Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data

Abstract

Smart homes for the aging population have recently started attracting the attention of the research community. The "health state" of smart homes is comprised of many different levels; starting with the physical health of citizens, it also includes longer-term health norms and outcomes, as well as the arena of positive behavior changes. One of the problems of interest is to monitor the activities of daily living (ADL) of the elderly, aiming at their protection and well-being. For this purpose, we installed passive infrared (PIR) sensors to detect motion in a specific area inside a smart apartment and used them to collect a set of ADL. In a novel approach, we describe a technology that allows the ground truth collected in one smart home to train activity recognition systems for other smart homes. We asked the users to label all instances of all ADL only once and subsequently applied data mining techniques to cluster in-home sensor firings. Each cluster would therefore represent the instances of the same activity. Once the clusters were associated to their corresponding activities, our system was able to recognize future activities. To improve the activity recognition accuracy, our system preprocessed raw sensor data by identifying overlapping activities. To evaluate the recognition performance from a 200-day dataset, we implemented three different active learning classification algorithms and compared their performance: naive Bayesian (NB), support vector machine (SVM) and random forest (RF). Based on our results, the RF classifier recognized activities with an average specificity of 96.53%, a sensitivity of 68.49%, a precision of 74.41% and an F-measure of 71.33%, outperforming both the NB and SVM classifiers. Further clustering markedly improved the results of the RF classifier. An activity recognition system based on PIR sensors in conjunction with a clustering classification approach was able to detect ADL from datasets collected from different homes. Thus, our PIR-based smart home technology could improve care and provide valuable information to better understand the functioning of our societies, as well as to inform both individual and collective action in a smart city scenario.

Keywords: activities of daily living; ambient assisted living; data classification; data mining; healthcare technology; smart cities; smart homes.

Figure 1

Starting with the (reformatted) raw data, a clustering further preprocessed the data before the actual classification was performed. Finally, the computed result was displayed.

Figure 2

Additionally to the activities of daily living (ADL) classifier, a parallel visitor classifier was used. The results of the two classifiers were then merged.

Figure 3

A token was calculated based on all passive infrared (PIR) values. Whenever the token changed (inactive states of all motion sensors were neglected), a change point was set. Periods between two change points were then compressed.

Figure 4

To provide the classifier with contextual information about overlapping time periods, additional feature columns were introduced.

Figure 5

Distribution of PIR recordings during 24 h of measurements for one volunteer. The x-axis shows the time of the day and the y-axis the normalized number of PIR recordings.