Discovering Human Activities from Binary Data in Smart Homes
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 di...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2513 |
| _version_ | 1827717776110780416 |
|---|---|
| author | Mohamed Eldib Wilfried Philips Hamid Aghajan |
| author_facet | Mohamed Eldib Wilfried Philips Hamid Aghajan |
| author_sort | Mohamed Eldib |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T20:09:11Z |
| format | Article |
| id | doaj.art-19adcafc56884421a936e25a733d16ec |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:09:11Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-19adcafc56884421a936e25a733d16ec2023-11-19T23:01:32ZengMDPI AGSensors1424-82202020-04-01209251310.3390/s20092513Discovering Human Activities from Binary Data in Smart HomesMohamed Eldib0Wilfried Philips1Hamid Aghajan2imec-TELIN-IPI, Ghent University, Sint-Pietersnieuwstraat 41, 9000 Ghent, Belgiumimec-TELIN-IPI, Ghent University, Sint-Pietersnieuwstraat 41, 9000 Ghent, Belgiumimec-TELIN-IPI, Ghent University, Sint-Pietersnieuwstraat 41, 9000 Ghent, BelgiumWith 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.https://www.mdpi.com/1424-8220/20/9/2513human activity discoverysmart homeshealth monitoringclusteringunsupervised learningsequence mining |
| spellingShingle | Mohamed Eldib Wilfried Philips Hamid Aghajan Discovering Human Activities from Binary Data in Smart Homes Sensors human activity discovery smart homes health monitoring clustering unsupervised learning sequence mining |
| title | Discovering Human Activities from Binary Data in Smart Homes |
| title_full | Discovering Human Activities from Binary Data in Smart Homes |
| title_fullStr | Discovering Human Activities from Binary Data in Smart Homes |
| title_full_unstemmed | Discovering Human Activities from Binary Data in Smart Homes |
| title_short | Discovering Human Activities from Binary Data in Smart Homes |
| title_sort | discovering human activities from binary data in smart homes |
| topic | human activity discovery smart homes health monitoring clustering unsupervised learning sequence mining |
| url | https://www.mdpi.com/1424-8220/20/9/2513 |
| work_keys_str_mv | AT mohamedeldib discoveringhumanactivitiesfrombinarydatainsmarthomes AT wilfriedphilips discoveringhumanactivitiesfrombinarydatainsmarthomes AT hamidaghajan discoveringhumanactivitiesfrombinarydatainsmarthomes |