WITS: an IoT-endowed computational framework for activity recognition in personalized smart homes

Lina Yao*, Quan Z. Sheng, Boualem Benatallah, Schahram Dustdar, Xianzhi Wang, Ali Shemshadi, Salil S. Kanhere

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

35 Citations (Scopus)


Over the past few years, activity recognition techniques have attracted unprecedented attentions. Along with the recent prevalence of pervasive e-Health in various applications such as smart homes, automatic activity recognition is being implemented increasingly for rehabilitation systems, chronic disease management, and monitoring the elderly for their personal well-being. In this paper, we present WITS, an end-to-end web-based in-home monitoring system for convenient and efficient care delivery. The system unifies the data- and knowledge-driven techniques to enable a real-time multi-level activity monitoring in a personalized smart home. The core components consist of a novel shared-structure dictionary learning approach combined with rule-based reasoning for continuous daily activity tracking and abnormal activities detection. WITS also exploits an Internet of Things middleware for the scalable and seamless management and learning of the information produced by ambient sensors. We further develop a user-friendly interface, which runs on both iOS and Andriod, as well as in Chrome, for the efficient customization of WITS monitoring services without programming efforts. This paper presents the architectural design of WITS, the core algorithms, along with our solutions to the technical challenges in the system implementation.

Original languageEnglish
Pages (from-to)369–385
Number of pages17
Issue number4
Publication statusPublished - Apr 2018


  • Activity recognition
  • Internet of Things
  • Localization
  • Shared dictionary learning
  • Smart homes


Dive into the research topics of 'WITS: an IoT-endowed computational framework for activity recognition in personalized smart homes'. Together they form a unique fingerprint.

Cite this