Comparison of Manual and Automated Feature Engineering for Daily Activity Classification in Mental Disorder Diagnosis

Authors

  • Jakub Adamczyk AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Institute of Computer Science, 30-059 Krakow, Poland
  • Filip Malawski AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Institute of Computer Science, 30-059 Krakow, Poland

DOI:

https://doi.org/10.31577/cai_2021_4_850

Keywords:

Feature engineering, feature selection, activity classification, time series, mental disorder diagnosis, AutoML, actigraphy, signal processing

Abstract

Motor activity data allows for analysis of complex behavioral patterns, including the diagnosis of mental disorders, such as depression or schizophrenia. However, the classification of actigraphy signals remains a challenge. The main reasons are small datasets and the need for sophisticated feature engineering. The recent development of AutoML approaches allows for automating feature extraction and selection. In this work, we compare automatic and manual feature engineering for applications in mental health. We also analyze classifier evaluation methods for small datasets. The automated approach results in better classification, as measured with several metrics, and in a shorter, cleaner code, providing software engineering advantages.

Downloads

Download data is not yet available.

Downloads

Published

2021-12-14

How to Cite

Adamczyk, J., & Malawski, F. (2021). Comparison of Manual and Automated Feature Engineering for Daily Activity Classification in Mental Disorder Diagnosis. Computing and Informatics, 40(4), 850–879. https://doi.org/10.31577/cai_2021_4_850

Issue

Section

Special Section Articles