, where each node represents the IP address of a host and edges capture the communication relationships between them. The statistical scale builds traffic statistic graphs based on interactions between port numbers, with nodes representing individual ports and edge weights corresponding to the lengths of transmitted packets. At the content scale, byte-level traffic graphs are generated, where nodes represent pairs of bytes extracted from the traffic data, and edges are weighted using pointwise mutual information (PMI) to reflect the statistical association between byte occurrences. To extract and fuse these multi-scale features, FMTF employs the Graph Attention Network (GAT), enhancing the model’s traffic representation capability. Furthermore, to reduce raw-data exposure in distributed edge environments, FMTF integrates a federated learning framework. In this framework, edge devices train models locally based on their multi-scale traffic features and periodically share model parameters with a central server for aggregation, thereby optimizing the global model without exposing raw data. Experimental results demonstrate that FMTF maintains efficient and accurate anomaly detection performance even under limited computing resources, offering a practical and effective solution for encrypted traffic identification and network security protection in edge computing environments. Full article

Cotton represents one of the world’s most significant agricultural commodities. However, severe weed proliferation in cotton fields seriously hampers the development of the cotton industry, making precise weed control essential for ensuring healthy cotton growth. Traditional object detection methods often suffer from computational complexity, rendering them difficult to deploy on resource-constrained edge devices. To address this challenge, this paper proposes AVGS-YOLO, a lightweight and enhanced model employing a Quadruple Synergistic Lightweight Perception Mechanism (QSLPM) for precise weed detection in complex cotton field environments. The QSLPM emphasizes synergistic interactions between modules. It integrates lightweight neck architecture (Slimneck) to optimize feature extraction pathways for cotton weeds; the ADown module (Adaptive Downsampling) replaces Conv modules to address model parameter redundancy; the small object attention modulation module (SEAM) enhances the recognition of small-scale cotton weed features; and angle-sensitive geometric regression (SIoU) improves bounding box localization accuracy. Experimental results demonstrate that the AVGS-YOLO model achieves 95.9% precision, 94.2% recall, 98.2% mAP50, and 93.3% mAP50-95. While maintaining high detection accuracy, the model achieves a lightweight design with reductions of 17.4% in parameters, 27% in GFLOPs, and 14.5% in model size. Demonstrating strong performance in identifying cotton weeds within complex cotton field environments, this model provides technical support for deployment on resource-constrained edge devices, thereby advancing intelligent agricultural development and safeguarding the healthy growth of cotton crops. Full article

Transforming a conventional university campus into a smart campus by leveraging modern technologies aims to deliver university services efficiently, effectively, and at low cost. Modern technologies enhance campus life by providing services, such as smart classrooms and campus security, on demand. Seamless service delivery requires reliable and efficient access to the services that take into consideration the dynamic contextual attributes related to, e.g., end-device mobility, latency sensitivity, and resource constraints. University staff, students, and visitors frequently submit different types of service requests on the move, which requires a robust orchestration framework capable of managing these requests across edge-cloud environments. The orchestration framework needs to intelligently distribute the workload, taking into consideration the latency sensitivity requirements and contextual conditions, including resource constraints. Therefore, a fuzzy-logic orchestration framework for smart-campus environments in edge-cloud architecture is proposed. The framework incorporates key factors, including user speed, resource utilization, and request delay sensitivity, in the decision-making process to satisfy both service consumers and service providers. It prioritizes latency-sensitive requests while simultaneously enhancing resource utilization efficiency. Simulation-based experimental results demonstrate the effectiveness of the proposed framework compared with benchmark approaches in orchestrating incoming workloads under several user and contextual conditions. Additionally, the results show that the proposed framework improves the execution rate by 30% compared to benchmark models and achieves more than double resource utilization efficiency. Full article

To address the urgent need for enhancing landslide risk monitoring in reservoir embankment slopes, a core component of water conservancy projects, this paper proposes the LRES-YOLO algorithm for real-time landslide detection on reservoir embankments. In LRES-YOLO, we first integrate coordinate attention into basic feature extraction convolutional blocks to form the CACBS attention module, which enhances the model’s ability to identify and locate landslide targets in complex reservoir terrain, overcoming positional information insensitivity in deep networks. Second, we add novel downsampling DP modules and ELAN-W modules to the backbone network, improving feature recognition efficiency for embankment slopes with diverse hydrological and topographical interference. Third, we optimize the feature fusion network with targeted concatenation and pooling operations, balancing semantic information enhancement with computational load reduction to mitigate overfitting in variable reservoir environments. Finally, we adopt Focal Loss and EIoU Loss to accelerate training convergence and strengthen target feature representation for small or obscured landslides on embankments. Experimental results show that LRES-YOLO outperforms traditional algorithms in detecting landslides across diverse reservoir embankment scenarios: it achieves an average improvement of 8.4 percentage points in mean mAP over the best-performing baseline across five independent trials, a detection speed of 8.2 ms per image, and memory usage of 139 MB. This lightweight design makes it suitable for edge computing devices, providing robust technical support for intelligent monitoring systems in water conservancy projects. Full article

With the rapid development of applications such as smart cities and the industrial internet, the computation-intensive tasks generated by massive sensing devices pose significant challenges to traditional cloud computing paradigms. Unmanned aerial vehicle (UAV)-assisted edge computing systems, leveraging their high mobility and wide-area coverage capabilities, offer an innovative architecture for low-latency and highly reliable edge services. However, the practical deployment of such systems faces a highly complex multi-objective optimization problem featured by the tight coupling of task offloading decisions, UAV trajectory planning, and edge server resource allocation. Conventional optimization methods are difficult to adapt to the dynamic and high-dimensional characteristics of this problem, leading to suboptimal system performance. To address this critical challenge, this paper constructs an intelligent collaborative optimization framework for UAV-assisted edge computing systems and formulates the system quality of service (QoS) optimization problem as a mixed-integer non-convex programming problem with the dual objectives of minimizing task processing latency and reducing overall system energy consumption. A multi-agent joint task association and trajectory optimization (MA-JTATO) algorithm based on hybrid reinforcement learning is proposed to solve this intractable problem, which innovatively decouples the original coupled optimization problem into three interrelated subproblems and realizes their collaborative and efficient solution. Specifically, the Advantage Actor-Critic (A2C) algorithm is adopted to realize dynamic and optimal task association between UAVs and edge servers for discrete decision-making requirements; the multi-agent deep deterministic policy gradient (MADDPG) method is employed to achieve cooperative and energy-efficient trajectory planning for multiple UAVs to meet the needs of continuous control in dynamic environments; and convex optimization theory is applied to obtain a closed-form optimal solution for the efficient allocation of computational resources on edge servers. Simulation results demonstrate that the proposed MA-JTATO algorithm significantly outperforms traditional baseline algorithms in enhancing overall QoS, effectively validating the framework’s superior performance and robustness in dynamic and complex scenarios. Full article

In intelligent excavator applications, traditional excavator posture recognition methods face two major challenges: limited recognition accuracy and insufficient computing resources on edge devices. To address these issues, this study proposes an excavator posture recognition method based on an improved Real-Time Detection Transformer (RT-DETR). First, a new backbone network is designed based on the Reparameterized Vision Transformer to improve feature utilization efficiency while reducing computational demands. Next, the overall architecture is optimized by introducing lightweight Dynamic Upsamplers, which reduce information loss during upsampling and enhance multi-scale feature fusion. In addition, a Cross-Attention Fusion Module is adopted to strengthen local feature extraction while retaining the global modeling capability of the Transformer, thereby improving the discrimination between foreground and background. Finally, a Multi-Scale Fusion Network is introduced to further enhance the multi-scale feature representation ability of RT-DETR. Experimental results show that the proposed method achieves a mean average precision (mAP) of 94.29% for small object detection, which is 7.96% higher than that of the baseline RT-DETR, while reducing the number of model parameters by 34.95%. Compared with YOLO-series models, the proposed method improves mAP by 8.62% to 12.75%. These results indicate that the proposed method outperforms existing methods in both detection accuracy and computational efficiency and provides an efficient and feasible solution for real-time excavator posture recognition. Full article