Scholarlink

<p>With the global growth in the elderly population, recognizing human activities using wearable sensors has become a crucial challenge in smart healthcare. However, Wearable Sensor-based Elderly Activity Recognition (WSEAR) remains difficult due to the diversity of activities, differences in execution, and overlapping or uncertain activities. This paper proposes a novel three-layered framework called OnFuDReC to improve recognition of complex and similar activities. It combines deep feature extraction, adaptive temporal modeling, and an ontology-based fuzzy inference system that refines classification using semantic rules. The framework was evaluated on benchmark datasets (e.g., PAMAP2, Opportunity), achieving F1-scores up to 97.01%, significantly outperforming existing methods.</p>

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

Deep learning and ontology-fuzzy inference system for elderly activity recognition

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Fatemeh Serpush,
  • Behrooz Masoumi,
  • Mohammad Bagher Menhaj,
  • Babak Karasfi

摘要

With the global growth in the elderly population, recognizing human activities using wearable sensors has become a crucial challenge in smart healthcare. However, Wearable Sensor-based Elderly Activity Recognition (WSEAR) remains difficult due to the diversity of activities, differences in execution, and overlapping or uncertain activities. This paper proposes a novel three-layered framework called OnFuDReC to improve recognition of complex and similar activities. It combines deep feature extraction, adaptive temporal modeling, and an ontology-based fuzzy inference system that refines classification using semantic rules. The framework was evaluated on benchmark datasets (e.g., PAMAP2, Opportunity), achieving F1-scores up to 97.01%, significantly outperforming existing methods.