Extension of HMM-Based ADL Recognition With Markov Chains of Activities and Activity Transition Cost

Abstract

Ambient assisted living in smart home environments is becoming an important goal in an aging society with challenges in elderly care. A key component in such environments is the accurate recognition of activities of daily living from various sensor data. Recent research directions explored several classification methods, including hidden Markov models. This research presents a hidden Markov model-based system for activity recognition, and extends it with a second-order Markov chain model of activity sequences to achieve long-term dependency in the model. We also introduce an activity transition cost to counteract the tendency of hidden Markov models to make a large number of transitions. The proposed models are used for activity recognition, with their scores being combined using heuristically determined weights for optimal performance. We also present a modified Viterbi algorithm, which incorporates both models and the activity transition cost. We used a dataset from the CASAS project to test and evaluate the proposed models. A comparison of the results shows the potential of introducing long term dependencies and the managing the number of activity transitions. We show results regarding the modeling ability to predict activity sequences, a comparison of predicted and actual activity transitions, and final recognition accuracy results. The results show an increase of total activity recognition accuracy from 93.9 % to 94.52 % on individual activities, and from 68.89 % to 70.95 % over the combination of all concurrent activities. The results also show a reduction of predicted activity transitions from 741 to 236, whereas the number of actual activity transitions in the evaluation set is 141. INDEX TERMS Activities of daily living, hidden Markov models, Markov chain, pattern recognition, Viterbi algorithm.

Global Research Trends on Smart Homes for Older Adults: Bibliometric and Scientometric Analyses

“…Based on this, Donaj and Maučec (2019) presented a system for activity recognition and used a dataset from the CASAS to test and evaluate the proposed model. The core of these studies is to accurately grasp the daily living and activities of older adults from various sensor data [ 64 ].…”

Employing automatic content recognition for teaching methodology analysis in classroom videos

“…Gregor et al [ 24 ] used sensor data to recognize elderly people activity recognition. The dataset for this project was collected from several sensors including 51 motion sensors, 4 item sensors on selected items, 15 door sensors, and 5 temperature sensors installed in different rooms of the apartment.…”

Discovering Daily Activity Patterns from Sensor Data Sequences and Activity Sequences

“…Data-driven approaches use various machine learning techniques to learn activities from collected sensor data. The most frequently used are: Naive Bayes classifier [ 15 ], Hidden Markov Models [ 8 , 16 , 17 ], Support Vector Machines [ 3 ], dictionaries of patterns [ 18 ], and neural networks [ 6 , 19 , 20 ]. These approaches require a great amount of annotated data to train the models accurately.…”

“…A literature review has shown that many problems regarding ADL recognition were addressed, and the proposed solutions demonstrated good results [ 7 , 8 , 9 ]. However, the question remains what to infer from the recognized sequence of activities.…”

“…Activity recognition infers a person’s activities from monitoring the environment. Approaches that recognize activities from simple environment sensors have been shown to perform well with an accuracy exceeding 90% [ 7 , 8 , 9 ]. However, the problem lies in how to interpret the gathered information and what to infer from it.…”