Search Results (2,420)

Channel time dispersion causes inter-symbol interference (ISI) which is mitigated by the Orthogonal Frequency Division Multiplexing (OFDM) symbol cyclic prefix (CP). However, CP is an overhead which reduces spectral efficiency and increases energy per delivered bit. In Long Term Evolution (LTE), the widely deployed normal CP corresponds to a fixed overhead of about 7% (4.69 $\mathsf{\mu }$s), which is conservative for many practical environments and is equivalent to path-length variations on the order of 1.4 km. This paper address CP sizing from an energy-efficiency viewpoint for OFDM-based 4G/5G radio networks. We combine an analytical model based on delay spread statistics with link-level simulations to determine a reduced CP that remains effective for ISI mitigation across indoor-to-urban scenarios. Optimal CP intervals are derived for the LTE M-ary Quadrature Amplitude Modulation formats (4-QAM, 16-QAM, and 64-QAM) and validated using standard delay-dispersive mobile radio channels. Results indicate that CP can be reduced by 70–95% relative to the LTE normal CP in typical deployments, yielding measurable net-throughput improvements and energy savings without compromising error-rate targets, supporting greener wireless communications. Full article

Passenger satisfaction is a key component of sustainable urban mobility, influencing public transport use, customer loyalty, and the attractiveness of railway systems. However, evidence from Latin American commuter rail services remains limited. This study evaluates the satisfaction of frequent users of the Limache–Puerto railway service operated by EFE Valparaíso in Greater Valparaíso, Chile, based on measurements conducted between 2024 and 2025. Using 400 surveys administered on station platforms and onboard trains, the analysis assessed overall satisfaction, Net Promoter Score (NPS), and experience attributes related to safety, predictability, cleanliness, information provision, comfort, and crowding. A repeated cross-sectional quantitative design with quota sampling was employed to compare successive measurement waves. Results indicate that passengers highly value the service’s speed and efficiency. Although NPS experienced a temporary decline during 2025, the final measurement remained comparable to the 2024 baseline. Key concerns included perceived platform safety, peak-hour crowding, onboard environmental conditions (temperature and odors), and service frequency in critical segments. Mentions of informal vendors decreased, whereas concerns regarding criminal incidents and passenger flow difficulties increased. The findings highlight the need for targeted interventions in safety, crowding management, environmental quality, and communication during disruptions. This pilot operational monitoring study proposes a practical framework for evaluating passenger satisfaction and NPS through repeated measurements, providing evidence to support service management and sustainable railway planning. Full article

Highland pastures in Montenegro, known as katuns, are seasonal settlements without grid power or network coverage and which are located where conventional monitoring is unfeasible. This study presents a solar-powered, off-grid system for livestock and environmental monitoring. It integrates, into a single portable unit, a solar power station, an edge-AI computer, a camera, environmental sensors, a LoRaWAN gateway, and a cellular router for backhaul. All parts are pre-wired in a modular enclosure, deployable by one operator in under 30 min. Data are fed to the agroNET farm-management platform and a purpose-built mobile web application; livestock detection runs on-device using a model from our earlier work. The system was evaluated at three sites, including a highland katun near Žabljak (~1450 m), under a two-phase energy-measurement protocol. During field logging it drew ~75 W on average against ~125 W solar input—a measured surplus that is used to recharge the battery—with a daily monitoring load of ~1560 Wh. The four-panel array’s nameplate potential in summer is an estimated ~3700 Wh/day, indicating substantial headroom relative to the measured load. At 80% depth of discharge the battery gives ~20 h autonomy, and the detection pipeline ran continuously, processing ~10,000 frames at under 3 s latency. The results demonstrate the feasibility of off-grid precision livestock farming, reaching TRL 6. Full article

Phase resistance unbalance in robotic joint drive systems can alter electromagnetic torque generation and degrade motion accuracy, but its early diagnosis is challenging because fault-related signatures are weak and coupled with operating dynamics. This study proposes a short-time Fourier transform (STFT)-based multi-scale attention ResNet for phase resistance-unbalance diagnosis using synchronized multi-sensor signals from a single industrial robotic joint. Controlled resistance-unbalance states were generated on an eRob70F100I-BM-18EN joint module by inserting 0.05 $\Omega$ and 0.1 $\Omega$ series resistors into one motor phase with a nominal single-phase resistance of 0.75 $\Omega$. Current, acceleration, rotational speed, and torque signals were segmented and converted into four-channel STFT log-amplitude maps. A modified ResNet18 backbone was integrated with feature pyramid network (FPN)-style multi-scale fusion and a convolutional block attention module (CBAM) to enhance discriminative time–frequency features. Under a window-level stratified split, the proposed model achieved 98.97% accuracy and 98.97% macro-F1, outperforming raw-signal, fast Fourier transform (FFT), wavelet, STFT-ResNet18, STFT-VGG11-BN, STFT-MobileNetV2, and STFT-ShuffleNetV2 baselines. Grouped validation was conducted using file-level, leave-one-speed-out, and leave-one-load-out splits to assess robustness under stricter data partitions. The proposed model achieved 91.75% macro-F1 under file-level splitting and average macro-F1 values of 89.77% and 84.22% under leave-one-speed-out and leave-one-load-out validation, respectively. Grad-CAM visualization further indicates that the model relies on non-uniform local time–frequency regions rather than uniformly using the entire spectrogram. These results demonstrate effective robotic-joint resistance-unbalance discrimination while revealing that unseen operating conditions, especially specific speed and load settings, remain challenging for robust cross-condition deployment. Full article

Emotion recognition remains a challenging task despite substantial progress in machine learning and affective computing. This study examines challenges in emotion recognition through a comparative analysis of two widely used modalities: facial images and speech signals. The analysis was conducted using FER-2013 for facial emotion recognition and the TESS and RAVDESS datasets for speech emotion recognition. A MobileNetV2-based approach was applied to visual data, while speech analysis employed MFCC-based representations and both classical and deep learning models. The study combines quantitative performance evaluation with qualitative analysis of classification behavior, focusing on emotion-specific recognition difficulties and recurring error patterns across modalities. Model performance was assessed using accuracy, precision, recall, F1-score, and confusion matrices. Across the analysed datasets, overall classification accuracy ranged from approximately 73% to 96%, while class-level F1-scores ranged from 0.48 to 0.89 depending on the emotion and modality. Happiness and surprise consistently achieved the highest recognition performance, whereas neutral emotion, fear, and disgust exhibited the lowest class-level F1-scores and generated the highest numbers of misclassifications. The experimental results confirmed that happiness and surprise achieved the highest classification performance across modalities, while neutral emotion, fear, and disgust showed reduced recognition accuracy due to weak expressive cues and overlapping feature representations. These difficulties are associated with weak or ambiguous expressive signals, overlap between emotional categories, and variability in emotional expression. The comparative findings suggest that recognition challenges arise from both modality-specific limitations and the inherent properties of emotional expression. The results highlight the importance of multimodal approaches and more flexible representations for improving emotion recognition systems. Full article

The precision of oil palm fresh fruit bunch (FFB) ripeness classification directly determines the extraction efficiency and chemical quality of the resulting crude palm oil (CPO). Traditional manual inspection at reception ramps remains labour-intensive, time-consuming, and subjective. To address these issues, this study presents a lightweight deep learning framework for automated oil palm FFB ripeness classification trained on a field-collected dataset of 857 images covering four ripeness classes (Over-ripe, Ripe, Under-ripe, and Unripe). Six lightweight classification backbones are evaluated, including MobileNetV2, EfficientNetV2B0/B1, and YOLO variants. An intra-class half-mixing augmentation with geometric transformation is proposed to address minority-class imbalance. Overall, YOLOv8n-cls achieved the highest accuracy (95.6%), followed by EfficientNetV2B0/B1, YOLO11n-cls, YOLO26n-cls, and MobileNetV2, respectively. In addition, all YOLO-family models achieved a recall score of 1.00 for the minority class while obtaining the highest $F_1$ scores for the other classes. The experimental results suggest that the proposed augmentation method enables lightweight deep learning models to achieve promising classification performance on an imbalanced field-collected FFB dataset while improving minority-class detection. Full article

Vehicle Ad Hoc Networks (VANETs) face critical challenges in trust management, privacy preservation, and scalability, particularly with the integration of 5G networks in Intelligent Transportation Systems (ITS). Traditional centralized trust models present single points of failure and privacy concerns that compromise network security and user anonymity. This paper presents a novel decentralized trust model leveraging blockchain technology, Interplanetary File System (IPFS) integration, and post-quantum cryptographic algorithms to address these limitations. Our proposed TrustChain-VANET framework implements advanced privacy-preserving encryption techniques including threshold and homomorphic encryption, geographical sharding for scalability, and edge-assisted consensus mechanisms. Performance evaluation demonstrates significant improvements: 40% reduction in authentication latency (90–120 ms vs. 150–300 ms), 90% malicious node detection rate (+15% improvement), 300% increase in transaction throughput (2000–2150 TPS), and 100% scalability enhancement supporting up to 5000 nodes. The system integrates seamlessly with 5G network slicing (URLLC, eMBB, mMTC) while maintaining quantum resistance through CRYSTALS-Dilithium, KYBER, and FALCON algorithms. Real-world deployment considerations including OBU computational constraints, standardization gaps, and energy efficiency are comprehensively analyzed. Results indicate that the proposed decentralized approach provides robust security, enhanced privacy, and improved scalability for next-generation vehicular networks, making it suitable for large-scale ITS deployment. The main contribution of this work is the development of a unified TrustChain-VA 48NET framework. The proposed framework integrates blockchain-based trust management, IPFS-assisted storage, 5G network slicing, Mobile Edge Computing (MEC), geographical sharding, and post-quantum cryptographic mechanisms within a single architecture for next-generation VANET environments. While these technologies have been investigated separately in previous studies, this work presents a consolidated framework that analyzes their interoperability, identifies integration challenges, and evaluates their combined impact on trust management, scalability, privacy preservation, and deployment feasibility in Intelligent Transportation Systems. Full article

Sensor-based human activity recognition (SHAR) serves as a core research direction in pervasive computing, mobile health, and related fields. Although existing deep learning methods have achieved promising progress in SHAR tasks, most optimize from a single dimension only. They struggle to simultaneously balance recognition accuracy, noise robustness, adaptation to class imbalance, and lightweight deployment requirements, leading to performance bottlenecks in real-world scenarios. To address these challenges, this paper proposes a lightweight joint optimization framework named AWARE-Net. Leveraging the lightweight TS-ResNet as a backbone encoder, the framework integrates spatiotemporal dynamic convolution feature encoding with a global loss function that fuses class-balanced loss, contrastive learning auxiliary loss, and temporal smooth regularization to achieve multi-objective joint optimization. Extensive experiments on three widely used SHAR benchmark datasets, namely OPPORTUNITY, PAMAP2, and USC-HAD, demonstrate that the proposed AWARE-Net achieves competitive performance compared with representative state-of-the-art HAR methods. Full article

To address the challenges of low detection accuracy and weak generalization in identifying mining-induced ground fissures from UAV imagery, caused by their slender and discontinuous morphology, complex background clutter, and multi-scale surface features, this paper proposes an enhanced deep semantic segmentation model, SAG-DeepLabV3+ (with Spatial Vision Transformer, Attention mechanisms, and Adaptive Gated Fusion). Specifically, to enhance global context modeling and fine boundary delineation, we introduce a Spatial Vision Transformer (SVT) branch within the Atrous Spatial Pyramid Pooling (ASPP) module. We further employ a dual attention mechanism, sequentially combining Squeeze-and-Excitation (SE) and a Convolutional Block Attention Module (CBAM), for progressive channel and spatial feature refinement. Moreover, an Adaptive Gated Fusion (AGF) module is designed to dynamically optimize the fusion of multi-level decoder features. Experiments on a dedicated UAV-based mining fissure dataset comprising 1280 annotated images show that SAG-DeepLabV3+ achieves a state-of-the-art mean Intersection over Union (mIoU) of 79.52% (with Xception backbone) and 79.19% (with lightweight MobileNetV2 backbone), surpassing DeepLabV3+, U-Net, and PSPNet by a significant margin. Furthermore, by leveraging transfer learning (pre-training on the public CrackVision12K dataset and fine-tuning on our mining fissure dataset), the model’s mIoU is further elevated to 82.04%, demonstrating superior generalization capability. The proposed SAG-DeepLabV3+ effectively balances high accuracy with operational efficiency, fulfilling the potential demand for lightweight automated fissure monitoring under resource-limited field deployments, and lays a foundation for subsequent real-time on-site deployment verification. Full article

Detecting deeply buried weak-signature ferromagnetic targets is essential for mine clearance and anti-submarine missions, yet conventional detection algorithms struggle to balance recognition accuracy and computational overhead under strong geomagnetic clutter. This work develops a lightweight detection framework tailored to low-SNR magnetic contour maps, named YOLOv8n-M3CA. The framework adopts MobileNetV3 as the lightweight backbone and introduces Coordinate Attention to strengthen the extraction of faint spatial magnetic anomaly features. We build a COMSOL (Multiphysics 6.2) simulation dataset with 1076 magnetic images covering five target geometries. The dataset is divided into 861 training samples and 215 test samples with 1519 annotated targets overall. Comparative experiments demonstrate that our model reduces parameters from 3.16 M to 2.78 M and GFLOPs from 8.9 to 6.5, while boosting precision, recall, and F1-score to 0.996, 0.994, and 0.995; its training time is shortened to 11.01 h, achieving an inference FPS of 21.5 on CPU. In a preliminary field test on a buried rectangular target, our method attains a detection confidence of 0.73, far exceeding the baseline YOLOv8n at 0.34. Experimental results verify that the proposed framework delivers notable anti-interference performance toward faint magnetic signals, though further field validation with diverse targets and conditions remains necessary before full operational deployment. Full article

This study examines the effectiveness of Genetic Algorithm (GA)-based image augmentation in enhancing Convolutional Neural Network (CNN) performance for Romblon marble texture classification. Five CNN architectures, AlexNet, InceptionV3, VGG16, MobileNet, and ResNet50, were trained and evaluated on both raw and GA-augmented datasets. Unprocessed dataset achieved limited accuracy, with InceptionV3 performing best at 35.33%, followed closely by VGG16 at 33.78%. In contrast, GA-augmented data significantly boosted performance, with VGG16 achieving 94.68% accuracy, followed by MobileNet (92.68%) and InceptionV3 (92.46%). Entropy loss values consistently decreased across all models, indicating improved convergence and reduced overfitting. Although ROC-AUC scores remained close to 0.5, reflecting modest improvements in class separability, overall results confirm that evolutionary augmentation enriches dataset diversity and strengthens CNN learning capacity. MobileNet showed a solid balance between accuracy and computational economy, underscoring the possibility of GA-based augmentation as a workable option for real-world marble categorization, while VGG16 emerged as the most accurate of the studied architectures. Full article

Cervical cancer remains a major global public health challenge, and the accurate classification of cervical transformation zones (TZs) constitutes a critical step in early detection and clinical decision-making. However, distinguishing between Type 2 and Type 3 transformation zones remains particularly challenging due to their high morphological similarity and the inherent interobserver variability associated with colposcopic assessment. In this study, we propose a novel Dual-Track Specialist Feature Fusion and Meta-Learning Stacking Ensemble architecture for the automated classification of cervical transformation zones using the Intel & MobileODT Cervical Cancer Screening dataset. The proposed framework integrates a global feature extractor based on ResNet50 (Gatekeeper) with a visual specialist based on InceptionResNetV2, trained exclusively on the most diagnostically ambiguous cases (Type 2 and Type 3). The extracted features are fused and processed through a multi-level stacking scheme composed of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boosting (GB), XGBoost, and LightGBM classifiers at the base level, followed by an XGBoost meta-learner and a clinically guided probability calibration strategy designed to maximize diagnostic sensitivity. Experimental results demonstrate a peak overall accuracy of 91.22%, substantially outperforming the baseline ResNet50 model (70%). Furthermore, the proposed system achieved Recall values of 0.90, 0.90, and 0.94 for Type 1, Type 2, and Type 3 transformation zones, respectively, highlighting its ability to accurately identify diagnostically challenging cases. Ablation studies, Grad-CAM visualizations, and external-image validation experiments confirm that the proposed architecture improves discrimination between ambiguous categories, learns clinically meaningful representations, and maintains strong generalization capability across heterogeneous scenarios. These findings demonstrate the potential of visual specialization and calibrated meta-learning strategies for the development of artificial intelligence-assisted colposcopic decision-support systems. Full article

Understanding the mechanisms that sustain plant diversity in arid regions is a current focus of ecological research. This study focused on the Gurbantunggut Desert, China’s largest fixed and semi-fixed desert, and systematically investigated the plant community diversity and its environmental drivers on fixed, semi-fixed, and mobile dunes. Data analysis was conducted using non-metric multidimensional scaling (NMDS) ordination, redundancy analysis (RDA), boosted regression tree (BRT), and structural equation modeling (SEM). The results indicated that taxonomic diversity (TD), functional diversity (FD), and phylogenetic diversity (PD) all exhibited consistent gradient patterns: fixed dunes > semi-fixed dunes > mobile dunes. The Net Relatedness Index (NRI) and the Nearest Taxon Index (NTI) primarily exhibited phylogenetic clustering, and habitat filtering was the dominant process in community assembly. Soil water content (SWC) and soil organic carbon (SOC) are the key drivers regulating plant diversity in this region. SWC and SOC directly and significantly influence FD and PD; however, their indirect effects on TD are weak, suggesting that species composition is also jointly constrained by abiotic processes such as dispersal limitation and interspecific competition. This study offers a theoretical foundation for differentiated ecological management of fixed, semi-fixed, and mobile dunes in the Gurbantunggut Desert. Full article

Multimedia data have been continuously increasing in magnitude, and so has the sophistication of manipulation methods, thereby making the digital forensic investigation process more complicated. The easy access to sophisticated image editing software and AI-generated materials has brought up the issue of information integrity, the reliability of legal evidence, and public trust. Traditional image forensics methods are usually concerned with either the detection of visual artifacts based on convolutional neural networks (CNNs) or based on metadata analysis, frequently independently of each other. This paper presents a multi-modal fusion paradigm, comprising visual feature-based feature extraction and metadata inconsistency-based detectors, to improve the classification strength. A two-stream design is used, comprising a high-level visual artifact capturing the transfer learning-based MobileNetV2 network and an XGBoost classifier that analyses EXIF metadata discrepancies. The heterogeneous representations are merged in a feature-level fusion strategy to generate a final authenticity prediction. It was tested on individual datasets and a compiled dataset of 26,023 images from CoMoFoD, CG-1050 and CASIA v1 and v2. The suggested approach had an overall accuracy of 83.85%, which was higher than the visual-only (68.61%) and metadata-only (75.85%) baselines. These findings show that complementary visual and metadata cues are much more useful in detection, while the use of a lightweight backbone enables efficient, high-throughput forensic analysis suitable for real-world deployment. Full article

Smartphone-based plant identification increasingly serves as the edge tier of agricultural Internet of Things (IoT) systems, where models must adapt to crowdsourced data under bandwidth, memory, and energy constraints. No prior work, to our knowledge, has systematically investigated continual learning at the scale of thousands of fine-grained medicinal plant species from crowdsourced images, nor how retraining frequency affects the cost–performance trade-off in an IoT model-lifecycle setting. We evaluate three continual learning strategies, naïve fine-tuning, experience replay, and Learning without Forgetting, under periodic retraining schedules (updating every K increments), tested on 2719 species (≥25 images each) from the Viet Medi Species 2026 dataset (310,647 images; 4799 species total). All three strategies exhibit negative forgetting (performance improvement rather than degradation) in the instance-incremental setting, with naïve fine-tuning and LwF showing the strongest gains. Periodic retraining with $K=2$ halves retraining operations while maintaining comparable performance. A baseline MobileNetV2 model achieves 54.07% top-10 accuracy across 2719 species and has been deployed via TensorFlow Lite (FP16, ∼11.5 MB) in the Med Herb Lens Android application. In this regime, naïve fine-tuning offers a favourable cost–performance trade-off and is a reasonable default for instance-incremental agricultural IoT deployments. Full article