arXiv subjects

Nhat Tan Le

Publications and source records attributed to Nhat Tan Le.

5 recordsLinked to original sources

arXiv2026

From Coordinates to Context: An LLM-Bootstrapped Semantic Encoding Framework for Privacy-Preserving Mobile Sensing Stress Recognition

Psychological stress is a widespread issue that significantly impacts student well-being and academic performance. Effective remote stress recognition is crucial, yet existing methods often rely on wearable devices or GPS-based clustering techniques that pose privacy risks and lack of human understandable explanations. In this study, we introduce a novel, end-to-end privacy-enhanced framework for semantic location encoding using a self-hosted OSM engine and an LLM-bootstrapped static map for human-friendly feature extraction, and pave a pathway for privacy-aware location data transformation for dataset sharing. We rigorously quantify the privacy-utility-explainability trilemma and demonstrate (via LOSO validation) that our Privacy-Aware (PA) model achieves robust privacy protection without being statistically distinguishable in stress recognition performance from a non-private model. Model explanation analysis highlights that our extracted features, which are user-friendly features, match with psychological literature about stress. In addition, an ablation study on the GeoLife dataset also demonstrates that our privacy framework improves privacy by 2-3 times compared to a non-privacy-aware approach. This suggests that our system can be utilized for the next generation of GPS transformations in open-source datasets for future researchers.

cs.CR↗

arXiv2026

A Unified XAI-LLM Approach for EndotrachealSuctioning Activity Recognition

Endotracheal suctioning (ES) is an invasive yet essential clinical procedure that requires a high degree of skill to minimize patient risk - particularly in home care and educational settings, where consistent supervision may be limited. Despite its critical importance, automated recognition and feedback systems for ES training remain underexplored. To address this gap, this study proposes a unified, LLM-centered framework for video-based activity recognition benchmarked against conventional machine learning and deep learning approaches, and a pilot study on feedback generation. Within this framework, the Large Language Model (LLM) serves as the central reasoning module, performing both spatiotemporal activity recognition and explainable decision analysis from video data. Furthermore, the LLM is capable of verbalizing feedback in natural language, thereby translating complex technical insights into accessible, human-understandable guidance for trainees. Experimental results demonstrate that the proposed LLM-based approach outperforms baseline models, achieving an improvement of approximately 15-20\% in both accuracy and F1 score. Beyond recognition, the framework incorporates a pilot student-support module built upon anomaly detection and explainable AI (XAI) principles, which provides automated, interpretable feedback highlighting correct actions and suggesting targeted improvements. Collectively, these contributions establish a scalable, interpretable, and data-driven foundation for advancing nursing education, enhancing training efficiency, and ultimately improving patient safety.

cs.AI↗

arXiv2026

Summary of the Unusual Activity Recognition Challenge for Developmental Disability Support

This paper presents an overview of the Recognize the Unseen: Unusual Behavior Recognition from Pose Data Challenge, hosted at ISAS 2025. The challenge aims to address the critical need for automated recognition of unusual behaviors in facilities for individuals with developmental disabilities using non-invasive pose estimation data. Participating teams were tasked with distinguishing between normal and unusual activities based on skeleton keypoints extracted from video recordings of simulated scenarios. The dataset reflects real-world imbalance and temporal irregularities in behavior, and the evaluation adopted a Leave-One-Subject-Out (LOSO) strategy to ensure subject-agnostic generalization. The challenge attracted broad participation from 40 teams applying diverse approaches ranging from classical machine learning to deep learning architectures. Submissions were assessed primarily using macro-averaged F1 scores to account for class imbalance. The results highlight the difficulty of modeling rare, abrupt actions in noisy, low-dimensional data, and emphasize the importance of capturing both temporal and contextual nuances in behavior modeling. Insights from this challenge may contribute to future developments in socially responsible AI applications for healthcare and behavior monitoring.

cs.CV↗

arXiv2025

Robust In-the-Wild Exercise Recognition from a Single Wearable: Data-Side Fusion, Sensor Rotation, and Feature Engineering

Monitoring physical exercises is vital for health promotion, with automated systems becoming standard in personal health surveillance. However, sensor placement variability and unconstrained movements limit their effectiveness. This study proposes the team "3KA"'s one-sensor workout activity recognition method using feature extraction and data augmentation in 2ndWEAR Dataset Challenge. From raw acceleration, angle and signal magnitude vector features were derived, followed by extraction of statistical, fractal/spectral, and higher-order differential features. A fused dataset combining left/right limb data was created, and augmented via sensor rotation and axis inversion. We utilized a soft voting model combining Hist Gradient Boosting with balanced weights and Extreme Gradient Boosting without. Under group 5-fold evaluation, the model achieved 58.83\% macro F1 overall (61.72% arm, 55.95% leg). ANOVA F-score showed fractal/spectral features were most important for arm-based recognition but least for leg-based. The code to reproduce the experiments is publicly available via: https://github.com/Khanghcmut/WEAR\_3K

cs.HC↗

arXiv2025

SOS: A Shuffle Order Strategy for Data Augmentation in Industrial Human Activity Recognition

In the realm of Human Activity Recognition (HAR), obtaining high quality and variance data is still a persistent challenge due to high costs and the inherent variability of real-world activities. This study introduces a generation dataset by deep learning approaches (Attention Autoencoder and conditional Generative Adversarial Networks). Another problem that data heterogeneity is a critical challenge, one of the solutions is to shuffle the data to homogenize the distribution. Experimental results demonstrate that the random sequence strategy significantly improves classification performance, achieving an accuracy of up to 0.70 $\pm$ 0.03 and a macro F1 score of 0.64 $\pm$ 0.01. For that, disrupting temporal dependencies through random sequence reordering compels the model to focus on instantaneous recognition, thereby improving robustness against activity transitions. This approach not only broadens the effective training dataset but also offers promising avenues for enhancing HAR systems in complex, real-world scenarios.

cs.HC↗