Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones
An aging society increases the demand for solutions that enable quick reactions, such as calling for help in response to events that may threaten life or health. One of such events is a fall, which is a common cause (or consequence) of injuries among the elderly, that can lead to health problems or...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6688 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849467596495126528 |
|---|---|
| author | Natalia Bartczak Marta Glanowska Karolina Kowalewicz Maciej Kunin Robert Susik |
| author_facet | Natalia Bartczak Marta Glanowska Karolina Kowalewicz Maciej Kunin Robert Susik |
| author_sort | Natalia Bartczak |
| collection | DOAJ |
| description | An aging society increases the demand for solutions that enable quick reactions, such as calling for help in response to events that may threaten life or health. One of such events is a fall, which is a common cause (or consequence) of injuries among the elderly, that can lead to health problems or even death. Fall may be also a symptom of a serious health problem, such as a stroke or a heart attack. This study addresses the fall detection problem. We propose a fall detection solution based on accelerometer data from smartphone devices. The proposed model is based on a Recurrent Neural Network employing a Gated Recurrent Unit (GRU) layer. We compared the results with the state-of-the-art solutions available in the literature using the UniMiB SHAR dataset containing accelerometer data collected using smartphone devices. The dataset contains the validation dataset prepared for evaluation using the Leave-One-Subject-Out (LOSO-CV) and 5-Fold Cross-Validation (CV) strategies; consequently, we used them for evaluation. Our solution achieves the highest result for Leave-One-Subject-Out and a comparable result for the <i>k</i>-Fold Cross-Validation strategy, achieving 98.99% and 99.82% accuracy, respectively. We believe it has the potential for adoption in production devices, which could be helpful, for example, in nursing homes, improving the provision of assistance especially when combined into a multimodal system with other sensors. We also provide all the data and code used in our experiments publicly, allowing other researchers to reproduce our results. |
| format | Article |
| id | doaj-art-5abea1df23444897a34da48d77075e20 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-5abea1df23444897a34da48d77075e202025-08-20T03:26:10ZengMDPI AGApplied Sciences2076-34172025-06-011512668810.3390/app15126688Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from SmartphonesNatalia Bartczak0Marta Glanowska1Karolina Kowalewicz2Maciej Kunin3Robert Susik4Institute of Applied Computer Science, Lodz University of Technology, Żeromskiego 116, 90-924 Lodz, PolandInstitute of Applied Computer Science, Lodz University of Technology, Żeromskiego 116, 90-924 Lodz, PolandInstitute of Applied Computer Science, Lodz University of Technology, Żeromskiego 116, 90-924 Lodz, PolandInstitute of Applied Computer Science, Lodz University of Technology, Żeromskiego 116, 90-924 Lodz, PolandInstitute of Applied Computer Science, Lodz University of Technology, Żeromskiego 116, 90-924 Lodz, PolandAn aging society increases the demand for solutions that enable quick reactions, such as calling for help in response to events that may threaten life or health. One of such events is a fall, which is a common cause (or consequence) of injuries among the elderly, that can lead to health problems or even death. Fall may be also a symptom of a serious health problem, such as a stroke or a heart attack. This study addresses the fall detection problem. We propose a fall detection solution based on accelerometer data from smartphone devices. The proposed model is based on a Recurrent Neural Network employing a Gated Recurrent Unit (GRU) layer. We compared the results with the state-of-the-art solutions available in the literature using the UniMiB SHAR dataset containing accelerometer data collected using smartphone devices. The dataset contains the validation dataset prepared for evaluation using the Leave-One-Subject-Out (LOSO-CV) and 5-Fold Cross-Validation (CV) strategies; consequently, we used them for evaluation. Our solution achieves the highest result for Leave-One-Subject-Out and a comparable result for the <i>k</i>-Fold Cross-Validation strategy, achieving 98.99% and 99.82% accuracy, respectively. We believe it has the potential for adoption in production devices, which could be helpful, for example, in nursing homes, improving the provision of assistance especially when combined into a multimodal system with other sensors. We also provide all the data and code used in our experiments publicly, allowing other researchers to reproduce our results.https://www.mdpi.com/2076-3417/15/12/6688fall detectionaccelerometercellphoneUniMiB SHARrecurrent neural networks |
| spellingShingle | Natalia Bartczak Marta Glanowska Karolina Kowalewicz Maciej Kunin Robert Susik Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones Applied Sciences fall detection accelerometer cellphone UniMiB SHAR recurrent neural networks |
| title | Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones |
| title_full | Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones |
| title_fullStr | Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones |
| title_full_unstemmed | Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones |
| title_short | Fall Detection Based on Recurrent Neural Networks and Accelerometer Data from Smartphones |
| title_sort | fall detection based on recurrent neural networks and accelerometer data from smartphones |
| topic | fall detection accelerometer cellphone UniMiB SHAR recurrent neural networks |
| url | https://www.mdpi.com/2076-3417/15/12/6688 |
| work_keys_str_mv | AT nataliabartczak falldetectionbasedonrecurrentneuralnetworksandaccelerometerdatafromsmartphones AT martaglanowska falldetectionbasedonrecurrentneuralnetworksandaccelerometerdatafromsmartphones AT karolinakowalewicz falldetectionbasedonrecurrentneuralnetworksandaccelerometerdatafromsmartphones AT maciejkunin falldetectionbasedonrecurrentneuralnetworksandaccelerometerdatafromsmartphones AT robertsusik falldetectionbasedonrecurrentneuralnetworksandaccelerometerdatafromsmartphones |