Search Results (147)

This study proposes a real-time multi-factor behavioral monitoring framework for Computer Vision Syndrome (CVS) using computer vision techniques and TensorFlow for browser-based implementation. Four vision-based detection pipelines—Dlib-based, MediaPipe-based, CNN-based, and TensorFlow-based implementations—were evaluated to identify a suitable configuration for real-time deployment. The selected browser-based implementation integrated MediaPipeFaceMesh for facial landmark extraction and MoveNet SinglePose Lightning for supplementary pose-related detection. During the pipeline-selection stage, the Dlib-based pipeline showed high task-specific accuracy in blink detection (0.9034) and head pose estimation (0.9005), while the MediaPipe-based pipeline provided the highest processing speed for these tasks, with 73.09 FPS and 75.36 FPS, respectively. The CNN-based baseline showed limited real-time suitability, with low F1-scores and FPS values ranging from 4.22 to 7.32 across tasks. These preliminary comparison results informed the selection of the browser-based pipeline, which provided the most practical trade-off among detection performance, real-time processing capability, browser-based execution, and deployment flexibility. In blink detection, the selected pipeline achieved a precision of 0.8906, a recall of 0.9490, an F1-score of 0.9189, and 13.94 FPS. The proposed framework integrates five core operational indicators: viewing distance, vertical viewing deviation, horizontal viewing deviation, blink rate, and continuous usage duration. These indicators support rule-based real-time alerts and session-based behavioral pattern analysis. After implementation, the prototype operated in real time, detected concurrent CVS-related behavioral conditions, generated interpretable rule-based alerts, and summarized recurring behavioral patterns across a monitoring session. A controlled alert-level evaluation further indicated that the warning layer operated consistently for most rule-based alert conditions, although low-blink and prolonged-focus alerts require further refinement. These findings highlight the potential of combining browser-based visual detection with interpretable operational indicators for practical CVS-related behavioral monitoring. Full article

With the development of human–computer interaction technology, non-contact interaction based on gaze tracking and facial movements has become a research hotspot. Traditional mouse-and-keyboard methods pose challenges for people with disabilities or limited hand movements, while existing gaze-tracking systems often rely on expensive hardware or lack sufficient accuracy. This paper designs and implements a real-time system using ordinary cameras, achieving natural, efficient interaction via multimodal input combination. The system uses an improved MobileNetV2 backbone to construct GazeTrackNet for gaze estimation. It adopts MediaPipe Face Mesh to detect facial landmarks. Meanwhile, it applies geometric feature analysis, including eye aspect ratio and mouth aspect ratio, to identify actions such as blinking and mouth opening. It adopts a hybrid control strategy that combines gaze jumping and head fine-tuning, using mouth state as the main control switch. Key contributions include a lightweight gaze-tracking algorithm that enables stable and efficient gaze detection on consumer-grade hardware, a multimodal interaction strategy based on facial movement that improves system stability and ease of use, and a complete prototype system that achieves real-time performance on standard laptops. Experimental results show an average gaze average angle error of 3.0°, 97% eye state recognition accuracy, and end-to-end latency below 70 ms. The system can satisfy the requirements of daily desktop interaction under normal indoor lighting, and shows potential for future barrier-free interaction applications after further validation with target users. Existing gaze-tracking methods either suffer from low precision on lightweight devices or bring heavy computational overhead. Common facial recognition approaches also face frequent false trigger interference. Compared with them, our scheme achieves balanced accuracy and real-time performance via an attention-enhanced structure, and the designed dual anti-shake mechanism effectively suppresses misjudgment, delivering a more stable hands-free interaction experience. Full article

As an important reproductive trait, teat number plays a vital role in the pork industry, which is related to the ability of sows to host more piglets. However, the genetic mechanism of the teat number in pigs is still not very clear. We collected phenotype data, including the total teat number (TTN), left teat number (LTN), and right teat number (RTN), from 300 Jishen Black (JSB) sows and performed genotyping using a porcine SNP 50K panel. Most JSB sows exhibited 14, 15, or 16 TTN (259, 86%). Only 41 pigs (14%) had TTN values outside this range. Moreover, the LTN and TTN exhibited approximate frequency distribution in the studied population. Seven was the most common LTN and RTN in JSB sows, accounting for 181 (60%) and 173 (57%), respectively. Additionally, these traits exhibited low-to-medium heritability (0.14–0.22). Using the BLINK and FarmCPU models, three, six, and three key loci were identified in the GWAS of TTN, LTN, and RTN, respectively. Additionally, five key genes were detected to play vital roles in teat number traits, including ME1, SCN8A, EVC, UBC, and PDE4D. Our research provided efficient molecular markers and new insights into further improvement and understanding for teat number traits in Jishen Black pigs. Full article

Verticillium wilt of hop (Humulus lupulus L.), caused by the soil-borne pathogen Verticillium nonalfalfae, is a devastating disease with no effective chemical control. In European hop-growing regions, breeding resistant cultivars is the most effective strategy. The lack of response differences in earlier studies suggests constitutive resistance. We therefore conducted a genome-wide association study (GWAS) using a phased hop genome assembly to improve detection of Verticillium resistance loci. A bi-parental population of 142 genotypes, derived from a cross between resistant Wye Target and susceptible BL2/1, was phenotyped for Verticillium wilt resistance and genotyped by sequencing. Association analyses with five statistical models (MLM in TASSEL 5, MLM, MLMM, FarmCPU and BLINK in GAPIT) did not identify any significant SNPs; however, several candidate loci were identified using exploratory threshold, particularly in the phase 2 genome assembly, including a wall-associated kinase (WAK) consistently detected across both genome phases and all models. GWAS results were further assessed with a Random Forest model, which identified SNPs of high feature importance and showed adequate predictive power (accuracy ≈ 0.4, correlation ≈ 0.8) for preliminary breeding screening. These findings provide an initial set of candidate markers and exploratory prediction models for Verticillium wilt resistance in hop, representing a valuable genomic resource for future marker-assisted selection and breeding strategies. Full article

This article presents the design, implementation, and experimental validation of an autonomous drone system for search and rescue operations in cluttered GNSS-denied environments. The proposed platform integrates advanced navigation, mapping, and victim-detection capabilities, leveraging a suite of RGB-D cameras and edge-AI computation for real-time perception and decision-making. A key contribution is the integration of an eye-blink-detection pipeline for onboard assessment of the consciousness states of detected victims, enabling the drone to prioritize rescue efforts based on victim alertness. The system employs a modular software architecture with a pipeline that combines a U-Net segmentation network with a MultiScaleLSTM classifier, achieving approximately 97.73% accuracy and a combined inference latency of 6.35 ms on the NVIDIA Jetson Xavier-NX. Experimental results demonstrate the drone’s ability to autonomously explore unknown environments, accurately detect and classify victims, and operate effectively in real-world scenarios. The article also discusses observed challenges, such as computational bottlenecks and false positive detections, and outlines future directions for improving system robustness and autonomy. Full article

This study investigates how chromatic manipulation of cinematic content modulates emotional engagement, with specific attention to sex-differentiated responses. We used a mixed factorial design with chromatic condition as a within-subject factor and biological sex as a between-subject factor, counterbalanced across scenes through a 3 × 3 Latin square that renders scene identity orthogonal to chromatic condition by construction. Thirty adult viewers were recorded with synchronised facial-expression analysis (AFFDEX 5.1), blink detection, and galvanic skin response (Shimmer GSR). The primary inferential target was the Condition × Sex interaction on automated positive facial valence. This interaction was statistically reliable under three converging tests: a mixed-effects model (${\beta }_{\mathrm{Mod}\times \mathrm{F}}=-4.48$, $SE=2.16$, 95% CI $[-8.81,-0.14]$, $p=0.043$), a participant-level cluster bootstrap (2000 resamples; 95% percentile CI $[-9.78,-0.63]$; $p_{\mathrm{boot}}=0.011$), and a label-permutation test. The effect was stable under leave-one-subject-out resampling (100% sign-stability) and persisted after introducing scene as a fixed factor. Blink rate and electrodermal activation showed directionally consistent but weaker interaction patterns. A multidimensional engagement framework that separates attentional-autonomic intensity from expressive valence supports interpretation of the finding as specific to expressive affective behavior rather than to overall activation. The results provide empirical evidence that chromatic manipulation in realistic cinematic stimuli modulates expressive affective responses in a sex-dependent manner, and they establish a reproducible multimodal biometric framework for chromatic impact assessment. Full article

Driver drowsiness detection has become an important application of sensor-based monitoring systems aimed at improving road safety. This review focuses on sensing technologies and physiological parameters used for real-time drowsiness detection in drivers. The surveyed approaches are categorized into physiological sensing methods, including electroencephalography (EEG), electrocardiography (ECG), galvanic skin response (GSR), and photoplethysmography (PPG), and mechanical sensing methods, including respiration rate, eye blinking, head movement, yawning, and steering wheel gripping force. Each method is analyzed from a sensor system perspective, considering signal acquisition principles, measurement location, and practical deployment constraints. In addition, the reviewed techniques are evaluated based on real-time capability, level of sensor attachment, cost, restriction of user movement, and suitability for standalone operation. The comparison highlights that mechanical sensing approaches provide non-invasive and cost-effective solutions; however, they are sensitive to environmental noise and behavioral variability. In contrast, physiological sensing methods offer more direct and earlier indicators of fatigue-related changes in biosignals, although they typically require wearable or contact-based sensors and more complex acquisition systems. The review further indicates that multimodal sensor fusion is increasingly being adopted to improve robustness and reliability in real-world driving conditions. Overall, this work provides a structured overview of sensing modalities and highlights key considerations for designing efficient, real-time driver monitoring systems. Full article

Accurate biomolecule quantification at ultralow concentrations remains a major challenge because conventional ensemble assays report population averaged signals and therefore lose sensitivity in low-abundance regimes. Single molecule fluorescence counting can overcome this limitation by converting emission into discrete digital events, but practical implementation is often hindered by manual inspection, limited reproducibility, and the complexity of machine learning based analysis. Here, we present a simple and general analytical framework for rapid single molecule detection based on a deterministic threshold algorithm that exploits the temporal signature of fluorescence blinking. The method operates directly on time resolved fluorescence image stacks, applies median filter-based noise suppression, and identifies candidate single molecule events from consecutive frame-to-frame intensity transitions without the need for training data or model fitting. Applied to Alexa Fluor 488, Alexa Fluor 647, and Rhodamine Red–X datasets, the approach reproduced the concentration dependent trends observed by manual counting, while providing more standardized detection under weak signal and high background conditions. Dye specific operating thresholds yielded robust counting behavior and preserved approximately linear concentration dependent response across the tested range. Compared with manual analysis, which required inspection of only selected grid regions, the automated workflow processed full movie stacks and reduced analysis time from ~3 h to ~20 min per concentration, corresponding to an approximately 9-fold gain in efficiency. These results establish an interpretable, computationally lightweight, and experimentally adaptable strategy for fluorescence single molecule counting that can support rapid diagnostics and provide a practical foundation for future extensions in automated localization, clustering, and real time molecular analysis. Full article

Given its substantial contribution to traffic accidents, one of the main goals of intelligent driver-assistance systems has become the detection and mitigation of driver fatigue to enhance driving safety and comfort. Among various approaches, vision-based facial analysis using deep learning has emerged as an effective and non-intrusive method for identifying driver drowsiness, as a key manifestation of fatigue. However, current drowsiness detection models do not account for demographic factors like gender, even though recent research has shown gender behavioral differences such as eye closure duration, blink frequency, yawning patterns, and facial muscle relaxation. In this paper, we present a fine-grained multi-stream transformer architecture that incorporates gender-awareness and shifted-windows attention for spatial feature fusion. Integrating gender embedding, by modulating the region-based features, allows the model to effectively learn gender-conditioned drowsiness features to minimize bias and diluted representations. Using the NTHU-DDD dataset, we evaluated two-stream and three-stream variants for gender-aware and gender-agnostic across three facial region contexts: the face region with a 20% margin, bare face region, and key facial regions (face, eyes, and mouth). A comprehensive ablation study was conducted to identify the most effective model setup. The results demonstrate that incorporating gender embedding improves detection performance, achieving an accuracy of 95.47% on the evaluation set. Moreover, using the proposed three-stream model (SWT-DD-3S) produced better results. Full article

Swallowing is a critical marker of neurological and emotional health. The ability to monitor it continuously and non-invasively, especially through smart ear-worn devices, holds significant promise for clinical applications. Despite this potential, no public audio datasets currently support reliable swallowing sound detection. Existing datasets focus primarily on speech and breathing, offering limited coverage and lacking detailed annotations for swallowing events. To address this gap, we introduce an in-ear audio dataset specifically designed to capture a wide range of verbal and non-verbal sounds. It includes comprehensive labeling focused on swallowing. The dataset was collected from 34 healthy adults (14 females and 20 males) between the ages of 20 and 29. Each participant performed a series of predefined tasks involving both non-verbal and verbal events. Non-verbal tasks included swallowing, clicking, forceful blinking, touching the scalp, and physical movements such as squatting or walking in place. Verbal tasks consisted of speaking (e.g., describing an image). Recordings were conducted in both quiet and noisy environments to better reflect real-world conditions. Data were captured using a combination of in-/outer-ear microphones, a chest belt to record electrocardiogram (ECG), respiration and acceleration signals, and an ultrasound probe to track tongue movement, which served as a reference for swallowing annotation. All signals were precisely synchronized. To ensure high data quality, the recordings were reviewed using both algorithmic analysis and manual inspection. Swallowing events were identified based on ultrasound signals and validated by an expert to guarantee accurate labeling. As a proof of concept that in-ear audio supports swallow classification, we fine-tune a fully connected neural network on YAMNet embeddings plus zero-crossing rate (ZCR) features. Across the completed folds, the model reaches an F1 score of 0.875 ± 0.013. Full article

Oat (Avena sativa L.), as an essential dual-purpose grain and forage crop, exhibits lodging resistance as a key factor directly impacting yield and quality. Therefore, breeding new oat varieties with lodging resistance is important to increase crop productivity and economic benefits. Using 130 oat germplasm as materials, 7 lodging resistance-related traits of oat, including plant height (PH), the fresh weight of single stem (FWSS), the length of basal second internode (LBSI), diameter of basal second internode (DBSI), wall thickness of basal second internode (WTBSI), stem breaking strength (SBS), and stalk puncture strength (SPS), were investigated in two experimental sites for one year. The results indicate that the seven lodging resistance-related traits exhibit a continuous distribution overall and generally follow a typical distribution pattern. A total of 36,928,068 high-quality Single-nucleotide polymorphisms (SNPs) generated from whole-genome resequencing were used for genome-wide association study (GWAS). Based on the BLINK (Bayesian-information and Linkage-disequilibrium Iteratively Nested Keyway) model threshold (−log₁₀(P) ≥ 6), 379 quantitative trait nucleotides (QTNs) associated with lodging resistance-related traits were identified. Among them, 38, 34, 78, 66, 55, 18, and 94 QTNs were associated with PH, FWSS, SBS, SPS, LBSI, DBSI, and WTBSI, respectively. Notably, three QTNs associated with FWSS and one QTN associated with SBS were stably detected across both environments, representing valuable markers for molecular breeding. From these loci, 54 candidate genes were annotated. Ranked by the number of candidate genes per trait, LBSI contained the highest number (14), followed by WTBSI (12), SPS (11), SBS (7), PH (5), and FWSS (5). Our findings provide critical support for analyzing the genetic mechanism of oat lodging resistance. Moreover, this study also offers a material and theoretical basis for the subsequent development of molecular markers and the breeding of new lodging-resistant oat varieties. Full article

Eye tracking in virtual reality (VR) head-mounted displays poses substantial engineering challenges, particularly under immersive display configurations with large fields of view (FOV), where optical layout, illumination, and image acquisition impose nontrivial system constraints. To address these design constraints, we present an integrated near-eye eye-tracking prototype tailored for immersive VR headsets, combining customized hardware components and a real-time software pipeline. The proposed system integrates optimized near-eye illumination and image acquisition with a pupil detection module and a deep learning-based gaze-vector estimation model, forming a real-time software pipeline for stable end-to-end gaze mapping under fixed calibration conditions. Under identical system settings, calibration procedures, and gaze-point mapping conditions, we evaluate the proposed gaze-vector estimation model through a controlled model-level ablation. The attention-enhanced model achieves an average angular deviation of 1.15°, corresponding to a 61.4% relative reduction compared with a baseline ResNet-152 model without attention. To demonstrate the usability of the system outputs at the application level, we further implement a real-time visualization example that integrates pupil diameter, gaze vectors, and blink events to depict the temporal evolution of eye-movement signals. This work provides a cost-effective and reproducible engineering reference for near-eye eye-movement acquisition and visualization in immersive VR settings and serves as a technical foundation for subsequent interaction design or behavioral analysis studies. Full article

Genome-wide association studies (GWAS) are essential for identifying genomic regions associated with agronomic traits, but Linear Mixed Model (LMM)-based GWAS face challenges in capturing complex gene interactions. This study explores the potential of machine learning (ML) methodologies to enhance marker identification and association modeling in plant breeding. Unlike LMM-based GWAS, ML approaches do not require prior assumptions about marker–phenotype relationships, enabling the detection of epistatic effects and non-linear interactions. The research sought to assess and contrast approaches utilizing ML (Decision Tree—DT; Bagging—BA; Random Forest—RF; Boosting—BO; and Multivariate Adaptive Regression Splines—MARS) and LMM-based GWAS. A simulated F₂ population comprising 1000 individuals was analyzed using 4010 SNP markers and ten traits modeled with epistatic interactions. The simulation included quantitative trait loci (QTL) counts varying between 8 and 240, with heritability levels set at 0.5 and 0.8. These characteristics simulate traits of candidate crops that represent a diverse range of agronomic species, including major cereal crops (e.g., maize and wheat) as well as leguminous crops (e.g., soybean), such as yield, with moderate heritability and a high number of QTLs, and plant height, with high heritability and an average number of QTLs, among others. To validate the simulation findings, the methodologies were further applied to a real Coffea arabica population (n = 195) to identify genomic regions associated with yield, a complex polygenic trait. Results demonstrated a fundamental trade-off between sensitivity and precision. Specifically, for the most complex trait evaluated (240 QTLs under epistatic control), Ensemble methods (Bagging and Random Forest) maintained a Detection Power (DP) exceeding 90%, significantly outperforming state-of-the-art GWAS methods (FarmCPU), which dropped to approximately 30%, and traditional Linear Mixed Models, which failed to detect signals (0%). However, this sensitivity resulted in lower precision for ensembles. In contrast, MARS (Degree 1) and BLINK achieved exceptional Specificity (>99%) and Precision (>90%), effectively minimizing false positives. The real data analysis corroborated these trends: while standard GWAS models failed to detect significant associations, the ML framework successfully prioritized consensus genomic regions harboring functional candidates, such as SWEET sugar transporters and NAC transcription factors. In conclusion, ML Ensembles are recommended for broad exploratory screening to recover missing heritability, while MARS and BLINK are the most effective methods for precise candidate gene validation. Full article

The Body Mass Index (BMI), integrating body weight and length, is a widely used metric for obesity assessment in humans. As pigs serve as crucial biomedical models, the application of BMI in swine and its genetic basis remain poorly explored. This study aimed to investigate the genetic architecture of pig BMI and compare two carcass-based BMI metrics (BMI-S and BMI-O) for breeding applicability. A total of 439 Landrace × Yorkshire crossbred pigs were genotyped with a 50 K SNP chip; heritability was estimated via a mixed linear model, and genome-wide association study (GWAS) was performed using the BLINK model. BMI-S and BMI-O exhibited moderate-to-high heritability of 0.55 and 0.47, respectively, with 17 genome-wide significant SNPs detected—including the top associated SNP rs81382440 on chromosome 4 and rs80898583 on chromosome 7. Key candidate genes (GPHN, ADAM33, KCNH8, PDCD4) and 5 SNP-trait associations validated in PigQTLdb were linked to lipid/energy metabolism and muscle development. Carcass-based BMI improved phenotypic accuracy, and our findings provide core genetic markers and a theoretical basis for molecular breeding of pig body conformation and lipid deposition traits. Full article

The development of effective and user-friendly brain–computer interface (BCI) systems is essential for enhancing mobility and autonomy among individuals with physical disabilities. Recent studies have demonstrated significant advances in BCI technologies, particularly in the areas of motor imagery (MI), blink detection, and attention-level analysis. However, existing systems often face limitations, such as low classification accuracy, high latency, and poor robustness in dynamic, real-world environments. Furthermore, most traditional BCIs rely on single-modality approaches, which restrict their adaptability and real-time performance. This paper aims to address these challenges by presenting a multi-modal Electroencephalography (EEG)–fusion neurointerface wheelchair system integrating MI, intentional blink detection, and attention-level analysis. The proposed system improves on previous methods by employing a novel eight-channel needle-shaped dry electrode EEG headset, which significantly enhances signal quality through better electrode–skin contact without the need for conductive gels. Additionally, the system processes EEG signals in real-time using a Jetson Nano platform, incorporating a dual-threshold blink detection algorithm for emergency stops, an optimized random forest classifier for decoding directional MI, and a support vector machine (SVM) for attention-level assessment. Experimental evaluations involving classification accuracy, response latency, and trajectory-following precision confirmed robust system performance. MI classification accuracy averaged around 80%, with optimized attention-level analysis reaching up to 94.1%. Trajectory control tests demonstrated minimal deviation from predefined paths (typically less than 0.25 m). These results highlight the system’s advancements over existing single-modality BCIs, showcasing its potential to significantly improve the quality of life for mobility-impaired users. Future studies should focus on enhancing lateral MI detection accuracy, expanding datasets, and validating system robustness across diverse real-world scenarios. Full article