Combination of gray level co-occurrence matrix and artificial neural networks for classification of COVID-19 based on chest X-ray images

IAES International Journal of Artificial Intelligence (IJ-AI)
Vol. 13, No. 2, June 2024, pp. 1625~1631
ISSN: 2252-8938, DOI: 10.11591/ijai.v13.i2.pp1625-1631  1625
Journal homepage: http://ijai.iaescore.com
Combination of gray level co-occurrence matrix and artificial
neural networks for classification of COVID-19
based on chest X-ray images
Bahtiar Imran1
, Lalu Delsi Samsumar2
, Ahmad Subki3
, Zaeniah4
, Salman5
,
Muhammad Rijal Alfian6
1
Department of Computer System Engineering, Faculty of Informatics and Communication Engineering,
Universitas Teknologi Mataram, Mataram, Indonesia
2
Department of Information Technology, Faculty of Information and Communication Technology, Universitas Teknologi Mataram,
Mataram, Indonesia
3
Department of Software Engineering, Faculty of Information and Communication Technology, Universitas Teknologi Mataram,
Mataram, Indonesia
4
Department of Information Systems, Faculty of Information and Communication Technology, Universitas Teknologi Mataram,
Mataram, Indonesia
5
Department of Informatics Engineering, Faculty of Information and Communication Technology, Universitas Teknologi Mataram,
Mataram, Indonesia
6
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Mataram, Mataram, Indonesia
Article Info ABSTRACT
Article history:
Received Jan 29, 2022
Revised Oct 19, 2023
Accepted Nov 1, 2023
This research uses the gray level co-occurrence matrix (GLCM) and artificial
neural networks to classify COVID-19 images based on chest X-ray images.
According to previous studies, there has never been a researcher who has
integrated GLCM with artificial neural networks. Epochs 10, 30, 50, 70, 100,
and 120 were used in this research. The total number of data points used in
this investigation was 600, divided into 300 normal chests and 300
COVID-19 data points. Epoch 10 had 91% accuracy, epoch 30 had 91%
accuracy, epoch 50 had 92% accuracy, epoch 70 had 91% accuracy, epoch
100 had 92% accuracy, and epoch 120 had 90% accuracy in categorization.
As indicated by the results of the classification tests, combining GLCM and
artificial neural networks can produce good results; a combination of these
methods can yield a classification for COVID-19.
Keywords:
Classification
COVID-19
Feature extraction
Method combination
Neural network This is an open access article under the CC BY-SA license.
Corresponding Author:
Lalu Delsi Samsumar
Department of Information Technology, Faculty of Information and Communication Technology
Universitas Teknologi Mataram
Mataram, Indonesia
Email: lalu.ellsyam@gmail.com
1. INTRODUCTION
In March 2020, World Health Organization (WHO) declared the coronavirus or COVID-19 as a
pandemic outbreak [1]–[3]. In December 2019, the first start of this coronavirus was found in the Wuhan area
of Hubei Province, China. This outbreak spread so quickly from one person to another and has spread rapidly to
all countries worldwide [4]. The emerging COVID-19 virus pandemic puts significant pressure on limited health
resources; several ways have been done to quickly reduce the number of COVID-19 sufferers [5], including
independently reducing transmission [2]. Most of the symptoms that arise are high temperature, persistent cough,
and loss of smell or taste [5]–[8]. Transmission can occur as a result of hand contact with contaminated surfaces.
Therefore, it is necessary to quickly and accurately prevent infection and potential diagnosis [9].

 ISSN: 2252-8938
Int J Artif Intell, Vol. 13, No. 2, June 2024: 1625-1631
1626
Several previous studies regarding the prediction and classification of COVID-19 have been carried out
using various methods with different results, such as in Alamsyah et al. [1] implements recurrent neural network
(RNN) on the Elman network and uses a dataset obtained from Kaggle. The dataset used consists of 70% training
data and 30% test data. Furthermore, Aminu et al. [4] proposes the CovidNet architecture, which requires fewer
parameters than the others. This research shows that CovidNet outperforms other deep learning models in
detecting COVID-19. Shorfuzzaman et al. [2] proposes learning based on convolution neural network (CNN) by
utilizing transfer learning using parameters (weights) from different models, then combining them into one model
by extracting features from each image, Maksum et al. [10] concluded that using the computer-aided diagnosis
system can be used to classify chest X-ray images using the machine learning method. The initial stage is to do
the preprocessing step using gray-level co-occurrence matrix (GLCM). Li et al. [11] proposes a combination of
deep learning methods with stacked generalization ensembles with VGG16 to form a data classification.
The results obtained from this combination are sensitivity 93.57%, specificity 94.21%, precision
89.40%, and F1-Score 91.74%. Hasan et al. [12] proposes a variety of deep learning with feature extraction
from Q-deformed to classify COVID-19 and pneumonia by utilizing the results of a computed tomography
(CT) scan of the lungs. The classification results obtained were 99.68% of the total 321 patients.
Santana et al. [13] proposed classification model is to implement and rely on preprocessed data sets by applying
several models from machine learning. The research results are the methods used to help detect COVID-19 in
Brazil. Pham [14] uses the COVID-19 dataset obtained from a shared database of CT scan results.
Classification of COVID-19 by proposing an investigative method from CNN, previously trained to get good
results. Jaiswal et al. [15] utilizes chest CT scan images to diagnose COVID-19 using deep learning
architecture. Training is carried out before the detection stage, and training is carried out on the deep learning
architecture. Miroshnichenko and Mikhelev [16] uses the CNN method to approach the problem-solving
classification of chest health. The data used in this study used X-ray images of COVID-19 and normal patients
[17]. This study uses CNN to automatically classify the chest of patients with COVID-19 by utilizing the results
of a chest CT scan. Researchers grouped the COVID-19 dataset into three classes. The results of this study can
help the government and hospitals in dealing with the upcoming pandemic. Ibrahim et al. [18] applies a multi-
classification model from deep learning to diagnose COVID-19 sufferers. Of the three proposed models, the
VGG19+ model got better results. VGG19+ achieves an accuracy of 98.05%. Ozyurt et al. [19] proposes deep
learning with a pyramid feature extraction and hybrid feature model for the automatic detection of COVID-19.
The results obtained are by using the hybrid feature to get better results. Elmuogy et al. [20] proposes a worried
deep neural network (WDNN) model from a deep neural network (DNN) for classification by utilizing transfer
learning. The results of the analysis show that WDNN gets better performance results.
Many feature extraction methods are proposed to classify COVID-19 or other diseases, including
using the feature extraction method. Most of these methods are combined with other classification methods to
get different performance results. However, to improve the method's performance, the feature extraction
method needs to be combined with other classification methods to get better performance results. Most previous
studies have never had a combination of feature extraction and artificial neural network implementation in an
application. Therefore, this study proposes a combination method of feature extraction and neural networks in
one application. Many methods are used to obtain good and accurate feature extraction results, one of which is
the GLCM method [21]. The extraction method used in this study is the GLCM. GLCM is a statistical analysis
for feature extraction on an image [22]. Meanwhile, the classification method used is backpropagation neural
network. The reason for choosing the backpropagation neural network classification method is that it can
provide good and accurate classification results [23]. The proposed method is implemented in an application
made using Matlab. In this study, the image of the lungs of patients with COVID-19 was extracted using GLCM
texture analysis. Then the image was converted into grayscale and classified using an artificial neural network.
Before the classification stage, lung images were first trained using 600 images, including 300 normal chest
images and 300 COVID-19 images. The data used as testing data was 20% of the total of each normal chest
data and COVID-19 data. A total of 120 data were used for the testing process, including 60 with a normal
chest and 60 with a COVID-19 chest.
2. METHOD
2.1. Literature study
The literature study stage is carried out by looking for the latest and relevant references from previous
studies related to the topics discussed and related articles such as the classification of COVID-19 in covid 19
patients, the theory of GLCM, artificial neural network theory. Then this literature study will be used as a
reference in improving this research. Literature studies use the latest research taken from quality journals.

Int J Artif Intell ISSN: 2252-8938 
Combination of gray level co-occurrence matrix and artificial neural networks for … (Bahtiar Imran)
1627
2.2. Data collection
This study uses datasets collected on dataset-sharing websites such as Kaggle. The dataset consists of
chest X-ray images in patients with COVID-19, normal, and pneumonia [23], [24]. The total data used in this
study amounted to 600 data, in Table 1 details the amount of data used in this study. After the data collection
stage is carried out, the next step is to apply the GLCM method for lung image extraction. Image extraction is
done to obtain image extraction values so that they are later used for the classification process. Figure 1 is an
example of a chest image with a COVID-19 patient and Figure 2 is an example of a normal chest image.
2.3. GLCM implementation
The implementation of GLCM was carried out to obtain extraction values from chest images of
patients with COVID-19 and normal chests. GLCM is a feature extraction often used to get the texture value
of an image, whose value is stored in a matrix I x j x n, where n is the GLCM number with a different rotation
direction [11], while the features used in this study are contrast, homogeneity, correlation, and energy [25].
Figure 3 is the rotation direction of the GLCM [26].
Correlation: ∑ = 1 ∑ = 1
k
j
k
i
(i−mr) (j−mc) pij
ϑr δc
(1)
Contrast: ∑ = 1 ∑ = 1
k
j
k
i (i − j)2
Pij (2)
Homogeneity: ∑ = 1 ∑ = 1
k
j
k
i Pij
2
(3)
Energy: ∑ = 1 ∑ = 1
Pij
1+[i−j]
k
j
k
i (4)
Table 1. Research data
Data used Image format Amount of data
COVID-19 JPEG 300
Normal JPEG 300
Figure 1. COVID-19 chest Figure 2. Normal chest
Figure 3. The direction of GLCM rotation
2.4. Application of artificial neural networks
The artificial neural network (ANN) classification method was chosen because ANN can think like a
human and process information from an image [27]. This research applies backpropagation neural network
with a multi-layer, two hidden layers, and one output. ANN is used to classify chest images of patients with
COVID-19 and normal chests, previously extracted using GLCM. The number of images used for the training
process is 600, consisting of 300 appearances for the chest of COVID-19 sufferers and 300 ideas for the average
bin. At the same time, the images used for the testing process are 120 images, consisting of 60 shots for the
chest of COVID-19 sufferers and 60 ideas for the average bin.

 ISSN: 2252-8938
1628
3. RESULTS AND DISCUSSION
In implementing the proposed combination method, the software used is MATLAB Version
R2020a [28], and the hardware specifications used are Windows 10 operating system, Intel i7 Gen 11th
Processor, and 8GB RAM. Before the testing phase, we first conduct training using 480 data, including 240
normal chest and 240 COVID-19 data. After data collection was carried out [29], the data was tested using a
combination of the proposed methods. Several tests have been carried out using Epochs 10, 30, 50, 70, 100,
and 120. The application's performance that we created can give good results using Epoch 30 and Epoch 100.
Training process using Epoch 10, learning rate 0.1 and getting an accuracy of 89.37% with 51
incorrect data and 429 correct data out of 480 data. Training process using Epoch 30, learning rate 0.1 and
getting an accuracy result of 92.5% with 36 incorrect data and 444 correct data out of 480 data. And the training
process using Epoch 50 learning rate of 0.1 and getting an accuracy of 93.12% with 33 incorrect data and 447
correct data out of a total of 480 data. Training process using Epoch 70, learning rate 0.1 and getting 93.54%
accuracy results with 31 incorrect data and 449 correct data out of 480 data. Training process using Epoch 100,
learning rate 0.1 and getting an accuracy result of 94.79% with 25 incorrect data and 455 correct data out of
480 data. Training process using Epoch 120, learning rate 0.1 and getting an accuracy result of 95.20% with
23 incorrect data and 457 correct data from 480 data. Table 2 is a detail of the overall results of the training.
In this study, we conducted a test to see how far the performance of the proposed method was. The
progress of the test can be seen in Figure 4, and Table 3 is the result of the overall difficulty. The data used at
the testing stage is 120 data, including 60 data from the normal chest and 60 from COVID-19.
Figure 4 is the result of a classification test carried out with several tests, and the classification stage
is carried out in stages based on the epoch that has been determined. Before the classification, the stage is
carried out. First, the network created during training needs to be loaded to get lessons from the training
process. The overall results of the classification can be seen in Table 3.
Table 2. The overall result of the training process
Epoch Iteration Time elapsed Amount of incorrect data Accuracy
10 10 00.00.00 51 89.37%
30 30 00.00.00 36 92.5%
50 50 00.00.00 33 93.12%
70 70 00.00.00 31 93.54%
100 100 00.00.02 25 94.79%
120 120 00.00.01 23 95.20%
Figure 4. Classification of COVID-19
Table 3 shows the overall classification results, whereby using epoch 50 and epoch 100 with a learning
rate of 0.1, the highest accuracy results from the other epochs are 92%. In this study, we tried to test by
increasing the number of epochs and learning rate, but the accuracy results obtained were lower. This study
uses epochs 10, 30, 50, 70, 100, and 120 and a learning rate of 0.1 in the training process because the epochs
experienced a significant increase. We have tried to increase epochs and use various epochs, but the results
obtained have decreased, and there are similarities in results, so it is concluded that the epochs used are 10, 30,
50, 70, 100, and 120 a learning rate of 0.1. Furthermore, comparing the results of the method used with relevant
research using the GLCM method and different classification models by utilizing X-ray image data on normal
lungs and COVID-19 lungs. The performance metrics used are the accuracy results obtained. The results
comparison can be seen in Table 4. In this research, we propose a classification system to classify COVID-19

1629
chest and normal chest, using a combination of GLCM feature extraction and backpropagation neural network.
A total of 300 data for COVID-19 chest and 300 data for Normal chest, based on the classification results,
show the system can classify COVID-19 chest and normal chest using Epoch 50 and 100 and learning rate 0.1
and achieve 92% accuracy.
Table 3. Overall results of the testing process
Epoch Classification result accuracy
10 91%
30 91%
50 92%
70 91%
100 92%
120 90%
Table 4. Comparison of the proposed COVID-19 classification model with the COVID-19 classification
with different methods
Method Number of X-ray datasets Classifiers Accuracy
GLCM [30] COVID-19 (127)
Normal (127)
Pneumonia (127)
Support vector machine 93.2%
GLCM [31] COVID-19 (180)
Non-COVID-19 (180)
Logistic 98.61%
GLCM [31] COVID-19 (180)
Non-COVID-19 (180)
Ensemble of logistic, simple
logistic, and randomforest
99.17%
GLCM [32] Test (+)
COVID-19 (453)
Non-COVID-19 (23)
Test (-)
COVID-19 (37)
Non-COVID-19 (467)
Latent-dynamic conditional
random fields (LDCRFs)
95.88%
GLCM [33] COVID-19 (1252)
No COVID-19 (1230)
Deep learning neural network 98%
Our method COVID-19 (300)
Normal (300)
Neural network backropagation Epoch 10: 91%, 30: 91%, 50: 92%, 70:
91%, 100: 92%, and 120: 90%
4. CONCLUSION
Based on the results of the tests that have been carried out, the proposed system can get good accuracy
results. The proposed method can give different results, including tests carried out using Epoch 10 and learning
rate 0.1 getting 91% accuracy results, testing with Epoch 30 and learning rate 0.1 getting 91% results, testing
with Epoch 50 and learning rate 0.1 getting 92% results, testing with Epoch 70 and learning rate 0.1 getting
91% results, testing with Epoch 100 and learning rate 0.1 getting 92% results while for testing with Epoch 120
and learning rate 0.1 getting 90% results. From various tests carried out, Epochs 50 and 100 with a learning
rate of 0.1 get better accuracy results than the other epochs, with an accuracy of 92%. In this study, the larger
the epoch used, the lower the accuracy. Therefore, it is necessary to improve the architecture of the proposed
model so that it can achieve maximum accuracy results.
REFERENCES
[1] Alamsyah, B. Prasetiyo, M. F. Al Hakim, and F. D. Pradana, “Prediction of COVID-19 using recurrent neural network model,” Sci.
J. Informatics, vol. 8, no. 1, pp. 98–103, 2021, doi: 10.15294/sji.v8i1.30070.
[2] M. Shorfuzzaman, M. Masud, H. Alhumyani, D. Anand, and A. Singh, “Artificial neural network-based deep learning model for
COVID-19 patient detection using X-Ray chest images,” J. Healthc. Eng., vol. 2021, 2021, doi: 10.1155/2021/5513679.
[3] A. B. Godbin and S. G. Jasmine, “Screening of COVID-19 based on GLCM features from CT images using machine learning
classifiers,” SN Comput. Sci., vol. 4, no. 2, pp. 1–11, 2023, doi: 10.1007/s42979-022-01583-2.
[4] M. Aminu, N. A. Ahmad, and M. H. Mohd Noor, “Covid-19 detection via deep neural network and occlusion sensitivity maps,”
Alexandria Eng. J., vol. 60, no. 5, pp. 4829–4855, 2021, doi: 10.1016/j.aej.2021.03.052.
[5] B. Udugama et al., “Diagnosing COVID-19: The disease and tools for detection,” ACS Nano, vol. 14, no. 4, pp. 3822–3835, 2020,
doi: 10.1021/acsnano.0c02624.
[6] M. Khan et al., “Applications of artificial intelligence in COVID-19 pandemic: A comprehensive review,” Expert Syst. Appl.,
vol. 185, no. August, p. 115695, 2021, doi: 10.1016/j.eswa.2021.115695.
[7] S. H. Wang, M. A. Khan, V. Govindaraj, S. L. Fernandes, Z. Zhu, and Y. D. Zhang, “Deep rank-based average pooling network for
Covid-19 recognition,” Comput. Mater. Contin., vol. 70, no. 2, pp. 2797–2813, 2022, doi: 10.32604/cmc.2022.020140.
[8] Y.-D. Zhang, M. Attique Khan, Z. Zhu, and S.-H. Wang, “Pseudo Zernike moment and deep stacked sparse autoencoder for COVID-
19 diagnosis,” Comput. Mater. Contin., vol. 69, no. 3, pp. 3145–3162, 2021, doi: 10.32604/cmc.2021.018040.

 ISSN: 2252-8938
1630
[9] F.-Y. Lan et al., “COVID-19 symptoms predictive of healthcare workers’ SARS-CoV-2 PCR results,” PLoS One, vol. 15, no. 6,
p. e0235460, Jun. 2020, doi: 10.1371/journal.pone.0235460.
[10] V. U. M. Maksum, D. C. R. Novitasari, and A. Hamid, “Image X-Ray classification for COVID-19 detection using GCLM-ELM,”
J. Mat. MANTIK, vol. 7, no. 1, pp. 74–85, 2021, doi: 10.15642/mantik.2021.7.1.74-85.
[11] X. Li, W. Tan, P. Liu, Q. Zhou, and J. Yang, “Classification of COVID-19 chest CT images based on ensemble deep learning,” J.
Healthc. Eng., vol. 2021, 2021, doi: 10.1155/2021/5528441.
[12] A. M. Hasan, M. M. AL-Jawad, H. A. Jalab, H. Shaiba, R. W. Ibrahim, and A. R. AL-Shamasneh, “Classification of Covid-19
Coronavirus, Pneumonia and Healthy Lungs in CT scans using Q-Deformed entropy and deep learning features,” Entropy, vol. 22,
2020.
[13] Í. V. Dos Santos Santana et al., “Classification models for COVID-19 test prioritization in Brazil: Machine learning approach,” J.
Med. Internet Res., vol. 23, no. 4, 2021, doi: 10.2196/27293.
[14] T. D. Pham, “A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural
networks,” Sci. Rep., vol. 10, no. 1, pp. 1–8, 2020, doi: 10.1038/s41598-020-74164-z.
[15] A. Jaiswal, N. Gianchandani, D. Singh, V. Kumar, and M. Kaur, “Classification of the COVID-19 infected patients using
DenseNet201 based deep transfer learning,” J. Biomol. Struct. Dyn., vol. 39, no. 15, pp. 5682–5689, 2021, doi:
10.1080/07391102.2020.1788642.
[16] A. S. Miroshnichenko and V. M. Mikhelev, “Classification of medical images of patients with Covid-19 using transfer learning
technology of convolutional neural network,” J. Phys. Conf. Ser., vol. 1801, no. 1, 2021, doi: 10.1088/1742-6596/1801/1/012010.
[17] S. Bhatti, D. N. Aziz, I. Usmani, Aamir, and D. Khan, “Automatic classification of the severity of COVID-19 patients based on CT
scans and X-rays using deep learning,” Eur. J. Mol. Clin., pp. 1436–1455, 2021.
[18] D. M. Ibrahim, N. M. Elshennawy, and A. M. Sarhan, “Deep-chest: Multi-classification deep learning model for diagnosing
COVID-19, Pneumonia, and lung cancer chest diseases,” Comput. Biol. Med., vol. 132, p. 104348, 2021, doi:
10.1016/j.compbiomed.2021.104348.
[19] F. Ozyurt, T. Tuncer, and A. Subasi, “An automated COVID-19 detection based on fused dynamic exemplar pyramid feature
extraction and hybrid feature selection using deep learning,” Comput. Biol. Med., vol. 132, no. October 2020, p. 104356, 2021, doi:
10.1016/j.compbiomed.2021.104356.
[20] S. Elmuogy, N. A. Hikal, and E. Hassan, “An efficient technique for CT scan images classification of COVID-19,” J. Intell. Fuzzy
Syst., vol. 40, no. 3, pp. 5225–5238, 2021, doi: 10.3233/JIFS-201985.
[21] B. Pathak and D. Barooah, “Texture analysis based on the gray-level co-occurrence matrix considering possible orientations,” Int.
J. Adv. Res. Electr. Electron. Instrum. Eng., vol. 2, no. 9, pp. 4206–4212, 2013, [Online]. Available:
http://www.ijareeie.com/upload/2013/september/7_-TEXTURE.pdf
[22] P. Mohanaiah, P. Sathyanarayana, and L. Gurukumar, “Image texture feature extraction using GLCM approach,” Int. J. Sci. Res.
Publ., vol. 3, no. 5, pp. 1–5, 2013.
[23] I. De Falco, G. De Pietro, and G. Sannino, “Classification of Covid-19 chest X-ray images by means of an interpretable evolutionary
rule-based approach,” Neural Comput. Appl., vol. 0123456789, 2022, doi: 10.1007/s00521-021-06806-w.
[24] M. E. H. Chowdhury et al., “Can AI help in screening viral and COVID-19 Pneumonia?,” IEEE Access, vol. 8, no. February 2021,
pp. 132665–132676, 2020, doi: 10.1109/ACCESS.2020.3010287.
[25] T. Rahman et al., “Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images,”
Comput. Biol. Med., vol. 132, no. November 2020, p. 104319, 2021, doi: 10.1016/j.compbiomed.2021.104319.
[26] B. Imran and M. M. Efendi, “The implementation of extraction feature using GLCM and back-propagation artificial neural network
to clasify Lombok songket woven cloth,” J. Techno Nusa Mandiri, vol. 17, no. 2, pp. 131–136, 2020.
[27] K. Nugroho, “World Covid-19 vaccine names classification using neural network method,” J. Bus. Technol., vol. 1, no. 1, p. 31,
2021, doi: 10.24167/jbt.v1i1.3219.
[28] A. Fadhil, Y. Althabhawee, B. Kadhim, and O. Chabor, “Fingerprint recognition based on collected images using deep learning
technology,” IAES Int. J. Artif. Intell., vol. 11, no. 1, pp. 81–88, 2022, doi: 10.11591/ijai.v11.i1.pp81-88.
[29] N. Azieta, M. Aseri, M. A. Ismail, A. S. Fakharudin, and A. Osman, “Comparison of meta-heuristic algorithms for fuzzy modelling
of COVID- 19 illness’ severity classification,” IAES Int. J. Artif. Intell., vol. 11, no. 1, pp. 50–64, 2022, doi:
10.11591/ijai.v11.i1.pp50-64.
[30] P. K. Sethy, S. K. Behera, P. K. Ratha, and P. Biswas, “Detection of coronavirus disease (COVID-19) based on deep features and
support vector machine,” Int. J. Math. Eng. Manag. Sci., vol. 5, no. 4, pp. 643–651, 2020, doi: 10.33889/IJMEMS.2020.5.4.052.
[31] S. D. Thepade and H. Jha, “Covid-19 identification using machine learning classifiers with glcm features of chest x-ray images,”
Trends Sci., vol. 18, no. 23, 2021, doi: 10.48048/tis.2021.46.
[32] S. Bakheet and A. Al-Hamadi, “Automatic detection of COVID-19 using pruned GLCM-Based texture features and LDCRF
classification,” Comput. Biol. Med., vol. 137, no. June, p. 104781, 2021, doi: 10.1016/j.compbiomed.2021.104781.
[33] E. A. Abbood and T. A. Al-Assadi, “GLCMs based multi-inputs 1D CNN deep learning neural network for COVID-19 texture
feature extraction and classification,” Karbala Int. J. Mod. Sci., vol. 8, no. 1, pp. 28–39, 2022, doi: 10.33640/2405-609X.3201.
BIOGRAPHIES OF AUTHORS
Bahtiar Imran is a lecturer in the Information and Communication Technology
Faculty Study Program at the Mataram University of Technology. He is currently active as a
lecturer researcher. He is also active as a reviewer for national and international journals. His
areas of interest are texture analysis, feature extraction, neural networks, information
systems, machine learning, and big data. He can be contacted at email:
bahtiarimranlombok@gmail.com.

1631
Lalu Delsi Samsumar currently works at Mataram University of Technology
as a permanent lecturer at the Faculty of Information and Communication Technology,
Informatics Engineering Study Program, Undergraduate Program. Currently, his research
interests are artificial intelligence, machine learning, and information systems. Besides being
a lecturer, I am also a consultant in the field of information technology. He can be contacted
at email: lalu.ellsyam@gmail.com.
Ahmad Subki is a lecturer in the Information and Communication Technology
Faculty and Software Engineer Study Program at the Mataram University of Technology. He
is currently active as a lecturer. His areas of interest are information systems, digital forensics,
mobile development, data science, and cloud engineering. He can be contacted at email:
ahmad.subki1992@gmail.com.
Zaeniah is a lecturer in the Information and Communication Technology Faculty
and information system Study Program at the Mataram University of Technology. She is
currently active as a lecturer researcher. Her areas of interest are information systems, data
scient, machine learning, image processing, deep learning, and artificial neural networks. She
can be contacted at email: zaen1989@gmail.com.
Salman is a lecturer in the Information and Communication Technology Faculty
and Software Engineer Study Program at the Mataram University of Technology. He is
currently active as a lecturer. His areas of interest are information systems, digital forensics,
mobile development, data science, and cloud engineering, big data, decision making systems,
databases, information systems, and e-learning. He can be contacted at email:
asal.lombok@gmail.com.
Muhammad Rizal Alfian is a lecturer in the Department of Mathematics at the
Faculty of Mathematics and Natural Sciences, University of Mataram. He is currently, the
author is actively engaged as a research lecturer in the field of modeling, simulation, and
optimization. The current research topics are related to simulations involving artificial neural
networks, discrete systems, dynamic systems, and optimization. He can be contacted at email:
rijal_alfian@unram.ac.id.

Combination of gray level co-occurrence matrix and artificial neural networks for classification of COVID-19 based on chest X-ray images

More Related Content

Similar to Combination of gray level co-occurrence matrix and artificial neural networks for classification of COVID-19 based on chest X-ray images (20)

More from IAESIJAI (20)

Recently uploaded (20)

Combination of gray level co-occurrence matrix and artificial neural networks for classification of COVID-19 based on chest X-ray images