Lijie Zhou

Lijie Zhou

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an adversarial evaluation framework that quantifies this cross-modal dependency by measuring accuracy degradation (Drop) when semantically conflicting text is paired with unchanged images. Four adversarial strategies -- shape\_swap, color\_swap, position\_swap, and random\_text -- are applied to a controlled geometric-shapes dataset ($n{=}1{,}000$). We compare three configurations: Baseline CLIP (ViT-B/32), LoRA fine-tuning, and LoRA Optimized (integrating Hard Negative Mining, Label Smoothing, layer-wise learning rates, Cosine Restarts, curriculum learning, and data augmentation). The optimized model reduces average Drop from 27.5\% to 9.8\% (64.4\% relative improvement, $p{<}0.001$) while maintaining 97\% normal accuracy. Attention visualization and embedding-space analysis confirm that the optimized model attends more to visual features and achieves tighter cross-modal alignment.

Lijie Zhou, Luran Wang

The increasing global aging population has intensified the demand for reliable health monitoring systems, particularly those capable of detecting critical events such as falls among elderly individuals. Traditional fall detection approaches relying on single-modality acceleration data suffer from high false alarm rates, while conventional machine learning methods require extensive hand-crafted feature engineering. This paper proposes a novel multi-modal deep learning framework, MultiModalFallDetector, designed for real-time elderly fall detection using wearable sensors. Our approach integrates multiple innovations: a multi-scale CNN-based feature extractor capturing motion dynamics at varying temporal resolutions; fusion of tri-axial accelerometer, gyroscope, and four-channel physiological signals; incorporation of a multi-head self-attention mechanism for dynamic temporal weighting; adoption of Focal Loss to mitigate severe class imbalance; introduction of an auxiliary activity classification task for regularization; and implementation of transfer learning from UCI HAR to SisFall dataset. Extensive experiments on the SisFall dataset, which includes real-world simulated fall trials from elderly participants (aged 60-85), demonstrate that our framework achieves an F1-score of 98. 7, Recall of 98. 9, and AUC-ROC of 99. 4, significantly outperforming baseline methods including traditional machine learning and standard deep learning approaches. The model maintains sub- 50ms inference latency on edge devices, confirming its suitability for real-time deployment in geriatric care settings.

Lijie Zhou, Luran Wang

The rapid aging of global populations has created an urgent need for intelligent healthcare monitoring systems to ensure the safety of elderly individuals living independently. Existing cloud-centric platforms face critical limitations, including high latency unsuitable for emergency response, privacy risks from continuous transmission of sensitive data, and limited, single-channel alert mechanisms lacking scalability and context awareness. This paper proposes an edge-cloud collaborative architecture that addresses these challenges through real-time multi-modal sensor fusion, a four-dimensional risk assessment model, and a three-level emergency response system. The framework adopts a five-layer design - device, edge, service, data, and application layers - enabling real-time risk evaluation with end-to-end alert latency under three seconds. At the edge, a weighted multi-modal fusion algorithm integrates data from five sensor types with confidence propagation. A unified risk score is generated by combining fall probability, physiological indicators, behavioral patterns, and sensor anomaly metrics. Based on dynamic thresholds, a three-tier notification system coordinates responses among family members, community doctors, and nearby volunteers. Experiments on CASAS, MIMIC-III, and SisFall datasets show that the approach achieves 91% activity recognition accuracy and an 84% anomaly detection F1-score, outperforming single-sensor methods. Deployment on Raspberry Pi 4 gateways demonstrates sub-100 ms inference latency while preserving privacy by keeping raw data local. This architecture advances practical, privacy-preserving, and responsive elderly care systems.

Xudong Wang, Hongyang Du, Dusit Niyato et al.

In wireless networks, applying deep learning models to solve matching problems between different entities has become a mainstream and effective approach. However, the complex network topology in 6G multiple access presents significant challenges for the real-time performance and stability of matching generation. Generative artificial intelligence (GenAI) has demonstrated strong capabilities in graph feature extraction, exploration, and generation, offering potential for graph-structured matching generation. In this paper, we propose a GenAI-enabled matching generation framework to support 6G multiple access. Specifically, we first summarize the classical matching theory, discuss common GenAI models and applications from the perspective of matching generation. Then, we propose a framework based on generative diffusion models (GDMs) that iteratively denoises toward reward maximization to generate a matching strategy that meets specific requirements. Experimental results show that, compared to decision-based AI approaches, our framework can generate more effective matching strategies based on given conditions and predefined rewards, helping to solve complex problems in 6G multiple access, such as task allocation.