Abstract
Many Human Activity Recognition (HAR) systems are able to detect sequential executed Activity of Daily Living (ADL). However, a person is capable of doing two things in parallel or pausing one ADL and finishing it later. Thus, a HAR system must be capable of remembering and deciding which ADL is completed and which might be continued after the current ADL. We address this case by combining a stochastic Markov model and a psychological memory function to detect parallel ADL. For the evaluation, we use an input dataset and a publicly available benchmark. Our approach outperforms the leading HAR systems for the used benchmark by 5%, while using a more cost-effective installation environment. Furthermore, we address an unsupervised learning method to train the HAR system and explain the algorithm of parallel ADL detection in detail.
Highlights
This paper is an extended version of the publication done in 2017 for the Pervasive TechnologiesRelated to Assistive Environments (PETRA) Conference in Greece [1]
The detection of activities in private households becomes more important for health-care and assisted accommodations because impaired people want to continue living in their homes [2], which leads to an increase of care
It includes the states derived from the data stream example above and an additional part to show one Markov Model (MM)-structure. Such a structure is a temporal correlation of sensor events, which is separated from the rest of the MM and represents a human habit
Summary
This paper is an extended version of the publication done in 2017 for the Pervasive Technologies. The detection of activities in private households becomes more important for health-care and assisted accommodations because impaired people want to continue living in their homes [2], which leads to an increase of care. The elderly tend to forget started activities, such as cooking or an open water tap This forgetfulness may lead to a severe threat to health. Human Activity Recognition (HAR) systems can help to prolong the elderly person’s stay at home. It relaxes relatives who are concerned about the health of their family members. That means the monitored person has to give feedback about his/her activities This is a very time-consuming and error-prone procedure. Afterwards, an evaluation is done, and the conclusion will be drawn
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
