Machine Learning / Deep Learning

Machine Learning / Deep Learning

Signal understanding and perception pipelines that combine CNNs, Transformers, and multimodal fusion to support sleep staging, activity recognition, and embedded inference.

• Sleep/ECG interpretation for wearable healthcare
• Multimodal human-action and sensor fusion models
• Edge-ready architectures with knowledge distillation

Research Area Overview

We develop advanced deep learning systems that respond to the market’s demand for reliable AI across computer vision, biosignal processing, and natural language tasks. Where traditional models fall short, we engineer multi-stream architectures that fuse RGB, depth, IMU, and physiological measurements to achieve robust perception on edge hardware.

Focus Topics

• Multi-modal perception (RGB, depth, event-based, and wearable sensors)
• Explainable sleep staging and biosignal interpretation
• Lightweight architectures and AutoML for embedded deployment
• Feature engineering and knowledge distillation for small datasets
• Energy-aware AI that blends neural networks with knowledge modeling and embedded reasoning
• Large-scale data mining pipelines that turn heterogeneous sensor, text, and biomedical records into ML-ready features