EEG workload estimation for simultaneous task using deep learning algorithm
1 Department of Electrical and Electronic Engineering, Pabna University of Science and Technology, Pabna-6600, Bangladesh.
2 Department of Electrical, Electronic and Communication Engineering, Pabna University of Science and Technology, Pabna-6600, Bangladesh.
3 Department of Information and Communication Engineering, Pabna University of Science and Technology, Pabna-6600, Bangladesh.
4 Department of Computer Science and Engineering, Bangamata Sheikh Fojilatunnesa Mujib Science & Technology University, Jamalpur-2012, Bangladesh.
Research Article
World Journal of Advanced Research and Reviews, 2023, 18(03), 533–542
Article DOI: 10.30574/wjarr.2023.18.3.1142
Publication history:
Received on 04 May 2023; revised on 11 June 2023; accepted on 14 June 2023
Abstract:
Mental workload plays a vital role in cognitive impairment refers to a person’s trouble of remembering, receiving new information, learning new things, concentrating, or making decisions that affect seriously in their everyday life. In this paper, the simultaneous capacity (SIMKAP) experiment-based EEG workload analysis was discussed with 45 subjects for multitasking mental workload estimation using an open access preprocessed EEG dataset. Discrete wavelet transforms (DWT) was used for feature extraction and selection. Scalogram formation was performed for data image conversion form from extracted data. AlexNet classification algorithm was used to classify dataset for low and high workload conditions including some other CNN models to show the comparative study of them. The comparative studies of the used classifier’s accuracy along with other performance parameters with the literature expresses the validation for the study which crossed state-of-the art methodologies in the literature by 77.78 percent.
Keywords:
Cognitive Impairment; EEG; SIMKAP; Workload
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0