Mental performance classification using fused multilevel feature generation with EEG signals

ABSTRACT

Mental performance classification is a critical issue for brain-computer interfaces. Accurate and reliable classification of good or bad mental performance gives important clues for the preliminary diagnosis of some diseases and mental stress. In this work, we put forward an objective artificial intelligence model to quantify the clarity of thought during mental arithmetic tasks. The proposed model consists of: (i) multilevel feature extraction based on statistical and texture analysis methods, (ii) feature ranking and selection with a Chi2 method, (iii) classification, and (iv) weightless majority voting classifier. The novelty of the presented model comes from multilevel fused feature generation. The presented model was developed using 20 channel electroencephalography data from 36 subjects. The signals were captured while the subjects were performing mental arithmetic tasks. The individual datasets were labeled as either good or bad, based on the task results. We have obtained an accuracy of 96.77% using O2 channel with a k-nearest neighbor classifier and reached 100.0% accuracy with the majority voting classifier. Our results indicate that it is possible to determine mental performance with artificial intelligence. That might be a steppingstone to establish objective measures for the clarity of thought during a wide range of mental tasks.

KEYWORDS:

• Mental task quality assessment
• EEG signals
• One-dimensional local graph structure
• Chi2 selector
• Fused multi level feature generation

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.

Notes on contributors

Emrah Aydemir

Emrah Aydemir is currently an Associate Professor Doctor in the Department of Technology and Information Management, Sakarya University, Turkiye. His research interests include signal processing, data mining and programming.

Mehmet Baygin

Mehmet Baygin is currently an Associate Professor doctor in the Department of Computer Engineering, Ardahan University, Turkiye. His research interests include machine learning, computer vision, signal processing, blockchain and photovoltaic systems.

Sengul Dogan

Sengul Dogan is currently an Associate Professor with the Digital Forensics Engineering, Technology Faculty, Firat University, Turkiye. Her main research interests include computer forensics, mobile forensics, image processing, and signal processing.

Turker Tuncer

Turker Tuncer is currently an Associate Professor with the Digital Forensics Engineering, Technology Faculty, Firat University, Turkiye. His main research interests include feature engineering, image processing, signal processing, information security, and pattern recognition.

Prabal Datta Barua

Dr Prabal Datta Barua is an Adjunct Professor at the University of Southern Queensland and an Honorary Industry Fellow at the University of Technology Sydney. He is interested in AI technologies and published several papers in the Q1 journal. He is an industry leader in ICT entrepreneurship in Australia.

Subrata Chakraborty

Dr Subrata Chakraborty is a Senior Lecturer with the School of Science and Technology, University of New England, Australia. He is also with the Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS) at UTS. He is a Senior member of IEEE and a professional Snr member of ACS.

Oliver Faust

Dr Oliver Faust is an Associate Professor with the School of Computing and Information Science at Anglia Ruskin University Cambridge Campus, UK. He holds PhDs from the University of Aberdeen and from Chiba University. He is also an associate editor for Computer Methods and Programs in Biomedicine.

N. Arunkumar

N. Arunkumar is an Associate Professor in Biomedical Engineering department of Ratinam college of engineering, Coimbatore, India. His research interests include artificial intelligence, biomedical signal/image processing. He is ranked in the top 1% of the Highly Cited Researchers in 2021 in Cross Field according to Essential Science Indicators of Thomson.

Feyzi Kaysi

Feyzi Kaysi is currently an Assistant Professor Doctor in the Department of Electronic and Otomation, Istanbul Cerrahpaşa University, Turkiye. His research interests include data mining, control systems and education technology.

U. Rajendra Acharya

U. Rajendra Acharya, is ranked in the top 1% of the Highly Cited Researchers for the past six consecutive years (2016 – 2022) in Computer Science according to the Essential Science Indicators of Thomson. Senior Editor of Computers in Biology Medicine (CBM) and Associate Editor of 8 ISI Journals.