arXiv subjects

Mayue Shi

Publications and source records attributed to Mayue Shi.

4 recordsLinked to original sources

arXiv2025

Structured Contrastive Learning for Interpretable Latent Representations

Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition performance with inertial measurement units (IMUs). We identify the root cause as "laissez-faire" representation learning, where latent spaces evolve unconstrained provided task performance is satisfied. We propose Structured Contrastive Learning (SCL), a framework that partitions latent space representations into three semantic groups: invariant features that remain consistent under given transformations (e.g., phase shifts or rotations), variant features that actively differentiate transformations via a novel variant mechanism, and free features that preserve task flexibility. This creates controllable push-pull dynamics where different latent dimensions serve distinct, interpretable purposes. The variant mechanism enhances contrastive learning by encouraging variant features to differentiate within positive pairs, enabling simultaneous robustness and interpretability. Our approach requires no architectural modifications and integrates seamlessly into existing training pipelines. Experiments on ECG phase invariance and IMU rotation robustness demonstrate superior performance: ECG similarity improves from 0.25 to 0.91 under phase shifts, while WISDM activity recognition achieves 86.65% accuracy with 95.38% rotation consistency, consistently outperforming traditional data augmentation. This work represents a paradigm shift from reactive data augmentation to proactive structural learning, enabling interpretable latent representations in neural networks.

cs.LG↗

arXiv2025

CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection

Chagas disease affects nearly 6 million people worldwide, with Chagas cardiomyopathy representing its most severe complication. In regions where serological testing capacity is limited, AI-enhanced electrocardiogram (ECG) screening provides a critical diagnostic alternative. However, existing machine learning approaches face challenges such as limited accuracy, reliance on large labeled datasets, and more importantly, weak integration with evidence-based clinical diagnostic indicators. We propose a retrieval-augmented generation framework, CardioRAG, integrating large language models with interpretable ECG-based clinical features, including right bundle branch block, left anterior fascicular block, and heart rate variability metrics. The framework uses variational autoencoder-learned representations for semantic case retrieval, providing contextual cases to guide clinical reasoning. Evaluation demonstrated high recall performance of 89.80%, with a maximum F1 score of 0.68 for effective identification of positive cases requiring prioritized serological testing. CardioRAG provides an interpretable, clinical evidence-based approach particularly valuable for resource-limited settings, demonstrating a pathway for embedding clinical indicators into trustworthy medical AI systems.

cs.CE↗

arXiv2025

COBRA: Multimodal Sensing Deep Learning Framework for Remote Chronic Obesity Management via Wrist-Worn Activity Monitoring

Chronic obesity management requires continuous monitoring of energy balance behaviors, yet traditional self-reported methods suffer from significant underreporting and recall bias, and difficulty in integration with modern digital health systems. This study presents COBRA (Chronic Obesity Behavioral Recognition Architecture), a novel deep learning framework for objective behavioral monitoring using wrist-worn multimodal sensors. COBRA integrates a hybrid D-Net architecture combining U-Net spatial modeling, multi-head self-attention mechanisms, and BiLSTM temporal processing to classify daily activities into four obesity-relevant categories: Food Intake, Physical Activity, Sedentary Behavior, and Daily Living. Validated on the WISDM-Smart dataset with 51 subjects performing 18 activities, COBRA's optimal preprocessing strategy combines spectral-temporal feature extraction, achieving high performance across multiple architectures. D-Net demonstrates 96.86% overall accuracy with category-specific F1-scores of 98.55% (Physical Activity), 95.53% (Food Intake), 94.63% (Sedentary Behavior), and 98.68% (Daily Living), outperforming state-of-the-art baselines by 1.18% in accuracy. The framework shows robust generalizability with low demographic variance (<3%), enabling scalable deployment for personalized obesity interventions and continuous lifestyle monitoring.

cs.CE↗

arXiv2024

High-Performance Vision-Based Tactile Sensing Enhanced by Microstructures and Lightweight CNN

Tactile sensing is critical in advanced interactive systems by emulating the human sense of touch to detect stimuli. Vision-based tactile sensors are promising for providing multimodal capabilities and high robustness, yet existing technologies still have limitations in sensitivity, spatial resolution, and high computational demands of deep learning-based image processing. This paper presents a comprehensive approach combining a novel microstructure-based sensor design and efficient image processing, demonstrating that carefully engineered microstructures can significantly enhance performance while reducing computational load. Without traditional tracking markers, our sensor incorporates an surface with micromachined trenches, as an example of microstructures, which modulate light transmission and amplify the response to applied force. The amplified image features can be extracted by a ultra lightweight convolutional neural network to accurately inferring contact location, displacement, and applied force with high precision. Through theoretical analysis, we demonstrated that the micro trenches significantly amplified the visual effects of shape distortion. Using only a commercial webcam, the sensor system effectively detected forces below 5 mN, and achieved a millimetre-level single-point spatial resolution. Using a model with only one convolutional layer, a mean absolute error below 0.05 mm was achieved. Its soft sensor body allows seamless integration with soft robots, while its immunity to electrical crosstalk and interference guarantees reliability in complex human-machine environments.

cs.RO↗