Search Results (1,981)

Emotion recognition from physiological signals has immense applications in healthcare and human–computer interaction. We developed an electrodermal activity (EDA)-graph signal processing pipeline that produces highly sensitive features for detecting the affective dimensions (arousal and valence) of emotions. Using the Continuously Annotated Signals of Emotion dataset, we compared our graph-based EDA features (EDA-graph) with traditional time- and frequency-domain EDA features and features derived from other signals (heart rate variability, pulse transit time, electromyography, skin temperature, and respiration) for detecting affective dimensions using machine learning regression models. The EDA-graph features showed superior performance in continuous affective dimension recognition compared to the most accurate state-of-the-art models, achieving RMSE values of 0.801 for arousal and 0.714 for valence. Furthermore, we used a variety of traditional and recently published datasets collected in laboratory and ambulatory settings to perform a comprehensive evaluation of the robust generalization capabilities of our approach across different emotional contexts. The models demonstrated exceptional performance in classifying emotional states across the datasets, achieving 98.2% accuracy in detecting positive, negative, and mixed emotions; 92.75% in discriminating between emotions (relaxed, amused, bored, scared, and neutral); and 86.54% in detecting stress vs. no stress. These results highlight the potential of a graph-based analysis of EDA in emotion recognition systems in different contexts, especially for real-world applications. Full article

As a non-invasive mucosal immunization strategy, intranasal vaccines are highly promising for preventing respiratory infectious diseases. Among them, recombinant subunit vaccines represent a safe and ideal option, as they induce targeted mucosal immunity without the safety risks associated with live-vectored or nucleic acid vaccines. However, nasal mucosal defenses rapidly clear antigens before immune activation, limiting protective efficacy. Therefore, intranasal vaccine adjuvants—key regulators of immune response intensity, duration, and type—are essential to overcome mucosal tolerance and improve immunogenicity. Based on a systematic search and analysis of 127 peer-reviewed articles (2010–2026) in PubMed, Web of Science, and Embase, this study comprehensively summarizes the mechanisms, applications, and limitations of existing and candidate adjuvants for intranasal vaccines. This review systematically categorizes and discusses the nasal mucosal barrier, major adjuvant types (e.g., pattern recognition receptor agonists, cytokine adjuvants, and carrier adjuvants), and their mechanisms of action. It also identifies key bottlenecks: insufficient mucosal targeting, inconsistent global safety evaluation standards for adjuvants, and interference from pre-existing antibodies in humans. Furthermore, this review highlights future development directions, including biomimetic adjuvants, pH-responsive nanoadjuvants, and thermostable vaccine formulations. This systematic review clarifies key scientific and technical barriers in intranasal vaccine adjuvant development. The findings provide valuable references for advancing the translation of intranasal vaccines from emergency countermeasures to routine, accessible preventive tools for respiratory infectious diseases. Full article

Wearable device-based Human Activity Recognition (HAR) is widely used in health management, rehabilitation, and personal safety. While contemporary HAR research effectively classifies a wide range of discrete activities, there remains a significant gap in organizing these heterogeneous motions into a structured intensity framework suitable for continuous risk assessment. Furthermore, many high-performing models rely on computationally intensive architectures that hinder real-time deployment on resource-constrained wearables. We propose an on-device method for estimating five-level activity intensity in real time using only accelerometer signals from a commercial smartwatch. To bridge the gap between simple identification and intensity modeling, 13 dynamic and emergency-like wrist motions were integrated with 11 daily activities from the PAMAP2 dataset, yielding 21 activities mapped onto an ordinal five-level intensity scale. A finetuned Multi-Layer Perceptron (MLP) classifier trained on this integrated dataset achieved 0.939 accuracy and a quadratic weighted kappa (QWK) of 0.971. The model was deployed on a Galaxy Watch 7, achieving $<1$ ms inference latency and a size $<0.1$ MB, confirming real-time feasibility. This approach demonstrates that organizing diverse activities into a lightweight, intensity-aware framework provides a robust foundation for safety-aware monitoring systems under real-world, on-device constraints. Full article

The development of the human brain starts with the orchestrated expression of our genes during embryogenesis. Non-protein-coding DNA sequences (gene promoters and enhancers) dynamically interact to form a three-dimensional (3D) network, orchestrating gene expression. We discuss novel perspectives on how DNA sequence variants within regulatory DNA, identified by whole-genome sequencing (WGS), contribute to the development of neurodevelopmental disorders (NDDs), including autism spectrum disorders (ASDs). We discuss two recent models explaining the evolution of a subset of regulatory sequences, Human Accelerated DNA Regions (HARs), proposed to be involved in the evolution of uniquely human brain features through their participation in the 3D interactions network. We connect this with the recent proposal that rare, recessive inherited sequence variants within HARs, interacting with distant target genes in neural cells, represent risk factors for the development of ASDs. The SOX2 transcription factor, whose heterozygous mutation causes NDDs, shapes the noncoding-DNA interaction network in neural cells, and binds DNA together with FOS, whose recognition sequence is enriched within HARs carrying human-specific substitutions modulating enhancer activity. SOX2 also binds regulatory regions (including HARs) carrying ASD-associated mutations. We highlight research directions based on these findings, which will hopefully improve our understanding of the connection between SOX2-dependent gene regulatory networks, NDDs, and brain evolution. Full article

Human Activity Recognition (HAR) is a pivotal research area for applications such as automated surveillance, smart homes, security, healthcare, and human behavior analysis. Traditional machine-learning approaches often rely on manual feature engineering, which can limit generalization. Although deep learning has improved HAR through automatic representation learning, achieving high detection performance under computational constraints remains challenging. This paper proposes an efficient HAR framework that combines deep learning with hybrid optimization. Surveillance videos are first decomposed into frames, and a keyframe selection stage identifies distinctive frames to reduce redundancy and computational cost while preserving informative content. Motion and appearance features are then extracted using Histogram of Oriented Optical Flow (HOOF) and a ResNet-101 model, respectively, and concatenated into a unified feature representation. Classification is performed using an Inception-based Long Short-Term Memory (Incept-LSTM) network, which is fine-tuned via the proposed Tricky Predator Optimization (TricP) over a restricted, low-dimensional parameter vector. TricP is inspired by predator poaching behavior and the social dynamics of Latrans to enhance exploration and exploitation during search. Experiments on the UCF-Crime dataset show that the proposed method achieves 96.84% specificity, 92.16% sensitivity, and 93.62% accuracy. Full article

On university campuses, trees and green spaces shape how students and staff move and use outdoor spaces. To support planning, tree species information is needed at the level of individual trees. Tree species classification from UAV RGB imagery remains difficult in complex campus scenes because roads, buildings, shadows and subtle inter species differences degrade recognition. To address background interference, the loss of subtle fine-grained cues before tokenization, and insufficient local structure modeling in lightweight transformer-based classification, we propose TreeSpecViT for tree species classification. It uses a MobileViT backbone and a Background Suppression Module (BSM) to reduce clutter from non-canopy regions. A Fine-Grained Feature Guidance (FGF) module is inserted before the unfold operation to enhance canopy details and guide tokenization toward key regions. $1\times 1$ convolutional neck layers align channels, and a Global and Local Fusion (GLF) module jointly models overall crown semantics and local textures for species recognition. From the predicted masks and species labels, we build an individual tree digital archive. The archive stores per tree geometric attributes and can be linked with grids of campus activity intensity to analyze how activity patterns relate to vegetation structure. TreeSpecViT achieves an Accuracy of 87.88% (+6.06%) and an F1 score of 76.48% (+5.08%) on the SZUTreeDataset. On our self constructed NJFUDataset, it reaches 76.30% (+5.10%) in Accuracy and 70.10% (+7.20%) in F1. These results surpass mainstream models. Ablation experiments show that the modules jointly reduce background clutter and enhance canopy features. Overall, TreeSpecViT supports campus scale analyses that link human activity intensity to vegetation patterns and provides a practical basis for planning and adjusting campus green spaces. Full article

Concrete placement surfaces are characterized by intensive construction processes, frequent equipment interactions, and strong spatial dynamics, which make it difficult to identify unsafe actions of construction workers in real time and to accurately quantify and warn about regional safety risks. To address these challenges, this study proposes a safety monitoring method for construction workers operating on complex concrete placement surfaces. First, a coupled risk assessment framework integrating regional hazard levels, unsafe action risks, and worker authorization is established based on trajectory intersection theory (TIT). Subsequently, a multi-source continuous sensing system is developed by integrating global navigation satellite system (GNSS) positioning, inertial measurement unit (IMU)-based human activity recognition (HAR) using a BiLSTM-Attention model, and unmanned aerial vehicle (UAV)-based 3D realistic scene modeling. On this basis, real-time visualization and risk warning of worker trajectories, action states, and spatial risks are achieved through multi-source data fusion and a WebGL-based visualization platform. Field validation results indicate that the proposed system can generate alarm outputs that are consistent with the predefined risk rules within 3 s in typical construction scenarios, demonstrating rule-consistent real-time feasibility and stable system response performance. Full article

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disorder in the aging population. Drug repurposing provides a cost-effective strategy to identify novel therapeutics that may mitigate age-associated pathologies. Here, we report the therapeutic potential of fluoxetine, a selective serotonin reuptake inhibitor commonly used as an antidepressant, in alleviating cognitive impairment and AD-like pathology in 5xFAD mice, a transgenic model of familial AD. Chronic fluoxetine administration significantly ameliorated anxiety-like behavior and cognitive deficits in 5xFAD mice, as assessed by open field, Y-maze, and novel object recognition tests. Fluoxetine treatment was associated with reduced amyloid plaque deposition in the hippocampus and cortex, attenuation of microglial activation, and decreased expression of inflammatory cytokines. At the molecular level, fluoxetine increased phosphorylation of GSK3β at Ser9, which was associated with enhanced CREB phosphorylation and upregulation of the α-secretase ADAM10. These effects were further examined in SH-SY5Y neuronal cells, where CREB phosphorylation and ADAM10 expression were significantly modulated by GSK3β inhibition, whereas CaMKII inhibition had no detectable effect under our experimental conditions. Our findings suggest that fluoxetine modulates amyloid-associated signaling pathways in the 5xFAD model, in part through regulation of the GSK3β-CREB signaling framework. These results provide mechanistic insight into how fluoxetine may influence APP processing in an amyloid-driven pathological context, although further studies are required to clarify its translational implications in human AD. Full article

This study investigates efficient thermal-image human pose estimation under edge deployment constraints for smart home activity recognition. A single-person thermal dataset of 2500 images was collected and annotated with 17 body keypoints. YOLO11-pose and YOLOv8-pose models were trained and evaluated across all five model scales (n–x) at three input resolutions 640 × 512, 320 × 256, and 160 × 128 px. The accuracy was evaluated using box mean Average Precision (mAP50–95), pose mAP50–95, and Object Keypoint Similarity (OKS) metrics. Runtime performance was assessed using per-image latency and power measurements on three NVIDIA Jetson platforms: Orin Nano 4 GB, Orin Nano 8 GB and AGX Orin 64 GB, using PyTorch and TensorRT at FP32, FP16, INT8 precision. Human detection remained consistently high across model variants, whereas pose accuracy decreased as the input resolution was reduced. TensorRT FP16 preserved pose accuracy relative to PyTorch and TensorRT FP32, with minimal changes in OKS and pose mAP50–95, while notably reducing per-image latency and power consumption. INT8 further reduced power consumption and in some configurations improved latency, but caused configuration-dependent losses in OKS and pose mAP50–95. The findings indicate that FP16 offers the best accuracy–efficiency balance for thermal pose estimation on edge devices, while practical feasibility depends on device capabilities and memory limitations. Full article

Multi-sensor-based human activity recognition (HAR) models trained with deep learning often exhibit limited generalization when applied to data collected under conditions different from those seen during training. To alleviate this issue, we present an adversarial domain adaptation framework that incorporates contrastive group construction to promote class-aware feature alignment. Specifically, augmented and perturbed sample groups are generated in both source and target domains and optimized through contrastive learning objectives, allowing the feature extractor to compact semantically similar representations while separating dissimilar ones without relying on target-domain annotations. This joint design preserves semantic structure while reducing cross-domain distribution discrepancies, resulting in representations that are both domain-invariant and discriminative. Experiments conducted on the Opportunity dataset validate the effectiveness of the proposed approach, demonstrating consistent performance gains over representative unsupervised domain adaptation methods. Full article

Plant defence elicitors have emerged as pivotal components of sustainable fruit crop protection, aligning with One Health principles by reducing chemical residues while enhancing ecosystem and human health. These exogenous agents—ranging from phytohormones, peptides, and cell-wall fragments to botanical extracts—activate or prime innate immune responses in fruit crops through pattern-triggered immunity (PTI), systemic acquired resistance (SAR), and induced systemic resistance (ISR) pathways. Over the last decade, advances in receptor biochemistry, genomics, metabolomics, and epigenetics have transformed this field. Recent mechanistic advances reveal that oligosaccharide elicitors derived from chitosan and laminarin are perceived by membrane-localised pattern recognition receptors (PRRs) that confer broad-spectrum resistance against fungal, bacterial, and viral pathogens in fruits. By contrast, no specific protein receptor has been identified for harpin proteins, the emerging evidence indicating that harpin perception may occur through direct interaction with plasma-membrane lipids or lipid-associated proteins. The One Health approach is supported by elicitors, biodegradability, minimal environmental persistence, and the ability to reduce synthetic fungicide usage by 30–70%. However, challenges remain regarding batch-to-batch variability, sensory acceptance due to bitter compounds, regulatory hurdles for novel food approvals, and the need for optimised application protocols that consider the fruit genotype and developmental stage. The future integration of nanotechnology for targeted delivery, the artificial-intelligence-driven screening of active molecules, and synergistic combinations with biocontrol agents promises to overcome these limitations, positioning plant defence elicitors as cornerstone tools for resilient, health-promoting fruit production systems. Full article

CD38 is a multifunctional enzyme that plays a pivotal role in NAD⁺ metabolism and calcium signaling, and its abnormal activity is closely associated with multiple myeloma, age-related metabolic decline, neurodegenerative diseases, and other disorders. Although monoclonal antibodies such as daratumumab have been approved for clinical application, their inherent limitations necessitate the development of novel small-molecule CD38 inhibitors. In this study, we employed DNA-encoded library (DEL) technology for the high-throughput screening of CD38 inhibitors, using a DEL library containing more than 100,000 unique compounds to screen against recombinant human CD38. A total of 1043 enriched compounds were initially identified, and after rigorous validation and screening to exclude non-specific binding and previously reported active compounds, eight hit compounds with diverse chemical scaffolds were obtained, among which Fenbendazole—a clinically approved antiparasitic drug—was included. Surface plasmon resonance (SPR) assays confirmed the direct binding of these hit compounds to CD38, with dissociation constants (KD) ranging from 7.74 × 10⁻⁵ M to 2.15 × 10⁻⁴ M. Fluorescence-based enzymatic activity assays demonstrated that these compounds exert dose-dependent inhibitory effects on both the hydrolase (with ε-NAD as substrate) and cyclase (with NGD as substrate) activities of CD38. Further structure–activity relationship (SAR) analysis of Fenbendazole analogues revealed the critical structural features that regulate CD38 inhibitory potency, and Flubendazole was found to exhibit excellent inhibitory activity, with an IC₅₀ of 14.78 ± 4.21 μM against CD38 hydrolase and 26.31 ± 3.40 μM against cyclase. Molecular docking and 100 ns molecular dynamics (MD) simulations further elucidated the molecular mechanism of CD38 inhibition by lead compounds, confirming that van der Waals interactions are the main driving force for the binding of small-molecule ligands to CD38, with conserved aromatic residues in the active site mediating ligand recognition. This study validates DEL technology as an efficient and reliable platform for the discovery of CD38 inhibitors, and the identified lead compounds—especially Fenbendazole and its analog Flubendazole—provide valuable molecular scaffolds for the further structural optimization of CD38 inhibitors. These findings lay a solid foundation for the development of novel therapeutic agents for the treatment of CD38-associated diseases. Full article

The use of artificial intelligence (AI) to recognize postures is a promising approach for the prevention of work-related musculoskeletal disorders (WMSDs). The aim was to conduct a systematic review with meta-analysis to assess the performance of work posture recognition systems during occupational activity. The results were reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The Google Scholar, IEEE Xplore, PubMed/MedLine, and ScienceDirect databases were screened without date restrictions. Two authors independently selected articles and extracted data. Studies were included if they presented a performance analysis of an AI deep learning (DL) or machine learning (ML) method that assessed the WMSD risk associated with working postures. Only peer-reviewed studies written in English including accuracy, precision, specificity, sensitivity, or F1-score values were included. The risk of bias was assessed using the Prediction Model Study Risk of Bias Assessment Tool. Of the 157 unique records, 58 studies were selected. The five performance parameters were investigated and averaged for seven occupational activities, eight posture categories, and the AI methods (ML vs. DL). Statistical analyses showed that DL methods produced better results. The reported systems detected sitting and standing postures with high accuracy. The solutions proposed in Manufacturing and Construction were the most numerous and the most effective on average. The major limitation lies in the wide variety of methods used. This analysis is a valuable source of information for designing new detection systems that are effective, ergonomic, easy to use, and acceptable so that humans remain at the center of the production process as defined by Industry 5.0. Full article

An intelligent multi-step action recognition system was designed for long-term caregiver training and assessment. Leveraging MediaPipe for precise and real-time human pose estimation, the system extracts detailed spatiotemporal body and hand keypoints. Temporal convolutional networks are employed to effectively capture temporal dependencies and complex features from sequential motion data. Dynamic time warping provides robust sequence alignment, allowing flexible comparison between performed actions and standard templates despite temporal variations in execution speed or style. A finite state machine imposes logical constraints by modeling expected action step sequences, enabling accurate detection of sequence anomalies or deviations. This hybrid architecture supports comprehensive evaluation and real-time feedback, facilitating improved caregiver skill acquisition, process adherence, and quality control within long-term care settings. The system aims to advance digital transformation in healthcare education by providing a scalable, precise, and adaptive training solution. Full article

Human rhinovirus (HRV) is one of the common respiratory viral infection agents that triggers airway obstruction and asthma exacerbations, especially during childhood. This project aimed at evaluating the mechanism of ultraviolet (UV) and infrared (IR) radiations to inactivate HRV infection and replication inside and outside infected airway epithelial cells and the resulting impact on interferon responses and epithelial barrier integrity. Hereby, airway epithelial cells were infected with different RV concentrations. Later these cells are exposed to UV and IR light to analyze their impact on the viral immune response of the host by real-time PCR. It was found that RV1B disrupted cell junctions of airway epithelial cell barriers. Moreover, high doses of RV1B activated pattern recognition receptor (TLR3), induced interferon (IFN-β) response and reduced SOCS1, which is a negative regulator of IFN-β. Further, IR lights inhibited rhinovirus post infection in primary nasal epithelial cells (NECs). Finally, UVC exposure significantly inhibited the antiviral effects of the host via SOCS1 inhibition and decreased RV1B within 72 h. Collectively, these findings support the role of UV light as an effective therapeutic approach for acutely eliminating RV but resulting in barrier and antiviral damage, which can have a drawback effect for asthma. Full article