IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm
Falls are the leading cause of fatal injuries in the elderly such as fractures, and secondary damage from falls can lead to death. As such, fall detection is a crucial topic. However, due to the trade-off relationship between privacy preservation, user convenience, and fall detection performance, it...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/20/5948 |
| _version_ | 1797550290140921856 |
|---|---|
| author | Taekjin Han Wonho Kang Gyunghyun Choi |
| author_facet | Taekjin Han Wonho Kang Gyunghyun Choi |
| author_sort | Taekjin Han |
| collection | DOAJ |
| description | Falls are the leading cause of fatal injuries in the elderly such as fractures, and secondary damage from falls can lead to death. As such, fall detection is a crucial topic. However, due to the trade-off relationship between privacy preservation, user convenience, and fall detection performance, it is generally difficult to develop a fall detection system that simultaneously satisfies all conditions. The main goal of this study is to build a practical fall detection framework that can effectively classify the various behavior types into “Fall” and “Activities of daily living (ADL)” while securing privacy preservation and user convenience. For this purpose, signal data containing the motion information of objects was collected using a non-contact, unobtrusive, and non-restraint impulse-radio ultra wideband (IR-UWB) radar. These data were then applied to a convolutional neural network (CNN) algorithm to create an object behavior type classifier that can classify the behavior types of objects into “Fall” and “ADL.” The data were collected by actually performing various activities of daily living, including falling. The performance of the classifier yielded satisfactory results. By combining an IR-UWB and CNN algorithm, this study demonstrates the feasibility of building a practical fall detection system that exceeds a certain level of detection accuracy while also ensuring privacy preservation and user convenience. |
| first_indexed | 2024-03-10T15:27:12Z |
| format | Article |
| id | doaj.art-0bae026b785d4e018da9a904761508fc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:27:12Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0bae026b785d4e018da9a904761508fc2023-11-20T17:56:22ZengMDPI AGSensors1424-82202020-10-012020594810.3390/s20205948IR-UWB Sensor Based Fall Detection Method Using CNN AlgorithmTaekjin Han0Wonho Kang1Gyunghyun Choi2Graduate School of Technology & Innovation Management, Hanyang University, Wangsimni-ro 222, Seongdong-gu, Seoul 04763, KoreaGraduate School of Technology & Innovation Management, Hanyang University, Wangsimni-ro 222, Seongdong-gu, Seoul 04763, KoreaGraduate School of Technology & Innovation Management, Hanyang University, Wangsimni-ro 222, Seongdong-gu, Seoul 04763, KoreaFalls are the leading cause of fatal injuries in the elderly such as fractures, and secondary damage from falls can lead to death. As such, fall detection is a crucial topic. However, due to the trade-off relationship between privacy preservation, user convenience, and fall detection performance, it is generally difficult to develop a fall detection system that simultaneously satisfies all conditions. The main goal of this study is to build a practical fall detection framework that can effectively classify the various behavior types into “Fall” and “Activities of daily living (ADL)” while securing privacy preservation and user convenience. For this purpose, signal data containing the motion information of objects was collected using a non-contact, unobtrusive, and non-restraint impulse-radio ultra wideband (IR-UWB) radar. These data were then applied to a convolutional neural network (CNN) algorithm to create an object behavior type classifier that can classify the behavior types of objects into “Fall” and “ADL.” The data were collected by actually performing various activities of daily living, including falling. The performance of the classifier yielded satisfactory results. By combining an IR-UWB and CNN algorithm, this study demonstrates the feasibility of building a practical fall detection system that exceeds a certain level of detection accuracy while also ensuring privacy preservation and user convenience.https://www.mdpi.com/1424-8220/20/20/5948IR-UWB radar sensorfall detectionfall/ADL classificationdeep learning classifierconvolutional neural network |
| spellingShingle | Taekjin Han Wonho Kang Gyunghyun Choi IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm Sensors IR-UWB radar sensor fall detection fall/ADL classification deep learning classifier convolutional neural network |
| title | IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm |
| title_full | IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm |
| title_fullStr | IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm |
| title_full_unstemmed | IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm |
| title_short | IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm |
| title_sort | ir uwb sensor based fall detection method using cnn algorithm |
| topic | IR-UWB radar sensor fall detection fall/ADL classification deep learning classifier convolutional neural network |
| url | https://www.mdpi.com/1424-8220/20/20/5948 |
| work_keys_str_mv | AT taekjinhan iruwbsensorbasedfalldetectionmethodusingcnnalgorithm AT wonhokang iruwbsensorbasedfalldetectionmethodusingcnnalgorithm AT gyunghyunchoi iruwbsensorbasedfalldetectionmethodusingcnnalgorithm |