Search Results (379)

With the rapid proliferation of short-video platforms and live-streaming commerce ecosystems, marketing activities are increasingly manifested through complex multimodal sensing signals. These heterogeneous sensor data streams exhibit strong temporal dependency, high cross-modal coupling, and progressive evolutionary characteristics, making early-stage fraud perception particularly challenging for conventional unimodal or static analytical paradigms. Existing approaches often fail to effectively capture weak anomalous cues emerging across multimodal channels during the initial stages of fraudulent campaigns. To address these limitations, an artificial intelligence-driven multimodal sensor perception framework is proposed for temporal fraud detection in short-video environments. A multimodal temporal alignment module is first designed to synchronize heterogeneous sensor signals with inconsistent sampling granularities. Subsequently, a shared temporal encoding network is constructed to learn evolution-aware representations across multimodal sensor sequences. On this basis, a cross-modal temporal attention fusion mechanism is introduced to dynamically weight sensor contributions at different behavioral stages. Finally, a fraud evolution modeling and early risk prediction module is developed to characterize the progressive intensification of fraudulent activities and to enable risk assessment under incomplete temporal observations. Extensive experiments conducted on real-world datasets collected from multiple mainstream short-video platforms demonstrate the effectiveness of the proposed AI-driven sensing framework. The model achieves an overall accuracy of 0.941, precision of 0.865, recall of 0.812, and F1 score of 0.838, with the AUC further reaching 0.956, significantly outperforming text-based, vision-based, temporal, and conventional multimodal baselines. In early-stage detection scenarios utilizing only the first 30% of video content, the framework maintains stable performance advantages, achieving a precision of 0.812, recall of 0.704, and F1 score of 0.754, validating its capability for proactive fraud warning. Full article

To advance automatic tomato leaf disease detection in precision agriculture, this study addresses critical challenges in complex field environments, such as variable lesion scales, background interference, and deployment constraints. We propose MSP-Net, a task-driven detection framework with targeted architectural refinements integrating three specific optimizations. First, a Multi-Scale Perception Convolution Module (MSPCM) is introduced to capture diverse disease features across early-to-late infection stages. Second, SimAM-enhanced C3k2 layers are utilized to suppress background noise and focus on fine-grained lesion cues. Third, a Multi-Scale Feature Enhancement Module (MSFEM) bridges the semantic gap between shallow and deep features to improve fusion efficacy. Furthermore, we construct a lightweight variant, L-MSP-Net, using architectural migration and structured pruning for edge efficiency. Experimental results on the real-world Tomato-Village dataset show that MSP-Net achieves 92.0% mAP@0.5, outperforming the YOLOv11s baseline by 2.0%. L-MSP-Net attains 86.1% mAP@0.5, improving by 3.6% over the lightweight YOLOv11n baseline while reducing parameters by 10.5%, and is successfully deployed on the RK3588 edge platform. Additional cross-dataset experiments on PASCAL VOC and MS COCO evaluate the transferability of the proposed architectural refinements to generic object detection tasks. Full article

Agentic AI is increasingly framed as enabling consumers to delegate commerce decisions and actions to digital assistants, yet consumer-facing evidence still centers on assistive chatbots and recommender-like systems, with scarce evaluation of execution-level delegation. This study provides an evidence-mapping review of empirical work on agentic commerce and synthesizes determinants and outcomes of delegation across three questions: (RQ1) how systems are operationalized (autonomy, task scope, interaction mode, and transaction capability/evidence realism), (RQ2) what facilitates or inhibits delegation, and (RQ3) what downstream outcomes follow for marketing performance and consumer experience. We searched Scopus and Web of Science for English-language, peer-reviewed primary studies (2015–2026) and applied conservative coding rules that distinguish claimed capability from simulated or demonstrated execution. The mapped literature is concentrated in text-based, low-autonomy assistants focused on recommendation and post-purchase support; coverage drops sharply for workflow-level autonomy, cart building, checkout/payment execution, and negotiation. Across studies, findings cluster into two motifs: a utility/assurance pathway in which performance cues and interaction quality increase perceived usefulness, satisfaction, and trust, and a governance pathway in which autonomy cues and system-initiated control trigger reactance/powerlessness and reduce acceptance unless mitigated by safeguards; urgency can attenuate governance resistance. Because most outcomes are intention- or vignette-based, calibration, verification, and error-recovery behaviors remain under-measured. Overall, delegation appears to depend less on maximizing autonomy than on coupling capability with user governance (consent, oversight, recourse, accountability), and we outline measurement priorities for evaluating execution-capable agents. Full article

Water utilities continue to lose a lot of Non-Revenue Water (NRW) because of leaks that go undetected. This makes it necessary to find accurate but easy-to-use monitoring solutions. This paper presents FiT-WST+, a wavelet-guided Frequency-Informed Transformer (FiT) designed for the classification of five distinct leak types utilising accelerometer measurements. The proposed architecture combines the spectral modelling ability of a FIT with the stable translation-invariant representation of the Wavelet Scattering Transform (WST). The model uses a guided attention mechanism to combine spectral and scattering cues that work well together to make classes more distinct, especially for fault types that are similar. On the held-out test set, FiT-WST+ achieves 99.6% accuracy, 99.6% balanced accuracy, and a 99.6% macro-averaged F1-score. Comparative benchmarking against recent methods tested on the same dataset shows that this method works at a low sampling rate (1 kHz), which greatly lowers bandwidth needs and allows for scalable deployment on edge devices with limited resources for real-time monitoring of important water infrastructure. Full article

The integration of wearable inertial measurement units (IMU) in animal welfare Internet of Things (IoT) systems has become crucial for monitoring animal behaviors and enhancing welfare management. However, the vulnerability of IoT devices to network and hardware attacks poses significant risks, potentially compromising data integrity and misleading caregivers, negatively impacting animal welfare. Additionally, current animal monitoring solutions often rely on intrusive tagging methods, such as Radio Frequency Identification (RFID) or ear tagging, which may cause unnecessary stress and discomfort to animals. In this study, we propose a lightweight integrity and provenance-oriented security stack that complements standard transport security, specifically tailored to IMU-based animal motion IoT systems. Our system utilizes a 1D-convolutional neural network (CNN) model, achieving 88% accuracy for precise motion recognition, alongside a lightweight behavioral fingerprinting CNN model attaining 83% accuracy, serving as an auxiliary consistency signal to support collar–animal association and reduce mis-attribution risks. We introduce a dynamically generated pre-shared key (PSK) mechanism based on SHA-256 hashes derived from motion features and timestamps, further securing communication channels via application-layer Hash-based Message Authentication Code (HMAC) combined with Message Queuing Telemetry Transport (MQTT)/Transport Layer Security (TLS) protocols. In our design, MQTT/TLS provides primary device authentication and channel protection, while behavioral fingerprinting and per-window dynamic–HMAC provide auxiliary provenance cues and tamper-evident integrity at the application layer. Experimental validation is conducted primarily via offline, dataset-driven experiments on a public canine IMU dataset; system-level overhead and sensor-to-edge latency are measured on a Raspberry Pi-based testbed by replaying windows through the MQTT/TLS pipeline. Overall, this work integrates motion recognition, behavioral fingerprinting, and dynamic key management into a cohesive, lightweight telemetry integrity/provenance stack and provides a foundation for future extensions to multi-species adaptive scenarios and federated learning applications. Full article

Drowsy driving contributes to roughly 20% of traffic fatalities, yet most detection systems rely on behavioral cues that appear only after impairment has set in. Here we ask whether first and second derivatives of heart rate variability (HRV) can detect pre-crash states earlier than conventional approaches. Twenty-five participants completed 49 driving simulator sessions while we recorded cardiac activity through capacitive ECG electrodes embedded in the seat backrest—a non-contact method that avoids the privacy concerns of camera-based monitoring. To prevent circular evaluation, ground truth labels were based solely on crash proximity rather than HRV-derived scores. The combined HRV feature set (conventional metrics plus derivatives) achieved AUC = 0.863 for pre-crash prediction; derivatives alone reached only AUC = 0.573, indicating their value as complementary rather than standalone features. Driving performance indicators remained the strongest predictors (AUC = 0.999). Temporally, derivative-based detection preceded behavioral manifestations by 5–8 min and crash events by 6.8 ± 2.3 min. Across 1591 crashes and 6.78 million data points, we found that HRV derivatives capture physiological changes that precede overt impairment, though their utility depends on integration with other feature types. Full article

Fragmented, irregular, and scale-heterogeneous farmland parcels introduce high spatial complexity into high-resolution remote sensing imagery, leading to boundary ambiguity and inter-class spectral confusion that hinder effective feature discrimination in semantic segmentation. To address these challenges, we propose CSMNet, which adopts a ConvNeXt V2 encoder for hierarchical representation learning and a multi-scale fusion architecture with redesigned skip connections and lateral outputs to reduce semantic gaps and preserve cross-scale information. An adaptive multi-head attention module dynamically integrates channel-wise, spatial, and global contextual cues through a lightweight gating mechanism, enhancing boundary awareness in structurally complex regions. To further improve robustness, a hybrid loss combining Binary Cross-Entropy and Dice loss is employed to alleviate class imbalance and ensure reliable extraction of small and fragmented parcels. Experimental results from Nong’an County demonstrate that the proposed model achieves superior performance compared with several state-of-the-art segmentation methods, attaining a Precision of 95.91%, a Recall of 93.95%, an F1-score of 94.92%, and an IoU of 90.85%. The IoU exceeds that of Unet++ by 8.92% and surpasses PSPNet, SegNet, DeepLabv3+, TransUNet, SeaFormer and SegMAN by more than 15%, 10%, 7%, 6%, 5% and 2%, respectively. These results indicate that CSMNet effectively improves information utilization and boundary delineation in complex agricultural landscapes. Full article

Effective dentist-patient communication underpins care, empowering informed decisions, reducing anxiety, improving efficiency, and fostering trust through clear, accurate, cohesive exchanges. This narrative review used a structured Medline search of literature, employing key terms to select and synthesize relevant English-language publications on dentist-patient communication without strict inclusion criteria. Key strategies include active listening, empathetic dialogue, patient-centred approaches, and the use of plain language and visual aids to demystify complex information. Additionally, integrating technology for appointment reminders, virtual consultations, and feedback mechanisms can streamline interactions. Crucially, cultural competency and sensitivity to individual needs ensure inclusivity and personalized care. Building on these findings, the study outlines ten actionable pillars for effective communication: (1) Initial Consultation: Establish rapport and gather comprehensive medical/dental histories. (2) Treatment Explanation: Simplify diagnoses and options using layman’s terms. (3) Informed Consent: Transparently discuss risks/benefits and invite questions. (4) Patient Education: Clarify oral hygiene practices and post-treatment expectations. (5) Anxiety Management: Address fears through reassurance and tailored coping strategies. (6) Follow-Up Care: Maintain post-treatment engagement to resolve concerns. (7) Feedback Systems: Leverage patient insights for service improvement. (8) Cultural Sensitivity: Adapt communication to diverse backgrounds. (9) Non-Verbal Cues: Employ positive body language and active listening. (10) Technology Integration: Utilize digital tools for efficiency and accessibility. By prioritizing empathy, clarity, and adaptability, clinicians can transform dental visits from anxiety-inducing encounters into collaborative partnerships. This approach not only elevates patient satisfaction and adherence but also redefines the standard of care, aligning clinical practice with the evolving needs of modern dentistry. Full article

In complex natural scenarios, facial expression recognition often encounters partial occlusions caused by glasses, hand gestures, and hairstyles, making it difficult for models to extract effective features and thereby reducing recognition accuracy. Existing methods often employ attention mechanisms to enhance expression-related features, but they fail to adequately address the issue where high-frequency responses in occluded regions can disperse attention weights (e.g., incorrectly focus on occluded areas), making it challenging to effectively utilize local cues around the occlusions and limiting performance improvement. To address this, this paper proposes a network based on an adaptive attention mechanism (Adaptive Attention Vision Transformer, AA-ViT). First, an Adaptive Attention module (ADA) is designed to dynamically adjust attention scores in occluded regions, enhancing the effective information in features. Next, a Dual-Branch Multi-Layer Perceptron (DB-MLP) replaces the single linear layer to improve feature representation and model classification capability. Additionally, a Random Erasure (RE) strategy is introduced to enhance model robustness. Finally, to address the issue of model training instability caused by class imbalance in the training dataset, a hybrid loss function combining Focal Loss and Cross-Entropy Loss is adopted to ensure training stability. Experimental results show that AA-ViT achieves expression recognition accuracies of 90.66% and 90.01% on the RAF-DB and FERPlus datasets, respectively, representing improvements of 4.58 and 18.9 percentage points over the baseline ViT model, with only a 24.3% increase in parameter count. Compared to existing methods, the proposed approach demonstrates superior performance in occluded facial expression recognition tasks. Full article

Malignant lymphoma and other cancer types remain major global health concerns due to their rapid progression and potential for fatal outcomes. Conventional diagnostic approaches are often invasive and time-consuming, contributing to delays in early detection and treatment. These limitations highlight the urgent need for more accurate, efficient, and non-invasive diagnostic solutions that support timely clinical decision-making. In this study, we introduce CancerNet-W, a deep learning (DL) model built upon EfficientNet-B3 for automated classification of breast and cervical cancers using histopathological images (HIs). The model incorporates an Intelligent Learning Rate Controller (ILRC) that adaptively optimizes the LR during training, enhancing stability and performance. The preprocessing pipeline includes data augmentation, resizing, and normalization for the two datasets to improve feature extraction. The Breast cancer HIs Classification (BreakHis) dataset contains 10,000 HIs and the Cervical cancer (SipaKMed) dataset consists of 25,000 images. Importantly, the model leverages morphological cues such as cellular symmetry, which plays a key role in differentiating normal tissue, typically exhibiting more symmetric cellular organization—from malignant tissue, where cancer progression disrupts structural symmetry and leads to notable nuclear and architectural asymmetry, a hallmark of breast and cervical malignancies. This observation aligns with established findings on symmetry breaking in tumorigenesis and nuclear pleomorphism in cancer pathology. CancerNet-W achieved remarkable performance as a general model, yielding 100% accuracy for cervical cancer and 99.89% for breast cancer, outperforming state-of-the-art models including EfficientNet-B4, EfficientNet-B5, DenseNet-201, and MobileNet-V2. To promote strong learning and reduce overfitting, stratified five-fold cross-validation was utilized for the training-validation dataset. Model selection and optimization were based solely on validation performance. An independent test set, kept separate from both training and validation, was employed for final evaluation. The results, accuracy at 98.11% for breast cancer and 99.60% for cervical cancer, reflect the average test performance from the model trained across the five folds. Therefore, the proposed framework provides consistent and dependable diagnostic predictions while significantly reducing the time and cost associated with cancer detection, demonstrating its potential as a valuable tool for clinical applications. Full article

Deep learning–based pansharpening methods for remote sensing have advanced rapidly in recent years. However, current methods still face three limitations that directly affect reconstruction quality. Content adaptivity is often implemented as an isolated step, which prevents effective interaction across scales and feature domains. Dynamic multi-scale mechanisms also remain constrained, since their scale selection is usually guided by global statistics and ignores regional heterogeneity. Moreover, frequency and spatial cues are commonly fused in a static manner, leading to an imbalance between global structural enhancement and local texture preservation. To address these issues, we design three complementary modules. We utilize the Adaptive Convolution Unit (ACU) to generate content-aware kernels through local feature clustering, thereby achieving fine-grained adaptation to diverse ground structures. We also develop the Multi-Scale Receptive Field Selection Unit (MSRFU), a module providing flexible scale modeling by selecting informative branches at varying receptive fields. Meanwhile, we incorporate the Frequency–Spatial Attention Unit (FSAU), designed to dynamically fuse spatial representations with frequency information. This effectively strengthens detail reconstruction while minimizing spectral distortion. Specifically, we propose the Hybrid Attention Fusion Network (HAFNet), which employs the Hybrid Attention-Driven Residual Block (HARB) as the fundamental utility to dynamically integrate the above three specialized components. This design enables dynamic content adaptivity, multi-scale responsiveness, and cross-domain feature fusion within a unified framework. Experiments on public benchmarks confirm the effectiveness of each component and demonstrate HAFNet’s state-of-the-art performance. Full article

Digital transformation in water conservancy and urban water utilities demands perception systems that are accurate, fast, and energy-efficient and maintainable over long service lifecycles at the edge. We present HydroSNN, a neuromorphic computer-vision framework that couples an event-driven sensing pipeline with a spiking-transformer backbone to support monitoring of canals, reservoirs, treatment plants, and buried pipeline networks. By reducing always-on compute and unnecessary data movement, HydroSNN targets sustainability goals in smart water infrastructure: lower operational energy use, fewer site visits, and improved resilience under harsh illumination and weather. HydroSNN introduces three novel components: (i) spiking temporal tokenization (STT), which converts asynchronous events and optional frames into latency-aware spike tokens while preserving motion cues relevant to hydraulics; (ii) physics-guided spiking attention (PGSA), which injects lightweight mass-conservation/continuity constraints into attention weights via a differentiable regularizer to suppress physically implausible interactions; and (iii) cross-modal self-supervision (CM-SSL), which aligns RGB frames, event streams, and low-cost acoustic/vibration traces using masked prediction to reduce annotation requirements. We evaluate HydroSNN on public water-surface and event-vision benchmarks (MaSTr1325, SeaDronesSee, DSEC, MVSEC, DAVIS, and DDD20) and report accuracy, latency, and an operation-based energy proxy. HydroSNN improves mIoU/F1 over strong CNN/ViT baselines while reducing end-to-end latency and the estimated energy proxy in event-driven settings. These efficiency gains are practically relevant for off-grid or power-constrained deployments and support sustainable development by enabling continuous, low-power monitoring and timely anomaly response. These results demonstrate that event-driven spiking vision, augmented with simple physics guidance, offers a practical and efficient solution for resilient perception in smart water infrastructure. Full article

Human iPSC-derived cardiomyocytes (iPSC-CMs) exhibit fetal-like mitochondrial networks and limited oxidative metabolism, constraining their translational utility. The key bottleneck is mitochondrial immaturity, resulting from blunted PGC-1α–NRF1/2–TFAM axis activation and insufficient nuclear–mitochondrial coordination, rather than sarcomeric or electrophysiological immaturity alone. This review synthesizes genome-guided interventions (CRISPRa and mtDNA editing) and complementary environmental strategies—including metabolic substrate switching, electromechanical stimulation, and extracellular vesicle (EV)-mediated mitochondrial transfer—to drive mitochondrial biogenesis and maturation in iPSC-CMs. We systematically reviewed studies (2005–2025) targeting (1) key regulators of mitochondrial biogenesis (PGC-1α, NRF1/2, TFAM), (2) CRISPR-based transcriptional activators/repressors and mtDNA editors (DdCBE, mitoTALENs), and (3) maturation approaches such as metabolic conditioning, electromechanical stimulation, 3D tissue culture, and EV-mediated mitochondrial transfer. CRISPRa-mediated activation of PGC-1α, NRF1, and GATA4, combined with mtDNA base editors, enhances mitochondrial mass and OXPHOS function, while integration with environmental maturation strategies further promotes adult-like phenotypes. Integrative approaches that combine genome-guided interventions (CRISPRa, mtDNA editing) with environmental maturation cues yield the most adult-like iPSC-CM phenotypes reported to date. CRISPR-guided mitochondrial biogenesis thus represents a frontier for producing metabolically competent, structurally mature iPSC-CMs for disease modeling and therapy. Remaining translational challenges include efficient mitochondrial delivery, metabolic homeostasis, and multi-omics validation. We propose standardized workflows to couple nuclear and mitochondrial editing with maturation strategies. Full article

Background: Parkinson’s disease (PD) is characterized by motor disturbances that significantly impact balance, gait, and quality of life. Personalized Rhythmic Auditory Stimulation (pRAS) is an emerging rehabilitative approach that utilizes auditory entrainment to improve step and gait control. The aim of this systematic review is to critically summarize the data from the most recent evidence concerning the use of pRAS in gait rehabilitation for patients with Parkinson’s disease. Methods: A systematic review was conducted following PRISMA guidelines, including records that evaluated music-based or technological interventions based on personalized RAS. Primary outcomes included spatiotemporal gait parameters and distance covered. Results: Ten studies were included in the analysis. All the studies reported clinically relevant improvements: increases in gait speed, step length, and amplitude. Moreover, a reduction in freezing of gait episodes (up to 36%), greater walking distance, and good adherence were reported. Conclusions: Personalized, adaptive, or on-demand solutions proved more effective than traditional forms of cueing. Moreover, the available evidence suggests that pRAS constitutes an effective and safe rehabilitative option for gait disturbances in PD. However, further studies with larger sample sizes and prolonged follow-up periods are necessary to evaluate its long-term impact and transferability into clinical practice. Full article

Graph anomaly detection (GAD) is pivotal for security-critical applications like cybersecurity and financial fraud detection. While reconstruction-based Graph Neural Networks (GNNs) are prevalent, their efficacy is often compromised by two phenomena: (1) anomaly overfitting, where expressive models capture anomalous patterns, and (2) homophily-induced attenuation, where message passing smooths localized anomaly cues. This paper proposes CLEAN-GAD, a contamination-aware framework that mitigates anomaly influence during training through multi-view robust learning. Specifically, we develop a contrastive augmentation module that utilizes local inconsistency scores to identify and suppress pseudo-anomalous nodes and edges, thereby yielding a purified augmented view. To capture diverse anomaly signals, a frequency-adaptive encoder with dual-pass channels is designed to integrate low- and high-frequency information. Furthermore, we introduce a distribution-separation regularizer and cross-view alignment to stabilize learning and resolve view shifts. Theoretical analysis confirms that reducing the contamination ratio $\rho$ expands the reconstruction-risk gap between normal and anomalous nodes, inherently boosting detection performance. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance of CLEAN-GAD. Full article