University of Kashan Soft Computing Journal 2322-3707 11 1 2022 08 23 Using string similarity techniques to detect daily activities in smart homes equipped with a binary sensor network Using string similarity techniques to detect daily activities in smart homes equipped with a binary sensor network 72 87 112899 10.22052/scj.2022.243385.1033 FA Ashkan Nikaiin Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, Iran Mohsen Rahmani Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, Iran Journal Article 2021 12 26 Human activity recognition can be employed in systems that provide support to people who need special care in their daily activities. Various machine learning methods, including Hidden Markov Models and their extensions, are widely used to deal with this problem. In the previous works, HMM-based methods use the conditional independent assumption to compute the probability of a segment of observations. In this research, instead of conditional independent assumption, a new probabilistic model for string space, based on Dynamic Time Warping and Weighted Levenstein Distance is proposed. The model, combined with the Hidden semi-Markov Model, is applied to a publicly available dataset. The results show that the use of the proposed model significantly increases the accuracy of identifying daily activities. All the code and data of this paper are available through the link github.com/ashnik1353. Human activity recognition can be employed in systems that provide support to people who need special care in their daily activities. Various machine learning methods, including Hidden Markov Models and their extensions, are widely used to deal with this problem. In the previous works, HMM-based methods use the conditional independent assumption to compute the probability of a segment of observations. In this research, instead of conditional independent assumption, a new probabilistic model for string space, based on Dynamic Time Warping and Weighted Levenstein Distance is proposed. The model, combined with the Hidden semi-Markov Model, is applied to a publicly available dataset. The results show that the use of the proposed model significantly increases the accuracy of identifying daily activities. All the code and data of this paper are available through the link github.com/ashnik1353. https://scj.kashanu.ac.ir/article_112899_2f755f27b7502114567ffcbdb021dbbe.pdf