This is an open access article under the CC BY license: 

 

   

Al-Khwarizmi 

Engineering 

Journal 
 

Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, December, (2023) 

P. P. 29- 41   

 

 

 

Working Memory Classification Enhancement of EEG Activity in 

Dementia: A Comparative Study 
 

Noor Kamal Al-Qazzaz*          Sawal Hamid Bin Mohd Ali ** 

Siti Anom Ahmad *** 
*Department of Biomedical Engineering/ Al-Khwarizmi College of Engineering/ University of Baghdad/ Baghdad / 

Iraq 

** Department of Electrical, Electronic & Systems Engineering, Faculty of Engineering & Built Environment, 

Universiti Kebangsaan Malaysia/ UKM Bangi/ Selangor 43600/ Malaysia 

Centre of Advanced Electronic and Communication Engineering, Department of Electrical/ Electronic and Systems 

Engineering/ Universiti Kebangsaan Malaysia/ Selangor 43600/ Malaysia 

***Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, UPM 

Serdang/ Selangor 43400/ Malaysia 

Malaysian Research Institute on Ageing (MyAgeing™)/ Universiti Putra Malaysia/ Serdang/ Selangor 43400/ Malaysia 

Corresponding Author *Email: noorbme@kecbu.uobaghdad.edu.iq         

**Email: sawal@ukm.edu.my  

***Email: sanom@upm.edu.my 

  
(Received 2 January 2023; accepted 20 September 2023) 

https://doi.org/10.22153/kej.2023.09.002

 
 

Abstract  

 
The purpose of the current investigation is to distinguish between working memory (𝑊𝑀) in five patients with 

vascular dementia (𝑉𝐷), fifteen post-stroke patients with mild cognitive impairment (𝑆𝑀𝐶𝐼), and fifteen healthy control 

individuals (𝐻𝐶) based on background electroencephalography (EEG) activity. The elimination of EEG artifacts using 

wavelet (WT) pre-processing denoising is demonstrated in this study. In the current study, spectral entropy (𝑆𝑝𝑒𝑐𝐸𝑛), 

permutation entropy (𝑃𝑒𝑟𝐸𝑛), and approximation entropy (𝐴𝑝𝐸𝑛) were all explored. To improve the 𝑊𝑀 classification 

using the k-nearest neighbors (𝑘NN) classifier scheme, a comparative study of using fuzzy neighbourhood preserving 

analysis with 𝑄𝑅-decomposition (𝐹𝑁𝑃𝐴𝑄𝑅) as a dimensionality reduction technique and the improved binary gravitation 

search (𝐼𝐵𝐺𝑆𝐴) optimization algorithm as a channel selection method has been conducted. The 𝑘NN classification 

accuracy was increased from 86.67% to 88.09% and 90.52% using the 𝐹𝑁𝑃𝐴𝑄𝑅 dimensionality reduction technique and 

the 𝐼𝐵𝐺𝑆𝐴  channel selection algorithm, respectively. According to the findings, 𝐼𝐵𝐺𝑆𝐴  reliably enhances 𝑊𝑀 

discrimination of 𝐻𝐶 , 𝑆𝑀𝐶𝐼 , and 𝑉𝐷  participants. Therefore, WT, entropy features, IBGSA and 𝑘NN classifiers 

provide a valid dementia index for looking at EEG background activity in patients with 𝑉𝐷 and 𝑆𝑀𝐶𝐼. 

 
Keywords: Dementia, wavelet, entropy, dimensionality reduction, channels selection, features, classification. 

 
 

1. Introduction 

 
Stroke is broadly categorized by its type and 

severity and the brain region affected. Dementia 

can be brought on after a stroke, and its severity 

relies on how quickly the condition is identified 

and treated [1]. Following a stroke, working 

memory (𝑊𝑀) impairment is common. Within the 

first year of stroke diagnosis, vascular dementia 

(𝑉𝐷) may develop in 30% of stroke patients. The 

prevalence of 𝑉𝐷 doubles every 5-10 years after 

the age of 65 in the elderly population. Clinically 

speaking, mild cognitive impairment ( 𝑀𝐶𝐼 ), in 

particular in attention, memory, language and 

orientation is a transition stage of cognitive decline 

[2]. At the time of diagnosis, attention, executive 

mailto:noorbme@kecbu.uobaghdad.edu.iq
mailto:aseel.m.ali@nahrainuniv.edu.iq
mailto:sanom@upm.edu.my
https://doi.org/10.22153/kej.2023.09.002
https://doi.org/10.22153/kej.2023.09.002


Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

30 

functioning, and memory show the greatest impact 

of a stroke [3]. 

Patients who had suffered from cognitive 

impairment as a result of a stroke were the first to 

be introduced to the vascular cognitive impairment 

(VCI) spectrum, which spans the range from mild 

cognitive impairment (𝑀𝐶𝐼) to advanced dementia. 

However, the phrase "cognitive impairment no 

dementia" (CIND) is used to refer to the period of 

time following dementia during which the brain is 

in danger [4]. People who have 𝑀𝐶𝐼 , have a more 

severe decline in cognitive performance when age 

and education level are included, yet this decline is 

not as obvious in day-to-day tasks. Although some 

people with 𝑀𝐶𝐼  will eventually develop 

dementia, others will remain in this 𝑀𝐶𝐼 stage for 

a significant amount of time before progressing to 

dementia. Because of this, 𝑀𝐶𝐼 is a disorder that 

can present very differently in different patients. In 

any case, research has been shown that patients 

diagnosed with 𝑀𝐶𝐼  have a substantial risk of 

developing dementia by the third month following 

the onset of dementia symptoms. This risk was 

observed to increase significantly with time. The 

symptoms most commonly associated with 𝑀𝐶𝐼 

are those related to attention and executive function 

in 𝑊𝑀. Daily functioning is unaffected by mild 

cognitive impairment. A decline in long-term 

memory, particularly episodic memory, is related 

to dementia, which is the next step following mild 

cognitive impairment. Mild cognitive impairment 

is the stage before dementia. 10% of patients will 

acquire post-stroke dementia (PSD) or severe 

dementia in the months following the 

commencement of an ischemic stroke (30% with 

recurrent ischemic stroke). This can happen as 

early as three months after the stroke [3]. 

Electroencephalography (EEG) has been 

extensively employed in recent years to investigate 

the cortical abnormalities linked to dementia and 

cognitive decline [5]. As a result, EEG signal 

analysis may reveal information on cognitive 

decline and dementia. Clinical EEG has a 

frequency range of 1 to 100 Hz and an amplitude 

of about 10-100 millivolts [6]. 

The main differences between healthy people and 

those with a problem with working memory (𝑊𝑀) 

can be summed up as follows: Dementia causes a 

slowing of EEG signals due to a power shift to 

lower frequencies and decreased cortical-

subcortical communication for patients with 𝑉𝐷 

and 𝑆𝑀𝐶𝐼 . Also, the reduction in signal 

complexity caused by dementia and other 

neurodegenerative diseases. Understanding the 

differences between how healthy people and 

people with 𝑊𝑀 problems show EEG signals can 

help make clinical signs and better ways to 

diagnose neurological illnesses [5]. 

However, the EEG is impacted by extracranial 

sources known as artifacts, which can imitate the 

abnormal activity of the brain and hence impair the 

analysis. Such artifacts have been seen in EEG 

recordings and wrongly attributed to neurological 

disorders. Clinical studies involving EEG signals 

necessitate the creation of automatic algorithms to 

eliminate artifacts. Several methods have been 

proposed for artifact removal in the literature [7], 

including regression-based analysis, wavelet 

transform (WT), Independent Component Analysis 

(ICA), blind source separation (BSS), and epoch 

rejection. In another example of an automated 

hybrid artifact removal method, Al-Qazzaz et al. 

estimated ICs first, then used DWT to detect 

components as artifacts that had been marked and 

denoised. To produce an EEG devoid of artifacts, 

we correct the ICs and then reconstruct them using 

inv-ICA. The benefits of the proposed method 

were seen by the authors, who found that it 

improved discriminating between dementia and 

healthy groups [5, 8]. 

Numerous studies have been conducted over the 

past few years to examine the impact of 𝑀𝐶𝐼 and 

AD on EEG signals and how they change over 

time. Using resting-state EEG recordings, Yin et al. 

have devised a scheme based on integrated spectral 

and temporal analysis for the identification of 

𝑀𝐶𝐼 . Stationary wavelet transform (SWT) and 

descriptive statistical analysis with support vector 

machine (SVM) classifiers were used to establish a 

three-dimensional discrete feature space. A 

machine learning-based methodology has been 

presented by Kashefpoor et al. to distinguish 

between 𝑀𝐶𝐼  and normal cases utilizing basic 

spectral frequency band EEG data [9]. Eight EEG 

biomarkers, including power spectral density, 

skewness, kurtosis, spectral skewness, spectral 

kurtosis, spectral crest factor, spectral entropy, and 

fractal dimension, have been studied by Sharma et 

al. for the diagnosis of individuals with 𝑀𝐶𝐼 [10]. 

Using the 𝑘-nearest neighbors (𝑘NN)  technique, 

Durongbhan et al. developed a supervised 

classification framework for EEG signals to 

distinguish between healthy controls and AD 

participants [11].  

Previous research has largely used a 2-way 

classification ( 𝐴𝐷  vs. 𝐻𝐶 , 𝑆𝑀𝐶𝐼  vs. 𝐻𝐶 ) 

however some studies have reported using a 3-way 

classification. Other researchers have looked into 

the possibility of using power spectrum analysis for 

the early diagnosis of AD and 𝑆𝑀𝐶𝐼 [5]. In [12] , 

neuro-markers based on complexity are calculated 

from AD patients and 𝐻𝐶  participants. These 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

31 

complexity measures include fractal dimension and 

Lempel-Ziv complexity. A variety of entropies, 

such as spectral entropy (𝑆𝑝𝑒𝑐𝐸𝑛 ), permutation 

entropy ( 𝑃𝑒𝑟𝐸𝑛 ), Tsallis entropy ( 𝑇𝑠𝐸𝑛 ), 

approximation entropy ( 𝐴𝑝𝐸𝑛 ), and sample 

entropy (𝑆𝑎𝑚𝑝𝐸𝑛 ), could be computed for this 

demand in order to examine the EEG markers that 

may aid in dementia early detection [13]. 

A three-way categorization methodology was 

used in one study [14]. Eyes-open, eyes-closed 

with a counting task, and eyes-closed conditions 

were used to compute spectral and complexity 

features from 𝐻𝐶 , 𝑆𝑀𝐶𝐼 , and AD participants, 

respectively. Time-frequency domain parameters 

(relative power band, median frequency) and 

entropy-based neuro-markers (spectral entropy, 

sample entropy, auto-mutual information) have 

been merged by Ruiz-Gomez et al. [15]. Eyes-open 

and eyes-closed EEG recordings were obtained 

from individuals with 𝐴𝐷 , 𝑀𝐶𝐼 , and 𝐻𝐶  [16]. 

Classification was carried out using Linear 

Discriminant Analysis (LDA), Quadratic 

Discriminant Analysis (QDA), and Multi-layer 

perceptron (MLP). Toural et al. have classified 

patients into three groups using wavelet entropy, 

relative beta, and theta power [17]. In the pre-

classification phase, a SVM is employed for binary 

assessment, and in the classification phase, a neural 

network is implemented for the voting mechanism. 

The power spectrum density of EEG sub-bands and 

interhemispheric coherence were determined by 

Oltu et al. using data from 𝐴𝐷 , 𝑀𝐶𝐼 , and 𝐻𝐶 . 

Each EEG sub-band's variance and amplitude sum, 

as well as the coherence amplitude sum, are 

included in the feature vectors [18].  

The use of EEG for the detection and 

classification of dementia-related brain activity 

patterns has shown encouraging results. In spite of 

this, additional study is required in two areas: 

dimensionality reduction and channel selection. 

First of all, dimensionality reduction strategies try 

to minimize the loss of information by simplifying 

the number of features or variables in EEG data. 

Next-generation classification algorithms can be 

made more manageable in terms of both 

complexity and computing overhead if the 

dimensionality of the data is reduced. The best 

dimensionality reduction strategies to improve 

EEG categorization in dementia are not yet fully 

understood. Despite their success elsewhere, 

techniques for dimensionality reduction were 

applied to increase the classification accuracy. 

There are many techniques that can be applied, 

including the well-known principal component 

analysis (PCA) technique for dimensionality 

reduction. The PCA approach is frequently used to 

prevent redundancy in high-dimensional data [19]. 

Additionally, channel selection  is a type of 

feature selection that may be applied to the removal 

of irrelevant or noisy channels and the selection of 

channels with related features [20]. The most 

efficient EEG channels have been determined 

using the sparse common spatial pattern (SCSP) 

algorithm, the mutual information technique [21, 

22], the recursive channel elimination (RCE) 

approach [23], and the differential evolution –

based channel selection algorithm (DEFS_Ch) 

[20, 24]. Although the strategy of 

channel selection  can offer the benefits of 

eliminating unimportant channels or choosing a 

small number of significant EEG features to 

enhance classification performance. 

Second, channel selection includes picking the 

EEG channels that add the most value to the 

categorization process. This method can enhance 

classification precision, however, the best way to 

pick channels for EEG classification purposes in 

dementia is not yet certain. Channel selection can 

be based on a variety of parameters, including 

statistics, spectral analysis, and geographical 

patterns; nevertheless, their efficacy and 

robustness must be assessed in the context of 

dementia [25]. 

Most of the approaches in the literature have a 

complicated structure and take a long time since 

they do not employ a data-efficient reduction 

technique, which is necessary for fast and accurate 

analysis. 

Effective dimensionality reduction approaches 

and optimal channel selection procedures are the 

last pieces of the puzzle when it comes to 

improving EEG classification for dementia. 

Closing these knowledge gaps will aid in the 

creation of more precise and time-saving EEG-

based categorization systems for the diagnosis and 

monitoring of dementia. To improve EEG 

categorization for dementia, more study is needed 

to analyze and compare different ways and 

determine the most suitable techniques. 

Based on background electroencephalography 

(EEG) activity, the goal of the current investigation 

is to differentiate between working memory (𝑊𝑀) 

in five patients with vascular dementia ( 𝑉𝐷 ), 

fifteen post-stroke patients with mild cognitive 

impairment (𝑆𝑀𝐶𝐼 ), and fifteen healthy control 

individuals (𝐻𝐶). In the current study,  as spectral 

entropy (𝑆𝑝𝑒𝑐𝐸𝑛), permutation entropy (𝑃𝑒𝑟𝐸𝑛) 

and approximation entropy ( 𝐴𝑝𝐸𝑛 ), were the 

features that were selected to investigate the 𝑊𝑀 

and classify their tasks using the k-nearest 

neighbours (𝑘NN) classifier scheme. Therefore, a 

comparative study of using the fuzzy neighborhood 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

32 

preserving analysis with 𝑄𝑅 -decomposition 

( 𝐹𝑁𝑃𝐴𝑄𝑅 ) as a dimensionality reduction 

technique and the improved binary gravitation 

search ( 𝐼𝐵𝐺𝑆𝐴 ) optimization algorithm as a 

channel selection method has been conducted. The 

𝐹𝑁𝑃𝐴𝑄𝑅  was used in this investigation as a 

dimensionality reduction  method to maximize 

the distance between the centers of various classes 

while minimizing the distance between samples 

that belong to the same class [26, 27]. Additionally, 

the most efficient channels that increase 

classification accuracy have been found using the 

𝐼𝐵𝐺𝑆𝐴  algorithm [25]. Additionally, the 

suitability of 𝑆𝑝𝑒𝑐𝐸𝑛 , 𝐴𝑝𝐸𝑛 , and 𝑃𝑒𝑟𝐸𝑛 

characteristics for the early identification of 𝑉𝐷 

was examined. 𝑘NN classifier has also been used 

to identify patients with post-stroke 𝑊𝑀 

dysfunction. 

 

 

 

2. Materials and Methods  
 

To improve the 𝑊𝑀 classification of dementia 

patients, the EEG signals would undergo various 

signal processing phases, as shown in Figure 1. The 

participants in this EEG study participated in a 

session of an auditory 𝑊𝑀  task. The non-

stationary EEG signals were initially processed 

using a wavelet (WT) denoising approach during 

the preprocessing step. After that, we look into and 

extract the meaningful features, such as non-linear 

𝑆𝑝𝑒𝑐𝐸𝑛, 𝐴𝑝𝐸𝑛, and 𝑃𝑒𝑟𝐸𝑛 entropy features, and 

conduct a comparison of the dimensionality 

reduction techniques fuzzy neighborhood 

preserving analysis with QR-decomposition 

(𝐹𝑁𝑃𝐴𝑄𝑅) and the improved binary gravitation 

search (IBGSA) optimization algorithm for 

channel selection. Finally, the performance of the 

classifiers utilized is evaluated, showing that 

dementia classification techniques can be used to 

categorize patients' mental disability after stroke.  

 

 
 

Fig. 1. The block diagram of the proposed study. 
 

 

2.1 Participants 
 

In the current investigation, 35 patients' EEG 

datasets were examined. The sample was recruited 

from the stroke unit and neurology clinic at the 

Pusat Perubatan Universiti Kebangsaan Malaysia 

(PPUKM). 15 𝐻𝐶  participants (7 male and 8 

female,age 60.06±5.21), 15 𝑆𝑀𝐶𝐼  patients (5 

male and 10 female,age 60.26±7.77), and 5 𝑉𝐷 

patients (3 male and 2 female,age 64.6±4.8) had 

their EEG data reviewed. The cognitive 

evaluations that were administered to the three 

groups were the mini-mental state examination 

(MMSE) [7] and the Montreal cognitive 

assessment (MoCA) [8]. 𝐻𝐶 participants' MMSE 

and MoCA scores were (29.6±0.73,29.06±0.88), 

but 𝑆𝑀𝐶𝐼  patients' MMSE and MoCA scores 

were (20.2±5.63 and 16.13±5.97), respectively.  

Lastly, the MMSE and MoCA scores for the 𝑉𝐷 

patients were (14.8±1.92 and 14.8±1.92) 

respectively. The experimental methods utilized 

throughout the research were approved by 

PPUKM's Human Ethics Committee, and the 

patients' voluntary and informed consent was 

secured by acquiring signed consent forms. All 

patients were diagnosed using computed 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

33 

tomography/magnetic resonance imaging 

(CT/MRI) scans, patient medical histories, and 

clinical and laboratory tests. 

 

2.2 EEG recording  
 

NicoletOne (V32) was utilized in order to 

collect the 19 EEG channel datasets. Using a single 

ground electrode and two reference electrodes with 

19 channels starting from left, right to the center, 

these are: Fp2, F8, T4, T6, O2, Fp1, F7, T3, T5, 

O1, F4, C4, P3, F3, C3, P3, Fz, Cz and Pz. 

A referential montage was created, and the 

channels were constructed according to the 10-20 

international framework. The Nicolet EEG system 

was sampled at 256 Hz, and the electrode-skin 

impedance was tested to ensure that it did not 

exceed10 kilo ohms. This corresponded to a 

sensitivity of 100 v/cm, whereas the low cut-off 

frequency and high cut-off frequency were, 

respectively, 0.5 Hz and 70 Hz. The EEG was 

recorded for 60 seconds, with a 0.5-second fixation 

cue preceding the start of the recording period. The 

patients were then asked to commit five words to 

memory for 10 seconds as part of a simple auditory 

𝑊𝑀  test involving working memory. Following 

this, EEG recordings were made as each subject 

attempted to recall the phrase. After the 60-second 

interval elapsed, the researcher instructed the 

participants of the sample group to open their eyes 

and to recall in turn each of the words they had 

memorized [3]. 

 

2.3 Preprocessing Stage 

 
In this investigation, WT denoising was utilized 

to eliminate EEG artifacts. Since the sampling 

frequency was 256 Hz [28], the symlets mother 

WT of order 9 'sym9' and 5 decomposition levels 

were utilized to decompose the acquired EEG 

information. 

As in Equation 1, the discrete values of 𝑎 and 

𝑏 can process the DWT.  It can be constructed as 

𝑎 set of decomposition functions of the correlation 

between the signal 𝑓(𝑡)  and the shifting and 

dilating of the mother wavelet function 𝜓(𝑡). In 

Equation 2, location parameter 𝑏 shifts MWT and 

the frequency scaling parameter 𝑎  dilates or 

contracts it [29, 30]: 

𝐷𝑊𝑇𝑚,𝑛(𝑓)

= 𝑎0
−𝑚

2⁄ ∫ 𝑓(𝑡) 𝜓(𝑎0
−𝑚𝑡

− 𝑛𝑏0)𝑑𝑡                             . . . (1)  
𝑎0 and 𝑏0 values are set to 2 and 1, respectively. 

𝜓𝑎,𝑏(𝑡)

=
1

√𝑎
𝜓 (

𝑡 − 𝑏

𝑎
) , 𝑎𝜖ℝ+, 𝑏𝜖ℝ         … (2) 

2.4 Features Extraction Stage 
 

Each EEG dataset had 19 channels with a 

duration of 60 seconds, so 15360 samples were 

utilized for this study. Entropies have been utilized 

to identify anomalies in dementia patients' EEGs. 

The EEGs of dementia patients have been 

separated from those of age-matched healthy 

people using 𝑆𝑝𝑒𝑐𝐸𝑛 [31-33].  

After normalizing the power spectral density 

( 𝑃𝑆𝐷 ) to a scale from 0 to 1  to obtain 

normalized PSD (PSDn), which has the value 1 

for ∑ PSDn(f) = 1, the 𝑆𝑝𝑒𝑐𝐸𝑛 is computed as in 

Equation 3 [31]. 

𝑆𝑝𝑒𝑐𝐸𝑛 =
−1

log(𝑁)
∑ 𝑃𝑆𝐷𝑛(𝑓) log[𝑃𝑆𝐷𝑛(𝑓)]64𝐻𝑧

𝑓=0.1𝐻𝑧      

… (3) 
                                        

Utilizing the algorithm described in [34], 𝐴𝑝𝐸𝑛 is 

calculated as in Equation 4 [35]. 

𝐴𝑝𝐸𝑛(𝑚, 𝑟, 𝑁) = ∅𝑚(𝑟) − ∅𝑚+1(𝑟)       … (4)  

where, ∅𝑚  is the natural logarithm for 𝑚 

contiguous observation within tolerance width 𝑟 

and 𝑁 is the number of points of the EEG time 

series. For the sake of our analysis, 𝐴𝑝𝐸𝑛  is 

calculated with a tolerance of r = 0.2 × SD and a 

run length of m = 2 epochs, where SD is the 

standard deviation. 

In the case of 𝑃𝑒𝑟𝐸𝑛, this sort of entropy is 

widely employed in the context of 

artefacts and noise , and one of its 

distinguishing properties [36] is its computational 

speed.  

In terms of 𝑃𝑒𝑟𝐸𝑛  's applications, non −
stationary and non − linear signals  are 

frequently employed [37]. 𝑃𝑒𝑟𝐸𝑛  has been 

utilized by researchers to assess the complexity of 

EEG signals in Alzheimer′s disease (AD) 

patients [38]. The 𝑃𝑒𝑟𝐸𝑛  can also be used to 

detect aberrant electrical activity in the brain, 

which cannot be demonstrated by traditional EEG 

signal detection methods [39]. 

When all motifs have equal probability, the 

largest value of 𝑃𝑒𝑟𝐸𝑛 is obtained, which has a 

value of ln 𝑑!, where 𝑑 = 3, 𝑙 = 1. In contrast, if 

there is only one 𝑝(𝜋𝑘) different from zero, 

which illustrates a completely regular signal, the 

smallest value of 𝑃𝑒𝑟𝐸𝑛 is obtained as much as 0 

[36, 40, 41]. For 60 seconds, 𝑁 = 15360 samples, 

6 windows of 10 second length (2560 samples) 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

34 

were extracted from the original EEG time series 

for each of 19 channels. 

In order to estimate the 𝑃𝑒𝑟𝐸𝑛 , assume the 

time series of 𝑦 = {𝑦1, 𝑦2, … , 𝑦𝑁} of length 𝑁, at 

each time 𝑡  of 𝑦  a vector including the 𝑑𝑡ℎ 

subsequence value constructed as: 𝑌𝑡
𝑑,𝑙 =

{𝑦𝑡 , 𝑦𝑡+1, … , 𝑦𝑡+(𝑑−2)𝑙 , 𝑦𝑡+(𝑑−1)𝑙}  for 𝑡 =

1,2, … , 𝑁 − (𝑑 − 1)𝑙 , where 𝑑  is the embedded 

dimension, determines how much information is 

contained in each vector and 𝑙 is the time delay. 

To calculate the 𝑃𝑒𝑟𝐸𝑛 , the 𝑑  of 𝑦𝑖  are 

associated with numbers from 1 to 𝑑 and arranged 

in increasing order as 

{𝑦𝑡+(𝑗1−1)𝑙, 𝑦𝑡+(𝑗2−1)𝑙 , … , 𝑦𝑡+(𝑗𝑑−1−1)𝑙 , 𝑦𝑡+(𝑗𝑑−1)𝑙} 

for different samples, there will be 𝑑!  potential 

ordinal patterns, 𝜋 , which are named “motifs” 

[38]. For each 𝜋𝑡 , 𝑝(𝜋𝑡) demonstrate the relative 

frequency as follows: 

𝑝(𝜋𝑖
𝑑,𝑙) =

#{𝑡|𝑡≤𝑁−𝑑,type(𝑌𝑡
𝑑,𝑙)=𝜋𝑖

𝑑,𝑙 }

𝑁−𝑑+1
        …(5) 

Where #{ } denotes the cardinality of the set (the 

number of elements). The 𝑃𝑒𝑟𝐸𝑛 is computed as 

follows: 

𝐻(𝑦, 𝑑, 𝑙) = − ∑ 𝑝(𝜋𝑘)𝜋𝑘=𝑑!
𝜋𝑘=1 ln 𝑝(𝜋𝑘)     …(6) 

When all motifs have equal probability, the 

largest value of 𝑃𝑒𝑟𝐸𝑛 is obtained, which has a 

value of ln 𝑑!, where 𝑑 = 3, 𝑙 = 1. In contrast, if 

there is only one 𝑝(𝜋𝑘) different from zero, 

which illustrates a completely regular signal, the 

smallest value of 𝑃𝑒𝑟𝐸𝑛 is obtained as much as 0 

[36, 40, 41]. For 60 seconds, 𝑁 = 15360 samples, 

6 windows of 10 second length (2560 samples) 

were extracted from the original EEG time series 

for each 19 channels. 

 

2.5 Statistical analysis  
 

The denoised 19 channels from the EEG dataset 

of 15 𝐻𝐶 , 15 𝑆𝑀𝐶𝐼 , and 5 𝑉𝐷  patients were 

preliminary divided into 5 recording regions that 

correspond to the scalp area of the cerebral cortex. 

The frontal includes seven channels: Fp1, Fp2, F3, 

F4, F7, F8 and Fz, temporal includes four channels: 

T3, T4, T5 and T6, parietal includes three channels: 

P3, P4 and Pz), occipital includes two channels: O1 

and O2), and central includes three channels: C3, 

C4 and Cz). The Kolmogorov–Smirnov test 

determined normality, while Levene's test 

confirmed homoscedasticity. Thus, SPSS 22 used 

two analysis of variance (ANOVA) sections on 

𝑆𝑝𝑒𝑐𝐸𝑛, 𝐴𝑝𝐸𝑛, and 𝑃𝑒𝑟𝐸𝑛 characteristics. Each 

segment had two independent variables (IVs): the 

subject groups ( 𝐻𝐶  subjects, 𝑆𝑀𝐶𝐼 , and 𝑉𝐷 

patients) and the five scalp regions (frontal, 

temporal, parietal, occipital, and central). One of 

the former attributes was the dependent variable 

(DV). All statistical tests were significant at P< 

0.05. 

2.6 Dimensionality reduction using 

𝐅𝐍𝐏𝐀𝐐𝐑  
 

In order to maximize the distance between the 

centers of various classes while minimizing the 

distance between samples that belong to the same 

class, this study also used the fuzzy neighborhood 

preserving analysis with QR-decomposition 

( 𝐹𝑁𝑃𝐴𝑄𝑅 ) dimensionality reduction technique 

[26] of Khushaba et al [20]. 𝐹𝑁𝑃𝐴𝑄𝑅 maintains 

the contribution of samples to various classes in 

this way [26]. For the first time, our study used 

𝐹𝑁𝑃𝐴𝑄𝑅  to distinguish between 𝐻𝐶  and 

demented participants during 𝑊𝑀 tasks.  

The matrix (𝐺𝐹𝑁𝐷𝐴𝑄𝑅) was built from the training 

set to project the input feature vector using 

𝐹𝑁𝑃𝐴𝑄𝑅 . To reduce dimensionality, the 

projection matrix was multiplied by the training 

and testing sets. 𝐹𝑁𝑃𝐴𝑄𝑅 projected training data 

input feature vector. Projecting the feature vector's 

testing set requires merely multiplying it by the 

projection matrix from the training data. Figure 2 

shows how the 𝐹𝑁𝑃𝐴𝑄𝑅  feature projection 

calculates the within-class scatter matrix (𝑆𝑊) and 

between-class scatter matrix (𝑆𝐵). 
calculates the within-class scatter matrix ( 𝑆𝑊 ) and 

between-class scatter matrix (𝑆𝐵). 

 

 
 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

35 

Fig. 2. The steps of Dimensionality reduction using 

𝐅𝐍𝐏𝐀𝐐𝐑 

 

 

In a comparative study, the 𝐹𝑁𝑃𝐴𝑄𝑅 

dimensionality reduction approach and 𝑘 NN 

classifier were used to identify 𝑉𝐷 , 𝑆𝑀𝐶𝐼 , and 

𝐻𝐶 subjects [5]. 

 

2.7 Channel Selection using 𝐈𝐁𝐆𝐒𝐀 

 
The most effective channels have been found, 

and the amount of information has been decreased, 

using the improved binary gravitation search 

algorithm ( 𝐼𝐵𝐺𝑆𝐴 ) optimization algorithm [25, 

42]. 𝐺𝑆𝐴  is a powerful optimization technique 

that was first proposed in [43]. for use in addressing 

binary-valued problems. It was created based on 

the Newtonian laws of gravity and motion. 𝑁 

objects (agents) are defined for the 𝐼𝐵𝐺𝑆𝐴 

algorithm to determine the best EEG channels. The 

population starts out with this collection of things. 

Each object in this study is regarded as a binary 

vector with a dimension of 19. The number of EEG 

channels is the same as the dimension that was 

given. The following vector can be regarded as the 

𝑖𝑡ℎ  object. Finding the item that gives the best 

fitness value is the main objective. Equation 7 [44] 

can be used to calculate the classification 

accuracies for each set of EEG channels, which are 

used in this work to determine the 𝑓𝑖𝑡𝑛𝑒𝑠𝑠 values 

for the objects: 

𝑓𝑖𝑡𝑖 = 𝜔1 × 𝑎𝑐𝑐𝑢𝑖 + 𝜔2

× [1 −
∑ 𝑓𝑗

𝑝
𝑗=1

𝑝
]           

                                                                              . . . (7) 

where 𝜔1, 𝜔2 are predefined weight factors, 

𝜔1 is the weight factor for the classification 

accuracy of the 𝑘 NN classifiers respectively 

determined by the 10-fold cross-validation (𝐶𝑉) 

method; 𝑎𝑐𝑐𝑢𝑖  is the 1-NN classification 

accuracy; 𝜔2 is the weight factor for the number 

of selected features and 𝑓𝑗  is the value of the 

feature mask. If precision is the most crucial factor, 

the 𝑤𝑒𝑖𝑔ℎ𝑡  factor might be increased to a high 

amount (such as 100%). The position of the object 

with a high fitness value should be set suitably 

since it has a high likelihood of influencing the 

positions of the other objects in the following 

iteration [14,15]. Equation 8 yields the 𝑎𝑐𝑐𝑢𝑖 , 

where corr is the number of cases that were 

properly classified and incorr is the number of 

examples that were classified wrongly [44]: 

𝑎𝑐𝑐𝑢𝑖 =
𝑐𝑜𝑟𝑟

𝑐𝑜𝑟𝑟+𝑖𝑛𝑐𝑜𝑟𝑟
× 100%               …(8) 

The IBGSA algorithm selects the most informative 

EEG channels for classification. The method selects 

the optimal EEG channel subset for classification. 

The technique optimizes channel selection to 

increase EEG-based classification accuracy and 

efficiency [43]. 

 

2.8 Dementia Classification Techniques 

 
The EEG signals were divided into (𝐻𝐶, 𝑆𝑀𝐶𝐼, 

and 𝑉𝐷) using a 𝑘NN classifier. The patients with 

𝑉𝐷 made up a statistically significant minority in 

this analysis. To address the discrepancy, the 

researchers used a synthetic oversampling 

technique (SMOTE) [45]. To prevent overfitting 

and bias in the classification analysis, the classifier 

parameters and the percentage of oversampling 

were evaluated by 10-fold cross-validation with a 

grid search approach [46]. The provided data set 

was partitioned into ten independent samples of 

similar size. Only one of these groups was utilized 

to train the classifier, while the other nine were 

used as the test set. Ten iterations of this process 

yielded ten reliable results. The 10-fold CV 

accuracy of this dataset was calculated as the mean 

of these accuracies [47].  

Since SMOTE modifies the dataset, the 

oversampling was incorporated into the settings. 

Because of this, it is possible that the parameters 

discovered with varying amounts of SMOTE are 

not equivalent. When using the SMOTE to 

normalize the class frequencies, we solely 

considered the training set [48, 49]. 

The classifier in this study was trained to find the 

best value of k, which was discovered to be k = 5, 

and to increase classification accuracy. Each trial 

has been classified by 𝑘NN using the Euclidean 

distance as a similarity metric. 

After selecting the optimal EEG channels, the 

𝑘NN algorithm classifies background signals from 

symptomatic and asymptomatic instances using 

entropy. 𝑘 NN uses labeled training samples to 

classify data points. EEG signal entropy measures 

randomness or chaos. The 𝑘NN method classifies 

symptomatic and asymptomatic cases based on 

their resemblance to training samples by computing 

the entropy of chosen EEG channels [50]. 

 

 

3. Results and Discussion 

3.1 Results of Preprocessing Stage 

 
Figure 3 depicts the denoised EEG signals 

produced by the WT method. Due to the 

heterogeneity of EEG artifacts, WT has been 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

36 

evaluated on every channel of the available EEG 

datasets. When comparing the original recorded 

EEG (red) with the suppressed version (blue), it is 

clear that the artifactual components were 

effectively eliminate

 

 
 

Fig. 3. The denoising resulting from the application of the WT technique to EEG Ch2 which represents F8. 

 

 

3.2 Results of Statistical analysis  
 

Patients with 𝑉𝐷 showed less complexity than 

those with 𝑆𝑀𝐶I and 𝐻𝐶  using 𝑆𝑝𝑒𝑐𝐸𝑛, 𝐴𝑝𝐸𝑛 

and 𝑃𝑒𝑟𝐸𝑛 as shown in Figures 4, 5 and 6. For all 

patients, but especially for those with 𝐻𝐶 and 𝑉𝐷, 

the complexity of the EEG signals reduces as the 

condition worsens. 

Figure 4 shows that the 𝑆𝑝𝑒𝑐𝐸𝑛 values of the 

𝑉𝐷 patients were lower than those of the 𝑆𝑀𝐶𝐼 

patients and that the 𝐻𝐶 patients' values were the 

greatest. 

Moreover, the 𝑉𝐷  patients had lower 𝐴𝑝𝐸𝑛 

values than the 𝑆𝑀𝐶𝐼  patients, and the 𝐻𝐶 

subjects had the highest 𝐴𝑝𝐸𝑛 values (Figure 5). 

Finally, the patients with 𝑉𝐷  had lower 𝑃𝑒𝑟𝐸𝑛 

values than those with 𝑆𝑀𝐶𝐼, and the participants 

with 𝐻𝐶 had the greatest value (Figure 6). 

 

 
 
Fig. 4. Comparative plot of the 𝑺𝒑𝒆𝒄𝑬𝒏 for the five 

scalp regions of the brain for 𝑽𝑫, 𝑺𝑴𝑪𝑰 patients 

and 𝑯𝑪 subjects. 

 

 

 
Fig. 5. Comparative plot of the 𝑨𝒑𝑬𝒏 for the five 

scalp regions of the brain for 𝑽𝑫, 𝑺𝑴𝑪𝑰 patients 

and 𝑯𝑪 subjects. 

 

 

 

 
 

Fig. 6. Comparative plot of the 𝑷𝒆𝒓𝑬𝒏 for the five 

scalp regions of the brain for 𝑽𝑫, 𝑺𝑴𝑪𝑰 patients 

and 𝑯𝑪 subjects. 

 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

37 

 

 

3.3 Results of Dementia Classification 

Techniques 
 

The classification confusion matrix for all three 

schemes proposed is shown in Tables I, II and III. 

Table I illustrates the confusion matrix for the 

𝑘NN Classifier without using the 𝐹𝑁𝑃𝐴𝑄𝑅 and 

IBGSA. Table II shows the confusion matrix for 

the 𝑘 NN Classifier with the 𝐹𝑁𝑃𝐴𝑄𝑅 

dimensionality reduction technique. The number of 

selected features by the 𝐹𝑁𝑃𝐴𝑄𝑅 dimensionality 

reduction technique was set to 40 characteristics, 

which are the most essential features in terms of 

differentiating between patients suffering from 𝑉𝐷 

and stroke-related 𝑆𝑀𝐶𝐼  and healthy control 

participants. Table III shows the confusion matrix 

for the 𝑘NN Classifier with the IBGSA channels 

selection algorithm. The 𝑘 NN classification 

accuracy was improved from 86.67% to 88.09 

using 𝐹𝑁𝑃𝐴𝑄𝑅  dimensionality reduction 

technique and 90.52 by IBGSA channel selection 

algorithm. The results suggested that IBGSA 

consistently improves 𝑊𝑀 discrimination of 𝑉𝐷, 

𝑆𝑀𝐶𝐼  patients and 𝐻𝐶  subjects. Therefore, 

IBGSA improves the classification over all 

accuracy for all three groups as in the 𝑘 NN 

classification over the 𝐹𝑁𝑃𝐴𝑄𝑅 accuracy.  

 
Table 1,  

Calculation of the confusion matrix for multi-class 

classification using the 𝒌NN Classifier. 

𝐜𝐨𝐧𝐟𝐮𝐬𝐢𝐨𝐧 𝐦𝐚𝐭𝐫𝐢𝐱 𝐕𝐃 𝐒𝐌𝐂𝐈 𝐇𝐂 

𝑽𝑫 93.33% 6.67% 0.00% 

𝑺𝑴𝑪𝑰 5.56% 93.33% 1.11% 

73.33% 𝑯𝑪 16.67% 10% 

 

Table 2,  

Calculation of the confusion matrix for multi-class 

classification using 𝒌NN and the 𝑭𝑵𝑷𝑨𝑸𝑹 

technique. 

𝐜𝐨𝐧𝐟𝐮𝐬𝐢𝐨𝐧 𝐦𝐚𝐭𝐫𝐢𝐱 𝐕𝐃 𝐒𝐌𝐂𝐈 𝐇𝐂 

𝑽𝑫 87.78% 11.11% 1.11% 

𝑺𝑴𝑪𝑰 7.78% 92.22% 0.00% 

𝑯𝑪 6.67% 16.67% 76.67% 

 

Table 3, 

Calculation of the confusion matrix for multi-class 

classification using 𝒌NN and the IBGSA technique. 

𝐜𝐨𝐧𝐟𝐮𝐬𝐢𝐨𝐧 𝐦𝐚𝐭𝐫𝐢𝐱 𝐕𝐃 𝐒𝐌𝐂𝐈 𝐇𝐂 

𝑽𝑫 67.78% 31.11% 1.11% 

𝑺𝑴𝑪𝑰 7.78% 88.89% 3.33% 

𝑯𝑪 3.33% 6.67% 90% 

 

As a result, 𝑘 NN was used in the study to 

support multi-class classification and to distinguish 

𝑉𝐷, 𝑆𝑀𝐶𝐼 patients, and 𝐻𝐶 subjects. This study 

had several limitations, including a small sample 

size, and an additional analysis with a large 

database should be performed in the future. 

Finally, we compared the proposed approach to 

other cutting-edge methods in the literature that 

employed the different dementia datasets as we did 

in our work. The results show that our model 

outperforms other existing methods in the literature, 

with the highest classification accuracy of 90.52% 

compared to Kashefpoor et al. [9] proposed a 

methodology that obtained an accuracy of around 

88%, Sharma et al. [10] investigated different 

features for control vs. 𝑀𝐶𝐼 signal classification 

and obtained accuracy ranges between 73.2% and 

89.8%. 

 

 

4. Conclusion 

 
The electroencephalogram (EEG) is a vital tool 

for studying mental processes. Here, we analyze 

and filter EEG signals to identify promising 

channels and useful markers for an earlier, more 

accurate diagnosis of dementia. The WT method 

has been implemented as a denoising method. 

Patients with 𝑉𝐷  and 𝑆𝑀𝐶𝐼  have had their 

irregularities assessed with 𝑆𝑝𝑒𝑐𝐸𝑛 , 𝐴𝑝𝐸𝑛 , and 

𝑃𝑒𝑟𝐸𝑛  as characteristics. To improve 𝑊𝑀 

categorization, we applied the 𝐹𝑁𝑃𝐴𝑄𝑅 

dimensionality reduction technique in conjunction 

with the IBGSA channel selection algorithm. 

𝐹𝑁𝑃𝐴𝑄𝑅  dimensionality reduction technique 

increased 𝑘 NN classification accuracy from 

86.67% to 88.09%, while the IBGSA channel 

selection algorithm increased it to 90.52%. 

Findings revealed that IBGSA reliably enhances 

𝑊𝑀  discrimination in 𝑉𝐷 , 𝑆𝑀𝐶𝐼  patients, and 

𝐻𝐶 controls. Because of these findings, it is clear 

that minimizing the number of channels used in the 

IBGSA selection process has a substantial impact 

on improving classification accuracy. 

Working memory stores and manipulates 

information for ongoing tasks. Dementia causes 

cognitive deterioration, including working memory 

loss. Therefore, working memory enhancement 

may slow dementia-related cognitive deterioration. 

Working memory training may increase brain 

activity in working memory-related areas, however, 

healthy volunteers trained working memory using 

an adaptive N-back task. The training did not 

directly cause changes in brain activation in several 

important locations. In spite of that, studies have 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

38 

implied that working memory training may have 

benefits, but more study is needed to determine the 

long-term consequences. Working memory training 

alone may not diminish dementia-related brain 

activity since dementia is complicated. Working 

memory training may also be affected by dementia 

stage, type, and training procedure. In general, 

improving working memory in people who have 

dementia continues to be our focus of research. 

Future studies may provide additional insights into 

effective interventions and techniques to improve 

cognitive function and quality of life. 

 

 

References 
 

[1] B. C. Campbell, D. A. De Silva, M. R. Macleod, 

S. B. Coutts, L. H. Schwamm, S. M. Davis, et 

al., "Ischaemic stroke," Nature Reviews 

Disease Primers, vol. 5, p. 70, 2019. 

[2] N. K. Al-Qazzaz, S. H. Ali, S. A. Ahmad, and 

S. Islam, "Cognitive assessments for the early 

diagnosis of dementia after stroke," 

Neuropsychiatric disease and treatment, vol. 

10, p. 1743, 2014. 

[3] N. K. Al-Qazzaz, S. H. Ali, S. A. Ahmad, S. 

Islam, and K. Mohamad, "Cognitive 

impairment and memory dysfunction after a 

stroke diagnosis: a post-stroke memory 

assessment," Neuropsychiatric disease and 

treatment, vol. 10, p. 1677, 2014. 

[4] C. N. Kan, J. Cano, X. Zhao, Z. Ismail, C. L.-H. 

Chen, and X. Xu, "Prevalence, clinical 

correlates, cognitive trajectories, and dementia 

risk associated with mild behavioral 

impairment in Asians," The Journal of Clinical 

Psychiatry, vol. 83, p. 40123, 2022. 

[5] N. K. Al-Qazzaz, S. H. B. M. Ali, S. A. Ahmad, 

M. S. Islam, and J. Escudero, "Discrimination 

of stroke-related mild cognitive impairment and 

vascular dementia using EEG signal analysis," 

Medical & biological engineering & 

computing, vol. 56, pp. 137-157, 2018. 

[6] N. K. Al-Qazzaz, S. H. B. Ali, S. A. Ahmad, K. 

Chellappan, M. S. Islam, and J. Escudero, "Role 

of EEG as Biomarker in the Early Detection and 

Classification of Dementia," The Scientific 

World Journal, vol. 2014, 2014. 

[7] E. H. Houssein, A. Hammad, and A. A. Ali, 

"Human emotion recognition from EEG-based 

brain–computer interface using machine 

learning: a comprehensive review," Neural 

Computing and Applications, vol. 34, pp. 

12527-12557, 2022. 

[8] N. K. Al-Qazzaz, S. Hamid Bin Mohd Ali, S. A. 

Ahmad, M. S. Islam, and J. Escudero, 

"Automatic artifact removal in EEG of normal 

and demented individuals using ICA–WT 

during working memory tasks," Sensors, vol. 

17, p. 1326, 2017. 

[9] M. Kashefpoor, H. Rabbani, and M. Barekatain, 

"Automatic diagnosis of mild cognitive 

impairment using electroencephalogram 

spectral features," Journal of medical signals 

and sensors, vol. 6, p. 25, 2016. 

[10] N. Sharma, M. Kolekar, K. Jha, and Y. 

Kumar, "EEG and cognitive biomarkers based 

mild cognitive impairment diagnosis," Irbm, 

vol. 40, pp. 113-121, 2019. 

[11] P. Durongbhan, Y. Zhao, L. Chen, P. Zis, M. 

De Marco, Z. C. Unwin, et al., "A dementia 

classification framework using frequency and 

time-frequency features based on EEG 

signals," IEEE Transactions on Neural 

Systems and Rehabilitation Engineering, vol. 

27, pp. 826-835, 2019. 

[12] A. H. H. Al-Nuaimi, E. Jammeh, L. Sun, and 

E. Ifeachor, "Complexity measures for 

quantifying changes in electroencephalogram 

in Alzheimer’s disease," Complexity, vol. 

2018, 2018. 

[13] N. K. Al-Qazzaz, M. K. Sabir, A. H. Al-

Timemy, and K. Grammer, "An integrated 

entropy-spatial framework for automatic 

gender recognition enhancement of emotion-

based EEGs," Medical & Biological 

Engineering & Computing, pp. 1-20, 2022. 

[14] M. Şeker, Y. Özbek, G. Yener, and M. S. 

Özerdem, "Complexity of EEG dynamics for 

early diagnosis of Alzheimer's disease using 

permutation entropy neuromarker," Computer 

Methods and Programs in Biomedicine, vol. 

206, p. 106116, 2021. 

[15] S. J. Ruiz-Gómez, C. Gómez, J. Poza, G. C. 

Gutiérrez-Tobal, M. A. Tola-Arribas, M. 

Cano, et al., "Automated multiclass 

classification of spontaneous EEG activity in 

Alzheimer’s disease and mild cognitive 

impairment," Entropy, vol. 20, p. 35, 2018. 

[16] C. S. Musaeus, K. Engedal, P. Høgh, V. Jelic, 

M. Mørup, M. Naik, et al., "EEG theta power 

is an early marker of cognitive decline in 

dementia due to Alzheimer’s disease," 

Journal of Alzheimer's Disease, vol. 64, pp. 

1359-1371, 2018. 

[17] J. E. Santos Toural, A. Montoya Pedrón, and 

E. J. Marañón Reyes, "Classification among 

healthy, mild cognitive impairment and 

Alzheimer’s disease subjects based on 

wavelet entropy and relative beta and theta 

power," Pattern Analysis and Applications, 

vol. 24, pp. 413-422, 2021. 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

39 

[18]  B. Oltu, M. F. Akşahin, and S. Kibaroğlu, "A 

novel electroencephalography based approach 

for Alzheimer’s disease and mild cognitive 

impairment detection," Biomedical Signal 

Processing and Control, vol. 63, p. 102223, 

2021. 

[19] M. KavitaMahajan and M. S. M. Rajput, "A 

Comparative study of ANN and SVM for 

EEG Classification," International Journal of 

Engineering, vol. 1, 2012. 

[20] N. K. Al-Qazzaz, S. H. M. Ali, and S. A. 

Ahmad, "Differential Evolution Based 

Channel Selection Algorithm on EEG Signal 

for Early Detection of Vascular Dementia 

among Stroke Survivors," in 2018 IEEE-

EMBS Conference on Biomedical 

Engineering and Sciences (IECBES), 2018, 

pp. 239-244. 

[21] T. Lan, D. Erdogmus, A. Adami, S. Mathan, 

and M. Pavel, "Channel selection and feature 

projection for cognitive load estimation using 

ambulatory EEG," Computational 

intelligence and neuroscience, vol. 2007, pp. 

8-8, 2007. 

[22] M. Arvaneh, C. Guan, K. K. Ang, and C. 

Quek, "Optimizing the channel selection and 

classification accuracy in EEG-based BCI," 

IEEE Transactions on Biomedical 

Engineering, vol. 58, pp. 1865-1873, 2011. 

[23] M. Schröder, T. N. Lal, T. Hinterberger, M. 

Bogdan, N. J. Hill, N. Birbaumer, et al., 

"Robust EEG channel selection across 

subjects for brain-computer interfaces," 

EURASIP Journal on Applied Signal 

Processing, vol. 2005, pp. 3103-3112, 2005. 

[24] N. K. Al-Qazzaz, M. K. Sabir, S. Ali, S. A. 

Ahmad, and K. Grammer, "Effective EEG 

Channels for Emotion Identification over the 

Brain Regions using Differential Evolution 

Algorithm," in 2019 41th Annual 

International Conference of the IEEE 

Engineering in Medicine and Biology Society 

(EMBC), 2019. 

[25] N. K. Al-Qazzaz, S. H. B. M. Ali, S. A. 

Ahmad, and J. Escudero, "Optimal EEG 

Channel Selection for Vascular Dementia 

Identification Using Improved Binary 

Gravitation Search Algorithm," in 

International Conference for Innovation in 

Biomedical Engineering and Life Sciences, 

2017, pp. 125-130. 

[26] R. N. Khushaba, S. Kodagoda, D. Liu, and G. 

Dissanayake, "Electromyogram (EMG) based 

fingers movement recognition using 

neighborhood preserving analysis with QR-

decomposition," in Intelligent Sensors, Sensor 

Networks and Information Processing 

(ISSNIP), 2011 Seventh International 

Conference on, 2011, pp. 1-105. 

[27] N. K. Al-Qazzaz, S. Ali, S. A. Ahmad, and J. 

Escudero, "Classification enhancement for 

post-stroke dementia using fuzzy 

neighborhood preserving analysis with QR-

decomposition," in 2017 39th Annual 

International Conference of the IEEE 

Engineering in Medicine and Biology Society 

(EMBC), 2017, pp. 3174-3177. 

[28] N. K. Al-Qazzaz, S. Ali, S. Islam, S. Ahmad, 

and J. Escudero, "EEG Wavelet Spectral 

Analysis During a Working Memory Tasks in 

Stroke-Related Mild Cognitive Impairment 

Patients," in International Conference for 

Innovation in Biomedical Engineering and 

Life Sciences, 2016, pp. 82-85. 

[29] Z. German-Sallo and C. Ciufudean, 

"Waveform-adapted wavelet denoising of 

ECG signals." 

[30] A. Shoeb and G. Cliord, "Chapter 16 - 

Wavelets; Multiscale Activity in 

Physiological Signals," in Biomedical Signal 

and Image Processing, ed, 2005. 

[31] J. Escudero, R. Hornero, D. Abásolo, and A. 

Fernández, "Blind source separation to 

enhance spectral and non-linear features of 

magnetoencephalogram recordings. 

Application to Alzheimer's disease," Medical 

engineering & physics, vol. 31, pp. 872-879, 

2009. 

[32] J. Escudero Rodríguez, "Applications of blind 

source separation to the 

magnetoencephalogram background activity 

in alzheimer's disease," Universidad de 

Valladolid, 2010. 

[33] R. Hornero, J. Escudero, A. Fernández, J. 

Poza, and C. Gómez, "Spectral and nonlinear 

analyses of MEG background activity in 

patients with Alzheimer's disease," 

Biomedical Engineering, IEEE Transactions 

on, vol. 55, pp. 1658-1665, 2008. 

[34] J. S. Richman and J. R. Moorman, 

"Physiological time-series analysis using 

approximate entropy and sample entropy," 

American Journal of Physiology-Heart and 

Circulatory Physiology, vol. 278, pp. H2039-

H2049, 2000. 

[35] D. E. Lake, J. S. Richman, M. P. Griffin, and 

J. R. Moorman, "Sample entropy analysis of 

neonatal heart rate variability," American 

Journal of Physiology-Regulatory, Integrative 

and Comparative Physiology, vol. 283, pp. 

R789-R797, 2002. 



Noor K. Al-Qazzaz                                 Al-Khwarizmi Engineering Journal, Vol. 19, No. 4, P.P. 29- 41(2023) 

40 

[36] H. Azami and J. Escudero, "Improved 

multiscale permutation entropy for 

biomedical signal analysis: Interpretation and 

application to electroencephalogram 

recordings," Biomedical Signal Processing 

and Control, vol. 23, pp. 28-41, 2016. 

[37] A. Holzinger, M. Hörtenhuber, C. Mayer, M. 

Bachler, S. Wassertheurer, A. J. Pinho, et al., 

"On entropy-based data mining," in 

Interactive Knowledge Discovery and Data 

Mining in Biomedical Informatics, ed: 

Springer, 2014, pp. 209-226. 

[38] F. C. Morabito, D. Labate, F. La Foresta, A. 

Bramanti, G. Morabito, and I. Palamara, 

"Multivariate multi-scale permutation entropy 

for complexity analysis of Alzheimer’s 

disease EEG," Entropy, vol. 14, pp. 1186-

1202, 2012. 

[39] E. Ferlazzo, N. Mammone, V. Cianci, S. 

Gasparini, A. Gambardella, A. Labate, et al., 

"Permutation entropy of scalp EEG: A tool to 

investigate epilepsies: Suggestions from 

absence epilepsies," Clinical 

Neurophysiology, vol. 125, pp. 13-20, 2014. 

[40] C. Bandt and B. Pompe, "Permutation 

entropy: a natural complexity measure for 

time series," Physical review letters, vol. 88, 

p. 174102, 2002. 

[41] M. Zanin, L. Zunino, O. A. Rosso, and D. 

Papo, "Permutation entropy and its main 

biomedical and econophysics applications: a 

review," Entropy, vol. 14, pp. 1553-1577, 

2012. 

[42] N. K. Al-Qazzaz, M. K. Sabir, S. H. B. M. Ali, 

S. A. Ahmad, and K. Grammer, 

"Multichannel optimization with hybrid 

spectral-entropy markers for gender 

identification enhancement of emotional-

based EEGs," IEEE Access, vol. 9, pp. 

107059-107078, 2021. 

[43] A. Ghaemi, E. Rashedi, A. M. Pourrahimi, M. 

Kamandar, and F. Rahdari, "Automatic 

channel selection in EEG signals for 

classification of left or right hand movement 

in Brain Computer Interfaces using improved 

binary gravitation search algorithm," 

Biomedical Signal Processing and Control, 

vol. 33, pp. 109-118, 2017. 

[44] J. Xiang, X. Han, F. Duan, Y. Qiang, X. 

Xiong, Y. Lan, et al., "A novel hybrid system 

for feature selection based on an improved 

gravitational search algorithm and k-NN 

method," Applied Soft Computing, vol. 31, pp. 

293-307, 2015. 

[45] N. V. Chawla, K. W. Bowyer, L. O. Hall, and 

W. P. Kegelmeyer, "SMOTE: synthetic 

minority over-sampling technique," Journal 

of artificial intelligence research, pp. 321-

357, 2002. 

[46] R. Kohavi, "A study of cross-validation and 

bootstrap for accuracy estimation and model 

selection," in Ijcai, 1995, pp. 1137-1145. 

[47] Y. Song and J. Zhang, "Discriminating 

preictal and interictal brain states in 

intracranial EEG by sample entropy and 

extreme learning machine," Journal of 

neuroscience methods, vol. 257, pp. 45-54, 

2016. 

[48] I. H. Witten and E. Frank, Data Mining: 

Practical machine learning tools and 

techniques: Morgan Kaufmann, 2005. 

[49] M. Hall, E. Frank, G. Holmes, B. Pfahringer, 

P. Reutemann, and I. H. Witten, "The WEKA 

data mining software: an update," ACM 

SIGKDD explorations newsletter, vol. 11, pp. 

10-18, 2009. 

[50] L. A. Moctezuma and M. Molinas, "Multi-

objective optimization for EEG channel 

selection and accurate intruder detection in an 

EEG-based subject identification system," 

Scientific Reports, vol. 10, pp. 1-12, 2020. 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

  



 (2023) 29-41، صفحة 4، العدد19المجلد  جلة الخوارزمي الهندسيةم                                                         القزازنور كمال 

41 

 

 

 تحسين تصنيف الذاكرة العاملة لنشاط تخطيط الدماغ في الخرف: دراسة مقارنة

 
 ** شوال حميد بن محمد علي            نور كمال القزاز *

 ***سيتي أنوم أحمد 
 العراق /بغداد  /جامعة بغداد /كلية الخوارزمي للهندسة /قسم الهندسة الطبية الحيوية*

 ماليزيا /سيالنغور /قسم الهندسة الكهربائية واإللكترونية والنظم، كلية الهندسة والبيئة المبنية، جامعة كيبانغسان ماليزيا **

 ماليزيا /سيالنغور /ماليزيا /جامعة كيبانغسان /قسم الهندسة الكهربائية واإللكترونية وهندسة النظم /مركز الهندسة اإللكترونية وهندسة االتصاالت المتقدمة
 ماليزيا /سيالنغور /جامعة بوترا ماليزيا /كلية الهندسة /قسم الهندسة الكهربائية واإللكترونية***

 ماليزيا /سيالنغور /سيردانغ /جامعة بوترا ماليزيا /المعهد الماليزي لبحوث الشيخوخة 
  noorbme@kecbu.uobaghdad.edu.iq *البريد االلكتروني:

  sawal@ukm.edu.my *البريد االلكتروني:*

  sanom@upm.edu.my *البريد االلكتروني:**  
 

 
 

 الخالصة 
 

(، وخمسة عشر مريًضا بعد السكتة VD( في خمسة مرضى يعانون من الخرف الوعائي )WMالعاملة )لغرض من التحقيق الحالي هو التمييز بين الذاكرة 

(. تم توضيح EEG( بناًء على الخلفية نشاط تخطيط كهربية الدماغ )HC(، وخمسة عشر فردًا سليًما للتحكم )MCIالدماغية يعانون من ضعف إدراكي خفيف )

(، ApEn( في هذه الدراسة. في الدراسة الحالية، تم استكشاف اإلنتروبيا الطيفية )WTباستخدام التعديل المسبق للموجات ) EEGالتخلص من القطع األثرية 

(، تم إجراء دراسة 𝑘NNأقرب الجيران )-kباستخدام مخطط تصنيف  WM(. لتحسين تصنيف SpecEn(، واإلنتروبيا التقريبية )PerEnوإنتروبي التبديل )

كتقنية لتقليل األبعاد وتحسين البحث عن الجاذبية الثنائية  QR-decomposition (FNPAQR)دام تحليل الحفاظ على الحي الغامض باستخدام مقارنة الستخ

(IBGSA تمت زيادة دقة تصنيف .)𝑘NN   باستخدام تقنية تقليل األبعاد 90.52٪ و 88.09٪ إلى 86.67من ٪FNPAQR   وخوارزمية اختيار قنوات

IBGSAى التوالي. وفقًا للنتائج، يعزز ، علIBGSA  بشكل موثوق التمييز فيWM  للمشاركين فيHC  وMCI  وVD لذلك، توفر .WT  وميزات اإلنتروبيا

 .MCIو  VDللمرضى الذين يعانون من  EEGمؤشًرا صحيًحا للخرف للبحث عن نشاط خلفية  𝑘NNومصنف  IBGSAو 

 

mailto:noorbme@kecbu.uobaghdad.edu.iq
mailto:sawal@ukm.edu.my
mailto:sanom@upm.edu.my

	Abstract
	Keywords: Dementia, wavelet, entropy, dimensionality reduction, channels selection, features, classification.
	1. Introduction
	2. Materials and Methods
	2.1 Participants
	2.2 EEG recording

	2.3 Preprocessing Stage
	2.4 Features Extraction Stage
	2.5 Statistical analysis
	2.6 Dimensionality reduction using 𝐅𝐍𝐏𝐀𝐐𝐑
	2.7 Channel Selection using 𝐈𝐁𝐆𝐒𝐀
	2.8 Dementia Classification Techniques
	3. Results and Discussion
	3.1 Results of Preprocessing Stage
	3.2 Results of Statistical analysis
	3.3 Results of Dementia Classification Techniques
	4. Conclusion
	References