An Unsupervised Approach for Automatic Activity Recognition Based on Hidden Markov Model Regression

Abstract

Abstract-Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This paper presents a new unsupervised approach for human activity recognition from raw acceleration data measured using inertial wearable sensors. The proposed method is based upon joint segmentation of multidimensional time series using a Hidden Markov Model (HMM) in a multiple regression context. The model is learned in an unsupervised framework using the ExpectationMaximization (EM) algorithm where no activity labels are needed. The proposed method takes into account the sequential appearance of the data. It is therefore adapted for the temporal acceleration data to accurately detect the activities. It allows both segmentation and classification of the human activities. Experimental results are provided to demonstrate the efficiency of the proposed approach with respect to standard supervised and unsupervised classification approaches.

A practical multi-sensor activity recognition system for home-based care

“…A variety of on-body sensors have been explored such as accelerometer [5,7,8,9,10,11], gyroscope [6,11], temperature [6,7,9], etc.…”

“…A number of studies use several sensors attached to different parts of human body to increase recognition accuracy. Locations such as chest [10,11], wrist [5,6,7,11], thigh [10], waist [12], ankle [10,11], etc. have been studied.…”

“…For example, accelerometers were used on subjects' wrists, ankles and chest [11]. Inertial sensors were attached to chest, right thigh and left ankle to detect postures and transition activities [10]. However, attaching several sensors on body may decrease mobility or even obstruct daily activities routine.…”

Analyzing the Relationship between Human Behavior and Indoor Air Quality

“…Activity recognition is a well-researched area, and there is a large amount of prior work that introduces machine learning approaches to model the activities using techniques such as hidden Markov models (HMMs) [32] and segmented hierarchical infinite hidden Markov models (siHMMs) [33]. Methods are chosen according to the realism of the smart environment and the sensor technologies that are used for collecting the data.…”

Recognition of unscripted kitchen activities and eating behaviour for health monitoring

“…They can be either unsupervised (i.e. clustering) [3], or supervised (i.e. classification based on training data) [15].…”