Recognition of Daily Activities of Two Residents in a Smart Home Based on Time Clustering

Abstract

With the development of population aging, the recognition of elderly activity in smart homes has received increasing attention. In recent years, single-resident activity recognition based on smart homes has made great progress. However, few researchers have focused on multi-resident activity recognition. In this paper, we propose a method to recognize two-resident activities based on time clustering. First, to use a de-noising method to extract the feature of the dataset. Second, to cluster the dataset based on the begin time and end time. Finally, to complete activity recognition using a similarity matching method. To test the performance of the method, we used two two-resident datasets provided by Center for Advanced Studies in Adaptive Systems (CASAS). We evaluated our method by comparing it with some common classifiers. The results show that our method has certain improvements in the accuracy, recall, precision, and F-Measure. At the end of the paper, we explain the parameter selection and summarize our method.

Activity Recognition for Ambient Assisted Living with Videos, Inertial Units and Ambient Sensors

“…Gochoo et al [ 94 ] extracted fixed-length sliding windows into a sparse two-dimensional time matrix to use Convolutional Neural Networks (CNN) for activity recognition. Guo et al [ 15 ] provided a data-driven framework for activity recognition from multiple residents using time clustering.…”

“…To date, most research on this field has focused on single modality approaches, which may consist of either RGB [ 12 ] or RGB-D videos [ 13 ], wearables such as inertial sensors (Inertial Measurement Units—IMUs) [ 14 ], or ambient sensors [ 15 ]. The scenarios in which each of these modalities have been employed for activity recognition vary according to the availability of data, which may be constrained by technical or ethical limitations.…”

An Entropy-Based Approach for Anomaly Detection in Activities of Daily Living in the Presence of a Visitor

“…Distinguishing and detecting a visitor in a single-occupancy home environment (represented as a multi-occupancy environment) based on ambient sensors is still a significant challenge for researchers. In recent years, some research works have been conducted on detecting and distinguishing activities in a multi-occupancy environment [ 4 , 30 , 31 , 32 , 33 ]. However, a few works have focused on visitor detection in a home environment based on ambient sensors, and especially on those with binary sensors.…”

“…The results obtained from this work show that the proposed method achieved an average activity recognition rate of 95.83% in the context of a multi-occupancy home environment. Another new research study [ 4 ] has presented a daily activity recognition method based on time clustering for multi-occupancy in a smart home environment. The required features are extracted from the raw data using a de-noising method.…”

“…This has a serious influence on the healthcare sector, with the cost of elderly care expected to increase enormously over the coming years [ 2 , 3 ]. Additionally, researchers have demonstrated that the number of older adults living alone at home and the number of single-occupancy homes are also growing worldwide, due partly to the high expense of residential care services [ 4 , 5 , 6 ]. The majority of older adults require continuous help in their Activities of Daily Living (ADL).…”