Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches

Faiza Guerrache; David J. Brown; Mufti Mahmud

doi:10.1007/978-3-031-98498-3_11

Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches

Faiza Guerrache
, David J. Brown
, Mufti Mahmud^*

^*Corresponding author for this work

Department of Information and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a comprehensive study on classifying depressed and healthy individuals using the Depresjon dataset, which contains motor activity data collected from wearable devices. We prepared six different datasets, including raw data, normalised raw data, PCA-transformed data, and statistical features extracted from the raw data. We trained and evaluated six popular machine learning models and their combinations using a 5-fold cross-validation technique. Our results demonstrate that most models achieved the highest accuracy with the normalised statistical feature dataset. Furthermore, we fine-tuned these algorithms using GridSearchCV and selected the best threshold using the ROC curve. Our findings provide valuable insights into the potential of wearable sensor data for detecting and predicting depressive episodes.

Original language	English
Title of host publication	Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings
Editors	Mufti Mahmud, Nelishia Pillay, M Shamim Kaiser
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	141-162
Number of pages	22
ISBN (Print)	9783031984976
DOIs	https://doi.org/10.1007/978-3-031-98498-3_11
State	Published - 2026
Event	1st Global Conference on Applications of Artificial Intelligence and Data Science, AAIDS 2024 - London, United Kingdom Duration: 3 Apr 2024 → 5 Apr 2024

Publication series

Name	Communications in Computer and Information Science
Volume	2601 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	1st Global Conference on Applications of Artificial Intelligence and Data Science, AAIDS 2024
Country/Territory	United Kingdom
City	London
Period	3/04/24 → 5/04/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

depression
depressive episodes
Gaussian Process Classifier
Gradient Boosting Classifier
K Nearest Neighbors Classifier
Logistic Regression
Machine Learning
motor activity
Random Forest Classifier
sleep disorder
Stress Prediction
Support Vector Machines

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-031-98498-3_11

Cite this

Guerrache, F., Brown, D. J., & Mahmud, M. (2026). Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches. In M. Mahmud, N. Pillay, & M. S. Kaiser (Eds.), Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings (pp. 141-162). (Communications in Computer and Information Science; Vol. 2601 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-98498-3_11

Guerrache, Faiza ; Brown, David J. ; Mahmud, Mufti. / Classifying Depressed and Healthy Individuals Using Wearable Sensor Data : A Comparative Analysis of Machine Learning and Deep Learning Approaches. Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings. editor / Mufti Mahmud ; Nelishia Pillay ; M Shamim Kaiser. Springer Science and Business Media Deutschland GmbH, 2026. pp. 141-162 (Communications in Computer and Information Science).

@inproceedings{1f6f414b3134420dbda99fd370019e51,

title = "Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches",

abstract = "This paper presents a comprehensive study on classifying depressed and healthy individuals using the Depresjon dataset, which contains motor activity data collected from wearable devices. We prepared six different datasets, including raw data, normalised raw data, PCA-transformed data, and statistical features extracted from the raw data. We trained and evaluated six popular machine learning models and their combinations using a 5-fold cross-validation technique. Our results demonstrate that most models achieved the highest accuracy with the normalised statistical feature dataset. Furthermore, we fine-tuned these algorithms using GridSearchCV and selected the best threshold using the ROC curve. Our findings provide valuable insights into the potential of wearable sensor data for detecting and predicting depressive episodes.",

keywords = "depression, depressive episodes, Gaussian Process Classifier, Gradient Boosting Classifier, K Nearest Neighbors Classifier, Logistic Regression, Machine Learning, motor activity, Random Forest Classifier, sleep disorder, Stress Prediction, Support Vector Machines",

author = "Faiza Guerrache and Brown, \{David J.\} and Mufti Mahmud",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 1st Global Conference on Applications of Artificial Intelligence and Data Science, AAIDS 2024 ; Conference date: 03-04-2024 Through 05-04-2024",

year = "2026",

doi = "10.1007/978-3-031-98498-3\_11",

language = "English",

isbn = "9783031984976",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "141--162",

editor = "Mufti Mahmud and Nelishia Pillay and Kaiser, \{M Shamim\}",

booktitle = "Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings",

address = "Germany",

}

Guerrache, F, Brown, DJ & Mahmud, M 2026, Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches. in M Mahmud, N Pillay & MS Kaiser (eds), Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings. Communications in Computer and Information Science, vol. 2601 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 141-162, 1st Global Conference on Applications of Artificial Intelligence and Data Science, AAIDS 2024, London, United Kingdom, 3/04/24. https://doi.org/10.1007/978-3-031-98498-3_11

Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches. / Guerrache, Faiza; Brown, David J.; Mahmud, Mufti.
Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings. ed. / Mufti Mahmud; Nelishia Pillay; M Shamim Kaiser. Springer Science and Business Media Deutschland GmbH, 2026. p. 141-162 (Communications in Computer and Information Science; Vol. 2601 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classifying Depressed and Healthy Individuals Using Wearable Sensor Data

T2 - 1st Global Conference on Applications of Artificial Intelligence and Data Science, AAIDS 2024

AU - Guerrache, Faiza

AU - Brown, David J.

AU - Mahmud, Mufti

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - This paper presents a comprehensive study on classifying depressed and healthy individuals using the Depresjon dataset, which contains motor activity data collected from wearable devices. We prepared six different datasets, including raw data, normalised raw data, PCA-transformed data, and statistical features extracted from the raw data. We trained and evaluated six popular machine learning models and their combinations using a 5-fold cross-validation technique. Our results demonstrate that most models achieved the highest accuracy with the normalised statistical feature dataset. Furthermore, we fine-tuned these algorithms using GridSearchCV and selected the best threshold using the ROC curve. Our findings provide valuable insights into the potential of wearable sensor data for detecting and predicting depressive episodes.

AB - This paper presents a comprehensive study on classifying depressed and healthy individuals using the Depresjon dataset, which contains motor activity data collected from wearable devices. We prepared six different datasets, including raw data, normalised raw data, PCA-transformed data, and statistical features extracted from the raw data. We trained and evaluated six popular machine learning models and their combinations using a 5-fold cross-validation technique. Our results demonstrate that most models achieved the highest accuracy with the normalised statistical feature dataset. Furthermore, we fine-tuned these algorithms using GridSearchCV and selected the best threshold using the ROC curve. Our findings provide valuable insights into the potential of wearable sensor data for detecting and predicting depressive episodes.

KW - depression

KW - depressive episodes

KW - Gaussian Process Classifier

KW - Gradient Boosting Classifier

KW - K Nearest Neighbors Classifier

KW - Logistic Regression

KW - Machine Learning

KW - motor activity

KW - Random Forest Classifier

KW - sleep disorder

KW - Stress Prediction

KW - Support Vector Machines

UR - https://www.scopus.com/pages/publications/105019048599

U2 - 10.1007/978-3-031-98498-3_11

DO - 10.1007/978-3-031-98498-3_11

M3 - Conference contribution

AN - SCOPUS:105019048599

SN - 9783031984976

T3 - Communications in Computer and Information Science

SP - 141

EP - 162

BT - Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings

A2 - Mahmud, Mufti

A2 - Pillay, Nelishia

A2 - Kaiser, M Shamim

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 3 April 2024 through 5 April 2024

ER -

Guerrache F, Brown DJ, Mahmud M. Classifying Depressed and Healthy Individuals Using Wearable Sensor Data: A Comparative Analysis of Machine Learning and Deep Learning Approaches. In Mahmud M, Pillay N, Kaiser MS, editors, Applications of Artificial Intelligence and Data Science - 1st Global Conference, AAIDS 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 141-162. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-98498-3_11