Scholarlink

Obstructive Sleep Apnoea (OSA) substantially compromises quality of life leading to cognitive decline, psychomotor difficulties, and behavioural abnormalities. Particularly for the elderly, careful monitoring and treatment are vitally essential. Many times, present OSA detection systems lack treatment recommendations and real-time aged care support. This paper proposes a new method combining open data from smart cities with detecting and supporting OSA therapy by monitoring sleep environment, status, physical activities and physiological indicators. The system design includes in batch data processing for descriptive and predictive analysis as well as real-time pre-processing incorporating smart device notifications using Deep Radial Basis Function (RDBF). In tests, predicting air quality indices using IoT sensors to guide OSA treatment turned out to be 93.3% efficient. Edge computing for data preparation enhanced system latency performance, therefore raising its overall general efficiency.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced Obstructive Sleep Apnoea Management Using Deep Radial Basis Function for Accurate Prediction and Efficient Data Processing for Internet of Things

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Muthumarilakshmi,
  • Sindhuja Jaya Kumar,
  • S. Suganya,
  • J. Kasthuri

摘要

Obstructive Sleep Apnoea (OSA) substantially compromises quality of life leading to cognitive decline, psychomotor difficulties, and behavioural abnormalities. Particularly for the elderly, careful monitoring and treatment are vitally essential. Many times, present OSA detection systems lack treatment recommendations and real-time aged care support. This paper proposes a new method combining open data from smart cities with detecting and supporting OSA therapy by monitoring sleep environment, status, physical activities and physiological indicators. The system design includes in batch data processing for descriptive and predictive analysis as well as real-time pre-processing incorporating smart device notifications using Deep Radial Basis Function (RDBF). In tests, predicting air quality indices using IoT sensors to guide OSA treatment turned out to be 93.3% efficient. Edge computing for data preparation enhanced system latency performance, therefore raising its overall general efficiency.