Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis

Aggression in patients with dementia poses significant caregiving and clinical issues. In this work, fusion approaches—Early Fusion and Late Fusion—were compared to classify aggression using audio and visual signals. Early Fusion integrates the extracted features of the two modalities into one datas...

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 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5823
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330693633474560
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 Aggression in patients with dementia poses significant caregiving and clinical issues. In this work, fusion approaches—Early Fusion and Late Fusion—were compared to classify aggression using audio and visual signals. Early Fusion integrates the extracted features of the two modalities into one dataset before classification, while Late Fusion integrates the prediction probabilities of standalone audio and visual classifiers with a meta-classifier. Both models were tested using a Random Forest classifier with five-fold cross-validation, and the performance was compared on accuracy, precision, recall, F1-score, ROC-AUC, and inference time. The results showcase that Late Fusion is superior to Early Fusion in terms of accuracy (0.876 vs. 0.828), recall (0.914 vs. 0.818), F1-score (0.867 vs. 0.835), and ROC-AUC score (0.970 vs. 0.922), proving more suitable for high-sensitivity use cases like healthcare and security. However, Early Fusion exhibited higher precision (0.852 vs. 0.824), indicating that in cases when false positives are a requirement, Early Fusion is preferable. Paired <i>t</i>-tests were applied for statistical comparison and indicate that precision alone is significantly different, with the advantage of Early Fusion. Late Fusion also performs slightly less in inference time, which makes it suitable for use in real-time systems. These findings provide significant information on multimodal fusion strategies and their applicability in the detection of aggressive behavior, which can contribute to the development of efficient monitoring systems for dementia care.
format Article
id doaj-art-c7d1f601202b4bdcb6827db774fcd1b1
institution Kabale University
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c7d1f601202b4bdcb6827db774fcd1b12025-08-20T03:46:50ZengMDPI AGApplied Sciences2076-34172025-05-011511582310.3390/app15115823Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative AnalysisIoannis Galanakis0Rigas Filippos Soldatos1Nikitas Karanikolas2Athanasios Voulodimos3Ioannis Voyiatzis4Maria Samarakou5Department of Informatics and Computing 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 Informatics and Computing Engineering, University of West Attica, 12243 Athens, GreeceDepartment of School of Electrical & Computing Engineering, National Technical University of Athens, 15780 Athens, GreeceDepartment of Informatics and Computing Engineering, University of West Attica, 12243 Athens, GreeceDepartment of Informatics and Computing Engineering, University of West Attica, 12243 Athens, GreeceAggression in patients with dementia poses significant caregiving and clinical issues. In this work, fusion approaches—Early Fusion and Late Fusion—were compared to classify aggression using audio and visual signals. Early Fusion integrates the extracted features of the two modalities into one dataset before classification, while Late Fusion integrates the prediction probabilities of standalone audio and visual classifiers with a meta-classifier. Both models were tested using a Random Forest classifier with five-fold cross-validation, and the performance was compared on accuracy, precision, recall, F1-score, ROC-AUC, and inference time. The results showcase that Late Fusion is superior to Early Fusion in terms of accuracy (0.876 vs. 0.828), recall (0.914 vs. 0.818), F1-score (0.867 vs. 0.835), and ROC-AUC score (0.970 vs. 0.922), proving more suitable for high-sensitivity use cases like healthcare and security. However, Early Fusion exhibited higher precision (0.852 vs. 0.824), indicating that in cases when false positives are a requirement, Early Fusion is preferable. Paired <i>t</i>-tests were applied for statistical comparison and indicate that precision alone is significantly different, with the advantage of Early Fusion. Late Fusion also performs slightly less in inference time, which makes it suitable for use in real-time systems. These findings provide significant information on multimodal fusion strategies and their applicability in the detection of aggressive behavior, which can contribute to the development of efficient monitoring systems for dementia care.https://www.mdpi.com/2076-3417/15/11/5823machine learningmultimodal analysislate fusionearly fusioncomparative analysismeta-classifier
spellingShingle Ioannis Galanakis
Rigas Filippos Soldatos
Nikitas Karanikolas
Athanasios Voulodimos
Ioannis Voyiatzis
Maria Samarakou
Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
Applied Sciences
machine learning
multimodal analysis
late fusion
early fusion
comparative analysis
meta-classifier
title Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
title_full Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
title_fullStr Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
title_full_unstemmed Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
title_short Early and Late Fusion for Multimodal Aggression Prediction in Dementia Patients: A Comparative Analysis
title_sort early and late fusion for multimodal aggression prediction in dementia patients a comparative analysis
topic machine learning
multimodal analysis
late fusion
early fusion
comparative analysis
meta-classifier
url https://www.mdpi.com/2076-3417/15/11/5823
work_keys_str_mv AT ioannisgalanakis earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis
AT rigasfilippossoldatos earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis
AT nikitaskaranikolas earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis
AT athanasiosvoulodimos earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis
AT ioannisvoyiatzis earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis
AT mariasamarakou earlyandlatefusionformultimodalaggressionpredictionindementiapatientsacomparativeanalysis