Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Optimizing Depression Prediction in Older Adults: A Comparative Study of Feature Extraction and Machine Learning Models
Blekinge Institute of Technology, Faculty of Engineering, Department of Health.ORCID iD: 0000-0003-4190-3532
Blekinge Institute of Technology, Faculty of Engineering, Department of Health.ORCID iD: 0000-0001-9870-8477
Blekinge Institute of Technology, Faculty of Engineering, Department of Health.ORCID iD: 0000-0001-8114-8813
Times Institute, Pakistan.
Show others and affiliations
2024 (English)In: International Conference on Control, Automation and Diagnosis, ICCAD 2024, Institute of Electrical and Electronics Engineers (IEEE), 2024Conference paper, Published paper (Refereed)
Abstract [en]

Depression emerged as a major public health concern in older adults, and timely prediction of depression has become a difficult problem in medical informatics. The latest studies have attentiveed on feature transformation and selection for better depression prediction. In this study, we assess the performance of various feature extraction algorithms, including principal component analysis (PCA), independent component analysis (ICA), locally linear Embedding (LLE), and t-distributed stochastic neighbor embedding (TSNE). These algorithms are combined with machine learning (ML) classifier algorithms such as Gaussian Naive Bayes (GNB), Logistic Regression (LR), K-nearest-neighbor (KNN), and Decision Tree (DT) to enhance depression prediction. In total, sixteen automated integrated systems are constructed based on the above-mentioned feature extraction methods and ML classifiers. The performance of all of these integrated models is assessed using data from the Swedish National Study on Aging and Care (SNAC). According to the experimental results, the PCA algorithm combined with the Logistic Regression (LR) model provides 89.04% depression classification accuracy. As a result, it is demonstrated that the PCA is a more suitable feature extraction method for depression data than ICA, LLE, and TSNE. © 2024 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024.
Keywords [en]
classification, depression, feature extraction, machine learning, Decision trees, Embeddings, Extraction, Forecasting, Independent component analysis, Nearest neighbor search, Principal component analysis, Stochastic systems, Features extraction, Independent components analysis, Learning classifiers, Locally linear embedding, Machine-learning, Older adults, Performance, Principal-component analysis, Stochastic neighbor embedding
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-26768DOI: 10.1109/ICCAD60883.2024.10553890Scopus ID: 2-s2.0-85197920799ISBN: 9798350361025 (print)OAI: oai:DiVA.org:bth-26768DiVA, id: diva2:1887439
Conference
2024 International Conference on Control, Automation and Diagnosis, ICCAD 2024, Paris, May 15-17 2024
Projects
SNACAvailable from: 2024-08-08 Created: 2024-08-08 Last updated: 2024-10-02Bibliographically approved

Open Access in DiVA

fulltext(760 kB)80 downloads
File information
File name FULLTEXT01.pdfFile size 760 kBChecksum SHA-512
1d5beb6ee0c48f0a3c48a70ebb5767b78cf0091f9ae028405581da440da92b0ff49c9f8d76e1084616b7fc00f03673d93af8b75b6ce41d01f6b55d395e3c4f90
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Javeed, AshirAnderberg, PeterGhazi, Sarah NaumanMoraes, Ana Luiza DalloraSanmartin Berglund, Johan

Search in DiVA

By author/editor
Javeed, AshirAnderberg, PeterGhazi, Sarah NaumanMoraes, Ana Luiza DalloraSanmartin Berglund, Johan
By organisation
Department of Health
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 80 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 259 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf