Research Article
A Novel Method Based on ERP and Brain Graph for the
Simultaneous Assessment of Various Types of Attention
Ali Esmaili Jami , Mohammad Ali Khalilzadeh , Majid Ghoshuni ,
and Mohammad Mahdi Khalilzadeh
Department of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
Correspondence should be addressed to Mohammad Ali Khalilzadeh; makhalilzadeh@mshdiau.ac.ir
Received 13 June 2022; Revised 28 July 2022; Accepted 5 August 2022; Published 29 September 2022
Academic Editor: Dalin Zhang
Copyright © 2022 Ali Esmaili Jami et al. is is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
Assessment of attention is of great importance as one of human cognitive abilities. Although neuropsychological tests have been
developed and used to evaluate the ability to pay attention, their validity and reliability have been reduced due to some limitations
such as the presence of intervention factors, including human factors, limited range of languages, and cultural influences.
erefore, direct outputs of the brain system, represented by event-related potentials (ERPs), and the analysis of its function in
cognitive activities have become very important as a complementary tool to assess various types of attention. is research tries to
assess 4 types of attention including sustained, alternative, selective, and divided, using an integrated visual-auditory test and brain
signals simultaneously. us, the electroencephalogram (EEG) data were recorded using 19 channels, and the integrated visual
and auditory (IVA-AE) test was simultaneously performed on twenty-eight healthy volunteers including 22 male and 6 female
subjects with the average age of 27 ± 5.3 years. en ERPs related to auditory and visual stimuli with synchronous averaging
technique were extracted. A topographic brain mapping (topo-map) was plotted for each frame of stimulation. Next, an optical
flow method was implemented on different topo-maps to obtain motion vectors from one map to another. After obtaining the
overall brain graph of an individual, some features were extracted and used as measures of local and global connectivity. e
extracted features were consequently evaluated along with the parameters of the IVA test by support vector machine regression
(SVM-R). e volume of attention was then quantified by combining the IVA parameters. Ultimately, estimation accuracy of each
type of attention including focused attention (86.1%), sustained attention (83.4%), selective attention (80.9%), and divided
attention (79.9%) was obtained. According to the present study, there is a significant relationship between response control and
attention indicators of the IVA test as well as ERP brain signals.
1. Introduction
Attention refers to a series of complex mental operations,
which includes engaging and focusing on a goal, holding or
tolerating, and being alert for a long period as well as
encoding stimulus properties and shifting focus from one
target to another [1]. Attention plays a significant role in
carrying out our daily activities and it is a key factor in the
process of learning and memorizing [2]. ere are some
limitations in neuropsychological tests such as lack of tests
with specific criteria to check the change in a person’s
performance over time, depending on the culture of the
tests, the length of the tests not being able to be translated
into other languages, and the lack of valid and predictive
local tests [3]. erefore, validity and reliability of the tests
decrease due to limitations such as the existence of inter-
vention factors, especially human factors. e use of direct
outputs of the brain system, the analysis of its function in
cognitive activities, and the creation of intelligent systems
with the help of machine learning have become very im-
portant in health care.
In previous studies, brain signals have been utilized for
two purposes to evaluate attention. In some articles, only the
separation between the group of healthy people and those
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 6318916, 8 pages
https://doi.org/10.1155/2022/6318916