Fall detection for elderly-people monitoring using learned features and recurrent neural networks
Elderly care is becoming a relevant issue with the increase of population ageing. Fall injuries, with their impact on social and healthcare cost, represent one of the biggest concerns over the years. Researchers are focusing their attention on several fall-detection algorithms. In this paper, we pre...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2020-01-01
|
| Series: | Experimental Results |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2516712X20000039/type/journal_article |
| _version_ | 1811156289202421760 |
|---|---|
| author | Daniele Berardini Sara Moccia Lucia Migliorelli Iacopo Pacifici Paolo di Massimo Marina Paolanti Emanuele Frontoni Adín Ramírez Rivera |
| author_facet | Daniele Berardini Sara Moccia Lucia Migliorelli Iacopo Pacifici Paolo di Massimo Marina Paolanti Emanuele Frontoni Adín Ramírez Rivera |
| author_sort | Daniele Berardini |
| collection | DOAJ |
| description | Elderly care is becoming a relevant issue with the increase of population ageing. Fall injuries, with their impact on social and healthcare cost, represent one of the biggest concerns over the years. Researchers are focusing their attention on several fall-detection algorithms. In this paper, we present a deep-learning solution for automatic fall detection from RGB videos. The proposed approach achieved a mean recall of 0.916, prompting the possibility of translating this approach in the actual monitoring practice. Moreover to enable the scientific community making research on the topic the dataset used for our experiments will be released. This could enhance elderly people safety and quality of life, attenuating risks during elderly activities of daily living with reduced healthcare costs as a final result. |
| first_indexed | 2024-04-10T04:48:00Z |
| format | Article |
| id | doaj.art-2a3ff302af6245d398c2fee0e6001d72 |
| institution | Directory Open Access Journal |
| issn | 2516-712X |
| language | English |
| last_indexed | 2024-04-10T04:48:00Z |
| publishDate | 2020-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Experimental Results |
| spelling | doaj.art-2a3ff302af6245d398c2fee0e6001d722023-03-09T12:34:21ZengCambridge University PressExperimental Results2516-712X2020-01-01110.1017/exp.2020.3Fall detection for elderly-people monitoring using learned features and recurrent neural networksDaniele Berardini0https://orcid.org/0000-0001-7009-6317Sara Moccia1Lucia Migliorelli2Iacopo Pacifici3Paolo di Massimo4Marina Paolanti5https://orcid.org/0000-0002-5523-7174Emanuele Frontoni6Adín Ramírez Rivera7Department of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Ancona, ItalyUNICAMP, Institute of Computing, Av. Albert Einstein 1251, Campinas, São Paulo, Brazil, 13083-872Elderly care is becoming a relevant issue with the increase of population ageing. Fall injuries, with their impact on social and healthcare cost, represent one of the biggest concerns over the years. Researchers are focusing their attention on several fall-detection algorithms. In this paper, we present a deep-learning solution for automatic fall detection from RGB videos. The proposed approach achieved a mean recall of 0.916, prompting the possibility of translating this approach in the actual monitoring practice. Moreover to enable the scientific community making research on the topic the dataset used for our experiments will be released. This could enhance elderly people safety and quality of life, attenuating risks during elderly activities of daily living with reduced healthcare costs as a final result.https://www.cambridge.org/core/product/identifier/S2516712X20000039/type/journal_articleBidirectional LSTMconvolutional neural networksfall detectionfine tuningRGB videos |
| spellingShingle | Daniele Berardini Sara Moccia Lucia Migliorelli Iacopo Pacifici Paolo di Massimo Marina Paolanti Emanuele Frontoni Adín Ramírez Rivera Fall detection for elderly-people monitoring using learned features and recurrent neural networks Experimental Results Bidirectional LSTM convolutional neural networks fall detection fine tuning RGB videos |
| title | Fall detection for elderly-people monitoring using learned features and recurrent neural networks |
| title_full | Fall detection for elderly-people monitoring using learned features and recurrent neural networks |
| title_fullStr | Fall detection for elderly-people monitoring using learned features and recurrent neural networks |
| title_full_unstemmed | Fall detection for elderly-people monitoring using learned features and recurrent neural networks |
| title_short | Fall detection for elderly-people monitoring using learned features and recurrent neural networks |
| title_sort | fall detection for elderly people monitoring using learned features and recurrent neural networks |
| topic | Bidirectional LSTM convolutional neural networks fall detection fine tuning RGB videos |
| url | https://www.cambridge.org/core/product/identifier/S2516712X20000039/type/journal_article |
| work_keys_str_mv | AT danieleberardini falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT saramoccia falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT luciamigliorelli falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT iacopopacifici falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT paolodimassimo falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT marinapaolanti falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT emanuelefrontoni falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks AT adinramirezrivera falldetectionforelderlypeoplemonitoringusinglearnedfeaturesandrecurrentneuralnetworks |