Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers
Accidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no highperformance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2022-08-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2021-0190 |
| _version_ | 1797985657413435392 |
|---|---|
| author | Mingi Jeong Sangyeoun Lee Kang Bok Lee |
| author_facet | Mingi Jeong Sangyeoun Lee Kang Bok Lee |
| author_sort | Mingi Jeong |
| collection | DOAJ |
| description | Accidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no highperformance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented in existing studies, collect new data (from two stunt performers and 15 people over age 60) using a developed wearable device, demonstrate new features and related accident detection algorithms, and analyze the performance of the proposed method against existing methods. Comparative analysis results show that the newly defined features extracted reflect more important risk factors than those used in existing studies. Further, although the traditional algorithms applied to integrated data achieved an accuracy (AC) of 79.5% and a false positive rate (FPR) of 19.4%, the proposed accident detection algorithms achieved 97.8% AC and 2.9% FPR. The high AC and low FPR for accidental falls indicate that the proposed method exhibits a considerable advancement toward developing a commercial accident detection system. |
| first_indexed | 2024-04-11T07:20:26Z |
| format | Article |
| id | doaj.art-e7c48e560ff34f68bf7d224dafd68c77 |
| institution | Directory Open Access Journal |
| issn | 1225-6463 |
| language | English |
| last_indexed | 2024-04-11T07:20:26Z |
| publishDate | 2022-08-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-e7c48e560ff34f68bf7d224dafd68c772022-12-22T04:37:46ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632022-08-0144465467110.4218/etrij.2021-019010.4218/etrij.2021-0190Accident detection algorithm using features associated with risk factors and acceleration data from stunt performersMingi JeongSangyeoun LeeKang Bok LeeAccidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no highperformance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented in existing studies, collect new data (from two stunt performers and 15 people over age 60) using a developed wearable device, demonstrate new features and related accident detection algorithms, and analyze the performance of the proposed method against existing methods. Comparative analysis results show that the newly defined features extracted reflect more important risk factors than those used in existing studies. Further, although the traditional algorithms applied to integrated data achieved an accuracy (AC) of 79.5% and a false positive rate (FPR) of 19.4%, the proposed accident detection algorithms achieved 97.8% AC and 2.9% FPR. The high AC and low FPR for accidental falls indicate that the proposed method exhibits a considerable advancement toward developing a commercial accident detection system.https://doi.org/10.4218/etrij.2021-0190accident detection systemactivities of daily lifebehavior datafall detectionmachine learning |
| spellingShingle | Mingi Jeong Sangyeoun Lee Kang Bok Lee Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers ETRI Journal accident detection system activities of daily life behavior data fall detection machine learning |
| title | Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| title_full | Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| title_fullStr | Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| title_full_unstemmed | Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| title_short | Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| title_sort | accident detection algorithm using features associated with risk factors and acceleration data from stunt performers |
| topic | accident detection system activities of daily life behavior data fall detection machine learning |
| url | https://doi.org/10.4218/etrij.2021-0190 |
| work_keys_str_mv | AT mingijeong accidentdetectionalgorithmusingfeaturesassociatedwithriskfactorsandaccelerationdatafromstuntperformers AT sangyeounlee accidentdetectionalgorithmusingfeaturesassociatedwithriskfactorsandaccelerationdatafromstuntperformers AT kangboklee accidentdetectionalgorithmusingfeaturesassociatedwithriskfactorsandaccelerationdatafromstuntperformers |