A5044996390- EEG and Brain-Computer Interfaces
- Sleep and Wakefulness Research
- Time Series Analysis and Forecasting
- Sleep and Work-Related Fatigue
- IoT and Edge/Fog Computing
- Hemodynamic Monitoring and Therapy
- Neural Networks and Applications
- Cardiovascular Health and Disease Prevention
- Vehicular Ad Hoc Networks (VANETs)
- Big Data and Business Intelligence
- Advanced Neural Network Applications
- Obstructive Sleep Apnea Research
- Social Robot Interaction and HRI
- Brain Tumor Detection and Classification
- Music and Audio Processing
- Anomaly Detection Techniques and Applications
- Context-Aware Activity Recognition Systems
- Fault Detection and Control Systems
- Mobile Ad Hoc Networks
- Data Stream Mining Techniques
- Non-Invasive Vital Sign Monitoring
- Sleep and related disorders
- Video Analysis and Summarization
- Wireless Body Area Networks
- Robotics and Automated Systems
Chinese University of Hong Kong
2023-2025
Nanjing University
2020-2023
Social interactions are fundamental to human life. The recent emergence of large language models (LLMs)-based virtual assistants has demonstrated their potential revolutionize and lifestyles. However, existing assistive systems mainly provide reactive services individual users, rather than offering in-situ assistance during live social with conversational partners. In this study, we introduce SocialMind, the first LLM-based proactive AR system that provides users assistance. SocialMind...
Large language models (LLMs) have the potential to transform digital healthcare, as evidenced by recent advances in LLM-based virtual doctors. However, current approaches rely on patient's subjective descriptions of symptoms, causing increased misdiagnosis. Recognizing value daily data from smart devices, we introduce a novel multi-turn consultation doctor system, DrHouse, which incorporates three significant contributions: 1) It utilizes sensor devices diagnosis process, enhancing accuracy...
Monitoring single-channel EEG is a promising home-based approach for insomnia identification. Currently, many automatic sleep stage scoring approaches based on have been developed, whereas few studies research identification labelled with annotations. In this paper, we propose one-dimensional convolutional neural network (1D-CNN) model annotations, and further investigate the performance different stages epochs. Single-channel 9 patients healthy subjects was used in study. We constructed 4...
Recently, smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore infrastructure-assisted driving, this paper presents design and deployment Soar, first end-to-end SRI system specifically designed to support Soar consists both software hardware components carefully overcome various physical challenges. can leverage existing operational like street lampposts for a lower barrier adoption. adopts new communication architecture...
Automatic sleep stage classification has gained much attention in recent researches. Various algorithms have been proposed for automatic staging, including deep neural networks and traditional machine learning models. However, the output of those models unreasonable transitions, as temporal dependence label adjacent data segment is ignored. In this article, we propose a novel contextual refinement algorithm based on conditional random fields (CRFs). The works post-processing step to rectify...
Despite the extensive use of sensors enabling intelligent applications, complementary potential co-existing sensor systems is often not fully utilized, limiting more advanced applications. This paper introduces a novel solution using Large Language Models (LLMs) to coordinate for handling complex user queries. It defines language systems, including vocabulary set and grammar rules, analogous natural components, LLMs translate intentions into coordination plans. Preliminary results show that...
Sleep arousals is a type of sleep disorder, which refers to the phenomenon waking up and falling asleep again. Monitoring number duration crucial aspect quality assessment. The detection caused by apnea relatively easy, existing methods have been able give high results. However, non-apnea remains an ongoing challenge, this also subject PhysioNet Computing in Cardiology Challenge 2018. We proposed automatic algorithm based on polysomnography (PSG) data. took 8 most representative signals...
Accurate and continuous blood pressure (BP) monitoring is essential to the early prevention of cardiovascular diseases. Non-invasive cuff-less BP estimation algorithm has gained much attention in recent years. Previous studies have demonstrated that brain bio-impedance (BIOZ) a promising technique for non-invasive intracranial (ICP) monitoring. Clinically, treatment patients with traumatic injuries (TBI) requires ICP simultaneously. Estimating by BIOZ directly can reduce number sensors...
Deep Learning (DL) models have been widely deployed on IoT devices with the help of advancements in DL algorithms and chips. However, limited resources edge make these on-device hard to be generalizable diverse environments tasks. Although recently emerged foundation (FMs) show impressive generalization power, how effectively leverage rich knowledge FMs resource-limited is still not explored. In this paper, we propose EdgeFM, a novel edge-cloud cooperative system open-set recognition...