Optimal decomposition of EEG sensor data using TQWT method for mind-wandering detection

Read full text Summarise with VIRAT
Authors: Kapil Gupta
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Mind wandering (MW) is a mental condition in which a person’s attention drifts away from the current task or stimulus. Researchers have detected more variation in electroencephalogram (EEG) signals due to MW. It is time-consuming to extract detailed information from raw EEG data in order to examine the negative impacts of MW. This work presents a multi-resolution analysis of raw EEG signals by utilizing an integrated tunable Q-wavelet transform technique (TQWT). In this study, the TQWT approach is employed to decompose EEG data into more significant subbands. An array of statistical features is generated from the obtained SBs and investigated for the effect of MW. Statistically relevant features are identified and supplied into machine learning modules to help identify the MW subjects. An ensemble bagged tree module attained the highest classification accuracy of 87.41%, a sensitivity of 87.56%, and a specificity of 87.27%. This paper provides a non-parametric method for determining the influence of MW by conducting a more detailed and representative examination of EEG signals. This research can be used to develop an effective human-machine interaction platform for automatically detecting MW patients and promoting overall and healthy living in society.

Fields of Study & Subjects

EEG and Brain-Computer Interfaces Mind wandering and attention Emotion and Mood Recognition

Publication details

Journal / source
International Conference on Optical and Wireless Technologies (OWT)
Pages
117–117
Publication date
30 March 2026
Language
EN