Lattice 123 pattern for automated Alzheimer’s detection using EEG signal

Abstract

This paper presents an innovative feature engineering framework based on lattice structures for the automated identification of Alzheimer's disease (AD) using electroencephalogram (EEG) signals. Inspired by the Shannon information entropy theorem, we apply a probabilistic function to create the novel Lattice123 pattern, generating two directed graphs with minimum and maximum distance-based kernels. Using these graphs and three kernel functions (signum, upper ternary, and lower ternary), we generate six feature vectors for each input signal block to extract textural features. Multilevel discrete wavelet transform (MDWT) was used to generate low-level wavelet subbands. Our proposed model mirrors deep learning approaches, facilitating feature extraction in frequency and spatial domains at various levels. We used iterative neighborhood component analysis to select the most discriminative features from the extracted vectors. An iterative hard majority voting and a greedy algorithm were used to generate voted vectors to select the optimal channel-wise and overall results. Our proposed model yielded a classification accuracy of more than 98% and a geometric mean of more than 96%. Our proposed Lattice123 pattern, dynamic graph generation, and MDWT-based multilevel feature extraction can detect AD accurately as the proposed pattern can extract subtle changes from the EEG signal accurately. Our prototype is ready to be validated using a large and diverse database.

Full text

RESEARCH ARTICLE
Lattice 123 pattern for automated Alzheimer’s detection using EEG
signal
Sengul Dogan
1
•Prabal Datta Barua
2
•Mehmet Baygin
3
•Turker Tuncer
1
•Ru-San Tan
4,5
•
Edward J. Ciaccio
6
•Hamido Fujita
7,8,9
•Aruna Devi
10
•U. Rajendra Acharya
11,12
Received: 16 October 2023 / Revised: 1 March 2024 / Accepted: 7 March 2024 / Published online: 3 April 2024
The Author(s) 2024
Abstract
This paper presents an innovative feature engineering framework based on lattice structures for the automated identifi-
cation of Alzheimer’s disease (AD) using electroencephalogram (EEG) signals. Inspired by the Shannon information
entropy theorem, we apply a probabilistic function to create the novel Lattice123 pattern, generating two directed graphs
with minimum and maximum distance-based kernels. Using these graphs and three kernel functions (signum, upper
ternary, and lower ternary), we generate six feature vectors for each input signal block to extract textural features.
Multilevel discrete wavelet transform (MDWT) was used to generate low-level wavelet subbands. Our proposed model
mirrors deep learning approaches, facilitating feature extraction in frequency and spatial domains at various levels. We
used iterative neighborhood component analysis to select the most discriminative features from the extracted vectors. An
iterative hard majority voting and a greedy algorithm were used to generate voted vectors to select the optimal channel-
wise and overall results. Our proposed model yielded a classification accuracy of more than 98% and a geometric mean of
more than 96%. Our proposed Lattice123 pattern, dynamic graph generation, and MDWT-based multilevel feature
extraction can detect AD accurately as the proposed pattern can extract subtle changes from the EEG signal accurately. Our
prototype is ready to be validated using a large and diverse database.
Keywords Lattice123 pattern AD detection EEG signal classification Feature engineering Self-organized
classification model
Introduction
Alzheimer’s disease (AD) is a neurologic disease (Ciaccio
et al. 2021; Santiago and Potashkin 2021). AD patients
manifest symptoms like recent memory loss (Morton et al.
2021) and, in advanced stages of the disease, the inability
to perform activities of daily living (Puthusseryppady et al.
2022). Age, head trauma, environmental, and genetic fac-
tors contribute to the development of the disease (Breijyeh
and Karaman 2020). AD generally affects persons aged
65 years and above, but there are also cases involving
younger persons (Atri 2019). There is no definitive diag-
nostic test for AD (Dubois et al. 2021; Khare and Acharya
2023). Instead, doctors diagnose based on the patient’s
history and assessment of neurological function (Sperling
et al. 2020). Blood tests and brain imaging are usually
performed to exclude organic causes before confirming a
final AD diagnosis (Fink et al. 2020; Wolinsky et al. 2018).
While no specific treatment currently targets AD, medi-
cations can help alleviate symptoms. Additionally, physical
modification of the living environment and personalized
therapy may help improve the quality of life (Atri 2019).
Artificial intelligence-based automated disorder detec-
tion models have been grown since AI is one of the most
effective methods to solve nondeterministic problems
(Haleem et al. 2019). For instance, Acharya et al. (2019)
proposed an automated model to automatically detect AD
using magnetic resonance images of the brain. However,
MRI is an expensive model to create an automated model.
Therefore, some researchers have been used EEG signals to
detect AD (Cassani et al. 2018). Our research has presented
a novel handcrafted method and our model aims to gen-
erate meaningful features from EEG signals to automati-
cally detect AD. The proposed model has been
Extended author information available on the last page of the article
123
Cognitive Neurodynamics (2024) 18:2503–2519
https://doi.org/10.1007/s11571-024-10104-1(0123456789().,-volV)(0123456789().,-volV)
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

implemented on an EEG dataset and this dataset has two
classes which are AD and control and proposal attained
more than 98% classification performances in three
experiments of the used EEG dataset.
Literature review
In the last few years, several studies have been published
on EEG-based automated diagnosis of AD and mild cog-
nitive impairment (MCI), a lesser state impairment in
cognition and activities of daily living that may lead to AD
(Table 1). Several studies used deep learning-based meth-
ods (Alves et al. 2022; Bi and Wang 2019; Huggins et al.
2021; Ieracitano et al. 2019), which entail high computa-
tional complexity and costs. Some studies attained only
modest classification performance (Cassani and Falk 2019;
Ieracitano et al. 2019,2020; Pirrone et al. 2022), whereas
others attained high accuracy (Alves et al. 2022; Dogan
et al. 2022) but on a balanced dataset.
Literature gaps
The literature gaps based on Table 1are given below:
•Most of the models developed have used conventional
feature extraction and classifiers.
•Few works based on deep learning techniques have
yielded high classification accuracies with high com-
putational complexity. Training a deep model requires
expensive hardware, such as graphical, tensor, or neural
processing units. To enable training on simpler com-
puter configurations, there is a need for a lightweight
yet highly accurate model.
Table 1 Related works on automated AD detection
Paper Dataset Method Results (%)
Bi and Wang (2019) 4 healthy, 4 MCI, 4 AD Spectral topography maps, spike convolutional deep
Boltzmann machine and discriminative contractive
slab
Acc: 95.04
Cassani and Falk (2019) 20 healthy, 34 AD Spectral feature extraction, ANOVA, and SVM Acc: 88.1
F1: 86.2
Ieracitano et al. (2019,2020)63 healthy, 63 MCI, 63 AD Power spectral density images, custom-designed
CNN
Acc: 83.3
Ieracitano et al. (2020) 63 healthy, 63 MCI, 63 AD Continuous wavelet transform, bispectrum features,
multi-layer perceptron classifier
Acc: 89.22
Huggins et al. (2021) 52 healthy, 37 MCI, 52 AD Continuous wavelet transform, tiled topographical
images, AlexNet-based CNN
Acc: 98.9
Pirrone et al. (2022) 20 healthy, 37 MCI, 48 AD Power spectrum density, short-time Fourier
transform, kNN
Acc: 86.0
Alves et al. (2022) 24 healthy, 24 AD Pearson’s correlation, custom-designed CNN,
hyperparameter optimization
Acc: 100
Pre: 100
Rec: 100
Dogan et al. (2022) 11 healthy, 12 AD Novel primate brain pattern, iterative neighborhood
component analysis, kNN
Acc: 100
Pre: 100
Rec: 100
Puri et al. (2022) 11 healthy, 12 AD Empirical mode decomposition, Hjorth parameters
using Kruskal–Wallis test, SVM
Acc: 92.90
Sen: 94.32
Spe: 94.34
Pre: 94.33
F1: 94.32
Puri et al. (2023) 11 healthy, 12 AD Low-complexity orthogonal wavelet filter banks,
SVM, wavelets
Acc: 98.60
Sen: 97.34
Spe: 99.85
Rossini et al. (2022) 16 MCI, 24 AD, 13 other dementias Graph theory, principal components analysis, SVM AUC: 97.00
Acc: 95.00
Acc accuracy, CNN convolutional neural network, F1 F1 score, kNN k-nearest neighbor, MCI mild cognitive impairment, Pre precision, Rec
recall, Sen sensitivity, Spe specificity, SVM support vector machine
2504 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Motivation
We have proposed a dynamic pattern-based feature
extraction function, a lattice-based function, to overcome
the existing literature gaps. This helps create a lightweight
model that works like a deep learning model. Our pre-
sented feature engineering model is accurate with lower
computational complexity than the deep learning models.
EEG depicts the spatiotemporal electrical activation of
underlying brain regions recorded using a set of surface
electrodes placed at standardized positions over the scalp
(Friedrich et al. 2022). It has been used to study diverse
neuropsychiatric conditions, including AD (Bouwman
et al. 2022). However, manual interpretation of the EEG
readouts from multiple electrodes (or channels) is time-
intensive and requires expert knowledge (Pirrone et al.
2022), which has necessitated the development of auto-
mated methods (Pirrone et al. 2022; Puri et al. 2023;
Rossini et al. 2022). We were motivated to develop an
accurate and computationally lightweight model for EEG-
based AD diagnosis. We adopted a handcrafted feature
engineering method on a novel lattice pattern termed Lat-
tice123. Lattices, a geometric construct common in popular
science (e.g., post-quantum cryptography), have been used
as directed graph pattern generators for local textural fea-
ture extraction (Cutello et al. 2007; Damewood et al. 2022;
Song et al. 2022). In this work, we proposed a simple
lattice pattern, Lattice123, combined with a probabilistic
kernel designed to dynamically generate directed graphs
for downstream textural feature extraction using binary
feature generation functions akin to local binary pattern
models (Ojala et al. 2002). The main contribution of this
work is the innovative lattice-based dynamic feature
extraction function. It searches for the optimal pattern in
the EEG signal through lattice-based feature extraction.
Our developed model comprises this novel lattice-based
pattern and a self-organized feature engineering process. In
our model, two directed graphs were generated by Lat-
tice123 for every one-dimensional EEG input signal data
block, and three binary feature generation functions were
used to extract local textural features, i.e., the feature
extraction function extracted 6 (= 2 93) feature vectors
per block. Moreover, the EEG signal was decomposed
using the multiple discrete wavelet transform (MDWT)
(Dia et al. 2009) to partition it in the frequency domain,
thereby enabling multilevel extraction of features to emu-
late deep modeling. Other model elements selected for
their known effectiveness and computational efficiency
included iterative neighborhood component analysis
(INCA) feature selection (Tuncer et al. 2020b) and iterative
hard majority voting (IHMV) (Dogan et al. 2021). The
latter facilitated the generation of additional voted results
from channel-wise outputs and the automatic selection of
both channel-wise and overall best results, which rendered
the model fully self-organized.
Novelties and contributions
We have proposed a new lattice-based pattern that
dynamically generated two directed graphs for extracting
features using three extraction kernels. Detailed binary
(AD vs. normal) channel-wise and overall classification
results were presented on the multichannel EEG study
dataset. The computationally lightweight and self-orga-
nized model was able to automatically generate the most
suitable feature extraction graphs per the signal input and
select the best channel-wise and overall voted results.
Dataset
We used a publicly available EEG signal dataset of 59
channels to investigate facial recognition deficits for
detecting AD (Mazzi et al. 2020). In this dataset, EEG
signals were collected from nine participants (eight healthy
individuals and one with AD) through three experiments.
Participants were seated comfortably before a monitor in a
dimly lit room, maintaining a fixed distance. Visual stimuli
were presented on acathode ray tube (CRT)monitor using
E-prime2 software, with eye movements monitored. Three
experiments were conducted on different days for patients
and on the same day for controls. Each trial began with a
fixation cross followed by a warning tone and stimulus
presentation. Participants performed a discrimination task
and stimuli were presented for 300 ms.
Experiment 1
Participants indicated whether the stimulus presented was a
face, a house, or a scrambled image.
For experiments 2 and 3, participants were instructed to
discriminate between upright and inverted faces.
Experiment 2
Stimuli consisted of faces with neutral or fearful
expressions.
Experiment 3
Stimuli involved famous or unfamiliar faces.
The primary objective of these experiments was to
detect amnesia or agnosia using EEG signals. We seg-
mented each EEG signal into 15-s intervals and sampled at
Cognitive Neurodynamics (2024) 18:2503–2519 2505
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

250 Hz to obtain 3750 sample values. The distribution
details of the dataset are shown in Table 2.
It may be noted from Table 2that the EEG signal
dataset used in this work is imbalanced.
Proposed model
The self-organized AD detection model has the following
layers: (1) feature extraction comprising EEG signal
decomposition using MDWT (this enabled downstream
multilevel feature generation, thereby mimicking deep
learning) and Lattice123-based feature engineering (see
section ‘‘Dataset’’); (2) INCA feature selector (Tuncer
et al. 2020b) to remove redundant features, thereby
reducing data dimensionality; (3) a standard shallow
k-nearest neighbor (kNN) classifier (Peterson 2009)to
calculate channel-wise results; (4) IHMV (Dogan et al.
2021) to generate additional channel-wise voted feature
vectors; (5) a greedy algorithm to calculate the best
channel-wise results; and (6) IHMV plus greedy algorithm
to generate additional overall voted prediction vectors and
to calculate the overall best results, respectively. Our
model was implemented in the MATLAB (2021a) pro-
gramming environment on a computer with 16 GB mem-
ory, an Intel i7 7700 processor, and a Windows 11
operating system. The graphical clarification of the pro-
posed Lattice123 pattern-based has been given in Fig. 1.
The steps involved in each of these layers are detailed in
the following subsections.
The abbreviations of this figure are as follows. AD:
Alzheimer’s disease, F: concatenated extracted feature
vector, f: extracted feature vector, HC: healthy control, L:
low-pass filter wavelet bands, s: selected feature vector.
In this work, each EEG record contained 59 channels,
each producing a spatially unique signal utilized as an input
signal to the model. MDWT was applied to each signal,
and four wavelet bands were generated, corresponding to
four low-pass filter coefficients. The raw EEG signal and
the four wavelet bands underwent Lattice123-based feature
extraction to generate six feature vectors each. INCA was
then applied to the generated six feature vectors to create
six selected feature vectors for each signal, which were
input to the kNN classifier to calculate six predicted
vectors. IHMV was then applied to the predicted vectors to
generate voted predicted vectors. The greedy algorithm
was implemented to select the final predicted vector, rep-
resenting the best channel-wise result. The 59 channel-wise
final predicted vectors generated per EEG record were next
input to the IHMV function to generate more voted vectors,
from which the best overall binary classification result was
selected using the greedy algorithm.
Lattice123 pattern
In graph-based feature engineering, features are generated
using kernel function operations within the framework of
either fixed patterns (Subasi et al. 2021; Tuncer et al.
2021a,2021b) or adaptive patterns that are dynamically
generated based on the signal input (Jiang et al. 2022;
Tuncer et al. 2020a). In feature engineering, conventional
feature extraction functions are employed as static patterns
to generate features. However, these static patterns are
limited in producing meaningful features from certain data
blocks. Therefore, a dynamic feature extractor is needed to
extract the hidden patterns from each block. In this
research focus, we utilized the novel Lattice123 process
(Fig. 2) to generate two directed graphs using a proba-
bilistic walking path detection function.
The lattice used for graph generation is shown in Fig. 2.
The patterns (graphs) are determined using this lattice,
which comprises 19 numbered vertexes (v) and 28 directed
edges (all angled downwards). First, the vertexes were
populated sequentially by bit values in the input signal
block. Maximum and minimum walking paths starting and
ending at v1 and v19 were then calculated to generate two
directed graphs for downstream (walking way) feature
extraction. Histogram-based features have been extracted
using the generated graphs. Therefore, the presented fea-
ture extraction model is named the Lattice123 pattern. The
overview of the Lattice123 pattern is shown in Fig. 3.
The presented Lattice123 pattern is a histogram-based
feature extraction algorithm, and the steps of this algorithm
are given below:
1. Normalize the input signal to integer values between 1
and 100 by deploying min–max normalization.
N¼SSmin
Smax Smin

99 þ1ð1Þ
where Nrepresents normalized signal; S, signal value;
Smin, the minimum value of the signal; and Smax, the
maximum value of the signal.
2. Extract the histogram of the normalized signal.
H¼hðNÞð2Þ
Table 2 Overview of the used EEG signal dataset
No Class Experiment 1 Experiment 2 Experiment 3
1 Healthy 1249 1209 1376
2 AD 348 353 374
Total 1597 1562 1750
2506 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

where Hrepresents the histogram of the normalized
signal; and hð:Þ, the histogram extraction function. In
this step, we have extracted a histogram of the nor-
malized signal.
3. Calculate the probability of each value.
pri¼Hi
Pn
i¼1Hi
;i2f1;2;...;ngð3Þ
where prirepresents the probability of the ith value;
and n, the length of the signal.
4. Divide the signal into overlapping blocks of length 19.
sjðÞ¼Siþj1ðÞ;i21;2;...;n18
fg
;j
21;2;...;19fg ð4Þ
vjðÞ¼Niþj1ðÞ ð5Þ
where srepresents an overlapping block of the input
signal, S; and v, the normalized overlapping block.
5. Calculate the probability matrix using probability
values and relationships.
Mk;j¼prvðjÞ;k21;2;...;18
fg ð6Þ
where Mrepresents the probability matrix; and Mk;j,
the probability of the jth value, where the parent value
of the jth value is the kth value.
6. Using minimization and maximization operations,
create two walking paths (directed graphs) from vertex
1 to vertex 19 of the Lattice 123 pattern.
w1
1¼1;w2
1¼1;ð7Þ
w1
t¼argmin Ms1
t1;:

;t2f2;3;...;8gð8Þ
w2
t¼argmax Ms2
t1;:
 ð9Þ
w1
9¼19;w2
9¼19 ð10Þ
where wrepresents the walking path. In this work, we
have generated two walking paths (w1and w2). By
using a probability matrix (Ms1
t1;:) of each data block,
we have generated patches and each path has nine
values.
7. Extract feature vectors using the walking paths and
three kernels: signum, upper ternary, and lower ternary.
j1a;bðÞ¼
0;ab\0
1;ab0
ð11Þ
j2a;bðÞ¼
0;abtr
1;ab[tr
ð12Þ
Fig. 1 Block diagram of the
proposed model: amodel
overview and bLattice123-
based feature extraction. In this
work, we have generated two
paths (maximum and minimum)
by deploying the probabilistic
way generation function,
applying three feature extraction
functions, and generating 6
(= 3 92) feature vectors
Cognitive Neurodynamics (2024) 18:2503–2519 2507
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

j3a;b
ðÞ
¼0;abtr
1;ab\tr
ð13Þ
where j1ð:Þ;j2ð:Þand j3ð:Þrepresent signum, upper
ternary and lower ternary kernels, respectively; a;b,
the input values of the kernels and we have used signal
values as inputs; and tr, the threshold value for the
ternary functions, which, in this model, was calculated
as half the standard deviation of the signal. Six-bit
groups were thus extracted using these three kernels
and two walking paths.
bitctðÞ¼jlsw
ktðÞ

;sw
ktþ1ðÞ

;
t21;2;...;8fgk21;2fg;l21;2;3fg;
c21;2;...;6
fg
ð14Þ
where bit represents the binary feature array and c:
category of the generated bit. Each bit array contained
eight binary features.
8. Generate feature signals (map signals) using binary-to-
decimal transformation.
mciðÞ¼X
8
t¼1
bitctðÞ2t1ð15Þ
where mrepresents the map signal. Six map signals
were generated.
9. Extract histograms of the map signals.
HciðÞ¼hðmcÞð16Þ
Each generated histogram represents a feature vector of
length 256 (= 2
8
). Six feature vectors were generated. The
proposed Lattice123 pattern generates two graphs for each
data block, which have been utilized as a pattern. More-
over, three kernels have been used to extract binary fea-
tures for each graph. Therefore, this feature extraction
method generated 6 feature vectors.
Feature extraction
The MDWT-based decomposition of the raw input EEG
signal yielded four wavelet bands. These banded signals
plus the raw EEG signal were input to the Lattice123-based
feature extraction model. The 11 steps that define the
proposed Lattice123-based model are detailed below.
Step 1: Read channel-wise signals from the EEG record
of the study dataset.
Step 2: Apply MDWT using Daubechies 4 (db4) mother
wavelet filter function to the raw EEG signal to decompose
it into four wavelet subbands corresponding to four low-
pass filter coefficients.
L1H1
½¼#ðSÞð17Þ
LhHh
½¼#Lh1
ðÞ;h2f2;3;4gð18Þ
where Lrepresents the low-band filter; H, the high-band
filter; and #ð:Þ, the discrete wavelet transform function, h:
number of wavelet levels.
Step 3: Extract features from the raw signal and low-
pass the wavelet subbands by deploying the Lattice123
pattern.
f1
0f2
0f3
0f4
0f5
0f6
0

¼LðSÞð19Þ
f1
tf2
tf3
tf4
tf5
tf6
t

¼LLt
ðÞ;t2f1;2;3;4gð20Þ
where Lð:Þrepresents the Lattice123-based feature
extraction function,S: EEG signal, and f, the extracted
feature vector of length 256. For instance,f1
0: the first fea-
ture vector of the raw EEG signal.
Step 4: Merge the feature vectors according to type.
FqjðÞ¼fq
pjþp256ðÞðÞ;p20;1;...;4
fg
;q
2f1;2;...;6gð21Þ
Fig. 2 The used lattice for the graph generation. There are one (v1),
two (v2 and v3), and three (v4, v5, and v6) vertexes in the top three
tiers, which explains its name: Lattice123. In this research, we have
used a nine-leveled Lattice123 Pattern. Therefore, we have used 19
vertexes
2508 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

where Frepresents the concatenated feature vector of
length 1280 (= 256 95). Six concatenated feature vectors
were obtained from each channel-wise input signal.
Feature selection
We employed an iterative feature selector, an enhanced
version of neighborhood component analysis (NCA),
known as INCA (Tuncer et al. 2020b). It is an iterative
approach used to determine the optimal number of features.
It involves a series of iterations, during which additional
features are systematically selected. A loss value calcula-
tion function is applied to evaluate the informativeness of
the selected feature vectors in each iteration. The process
continues iteratively, and the feature vector with the best-
computed loss value is ultimately chosen as the final
selected feature vector. The steps involved in feature
selection are given below.
Step 5: Apply INCA to calculate the qualified indexes of
all features in each concatenated feature vector.
idq¼uðFq;yÞð22Þ
where uð:Þrepresents the neighborhood component anal-
ysis feature selection function; y, the real output; and id,
the qualified indexes array. The most accurate feature
vector was selected using the following operations.
fsr
qk;jðÞ¼Fqk;idqjðÞ

;r21;2;...;fv iv þ1
fg
;
k21;2;...;dim
fg
;j21;2;...;v
fg
;v2fiv;iv þ1;...;fvg:
ð23Þ
accr
q¼Cfsr
q;y

:ð24Þ
inq¼argmax accr
q
 ð25Þ
sqk;zðÞ¼Fqk;idqzðÞ

;z21;2;...;inqþiv 1

ð26Þ
where fs represents the selected feature vectors; acc,
accuracy value; Cð:Þ, the accuracy calculation function; in,
index of most accurate feature vector; iv. initial value of
loop; fv, the final value of loop; s, the selected final vector.
These equations describe the process of iterative feature
selection using the INCA algorithm. The aim is to
Fig. 3 Overview of the
Lattice123 pattern. In this work,
we have used a one-dimensional
signalsix, and we have obtained
six feature vectors, and the
length of each feature vector is
equal to 256
Cognitive Neurodynamics (2024) 18:2503–2519 2509
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

iteratively select and evaluate feature vectors to identify
the most accurate and informative features for further
processing. The loop range is set from 100 to 512, and the
accuracy is obtained using the kNN classifier function.
Calculation of channel-wise predicted vectors
The six selected feature vectors were input to a standard
distance-based kNN classifier [50] to calculate the corre-
sponding predicted vectors. The parameter settings were:
k,1; distance, L1-norm; voting, no; validation and tenfold
cross-validation (CV).
Step 6: Classify the selected six feature vectors using the
1NN classifier (k = 1) with a tenfold CV.
pq¼dðsq;yÞð27Þ
where prepresents the predicted vector; and dð:Þ, the kNN
classifier function.
Calculation of channel-wise voted prediction
vectors
IHMV (Dogan et al. 2021) can potentially generate better
results in systems that give rise to multiple results, such as
our model, which produced six predicted vectors per
channel. IHMV calculated qualified indexes for the pre-
dicted vectors, sorted in descending order. Then, the pre-
dicted vectors were iteratively (loop range 3 to 6) voted on
by deploying the mode function, which generated addi-
tional voted vectors.
accq¼Hðpq;yÞð28Þ
id ¼nðaccÞð29Þ
vpr2¼xpid jðÞ;pid jþ1ðÞ
;...;pid rðÞ

;r2f3;4;...;npg
ð30Þ
where Hð:Þrepresents the accuracy calculation function;
nð:Þ, the sorting function; id, are sorted indexes; xð:Þ, the
mode function; np, the number of predicted vectors; and
vp, voted prediction vector, of which four were created
from the six predicted vectors generated per channel.
Step 7: Apply IHMV to the six predicted vectors to
create four voted prediction vectors.
Calculation of best channel-wise result
From among the ten prediction vectors per channel (six
calculated by the kNN classifier; four voted by IHMV), the
greedy algorithm was applied to calculate, one at a time,
the best channel-wise results for 59 channels.
Step 8: Apply a greedy algorithm to select the best
channel-wise result.
accq¼Hðpq;yÞð31Þ
accqþg¼Hvpg;y

;g2f1;2;3;4gð32Þ
x¼maxðaccÞð33Þ
where xrepresents the index of the most accurate predic-
tion vector and cp, the channel-wise prediction vector;
Step 9: Repeat steps 1 to 8 until the best channel-wise
results are calculated for all channels.
cpa¼px;x6
vpx6;x[6
;a21;2;...;ncfg ð34Þ
where nc represents the number of channels, i.e., 59.
Calculation of the overall best result layer
After calculating the results of all channels, the IHMV and
greedy algorithm were again applied to these results to
iteratively (loop range 3 to 59) generate the overall best
result for the 59-channel EEG record.
Step 10: Apply IHMV to all 59 channel-wise results to
generate an additional 57 (= 59–3 ?1) voted prediction
vectors.
Step 11: Select the most accurate predicted vector
among the 116 (= 59 ?57) predicted vectors by deploying
the greedy algorithm.
Results
Model parameters
Model parameters are summarized in Table 3.
Performance metrics
Model performance for binary classification into AD versus
healthy classes in the three experiments was assessed using
standard metrics: accuracy and geometric mean (square
root of the product of sensitivity and specificity) (Powers
2020), the latter being preferred due to the imbalanced
study dataset.
Channel-wise results
Channel-wise results in the three experiments were excel-
lent, with at least 96% accuracy and 93% geometric mean
across all experiments (Fig. 4). For Experiments 1, 2, and
3, the best channel-wise accuracies were 97.62% (Channel
56), 99.42% (Channel 32), and 98% (Channel 21),
respectively, while the best geometric means were 96.09%
(Channel 36), 99.10% (Channel 49), and 96.52% (Channel
53), respectively.
2510 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Confusion matrixes of the best channel-wise results as
ascertained by the geometric mean (Fig. 5) or accuracy
criteria (Fig. 6) demonstrate low rates of misclassification,
which attest to the robustness of the model.
Overall classification results
For Experiments 1, 2, and 3, the overall best accuracies
were 98.37%, 99.62%, and 98.74%, respectively and the
overall best geometric means were 96.74%, 99.45%, and
97.52%, respectively. In addition, confusion matrices of
the overall best results obtained demonstrated low mis-
classification rates (Fig. 7).
Using Fig. 7, we have computed this model’s classifi-
cation accuracy, sensitivity, specificity, precision, F1-score
and geometric mean. These results are presented in
Table 4.
The results presented in Table 4the used metrics are:
accuracy, sensitivity, specificity, precision, F1-score, and
geometric mean.
Our Lattice123 pattern-based self-organized feature
engineering model demonstrated high performance metrics
for all three experiments. In Experiment 1, the proposed
model achieved 98.37% overall accuracy and this results is
a high classification accuracy. Moreover, our model
reached 93.97% sensitivity for AD detection and 96.74% of
geometric mean was computed.
In Experiment 2 is the best accurate expirement since
our model yielded 99.62% and 99.45% classification
accuracy and geometric mean respectively. Moreover, our
model reached 99.15% AD detection rate for this
experiment.
In Experiment 3, our proposal achieved 98.64% overall
classification accuracy. In this point, our model reached
higher classification performance than Experiment 1 for
Experiment 3.
Table 4clearly illustrates that the presented lattice-
based EEG signal classification model achieved [98%
overall classification accuracies and over 93% AD detec-
tion sensitivities for all experiments. These results high-
light that our proposed model has high and general (tested
across three different experiments) classification perfor-
mances for AD detection using EEG signals, attributable to
the dynamic structure of the recommended Lattice123
feature extraction function.
Computational complexity
The proposed handcrafted feature engineering architecture
has low time complexity. Lattice123 is a dynamic pattern-
based feature generator in which a probabilistic matrix was
created using relations (directed edges in Fig. 1). The time
burden is OðrnÞ, where rrepresents the number of
edges; and n, the length of the signal. Taking into account
the signal decomposition using MDWT, the combined
MDWT- and Lattice123-based multilevel feature extrac-
tion has a time burden given by Ornlog rnðÞðÞ. The
time burden of the INCA-based feature selection is
OsþlcðÞ; where srepresents the time complexity coeffi-
cient of the neighborhood component analysis; l, the
number of loops; and c, the time complexity coefficient of
the classifier—we used kNN as the classifier, which has a
time complexity of OðcÞ. The computational complexity of
IHMV, a basic loop-based mode function majority voting
algorithm, depends on the length of the predicted vectors
(number of observations) and the number of feature vectors
(channels). Hence, the time complexity is OðifÞ, where i
represents the number of iterations; and f, the number of
Table 3 Transition table of the Lattice123-based classification model
Method Parameters Output
MDWT Wavelet filter, db4; levels, n = 4; subbands, low-pass filter
coefficient subbands
4 wavelet subbands
Lattice123 Block size, 19; walking path creation function, probability;
generated graphs, n = 2; kernels, n = 3
The proposed feature vector generates six
types of feature vectors, and each feature
vector’s length is 256
Feature extraction using
MDWT ?Lattice123
Raw EEG signal ?4 wavelet subbands used as input 6 concatenated feature vectors, each of
length 1280
INCA Loop range, 100–512; accuracy calculator, kNN 6 selected feature vectors, each of different
optimal lengths
kNN k, 1; distance, L1-norm; voting, no; validation, tenfold CV 6 predicted vectors
IHMV Loop range, 3 to N, where N = 6 for channel-wise and N = 59 for
overall result calculations; kernel, mode function
4 voted vectors were generated for each
channel, and 57 were generated for overall
result calculation
Greedy algorithm Selection criteria: predicted vector with maximum accuracy Most accurate predicted vector
Cognitive Neurodynamics (2024) 18:2503–2519 2511
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

observations. The time burden of the greedy algorithm is
OðafÞ, where arepresents the time complexity coeffi-
cient of the accuracy calculation. Therefore, the total time
burden of our architecture is
Ornlog rnðÞþsþlc þifþafðÞ, which is a
linear function. Unlike deep learning architectures, there is
0 102030405060
Channel
0.93
0.94
0.95
0.96
0.97
0.98
Result
Accuracy Geometric mean
0 102030405060
Channel
0.97
0.975
0.98
0.985
0.99
0.995
Result
Accuracy Geometric mean
0 102030405060
Channel
0.92
0.93
0.94
0.95
0.96
0.97
0.98
Result
Accuracy Geometric mean
Fig. 4 Channel-wise classification performance in the three experiments
(a) Experiment 1- Channel 36 (b) Experiment 2- Channel 49 (c) Experiment 3- Channel 53
12
Predicted Class
1
2
True Class
22
18
326
1231
12
Predicted Class
1
2
True Class
4
8
349
1201
12
Predicted Class
1
2
True Class
22
14
352
1362
Fig. 5 Confusion matrixes of the best channel-wise results per geometric mean. Classes 1 and 2 represent Control and AD, respectively
2512 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

no need for computationally intensive hyperparameter
tuning.
Comparison with the literature
We benchmarked our model against published binary AD
vs. healthy classification models (Table 5). All studies used
different datasets. Dogan (2022) and Alves (2022) attained
100% classification performance on balanced datasets.
Using the hold-out CV strategy, Fabrizio (Vecchio et al.
2020) attained 95% accuracy on a large dataset. Cassani
and Falk (2019) attained a modest 88% accuracy using a
leave-one-subject-out CV. We attained over 98% accuracy
in all experiments based on a small study dataset using a
tenfold CV. The small dataset precluded the use of the
leave-one-subject-out CV strategy. Our model attained
excellent results on an imbalanced dataset, offering a good
balance of performance and undemanding computational
cost.
Discussion
We have presented an accurate, computationally light-
weight, handcrafted lattice-based feature engineering
architecture for automated AD detection using EEG sig-
nals. Inspired by the Shannon information entropy theorem
(Shannon 1951), we applied a probabilistic function to a
novel Lattice123 pattern to generate two directed graphs
using minimum and maximum distance-based kernels
(Tasci et al. 2022). Six feature vectors were produced for
each input signal block using these two graphs and three
kernel functions: the signum, upper ternary, and lower
ternary. Moreover, MDWT-based signal decomposition
gave rise to low-level wavelet subbands that enabled
downstream feature extraction in the frequency and spatial
domains at multiple levels, which mimicked deep models.
To reduce data dimensionality, INCA selected the optimal
numbers of the most discriminative features from the
extracted feature vectors. Finally, the coupled IHMV and
greedy algorithm were applied to generate additional voted
(a) Experiment 1- Channel 56 (b) Experiment 2- Channel 32 (c) Experiment 3- Channel 21
12
Predicted Class
1
2
True Class
22
14
352
1362
12
Predicted Class
1
2
True Class
9 344
1209
12
Predicted Class
1
2
True Class
29
6
345
1370
Fig. 6 Confusion matrixes of the best channel-wise results per accuracy. Classes 1 and 2 represent Control and AD, respectively
12
Predicted Class
1
2
True Class
21
5
327
1244
12
Predicted Class
1
2
True Class
3
3
350
1206
12
Predicted Class
2
True Class
17
5
357
1371
(a) Experiment 1 (b) Experiment 2 (c) Experiment 3
Top 4 channels are used Top 9 channels are used Top 7 channels are used
Fig. 7 Confusion matrices of the overall best results. Classes 1 and 2 represent Control and AD classes, respectively
Cognitive Neurodynamics (2024) 18:2503–2519 2513
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

vectors and the final selection of the best channel-wise and
overall results. Our model was trained and tested on a
dataset partitioned into three experiments. Excellent binary
classification accuracy exceeding 98% was attained for all
experiments. Moreover, the used dataset is imbalanced.
Therefore, we computed other classification performance
metrics as well. For instance, our model achieved over 96%
geometric mean for all experiments. The computed results
have been discussed below.
Across all experiments, the model consistently demon-
strated exceptional performance, achieving an overall
accuracy of 98.37%, 99.62%, and 98.74% in Experiments
1, 2, and 3, respectively. The overall geometric means were
96.74%, 99.45%, and 97.52% for Experiments 1, 2, and 3,
Table 4 Results (%) obtained
using Lattice123 Pattern-based
self-organized feature
engineering model
Metric Experiment 1 Experiment 2 Experiment 3
Class Result Class Result Class Result
Accuracy Control – Control – Control –
AD – AD – AD –
Overall 98.37 Overall 99.62 Overall 98.74
Sensitivity Control 99.60 Control 99.75 Control 99.64
AD 93.97 AD 99.15 AD 95.45
Overall 96.79 Overall 99.45 Overall 97.55
Specificity Control 93.97 Control 99.15 Control 95.45
AD 99.60 AD 99.75 AD 99.64
Overall 96.79 Overall 99.45 Overall 97.55
Precision Control 98.34 Control 99.75 Control 98.78
AD 98.49 AD 99.15 AD 98.62
Overall 98.42 Overall 99.45 Overall 98.70
F1-score Control 98.97 Control 99.75 Control 98.21
AD 96.18 AD 99.15 AD 97.01
Overall 97.58 Overall 99.45 Overall 98.46
Geometric mean Control – Control – Control –
AD – AD – AD –
Overall 96.74 Overall 99.45 Overall 97.52
Table 5 Comparison of our study with published models for binary classification of Alzheimer’s disease vs. healthy control (HC)
Paper Dataset Method Validation Results (%)
Cassani and Falk (2019) 20 HC, 34 AD Spectral feature extraction,
ANOVA, SVM
LOSO CV Acc: 88.1, F1 86.2
Vecchio et al. (2020) 120 HC, 175 AD Exact low-resolution brain
electromagnetic tomography,
SVM
Hold-out CV (80:20) Acc: 95.0, Sen: 95.0,
Spe: 96.0
Alves et al. (2022) 24 HC, 24 AD Pearson’s correlation, custom-
designed CNN, hyperparameter
optimization
tenfold CV Acc: 100, Pre: 100,
Rec: 100
Dogan et al. (2022) 11 HC, 12 AD Primate brain pattern, INCA, kNN tenfold CV Acc: 100, Pre: 100,
Rec: 100
Our model 8 HC, 1 AD Lattice123, MDWT, INCA, kNN,
IHMV, greedy algorithm
tenfold CV Experiment 1:
•Acc:98.37, GM:96.74
Experiment 2:
•Acc:99.62, GM:99.45
Experiment 3:
•Acc:98.74, GM:97.52
Alternative dataset
11 HC, 12 AD
Acc: 100, Pre: 100,
Rec: 100
2514 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

respectively, further emphasizing the model’s robustness.
The confusion matrices obtained for the overall best results
are shown in Fig. 7.
The consistent high performance across all experiments
indicates that the Lattice123 Pattern-based self-organized
feature engineering model effectively captures intricate
patterns from the EEG signals.
Experiment 2 performed better than other experiments
yielding an accuracy of 99.62%, highlighting the model’s
ability to discriminate between upright and inverted faces
based on EEG signals.
Hence, our presented Lattice123 Pattern-based self-or-
ganized feature engineering model is an accurate and
robust automated AD detection model.
To examine the relative contributions of the dynami-
cally generated graphs and local feature extraction kernel
functions to the accuracy of the Lattice123 model, we
analyzed the mean accuracies of the six individual pre-
dicted feature vectors generated from every channel
(Fig. 8). The combination of minimum probabil-
ity ?lower ternary function in Experiment 2 attained the
highest accuracy.
The feature vectors are enumerated 1 to 6 based on
combinations of Lattice123-generated minimum- and
maximum-distance probability graphs and local textural
feature extraction kernel functions: 1, minimum probabil-
ity ?signum function; 2, maximum probability ?signum
function; 3, minimum probability ?upper ternary func-
tion; 4, minimum probability ?lower ternary function; 5,
maximum probability ?upper ternary function; 6, maxi-
mum probability ?lower ternary function.
We evaluated their feature selector indexes to examine
the relative contributions of the one-dimensional raw EEG
signal and the four MDWT-generated wavelet subbands to
feature engineering accuracy. To standardize the compar-
ison, we analyzed only the most accurate channel-wise
performance, i.e., Channel 32 in Experiment 2 (Fig. 6),
using the optimal combination of minimum-distance
graph ?lower ternary function (Fig. 8). Using this stan-
dardized scheme, INCA chose 214 features, which yielded
a 98.37% classification accuracy. The distribution of these
features across the signal input and their relative neigh-
borhood component analysis-generated weights (Fig. 9)
demonstrate that the raw EEG signal contributed the
greatest number of selected features (86/214) to the chan-
nel-wise results. The most weighted signal input was the
L1 wavelet subband, in which the sum of weights of its
selected features was the highest at 6.55. These analyses
underscore the positive effect of MDWT on feature
extraction and downstream model classification
performance.
We also analyzed the optimal lengths of INCA-gener-
ated selected feature vectors in the three experiments. The
mean lengths of the selected feature vectors were 274.02,
253.65, and 262.20 for Experiments 1, 2, and 3, respec-
tively (Fig. 10).
Feeding the selected feature vectors to the downstream
kNN classifier, the model attained (without using majority
voting) accuracies of 96%, 98.27%, and 96% for Experi-
ments 1, 2, and 3, respectively. By applying the IMHV and
greedy algorithm, more accurate channel-wise results were
observed, albeit on the specific best-performing single
channels (see section ‘‘Overall classification results’’ and
Figs. 3and 5), which underscore the positive effects of
majority voting. In the last layer of the model, IHMV was
applied to all the best channel-wise results, and the greedy
algorithm was employed to calculate the final overall best
result. As a result, 98.37%, 99.62%, and 98.74% classifi-
cation accuracies were attained for Experiments 1, 2, and 3,
respectively, based only on limited numbers of the top 4, 9,
and 7 channel-wise results. Accordingly, for the study
dataset, the individual EEG channels that contributed the
most toward model accuracy in all three experiments can
be summarized (Table 6), the position of which may offer
an element of explainability for result interpretation. For
instance, EEG channels overlying the frontal region (de-
noted by ‘‘F’’ in Table 6) feature relatively prominent
among valuable channels contributing to accurate AD
classification.
Based on the above analysis, our findings are given
below:
•The proposed Lattice123 pattern produced six feature
vectors per input signal block using these graphs and
three kernel functions (signum, upper ternary, and
lower ternary). The minimum-distance graph ?lower
ternary function is found to be the best combination
based on our analysis.
•Mean lengths varied between 253.65 and 274.02,
demonstrating diversity in selected feature vector
lengths.
•Selected feature vectors coupled with the kNN classifier
achieved 96%, 98.27%, and 96% accuracy for Exper-
iments 1, 2, and 3, respectively.
•IHMV and greedy algorithm achieved the channel-wise
overall accuracies of 98.37%, 99.62%, and 98.74% for
Experiments 1, 2, and 3, respectively.
•Identified the EEG channels that contributed to obtain-
ing the highest detection performance in the frontal
region.
Highlights and limitations
Highlights of the work are given below:
Cognitive Neurodynamics (2024) 18:2503–2519 2515
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

•We have proposed a novel Lattice123 pattern. Using a
probabilistic graph generation function, directed graphs
(walking paths) were dynamically generated per signal
data block for downstream textural feature extraction
•The diagnostic model comprising Lattice123, multi-
level feature extraction enabled by MDWT signal
decomposition, INCA feature selector, kNN classifier,
IHMV, and the greedy algorithm was trained and tested
on an imbalanced public EEG dataset partitioned into
three experiments.
•The handcrafted self-organized model attained an
excellent performance level of [98% accuracy for
binary classification of AD versus healthy subjects
across all three experiments, with linear computational
complexity.
Limitations of our work are as follows:
•The small study dataset comprised only nine subjects,
which precluded subject-wise validation.
•Default classifier settings were used. Fine-tuning oper-
ations could result in better classification performance.
123456
Method
0.88
0.9
0.92
0.94
0.96
Accuracy
123456
Method
0.92
0.94
0.96
0.98
Accuracy
123456
Method
0.9
0.92
0.94
0.96
Accuracy
(a) Experiment 1 (b) Experiment 2 (c) Experiment 3
Fig. 8 Statistical attributes of the six predicted feature vectors across all 59 channels. Herein, red lines demonstrate average classification
accuracies, boxes show quartile range (Q3–Q1), and red plusses depict abnormal (extreme values per the Gaussian distribution)
(a) (b)
01234567
Sum of the weights
EEG
L1
L2
L3
L4
Fig. 9 Distribution (a) and
weight analysis (b) of the
selected features by the type of
signal input
123
Experiment
100
150
200
250
300
350
400
450
500
Number of features
Fig. 10 Comparison of mean lengths of selected feature vectors by
experiments. In each experiment, INCA was applied 354 times to
every one of the six feature vectors generated for each of the 59
channels to give rise to 354 (= 59 96) selected feature vectors, each
of which had different optimal lengths
2516 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Conclusions
A novel lattice-based feature engineering model was pro-
posed, demonstrating accuracy and computational effi-
ciency for EEG-based AD detection. Dynamic directed
graph generation by the proposed Lattice123 allowed local
textural feature extraction customization specific to the
input signal data block. Additionally, MDWT enabled
multilevel feature generation, positively affecting model
performance as assessed by the higher relative weight of
decomposed wavelet subbands on feature selection.
Incorporating effective information fusion methodology
through IHMV and the greedy algorithm facilitated the
automatic selection of the best channel-wise and overall
results. The model achieved over 98% classification
accuracies across all experiments in the study dataset,
underscoring the advantages of the individual upstream
model components. Moreover, this model is explainable
since we have detected the most informative channels by
using the findings of the presented Lattice123-based AD
detection model. In our future work, we aim to gather
larger EEG datasets to enhance our model’s capabilities.
We plan to incorporate extensive validation on independent
datasets to address the need for validation. This validation
process will enable us to accurately assess the generaliz-
ability of our proposed model across diverse scenarios.
Additionally, we plan to broaden the scope of our model to
include the detection of neurodegenerative disorders like,
such as mild cognitive impairment (MCI), Alzheimer’s
disease, Parkinson’s disease etc. Furthermore, we will
explore alternative models like lattice structures to generate
features and improve the classification performances. Also,
we aim to provide confidence to the clinicians by imple-
menting the explainable artificial intelligence to the pro-
posed model (Loh et al. 2022). These enhancements will
ensure that our model meets the highest standards of val-
idation and generalizability.
Funding Open access funding provided by the Scientific and Tech-
nological Research Council of Tu
¨rkiye (TU
¨BI
˙TAK). The authors
state that this work has not received any funding.
Data availability statement Not applicable.
Declarations
Conflict of interest The authors declare that they have no conflict of
interest.
Ethical approval Ethics approval was not required for this research.
Open Access This article is licensed under a Creative Commons
Attribution 4.0 International License, which permits use, sharing,
adaptation, distribution and reproduction in any medium or format, as
long as you give appropriate credit to the original author(s) and the
source, provide a link to the Creative Commons licence, and indicate
if changes were made. The images or other third party material in this
article are included in the article’s Creative Commons licence, unless
indicated otherwise in a credit line to the material. If material is not
included in the article’s Creative Commons licence and your intended
use is not permitted by statutory regulation or exceeds the permitted
use, you will need to obtain permission directly from the copyright
holder. To view a copy of this licence, visit http://creativecommons.
org/licenses/by/4.0/.
References
Acharya UR et al (2019) Automated detection of Alzheimer’s disease
using brain MRI images: a study with various feature extraction
techniques. J Med Syst 43:1–14
Alves CL, Pineda AM, Roster K, Thielemann C, Rodrigues FA
(2022) EEG functional connectivity and deep learning for
automatic diagnosis of brain disorders: Alzheimer’s disease and
schizophrenia. J Phys Complexity 3:025001
Atri A (2019) The Alzheimer’s disease clinical spectrum: diagnosis
and management. Med Clin 103:263–293
Atri A (2019) Current and future treatments in Alzheimer’s disease.
Thieme Medical Publishers, pp 227–240
Bi X, Wang H (2019) Early Alzheimer’s disease diagnosis based on
EEG spectral images using deep learning. Neural Netw
114:119–135
Bouwman FH et al (2022) Clinical application of CSF biomarkers for
Alzheimer’s disease: from rationale to ratios Alzheimer’s &
Dementia: Diagnosis. Assess Dis Monitor 14:e12314
Table 6 EEG channels
contribute to the final overall
best results in the experiments
Experiment Channel number (spatial position of scalp electrode*)
1 56 (AF4), 54 (AF7), 25 (CP6), 36 (FT7)
2 32 (C2), 49 (Fz), 30 (C1), 4 (PO7), 15 (P4), 34 (C6), 37 (FC5), 39 (FC1), 47 (F3)
3 21 (CP1), 53 (F8), 36 (FT7), 3 (O2), 18 (TP7), 1 (O1), 9 (P7)
*Within the parentheses, capital letters A, C, F, O, P, and T refer to the anterior, central, frontal, occipital,
parietal, and temporal positions of the scalp electrodes (channels) that overlie the corresponding brain
regions; a small letter z refers to the mid-sagittal centerline. There is no anatomical ‘‘anterior’’ or ‘‘central’’
lobe, but the terms were used to describe the relative positions of the channels to the frontal lobe channel.
Even numbers represent left-brain channels, and odd numbers represent right-brain channels
Cognitive Neurodynamics (2024) 18:2503–2519 2517
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Breijyeh Z, Karaman R (2020) Comprehensive review on Alzhei-
mer’s disease: causes and treatment. Molecules 25:5789
Cassani R, Estarellas M, San-Martin R, Fraga FJ, Falk TH (2018)
Systematic review on resting-state EEG for Alzheimer’s disease
diagnosis and progression assessment. Dis Markers
Cassani R, Falk TH (2019) Alzheimer’s disease diagnosis and
severity level detection based on electroencephalography mod-
ulation spectral ‘‘patch’’ features. IEEE J Biomed Health Inform
24:1982–1993
Ciaccio M et al (2021) COVID-19 and Alzheimer’s disease. Brain Sci
11:305
Cutello V, Nicosia G, Pavone M, Timmis J (2007) An immune
algorithm for protein structure prediction on lattice models.
IEEE Trans Evol Comput 11:101–117
Damewood J, Schwalbe-Koda D, Go
´mez-Bombarelli R (2022)
Sampling lattices in semi-grand canonical ensemble with
autoregressive machine learning. Npj Comput Mater 8:1–10
Dia D, Zeghid M, Saidani T, Atri M, Bouallegue B, Machhout M,
Tourki R (2009) Multi-level discrete wavelet transform archi-
tecture design. In: Proceedings of the World congress on
engineering, pp 1–2
Dogan A et al (2021) PrimePatNet87: prime pattern and tunable
q-factor wavelet transform techniques for automated accurate
EEG emotion recognition. Comput Biol Med 138:104867
Dogan S, et al (2022) Primate brain pattern-based automated
Alzheimer’s disease detection model using EEG signals. Cognit
Neurodyn, 1–13
Dubois B et al (2021) Clinical diagnosis of Alzheimer’s disease:
recommendations of the International Working Group. Lancet
Neurol 20:484–496
Fink HA et al (2020) Accuracy of biomarker testing for neuropatho-
logically defined alzheimer disease in older adults with demen-
tia: a systematic review. Ann Intern Med 172:669–677
Friedrich EV, et al (2022) Spatio-temporal dynamics of oscillatory
brain activity during the observation of actions and interactions
between point-light agents. Eur J Neurosci
Haleem A, Javaid M, Khan IH (2019) Current status and applications
of artificial intelligence (AI) in medical field: an overview. Curr
Med Res Pract 9:231–237
Huggins CJ et al (2021) Deep learning of resting-state electroen-
cephalogram signals for three-class classification of Alzheimer’s
disease, mild cognitive impairment and healthy ageing. J Neural
Eng 18:046087
Ieracitano C, Mammone N, Bramanti A, Hussain A, Morabito FC
(2019) A convolutional neural network approach for classifica-
tion of dementia stages based on 2D-spectral representation of
EEG recordings. Neurocomputing 323:96–107
Ieracitano C, Mammone N, Hussain A, Morabito FC (2020) A novel
multi-modal machine learning based approach for automatic clas-
sification of EEG recordings in dementia. Neural Netw 123:176–190
Jiang X, Xia Y, Zhang X-P, Ma J (2022) Robust image matching via
local graph structure consensus. Pattern Recogn 126:108588
Khare SK, Acharya UR (2023) Adazd-Net: Automated adaptive and
explainable Alzheimer’s disease detection system using EEG
signals. Knowl-Based Syst 278:110858
Loh HW, Ooi CP, Seoni S, Barua PD, Molinari F, Acharya UR (2022)
Application of explainable artificial intelligence for healthcare: a
systematic review of the last decade (2011–2022). Comput
Methods Programs Biomed, 107161
Mazzi C, Massironi G, Sanchez-Lopez J, De Togni L, Savazzi S (2020)
Face recognition deficits in a patient with Alzheimer’s disease:
amnesia or agnosia? The importance of electrophysiological
markers for differential diagnosis. Front Aging Neurosci 12:580609
Morton H et al (2021) Defective mitophagy and synaptic degener-
ation in Alzheimer’s disease: focus on aging, mitochondria and
synapse. Free Radical Biol Med 172:652–667
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale
and rotation invariant texture classification with local binary
patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987
Peterson LE (2009) K-nearest neighbor. Scholarpedia 4:1883
Pirrone D, Weitschek E, Di Paolo P, De Salvo S, De Cola MC (2022)
EEG signal processing and supervised machine learning to early
diagnose Alzheimer’s disease. Appl Sci 12:5413
Powers DM (2020) Evaluation: from precision, recall and F-measure
to ROC, informedness, markedness and correlation arXiv
preprint. arXiv:201016061
Puri D, Nalbalwar S, Nandgaonkar A, Kachare P, Rajput J, Wagh A
(2022) Alzheimer’s Disease detection using empirical mode
decomposition and Hjorth parameters of EEG signal. IEEE,
pp 23–28
Puri DV, Nalbalwar SL, Nandgaonkar AB, Gawande JP, Wagh A
(2023) Automatic detection of Alzheimer’s disease from EEG
signals using low-complexity orthogonal wavelet filter banks.
Biomed Signal Process Control 81:104439
Puthusseryppady V, Morrissey S, Aung MH, Coughlan G, Patel M,
Hornberger M (2022) Using GPS tracking to investigate outdoor
navigation patterns in patients with alzheimer disease: cross-
sectional study. JMIR Aging 5:e28222
Rossini PM, Miraglia F, Vecchio F (2022) Early dementia diagnosis,
MCI-to-dementia risk prediction, and the role of machine
learning methods for feature extraction from integrated biomark-
ers, in particular for EEG signal analysis. Alzheimer’s and
Dementia
Santiago JA, Potashkin JA (2021) The impact of disease comorbidi-
ties in Alzheimer’s disease. Front Aging Neurosci 13:631770
Shannon CE (1951) Prediction and entropy of printed English. Bell
Syst Tech J 30:50–64
Song C-H et al (2022) Machine learning of the X Y model on a
spherical Fibonacci lattice. Phys Rev Res 4:023005
Sperling RA et al (2020) Association of factors with elevated amyloid
burden in clinically normal older individuals. JAMA Neurol
77:735–745
Subasi A, Dogan S, Tuncer T (2021) A novel automated tower graph
based ECG signal classification method with hexadecimal local
adaptive binary pattern and deep learning. J Ambient Intell
Human Comput, 1–15
Tasci G, et al. (2022) Automated accurate detection of depression
using twin Pascal’s triangles lattice pattern with EEG Signals.
Knowl-Based Syst 110190
Tuncer T, Aydemir E, Dogan S, Kobat MA, Kaya MC, Metin S
(2021a) New human identification method using Tietze graph-
based feature generation. Soft Comput 25:13437–13449
Tuncer T, Dogan S, Ertam F, Subasi A (2020a) A novel ensemble
local graph structure based feature extraction network for EEG
signal analysis. Biomed Signal Process Control 61:102006
2518 Cognitive Neurodynamics (2024) 18:2503–2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Tuncer T, Dogan S, O
¨zyurt F, Belhaouari SB, Bensmail H (2020b)
Novel multi center and threshold ternary pattern based method for
disease detection method using voice. IEEE Access
8:84532–84540
Tuncer T, Dogan S, Tan R-S, Acharya UR (2021b) Application of
Petersen graph pattern technique for automated detection of
heart valve diseases with PCG signals. Inf Sci 565:91–104
Vecchio F, Miraglia F, Alu
`F, Menna M, Judica E, Cotelli M, Rossini PM
(2020) Classification of Alzheimer’s disease with respect to
physiological aging with innovative EEG biomarkers in a machine
learning implementation. J Alzheimers Dis 75:1253–1261
Wolinsky D, Drake K, Bostwick J (2018) Diagnosis and management
of neuropsychiatric symptoms in Alzheimer’s disease. Curr
Psychiatry Rep 20:1–13
Publisher’s Note Springer Nature remains neutral with regard to
jurisdictional claims in published maps and institutional affiliations.
Authors and Affiliations
Sengul Dogan
1
•Prabal Datta Barua
2
•Mehmet Baygin
3
•Turker Tuncer
1
•Ru-San Tan
4,5
•Edward J. Ciaccio
6
•
Hamido Fujita
7,8,9
•Aruna Devi
10
•U. Rajendra Acharya
11,12
&Sengul Dogan
sdogan@firat.edu.tr
Prabal Datta Barua
Prabal.Barua@usq.edu.au
Mehmet Baygin
mehmet.baygin@erzurum.edu.tr
Turker Tuncer
turkertuncer@firat.edu.tr
Ru-San Tan
tanrsnhc@gmail.com
Edward J. Ciaccio
ciaccio@columbia.edu
Hamido Fujita
hfujita-799@acm.org; fujitahamido@utm.my
Aruna Devi
adevi@usc.edu.au
U. Rajendra Acharya
Rajendra.Acharya@usq.edu.au
1
Department of Digital Forensics Engineering, College of
Technology, Firat University, Elazig, Turkey
2
School of Business (Information System), University of
Southern Queensland, Springfield, Australia
3
Department of Computer Engineering, College of
Engineering, Erzurum Technical University, Erzurum,
Turkey
4
Department of Cardiology, National Heart Centre Singapore,
Singapore, Singapore
5
Duke-NUS Medical School, Singapore, Singapore
6
Department of Medicine, Columbia University Irving
Medical Center, New York, NY, USA
7
Malaysia-Japan International Institute of Technology
(MJIIT), Universiti Teknologi Malaysia,
54100 Kuala Lumpur, Malaysia
8
Andalusian Research Institute in Data Science and
Computational Intelligence, University of Granada, Granada,
Spain
9
Regional Research Center, Iwate Prefectural University,
Iwate, Japan
10
School of Education and Tertiary Access, University of the
Sunshine Coast, Sippy Downs, Caboolture Campus, QLD,
Australia
11
School of Mathematics, Physics and Computing, University
of Southern Queensland, Springfield, Australia
12
Centre for Health Research, University of Southern
Queensland, Springfield, Australia
Cognitive Neurodynamics (2024) 18:2503–2519 2519
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

1.
2.
3.
4.
5.
6.
Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers and authorised users (“Users”), for small-
scale personal, non-commercial use provided that all copyright, trade and service marks and other proprietary notices are maintained. By
accessing, sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of use (“Terms”). For these
purposes, Springer Nature considers academic use (by researchers and students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and conditions, a relevant site licence or a personal
subscription. These Terms will prevail over any conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription
(to the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of the Creative Commons license used will
apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may also use these personal data internally within
ResearchGate and Springer Nature and as agreed share it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not
otherwise disclose your personal data outside the ResearchGate or the Springer Nature group of companies unless we have your permission as
detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial use, it is important to note that Users may
not:
use such content for the purpose of providing other users with access on a regular or large scale basis or as a means to circumvent access
control;
use such content where to do so would be considered a criminal or statutory offence in any jurisdiction, or gives rise to civil liability, or is
otherwise unlawful;
falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association unless explicitly agreed to by Springer Nature in
writing;
use bots or other automated methods to access the content or redirect messages
override any security feature or exclusionary protocol; or
share the content in order to create substitute for Springer Nature products or services or a systematic database of Springer Nature journal
content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a product or service that creates revenue,
royalties, rent or income from our content or its inclusion as part of a paid for service or for other commercial gain. Springer Nature journal
content cannot be used for inter-library loans and librarians may not upload Springer Nature journal content on a large scale into their, or any
other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not obligated to publish any information or
content on this website and may remove it or features or functionality at our sole discretion, at any time with or without notice. Springer Nature
may revoke this licence to you at any time and remove access to any copies of the Springer Nature journal content which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or guarantees to Users, either express or implied
with respect to the Springer nature journal content and all parties disclaim and waive any implied warranties or warranties imposed by law,
including merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published by Springer Nature that may be licensed
from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a regular basis or in any other manner not
expressly permitted by these Terms, please contact Springer Nature at
onlineservice@springernature.com