Dynamic similarity‐based activity detection and recognition within smart homes

Abstract

Purpose-Within smart homes, ambient sensors are used to monitor interactions between users and the home environment. The data produced from the sensors are used as the basis for the inference of the users' behaviour information. Partitioning sensor data in response to individual instances of activity is critical for a smart home to be fully functional and to fulfil its roles, such as correctly measuring health status and detecting emergency situations. The purpose of this study is to propose a similarity-based segmentation approach applied on time series sensor data in an effort to detect and recognise activities within a smart home. Design/methodology/approach-The paper explores methods for analysing time-related sensor activation events in an effort to undercover hidden activity events through the use of generic sensor modelling of activity based upon the general knowledge of the activities. Two similarity measures are proposed to compare a time series based sensor sequence and a generic sensor model of an activity. In addition, a framework is developed for automatically analysing sensor streams. Findings-The results from evaluation of the proposed methodology on a publicly accessible reference dataset show that the proposed methods can detect and recognise multi-category activities with satisfying accuracy, in addition to the capability of detecting interleaved activities. Originality/value-The concepts introduced in this paper will improve automatic detection and recognition of daily living activities from timely ordered sensor events based on domain knowledge of the activities.

Human Activity Recognition in Smart-Home Environments for Health-Care Applications

“…Observations regarding the user's surrounding environment (in particular, objects' use), possibly coupled with body-worn sensor data, are the basis of those activity recognition systems [3,55]. In [56] the authors propose a time series data analysis method to segment sequences of sensor events in order to recognize ADLs. The application of Hidden Markov Models inference is proposed in [42] to recognize activities based on features extracted from recent sensor events according to a sliding window.…”

“…Other works rely on description logic languages to formally express activity definitions [63,64]. Background knowledge of ADLs has been used to create activity models, used to recognize ADLs based on the similarity of sequences of sensor events to the general models [67]. Ontological reasoning has also been proposed to perform dynamic segmentation of sensor data [68,69,70] or to refine the output of supervised learning methods [71].…”

Insights into the Impact of Implementing a Smart House on Special Needs People in the UAE

“…As a result of numerous security breaches, smart home system has to be protected against intrusion and has to make sure that the information reaches only to the right people (Portet et al, 2013). As mentioned before, to cover the many functions in the house, there has to be a variety of sensing technologies are available, such as cameras, audio devices and statechange sensors fire guard and smart door guard (Hong et al, 2012;Melkas, 2013).…”

“…According to (Hong et al, 2012), ADL covers a broad range of living functions in any house, be it normal or smart. Activities like using the telephone, preparing meals and drinks, washing the dishes, taking baths and showers, wearing clothes, taking medications, toileting and many other simple activities.…”

HoTAAL: Home of social things meet ambient assisted living

“…These approaches are predominantly based on sensors attached to the environment, to detect changes in the environment as a result of human activities [3]. Examples of such sensors include switches, passive infra-red (PIR) sensors and proximity sensors.…”