Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities

Abstract Non‐suicide self‐injury (NSSI) can be dangerous and difficult for guardians or caregivers to detect in time. NSSI refers to when people hurt themselves even though they have no wish to cause critical or long‐lasting hurt. To timely identify and effectively prevent NSSI in order to reduce th...

Full description

Saved in:
Bibliographic Details
Main Authors: Guanci Yang, Siyuan Yang, Kexin Luo, Shangen Lan, Ling He, Yang Li
Format: Article
Language:English
Published: Wiley 2023-03-01
Series:IET Biometrics
Subjects:
Online Access:https://doi.org/10.1049/bme2.12110
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832546756687036416
author Guanci Yang
Siyuan Yang
Kexin Luo
Shangen Lan
Ling He
Yang Li
author_facet Guanci Yang
Siyuan Yang
Kexin Luo
Shangen Lan
Ling He
Yang Li
author_sort Guanci Yang
collection DOAJ
description Abstract Non‐suicide self‐injury (NSSI) can be dangerous and difficult for guardians or caregivers to detect in time. NSSI refers to when people hurt themselves even though they have no wish to cause critical or long‐lasting hurt. To timely identify and effectively prevent NSSI in order to reduce the suicide rates of patients with a potential suicide risk, the detection of NSSI based on the spatiotemporal features of indoor activities is proposed. Firstly, an NSSI behaviour dataset is provided, and it includes four categories that can be used for scientific research on NSSI evaluation. Secondly, an NSSI detection algorithm based on the spatiotemporal features of indoor activities (NssiDetection) is proposed. NssiDetection calculates the human bounding box by using an object detection model and employs a behaviour detection model to extract the temporal and spatial features of NSSI behaviour. Thirdly, the optimal combination schemes of NssiDetection is investigated by checking its performance with different behaviour detection methods and training strategies. Lastly, a case study is performed by implementing an NSSI behaviour detection prototype system. The prototype system has a recognition accuracy of 84.18% for NSSI actions with new backgrounds, persons, or camera angles.
format Article
id doaj-art-af2bd0343d2d4dc59d1d16493e4b2892
institution Kabale University
issn 2047-4938
2047-4946
language English
publishDate 2023-03-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-af2bd0343d2d4dc59d1d16493e4b28922025-02-03T06:47:18ZengWileyIET Biometrics2047-49382047-49462023-03-011229110110.1049/bme2.12110Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activitiesGuanci Yang0Siyuan Yang1Kexin Luo2Shangen Lan3Ling He4Yang Li5Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaAbstract Non‐suicide self‐injury (NSSI) can be dangerous and difficult for guardians or caregivers to detect in time. NSSI refers to when people hurt themselves even though they have no wish to cause critical or long‐lasting hurt. To timely identify and effectively prevent NSSI in order to reduce the suicide rates of patients with a potential suicide risk, the detection of NSSI based on the spatiotemporal features of indoor activities is proposed. Firstly, an NSSI behaviour dataset is provided, and it includes four categories that can be used for scientific research on NSSI evaluation. Secondly, an NSSI detection algorithm based on the spatiotemporal features of indoor activities (NssiDetection) is proposed. NssiDetection calculates the human bounding box by using an object detection model and employs a behaviour detection model to extract the temporal and spatial features of NSSI behaviour. Thirdly, the optimal combination schemes of NssiDetection is investigated by checking its performance with different behaviour detection methods and training strategies. Lastly, a case study is performed by implementing an NSSI behaviour detection prototype system. The prototype system has a recognition accuracy of 84.18% for NSSI actions with new backgrounds, persons, or camera angles.https://doi.org/10.1049/bme2.12110behavioural sciences computingcomputer visionconvolutional neural netsfeature extractionobject detection
spellingShingle Guanci Yang
Siyuan Yang
Kexin Luo
Shangen Lan
Ling He
Yang Li
Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
IET Biometrics
behavioural sciences computing
computer vision
convolutional neural nets
feature extraction
object detection
title Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
title_full Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
title_fullStr Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
title_full_unstemmed Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
title_short Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities
title_sort detection of non suicidal self injury based on spatiotemporal features of indoor activities
topic behavioural sciences computing
computer vision
convolutional neural nets
feature extraction
object detection
url https://doi.org/10.1049/bme2.12110
work_keys_str_mv AT guanciyang detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities
AT siyuanyang detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities
AT kexinluo detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities
AT shangenlan detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities
AT linghe detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities
AT yangli detectionofnonsuicidalselfinjurybasedonspatiotemporalfeaturesofindooractivities