A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia

This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of tw...

Full description

Saved in:
Bibliographic Details
Main Authors: Ioannis Galanakis, Rigas Filippos Soldatos, Nikitas Karanikolas, Athanasios Voulodimos, Ioannis Voyiatzis, Maria Samarakou
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10266
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154585298698240
author Ioannis Galanakis
Rigas Filippos Soldatos
Nikitas Karanikolas
Athanasios Voulodimos
Ioannis Voyiatzis
Maria Samarakou
author_facet Ioannis Galanakis
Rigas Filippos Soldatos
Nikitas Karanikolas
Athanasios Voulodimos
Ioannis Voyiatzis
Maria Samarakou
author_sort Ioannis Galanakis
collection DOAJ
description This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset.
format Article
id doaj-art-f8da128352ce4fdfab5eb9ff0645a699
institution Kabale University
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-f8da128352ce4fdfab5eb9ff0645a6992024-11-26T17:48:06ZengMDPI AGApplied Sciences2076-34172024-11-0114221026610.3390/app142210266A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with DementiaIoannis Galanakis0Rigas Filippos Soldatos1Nikitas Karanikolas2Athanasios Voulodimos3Ioannis Voyiatzis4Maria Samarakou5Department of Software Engineering, University of West Attica, 12243 Athens, GreeceFirst Department of Psychiatry, Eginition Hospital, National and Kapodistrian University of Athens Medical School, 11528 Athens, GreeceDepartment of Software Engineering, University of West Attica, 12243 Athens, GreeceDepartment of School of Electrical & Computing Engineering, National Technical University of Athens, 15780 Athens, GreeceDepartment of Software Engineering, University of West Attica, 12243 Athens, GreeceDepartment of Software Engineering, University of West Attica, 12243 Athens, GreeceThis paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset.https://www.mdpi.com/2076-3417/14/22/10266machine learningMediaPipeholistic modelaggressive behavior predictionargumentative detectiondementia
spellingShingle Ioannis Galanakis
Rigas Filippos Soldatos
Nikitas Karanikolas
Athanasios Voulodimos
Ioannis Voyiatzis
Maria Samarakou
A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
Applied Sciences
machine learning
MediaPipe
holistic model
aggressive behavior prediction
argumentative detection
dementia
title A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
title_full A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
title_fullStr A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
title_full_unstemmed A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
title_short A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia
title_sort mediapipe holistic behavior classification model as a potential model for predicting aggressive behavior in individuals with dementia
topic machine learning
MediaPipe
holistic model
aggressive behavior prediction
argumentative detection
dementia
url https://www.mdpi.com/2076-3417/14/22/10266
work_keys_str_mv AT ioannisgalanakis amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT rigasfilippossoldatos amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT nikitaskaranikolas amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT athanasiosvoulodimos amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT ioannisvoyiatzis amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT mariasamarakou amediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT ioannisgalanakis mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT rigasfilippossoldatos mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT nikitaskaranikolas mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT athanasiosvoulodimos mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT ioannisvoyiatzis mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia
AT mariasamarakou mediapipeholisticbehaviorclassificationmodelasapotentialmodelforpredictingaggressivebehaviorinindividualswithdementia