Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM
Human falls are the premier cause of fatal and nonfatal injuries among older adults. The health outcome of a fall event is largely dependent on rapid response and rescue of the fallen elder. Being able to provide an accurate and fast fall detection will dramatically improve the health outcomes of th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/17/3720 |
| _version_ | 1811300607470862336 |
|---|---|
| author | Chengyin Liu Zhaoshuo Jiang Xiangxiang Su Samuel Benzoni Alec Maxwell |
| author_facet | Chengyin Liu Zhaoshuo Jiang Xiangxiang Su Samuel Benzoni Alec Maxwell |
| author_sort | Chengyin Liu |
| collection | DOAJ |
| description | Human falls are the premier cause of fatal and nonfatal injuries among older adults. The health outcome of a fall event is largely dependent on rapid response and rescue of the fallen elder. Being able to provide an accurate and fast fall detection will dramatically improve the health outcomes of the older population and reduce the associated healthcare cost after a fall. To achieve the goal, a multi-features semi-supervised support vector machines (MFSS-SVM) algorithm utilizing measurements from structural floor vibration obtained through accelerometers is proposed in this study to detect falling events with limited labeled samples. In this MFSS-SVM algorithm, the peak value, energy, and correlation coefficient of the accelerometer signal are used as classification features. The performance of the proposed algorithm was validated with laboratory experiments among activities including falling, walking, free jumping, rhythmic jumping, bag dropping, and ball dropping. To further illustrate the performance of the algorithm, a benchmark database was adopted and expanded to test its ability to accurately identify falling, compared with the algorithm used in the benchmark study. Results show that by using the proposed algorithm, the falling events can be identified with high accuracy and confidence, even with small training datasets and test nodes. |
| first_indexed | 2024-04-13T06:54:51Z |
| format | Article |
| id | doaj.art-371929e088c24daf87a077da958653dd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T06:54:51Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-371929e088c24daf87a077da958653dd2022-12-22T02:57:17ZengMDPI AGSensors1424-82202019-08-011917372010.3390/s19173720s19173720Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVMChengyin Liu0Zhaoshuo Jiang1Xiangxiang Su2Samuel Benzoni3Alec Maxwell4Department of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen 518055, ChinaSchool of Engineering, San Francisco State University, San Francisco, CA 94132, USADepartment of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen 518055, ChinaSchool of Engineering, San Francisco State University, San Francisco, CA 94132, USASchool of Engineering, San Francisco State University, San Francisco, CA 94132, USAHuman falls are the premier cause of fatal and nonfatal injuries among older adults. The health outcome of a fall event is largely dependent on rapid response and rescue of the fallen elder. Being able to provide an accurate and fast fall detection will dramatically improve the health outcomes of the older population and reduce the associated healthcare cost after a fall. To achieve the goal, a multi-features semi-supervised support vector machines (MFSS-SVM) algorithm utilizing measurements from structural floor vibration obtained through accelerometers is proposed in this study to detect falling events with limited labeled samples. In this MFSS-SVM algorithm, the peak value, energy, and correlation coefficient of the accelerometer signal are used as classification features. The performance of the proposed algorithm was validated with laboratory experiments among activities including falling, walking, free jumping, rhythmic jumping, bag dropping, and ball dropping. To further illustrate the performance of the algorithm, a benchmark database was adopted and expanded to test its ability to accurately identify falling, compared with the algorithm used in the benchmark study. Results show that by using the proposed algorithm, the falling events can be identified with high accuracy and confidence, even with small training datasets and test nodes.https://www.mdpi.com/1424-8220/19/17/3720falling detectionfall loading modelfloor vibrationmulti-features semi-supervised support vector machinesbenchmark problem |
| spellingShingle | Chengyin Liu Zhaoshuo Jiang Xiangxiang Su Samuel Benzoni Alec Maxwell Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM Sensors falling detection fall loading model floor vibration multi-features semi-supervised support vector machines benchmark problem |
| title | Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM |
| title_full | Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM |
| title_fullStr | Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM |
| title_full_unstemmed | Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM |
| title_short | Detection of Human Fall Using Floor Vibration and Multi-Features Semi-Supervised SVM |
| title_sort | detection of human fall using floor vibration and multi features semi supervised svm |
| topic | falling detection fall loading model floor vibration multi-features semi-supervised support vector machines benchmark problem |
| url | https://www.mdpi.com/1424-8220/19/17/3720 |
| work_keys_str_mv | AT chengyinliu detectionofhumanfallusingfloorvibrationandmultifeaturessemisupervisedsvm AT zhaoshuojiang detectionofhumanfallusingfloorvibrationandmultifeaturessemisupervisedsvm AT xiangxiangsu detectionofhumanfallusingfloorvibrationandmultifeaturessemisupervisedsvm AT samuelbenzoni detectionofhumanfallusingfloorvibrationandmultifeaturessemisupervisedsvm AT alecmaxwell detectionofhumanfallusingfloorvibrationandmultifeaturessemisupervisedsvm |