IoT-Based Activities of Daily Living for Abnormal Behavior Detection: Privacy Issues and Potential Countermeasures

Abstract

Activities of daily living (ADL) systems have been playing an important role in assessing and monitoring the quality of life of elderly people for many years. With the recent advancement and integration of internet of things (IoT) devices within the ADL systems, the number and quality of services offered has increased significantly. One of these vital services is abnormal behaviour detection based on the data collected from IoT devices within smart homes. However, the IoT data collected could have enormous privacy implications on smart home users if the data is not handled properly. We address this issue by analysing a generic ADL system for abnormal behaviour detection, including its entities and their interactions. We highlight three major privacy issues: (i) identity privacy, (ii) data confidentiality, and (iii) metadata data leakage. These issues are particularly relevant to ADL systems and we propose potential countermeasures to tackle them. Finally, we sketch a privacy-preserving version of an example ADL system to demonstrate the effectiveness of our proposed countermeasures, before suggesting future research directions.

Analysis of Accelerometer Data for Personalised Mood Detection in Activities of Daily Living

“…This work continues the research presented in [7], [8], [9], [14] and [19]. In [7], Petri nets were used to model and verify ADLs preparing and drinking a hot beverage, and preparing pasta.…”

“…In [14], the approach presented in [8] is extended by considering the sequential aspects of the ADLs in addition to the temporal aspects and using Cumulative Distribution Function (CDF) to provide accurate and reliable results regarding the presence of abnormal behaviour. Privacy issues and potential coun-termeasures in the context of IoT-based ADLs for abnormal behaviour detection were investigated in [19]. In [9], an initial approach using just accelerometer data for activity recognition in the context of ADLs was presented.…”

Fault Detection on the Edge and Adaptive Communication for State of Alert in Industrial Internet of Things

“…Dofe et al [ 13 ] present a comprehensive perspective on countermeasures against IoT attacks. Mustafa et al [ 14 ] propose three countermeasures to preserve privacy when abnormal behavior is detected in assisted living applications.…”