Dataset Information

Discovering Human Activities from Binary Data in Smart Homes.

ABSTRACT: With the rapid development in sensing technology, data mining, and machine learning fields for human health monitoring, it became possible to enable monitoring of personal motion and vital signs in a manner that minimizes the disruption of an individual's daily routine and assist individuals with difficulties to live independently at home. A primary difficulty that researchers confront is acquiring an adequate amount of labeled data for model training and validation purposes. Therefore, activity discovery handles the problem that activity labels are not available using approaches based on sequence mining and clustering. In this paper, we introduce an unsupervised method for discovering activities from a network of motion detectors in a smart home setting. First, we present an intra-day clustering algorithm to find frequent sequential patterns within a day. As a second step, we present an inter-day clustering algorithm to find the common frequent patterns between days. Furthermore, we refine the patterns to have more compressed and defined cluster characterizations. Finally, we track the occurrences of various regular routines to monitor the functional health in an individual's patterns and lifestyle. We evaluate our methods on two public data sets captured in real-life settings from two apartments during seven-month and three-month periods.

SUBMITTER: Eldib M

PROVIDER: S-EPMC7248863 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Discovering Human Activities from Binary Data in Smart Homes.

Eldib Mohamed M Philips Wilfried W Aghajan Hamid H

Sensors (Basel, Switzerland) 20200429 9

With the rapid development in sensing technology, data mining, and machine learning fields for human health monitoring, it became possible to enable monitoring of personal motion and vital signs in a manner that minimizes the disruption of an individual's daily routine and assist individuals with difficulties to live independently at home. A primary difficulty that researchers confront is acquiring an adequate amount of labeled data for model training and validation purposes. Therefore, activity ...[more]

PMID: 32365545

Similar Datasets

Project description:BACKGROUND:Smart homes are considered effective solutions for home health care for the elderly, as smart home technologies can reduce care costs and improve elderly residents' independence. To develop a greater understanding of smart homes for health care services (SHHSs), this study accentuated the necessity of ecological approaches with an emphasis on environmental constraints. This study was based on 2 rationales: (1) users are inclined to perceive the service quality and service experience from environments (ie, servicescape) owing to the intangibility of health care and the pervasiveness of smart home technologies, and (2) both service domains are complex adaptive systems in which diversified and undefined service experiences-not only a few intended service flows-can be generated by complex combinations of servicescape elements. OBJECTIVE:This study proposed the conceptual framework of a Smart Servicescape Wheel (SSW) as an ecological approach delineating the extensive spectrum of environmental constraints in SHHSs. METHODS:The SSW framework was established based on a literature review. RESULTS:Generally divided by perceptible and imperceptible servicescapes, the SSW consists of the perceptible Physical scape (ie, hardware components, environmental cues, and human states) and Social scape (ie, service relationships and social relationships) as well as the imperceptible Datascape (ie, computing intelligence, databases, and communication networks). Following the ecological approach, each category of the SSW is subdivided and defined at the level of components or functions. CONCLUSIONS:The SSW's strengths lie in the various application opportunities for SHHSs. In terms of service planning and development, the SSW can be utilized to (1) establish the requirements for SHHS development, (2) associate with work domain analysis by defining component layers, and (3) understand the real contexts of SHHSs for the enhanced prediction of diverse service experiences. Regarding service management, it can be applied to develop measurement items for the operation and evaluation of SHHSs.

Dataset Information

Discovering Human Activities from Binary Data in Smart Homes.

Publications

Discovering Human Activities from Binary Data in Smart Homes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets