A Robust and Device-Free System for the Recognition and Classification of Elderly Activities
Human activity recognition, tracking and classification is an essential trend in assisted living systems that can help support elderly people with their daily activities. Traditional activity recognition approaches depend on vision-based or sensor-based techniques. Nowadays, a novel promising techni...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/12/2043 |
| _version_ | 1818014144802062336 |
|---|---|
| author | Fangmin Li Mohammed Abdulaziz Aide Al-qaness Yong Zhang Bihai Zhao Xidao Luan |
| author_facet | Fangmin Li Mohammed Abdulaziz Aide Al-qaness Yong Zhang Bihai Zhao Xidao Luan |
| author_sort | Fangmin Li |
| collection | DOAJ |
| description | Human activity recognition, tracking and classification is an essential trend in assisted living systems that can help support elderly people with their daily activities. Traditional activity recognition approaches depend on vision-based or sensor-based techniques. Nowadays, a novel promising technique has obtained more attention, namely device-free human activity recognition that neither requires the target object to wear or carry a device nor install cameras in a perceived area. The device-free technique for activity recognition uses only the signals of common wireless local area network (WLAN) devices available everywhere. In this paper, we present a novel elderly activities recognition system by leveraging the fluctuation of the wireless signals caused by human motion. We present an efficient method to select the correct data from the Channel State Information (CSI) streams that were neglected in previous approaches. We apply a Principle Component Analysis method that exposes the useful information from raw CSI. Thereafter, Forest Decision (FD) is adopted to classify the proposed activities and has gained a high accuracy rate. Extensive experiments have been conducted in an indoor environment to test the feasibility of the proposed system with a total of five volunteer users. The evaluation shows that the proposed system is applicable and robust to electromagnetic noise. |
| first_indexed | 2024-04-14T06:41:27Z |
| format | Article |
| id | doaj.art-cb66dd65854d49bda45a283842b8e984 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T06:41:27Z |
| publishDate | 2016-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cb66dd65854d49bda45a283842b8e9842022-12-22T02:07:19ZengMDPI AGSensors1424-82202016-12-011612204310.3390/s16122043s16122043A Robust and Device-Free System for the Recognition and Classification of Elderly ActivitiesFangmin Li0Mohammed Abdulaziz Aide Al-qaness1Yong Zhang2Bihai Zhao3Xidao Luan4Department of Mathematics and Computer Science, Changsha University, Changsha 410022, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 407003, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 407003, ChinaDepartment of Mathematics and Computer Science, Changsha University, Changsha 410022, ChinaDepartment of Mathematics and Computer Science, Changsha University, Changsha 410022, ChinaHuman activity recognition, tracking and classification is an essential trend in assisted living systems that can help support elderly people with their daily activities. Traditional activity recognition approaches depend on vision-based or sensor-based techniques. Nowadays, a novel promising technique has obtained more attention, namely device-free human activity recognition that neither requires the target object to wear or carry a device nor install cameras in a perceived area. The device-free technique for activity recognition uses only the signals of common wireless local area network (WLAN) devices available everywhere. In this paper, we present a novel elderly activities recognition system by leveraging the fluctuation of the wireless signals caused by human motion. We present an efficient method to select the correct data from the Channel State Information (CSI) streams that were neglected in previous approaches. We apply a Principle Component Analysis method that exposes the useful information from raw CSI. Thereafter, Forest Decision (FD) is adopted to classify the proposed activities and has gained a high accuracy rate. Extensive experiments have been conducted in an indoor environment to test the feasibility of the proposed system with a total of five volunteer users. The evaluation shows that the proposed system is applicable and robust to electromagnetic noise.http://www.mdpi.com/1424-8220/16/12/2043Wi-Fiactivity recognitiondevice-freefeature extractionPrinciple Component Analysis |
| spellingShingle | Fangmin Li Mohammed Abdulaziz Aide Al-qaness Yong Zhang Bihai Zhao Xidao Luan A Robust and Device-Free System for the Recognition and Classification of Elderly Activities Sensors Wi-Fi activity recognition device-free feature extraction Principle Component Analysis |
| title | A Robust and Device-Free System for the Recognition and Classification of Elderly Activities |
| title_full | A Robust and Device-Free System for the Recognition and Classification of Elderly Activities |
| title_fullStr | A Robust and Device-Free System for the Recognition and Classification of Elderly Activities |
| title_full_unstemmed | A Robust and Device-Free System for the Recognition and Classification of Elderly Activities |
| title_short | A Robust and Device-Free System for the Recognition and Classification of Elderly Activities |
| title_sort | robust and device free system for the recognition and classification of elderly activities |
| topic | Wi-Fi activity recognition device-free feature extraction Principle Component Analysis |
| url | http://www.mdpi.com/1424-8220/16/12/2043 |
| work_keys_str_mv | AT fangminli arobustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT mohammedabdulazizaidealqaness arobustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT yongzhang arobustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT bihaizhao arobustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT xidaoluan arobustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT fangminli robustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT mohammedabdulazizaidealqaness robustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT yongzhang robustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT bihaizhao robustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities AT xidaoluan robustanddevicefreesystemfortherecognitionandclassificationofelderlyactivities |