Search Results (254)

High-resolution remote sensing images are gradually playing an important role in land cover mapping, urban planning, and environmental monitoring tasks. However, current segmentation approaches frequently encounter challenges such as loss of detail and blurred boundaries when processing high-resolution remote sensing imagery, owing to their complex backgrounds and dense semantic content. In response to the aforementioned limitations, this study introduces HMA-UNet, a novel segmentation network built upon the UNet framework and enhanced through a hybrid attention strategy. The architecture’s innovation centers on a composite attention block, where a lightweight split fusion attention (LSFA) mechanism and a lightweight channel-spatial attention (LCSA) mechanism are synergistically integrated within a residual learning structure to replace the stacked convolutional structure in UNet, which can improve the utilization of important shallow features and eliminate redundant information interference. Comprehensive experiments on the WHDLD dataset and the DeepGlobe road extraction dataset show that our proposed method achieves effective segmentation in remote sensing images by fully utilizing shallow features and eliminating redundant information interference. The quantitative evaluation results demonstrate the performance of the proposed method across two benchmark datasets. On the WHDLD dataset, the model attains a mean accuracy, IoU, precision, and recall of 72.40%, 60.71%, 75.46%, and 72.41%, respectively. Correspondingly, on the DeepGlobe road extraction dataset, it achieves a mean accuracy of 57.87%, an mIoU of 49.82%, a mean precision of 78.18%, and a mean recall of 57.87%. Full article

Understanding surface textures through visual cues is crucial for applications in haptic rendering and virtual reality. However, accurately translating visual information into tactile feedback remains a challenging problem. To address this challenge, this paper presents a class-conditional Generative Adversarial Network (cGAN) for cross-modal translation from texture images to vibrotactile spectrograms, using samples from the LMT-108 dataset. The generator is adapted from pix2pix and enhanced with Conditional Batch Normalization (CBN) at the bottleneck to incorporate texture class semantics. A dedicated label predictor, based on a DenseNet-201 and trained separately prior to cGAN training, provides the conditioning label. The discriminator is derived from pix2pixHD and uses a multi-scale architecture with three discriminators, each comprising three downsampling layers. A grid search over multi-scale discriminator configurations shows that this setup yields optimal perceptual similarity measured by Learned Perceptual Image Patch Similarity (LPIPS). The generator is trained using a hybrid loss that combines adversarial, $L_1$, and feature matching losses derived from intermediate discriminator features, while the discriminators are trained using standard adversarial loss. Quantitative evaluation with LPIPS and Fréchet Inception Distance (FID) confirms superior similarity to real spectrograms. GradCAM visualizations highlight the benefit of class conditioning. The proposed model outperforms pix2pix, pix2pixHD, Residue-Fusion GAN, and several ablated versions. The generated spectrograms can be converted into vibrotactile signals using the Griffin–Lim algorithm, enabling applications in haptic feedback and virtual material simulation. Full article

Small-object semantic segmentation remains challenging in urban driving scenes due to limited pixel occupancy, blurred boundaries, and the constraints imposed by lightweight deployment. To address these issues, this paper presents a lightweight semantic segmentation framework that enhances boundary awareness and contextual representation while maintaining computational efficiency. The proposed method integrates an edge-supervised boundary gating module to emphasize object boundaries, an efficient multi-scale context aggregation strategy to mitigate scale variation, and a lightweight feature enhancement mechanism for effective feature fusion. Edge supervision is introduced as an auxiliary regularization signal and does not require additional manual annotations. Extensive experiments conducted on multiple benchmark datasets, including Cityscapes, CamVid, PASCAL VOC 2012, and IDDA, demonstrate that the proposed framework consistently improves segmentation performance, particularly for small-object categories, while preserving a favorable balance between accuracy and efficiency. Full article

Material tracking and localization are key applications of Industry 4.0 in manufacturing process control. Traditional approaches—such as barcode or QR code identification and RTLS-based localization using RF/UWB, 5G or GPS–require a large and complex infrastructure. As an alternative, this paper proposes an IoT-based solution that combines short-range Bluetooth Low Energy (BLE) communication with LPWAN LoRaWAN networks. Hybrid solutions using LoRaWAN and BLE technologies already exist, but pure localization based on BLE tags can lead to ambiguous asset identification in geometrically dense scenarios. Our paper aims to solve this problem with an alternative concept called Associated LoRaWAN Sensors (ALSs). An ALS enables logical grouping and integration of heterogeneous LoRaWAN sensors, providing their own data or directly scanning BLE tags. Sensor data can be combined and supplemented with new information, data, and events, supported by application logic (use case). Although ALS represents a general concept that could be applicable to various use cases (such as warehouse monitoring, object tracking), our paper will focus mainly on material tracking and validation in manufacturing. For this purpose, we designed a specific ALS model that integrates a classic LoRaWAN BLE sensor with an additional LoRaWAN magnetic contact sensor. The magnetic contact switch can provide validation of exact position, in addition to localization by BLE tag. Experimental validation using BLE tags (Trax 10229) and LoRaWAN sensors (IoTracker3, Milesight WS301) demonstrates the usability of the ALS model in typical industrial scenarios. We also measured RSSI and evaluated the accuracy of tag localization (3 × 25 = 75 tests) for the worst-case scenario: material validation on a machine with a BLE tag distance of ~0.5 m. While the traditional approach showed up to a 20% failure rate, our ALS model avoided the issue of incorrect accuracy. An additional magnetic switch in ALS confirmed that the correct carrier with the associated tag is attached to the machine and eliminated incorrect localization. The results confirm that a hybrid model based on BLE and LoRaWAN scanning can reliably support material localization and validation without the need for dense RTLS infrastructures. Full article

One major factor influencing the development of eco-friendly policies and the implementation of climate change mitigation strategies is the accurate projection of CO₂ emissions. Traditional statistical models face significant limitations in capturing complex nonlinear interactions within high-dimensional emissions data. Advanced deep learning architectures offer new opportunities to overcome these computational challenges due to their strong pattern-recognition capabilities. This paper evaluates four distinct deep learning architectures for CO₂ emissions forecasting: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Hybrid Convolutional–LSTM (CNN–LSTM) systems, and Dense Neural Networks (DNNs). A comprehensive comparison is conducted using consistent training protocols, hyperparameters, and performance metrics across five prediction horizons (1, 3, 6, 12, and 24 steps ahead) to reveal architecture-specific degradation patterns. Furthermore, analyzing emissions by category provides insight into the suitability of each architecture for varying levels of pattern complexity. LSTM-based models demonstrate particular strength in modeling long-term temporal dependencies, making them well-suited for integration into long-range environmental policy planning frameworks. Overall, this study provides empirical evidence supporting the use of neural networks in climate modeling and proposes criteria for selecting optimal architectures based on forecasting horizon and computational constraints. Full article

This study presents a graph-based framework for improving predictive maintenance in nuclear power plants (NPPs), integrating data balancing techniques with a proposed Graph Attention Network (GAT) with a Mutual k-Nearest Neighbor (Mk-NN) strategy, named GAT-Mk-NN. To enhance the system’s ability to discriminate between genuine faults and sensor anomalies, we introduce a novel procedure for generating synthetic false positives that simulate realistic sensor failures. To mitigate class imbalance, we employ structured oversampling and multiple synthetic data generation strategies. Our results demonstrate that our GAT-Mk-NN model achieves the best trade-off between accuracy and computational efficiency, reaching an F1-score of 0.882 and an accuracy of 0.884. Performance analysis reveals that low to moderate graph connectivity enhances both robustness and model generalization. Our GAT-Mk-NN model structure outperformed other state-of-the-art graph architectures (enhanced GCN, GraphSAGE, GIN, graph transformer, ChebNet, TAG, ARMA graph, simple GCN, GATv2, and hybrid GNN). The findings highlight the potential of graph-based learning for fault detection in sensor-dense industrial environments, offering actionable insights for deploying fault-tolerant diagnostics in critical systems. Full article

The use of wireless sensor networks (WSNs) enables multidimensional and high-precision forest environment monitoring around the clock. However, the limited energy supply of sensor nodes using solely batteries is insufficient to support long-term data collection. Furthermore, since the complex terrain, dense vegetation, and variable weather in forests present unique challenges, relying on a single energy source is insufficient to ensure a stable energy supply for sensor nodes. Combining multiple energy sources is a promising way which has not been well studied. In this paper, to effectively utilize multiple energy sources, we propose a novel dynamic clustering routing protocol which considers the inherent diversity and intermittency of energy sources of the WSN in the forest. First, to address the inconsistency in residual energy caused by uneven energy harvesting among sensor nodes, a cluster head selection weight function is developed, and a dynamic weight-based cluster head election algorithm is proposed. This mechanism effectively prevents low-energy nodes from being selected as cluster heads, thereby maximizing the utilization of harvested energy. Second, a Q-learning-based adaptive hybrid transmission scheme is introduced, integrating both single-hop and multi-hop communication. The scheme dynamically optimizes intra-cluster transmission paths based on the current network state, reducing energy consumption during data transmission. The simulation results show that the proposed routing algorithm significantly outperforms existing methods in total network energy consumption, network lifetime, and energy balance. These advantages make it particularly suitable for forest environments characterized by strong fluctuations in harvested energy. In summary, this work provides an energy-efficient and adaptive routing solution suitable for forest environments with fluctuating energy availability. Full article

Precise recognition and localization of electronic components on printed circuit boards (PCBs) are crucial for industrial automation tasks, including robotic disassembly, high-precision assembly, and quality inspection. However, strong visual interference from silkscreen characters, copper traces, solder pads, and densely packed small components often degrades the accuracy of deep learning-based detectors, particularly under complex industrial imaging conditions. This paper presents a two-stage, coarse-to-fine PCB component localization framework based on an optimized YOLOv11 architecture and a sub-pixel geometric refinement module. The proposed method enhances the backbone with a Convolutional Block Attention Module (CBAM) to suppress background noise and strengthen discriminative features. It also integrates a tiny-object detection branch and a weighted Bi-directional Feature Pyramid Network (BiFPN) for more effective multi-scale feature fusion, and it employs a customized hybrid loss with vertex-offset supervision to enable pose-aware bounding box regression. In the second stage, the coarse predictions guide contour-based sub-pixel fitting using template geometry to achieve industrial-grade precision. Experiments show significant improvements over baseline YOLOv11, particularly for small and densely arranged components, indicating that the proposed approach meets the stringent requirements of industrial robotic disassembly. Full article

The reliability of electric vehicle (EV) batteries requires detecting surface defects but also precisely locating them on the physical module for automated inspection, repair, and process optimisation. Conventional 2D computer vision methods, though accurate in image-space, do not provide traceable, real-world defect coordinates on complex or curved battery surfaces, limiting utility for digital twins, root cause analysis, and automated quality control. This work proposes a hybrid inspection pipeline that produces millimetre-level three-dimensional (3D) defect maps for EV battery modules. The approach integrates (i) calibrated dual-view multi-view geometry to project defect points onto the CAD geometry and triangulate them where dual-view coverage is available, (ii) single-image neural 3D shape inference calibrated to the module geometry to complement regions with limited multi-view coverage, and (iii) generative, physically informed augmentation of rare or complex defect types. Defects are first detected in 2D images using a convolutional neural network (CNN), then projected onto a dense 3D CAD model of each module, complemented by a single-image depth prediction in regions with limited dual-view coverage, yielding true as-built localisation on the battery’s surface. GenAI methods are employed to expand the dataset with synthetic defect variations. Synthetic, physically informed defect examples are incorporated during training to mitigate the scarcity of rare defect types. Evaluation on a pilot industrial dataset, with a physically measured reference subset, demonstrates that the hybrid 3D approach achieves millimetre-scale localisation accuracy and outperforms a per-view CNN baseline in both segmentation and 3D continuity. Full article

We experimentally demonstrate an 80 Gbit/s Nyquist-dense wavelength division multiplexed (Nyquist-DWDM) transmission system operating in a simulated atmospheric turbulence channel. The system utilizes eight wavelength-tunable lasers with 100 GHz spacing, modulated by cascaded Mach–Zehnder modulators, to generate phase-locked Nyquist pulse sequences with a 10 GHz repetition rate and a temporal width of 66.7 ps. Each channel is synchronously modulated with a 10 Gbit/s pseudo-random bit sequence (PRBS) and transmitted through controlled weak turbulence conditions generated by a temperature-gradient convection chamber. Experimental measurements reveal that, as the turbulence intensity increases from $C_n^2=1.01\times {10}^{-16}$ to $5.71\times {10}^{-16} {\mathrm{m}}^{-2/3}$, the signal-to-noise ratio (SNR) of the edge channel (C29) and central channel (C33) decreases by approximately 6.5 dB while maintaining stable Nyquist waveform profiles and inter-channel orthogonality. At a forward-error-correction (FEC) threshold of $3.8\times {10}^{-3}$, the minimum receiver sensitivity is −17.66 dBm, corresponding to power penalties below 5 dB relative to the back-to-back condition. The consistent SNR difference (<2 dB) between adjacent channels confirms uniform power distribution and low inter-channel crosstalk under turbulence. These findings verify that Nyquist pulse shaping substantially mitigates phase distortion and scintillation effects, demonstrating the feasibility of high-capacity DWDM free-space optical (FSO) systems with enhanced spectral efficiency and turbulence resilience. The proposed configuration provides a scalable foundation for future multi-wavelength FSO links and hybrid fiber-wireless optical networks. Full article

The exponential growth of candidate data from large-scale radio pulsar surveys has created a pressing need for efficient and accurate classification methods. This paper presents a novel hybrid pulsar candidate recognition algorithm that integrates diagnostic plot images and structured numerical features using a multi-scale DenseNet framework. The proposed model combines convolutional neural networks (CNNs) for extracting spatial patterns from pulsar diagnostic plots and feedforward neural networks (FNNs) for processing scalar features such as SNR, DM, and pulse width. By fusing these multimodal representations, the model achieves superior classification performance, particularly in class-imbalanced settings standard to pulsar survey data. Evaluated on a synthesized dataset constructed from FAST and HTRU survey characteristics, the model demonstrates robust performance, achieving an F1-score of 0.904 and AUC-ROC of 0.978. Extensive ablation and cross-validation analyses confirm the contribution of each data modality and the model’s generalizability. Furthermore, the system maintains low inference latency (4.2 ms per candidate) and a compact architecture (~2.3 million parameters), indicating potential for real-time deployment once validated on real observational datasets. The proposed approach offers a scalable and interpretable multimodal framework for automated pulsar classification and provides a foundation for future validation and potential integration into observatories such as FAST and the Square Kilometre Array (SKA). Full article

Deep learning has demonstrated significant promise in medical image analysis; however, standard CNNs frequently encounter challenges in detecting subtle and intricate features vital for accurate diagnosis. To address this limitation, we systematically integrated attention mechanisms into five commonly used CNN backbones: VGG16, ResNet18, InceptionV3, DenseNet121, and EfficientNetB5. Each network was modified using either a Squeeze-and-Excitation block or a hybrid Convolutional Block Attention Module, allowing for more effective recalibration of channel and spatial features. We evaluated these attention-augmented models on two distinct datasets: (1) a Products of Conception histopathological dataset containing four tissue categories, and (2) a brain tumor MRI dataset that includes multiple tumor subtypes. Across both datasets, networks enhanced with attention mechanisms consistently outperformed their baseline counterparts on all measured evaluation criteria. Importantly, EfficientNetB5 with hybrid attention achieved superior overall results, with notable enhancements in both accuracy and generalizability. In addition to improved classification outcomes, the inclusion of attention mechanisms also advanced feature localization, thereby increasing robustness across a range of imaging modalities. Our study established a comprehensive framework for incorporating attention modules into diverse CNN architectures and delineated their impact on medical image classification. These results provide important insights for the development of interpretable and clinically robust deep learning-driven diagnostic systems. Full article

Infrared small target detection (IRSTD) is hindered by low signal-to-noise ratios, minute object scales, and strong target–background similarity. Although long-range skip fusion is exploited in SCTransNet, the global context is insufficiently captured by its convolutional encoder, and the fusion block remains vulnerable to structured clutter. To address these issues, a Mamba-enhanced framework, MixMambaNet, is proposed with three mutually reinforcing components. First, ResBlocks are replaced by a perception-aware hybrid encoder, in which local perceptual attention is coupled with mixed pixel–channel attention along multi-branch paths to emphasize weak target cues while modeling image-wide context. Second, at the bottleneck, dense pre-enhancement is integrated with a selective-scan 2D (SS2D) state-space (Mamba) core and a lightweight hybrid-attention tail, enabling linear-complexity long-range reasoning that is better suited to faint signals than quadratic self-attention. Third, the baseline fusion is substituted with a non-local Mamba aggregation module, where DASI-inspired multi-scale integration, SS2D-driven scanning, and adaptive non-local enhancement are employed to align cross-scale semantics and suppress structured noise. The resulting U-shaped network with deep supervision achieves higher accuracy and fewer false alarms at a competitive cost. Extensive evaluations on NUDT-SIRST, NUAA-SIRST, and IRSTD-1k demonstrate consistent improvements over prevailing IRSTD approaches, including SCTransNet. Full article

Accurate short-term load forecasting (STLF) is essential for energy management in buildings, yet remains challenging due to the nonlinear interactions among weather, occupancy, and operational patterns. This study presents a reproducible forecasting pipeline applied as a case study to a single anonymized hotel in Greece, representing a highly variable building-scale load. Three heterogeneous data streams were programmatically ingested and aligned: distribution-operator smart meter telemetry (15 min intervals aggregated to daily active energy), enterprise guest-night counts as an occupancy proxy, and meteorological observations from the National Observatory of Athens (NOA). Following rigorous preprocessing, feature construction incorporated lagged demand, calendar encodings, and exogenous drivers. Forecasting was performed with a stacked LSTM architecture (BiLSTM → LSTM → LSTM with dropout and a compact dense head), trained and validated under a leakage-safe chronological split. A bounded random hyperparameter search of forty configurations was tracked in MLflow 3.5.0 to ensure full reproducibility. The best model achieved RMSE of 4.71 kWh, MAE of 3.48 kWh, and MAPE of 3.29% on the hold-out test set, with stable training and robust diagnostics. The findings confirm that compact recurrent networks can deliver accurate and transparent hotel-level forecasts, providing a practical template for operational energy planning and sustainability reporting. Future research should extend this case study to multi-building portfolios and hybrid deep learning architectures. Full article

Early diagnosis and rapid treatment of respiratory abnormalities such as many lung diseases including pneumonia, TB, cancer, and other pulmonary problems depend on accurate and fast classification of chest X-ray images. Delayed diagnosis and insufficient treatment lead to the subjective, labour-intensive, error-prone features of current manual diagnosis systems. To tackle this pressing healthcare issue, this work investigates many deep convolutional neural network (CNN) architectures including VGG16, VGG19, ResNet50, InceptionV3, Xception, DenseNet121, NASNetMobile, and NASNet Large. LungVisionNet (LVNet) is an innovative hybrid model proposed here that combines MobileNetV2 with multilayer perceptron (MLP) layers in a unique way. LungVisionNet outperformed previous models in accuracy 96.91%, recall 97.59%, precision, specificity, F1-score 97.01%, and area under the curve (AUC) measurements according to thorough examination on two publicly available datasets including various chest abnormalities and normal cases exhibited. Comprehensive evaluation with an independent, real-world clinical dataset from King Hussein Cancer Centre (KHCC), which achieved 95.3% accuracy, 95.3% precision, 78.8% recall, 99.1% specificity, and 86.4% F1-score, confirmed the model’s robustness, generalizability, and clinical usefulness. We also created a simple mobile application that lets doctors quickly classify and evaluate chest X-ray images in hospitals, so enhancing clinical integration and practical application and supporting fast decision-making and better patient outcomes. Full article