Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219

Diagnostic Algorithm for Early Detection of Breast

Cancer Based on Error Minimization Approach
Nishanov Akhram Khasanovich 1; Mamazhanov Rakhmatilla Yakubzhanovich 2;
Khaidarov Sherali Islom o’g’li3; Xolbekov Abdusattor Maxammatovich 4; Karimova Zilola Botirovna5
2
ORCID: 0000-0002-8188-6389; 3ORCID: 0000-0002-2514-3329;
4
ORCID: 0009-0005-4424-1089; 5ORCID: 0009-0007-4268-5406
1
Muhammad al-Xoraxmiy Tashkent University of Information Technologies, Tashkent, Republic of Uzbekistan
2
Denau Institute of Entrepreneurship and Pedagogy, Denau, Republic of Uzbekistan,
3
Denau Institute of Entrepreneurship and Pedagogy, Denau, Republic of Uzbekistan,
4
Denau Institute of Entrepreneurship and Pedagogy, Denau, Republic of Uzbekistan,
5
Denau Institute of Entrepreneurship and Pedagogy, Denau, Republic of Uzbekistan,

Abstract:- The relevance of the study lies in the fact that This article examines the importance of artificial
breast cancer is one of the most common oncological intelligence and deep learning algorithms in the early
diseases among women, millions of women are diagnosed detection of breast cancer, how they work, and how to
with it every year. Early detection is important in this minimize errors while using the software. The goal is to
disease, because if the disease is detected at an early stage, combine traditional methods with artificial intelligence to
the chances of treatment are much higher. The study increase the accuracy of diagnosis and provide more effective
examines the use of artificial intelligence algorithms, in care to patients[3-4].
particular, ways to automate the process and improve
accuracy based on interviewing users using a program  Data Collection –
created in Python. The practical significance of this Improving detection of breast cancer and collecting data
scientific work lies in the fact that it proposes algorithmic through the census is essential. The data collection process is
approaches aimed at improving the early detection of important for improving breast cancer detection and
breast cancer and improving the quality of life of patients automating the diagnostic process. Once medical images,
by reducing errors. This scientific work is devoted to the demographics, medical history, and lifestyle data are
development of diagnostic algorithms based on collected, their proper storage and analysis can increase the
minimizing errors in early detection of breast cancer. The chances of early disease detection[5-6]. This plays an
importance of diagnosis for early detection of breast important role in improving the quality of life of patients.
cancer is considered and special attention is paid to the
development of diagnostic software. This software  Creating an Algorithm –
package collects information about breast cancer and Based on the latest scientific achievements and clinical
creates an algorithm that supports its diagnosis and practices, the process of creating an algorithm for early
treatment. detection of breast cancer includes the following main steps.
Below are general steps and recommendations for creating an
Keywords:- Breast Cancer, Diagnosis, Algorithm, Software, algorithm.
Data Collection, Parameters, Classes, Objects.
 Software Development –
I. INTRODUCTION According to the parameters defined in the algorithm,
the software is developed. This application can act as a
Breast cancer (mammacarcinoma) is one of the most platform and application that can accept clinical contracts and
common oncological diseases among women and has a medical presentations.
negative impact on the lives of millions of people around the
world. According to the World Health Organization, the  The Object of the Study –
incidence of breast cancer is increasing every year, which Breast cancerdisease preventionearly diagnosis of
makes early detection of the disease even more important[1- objects, determining the importance of objects and signs,
2]. Cases of breast cancer detected early are often able to be information measurement criteria and algorithms, approaches
successfully treated, but detection of the disease in late stages based on the selection of sets of signs were obtained.
significantly increases the risk of death.

IJISRT24DEC1276 www.ijisrt.com 1535

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219

Fig 1 Data collection

 Subject of Research - algorithm for determining the information dimension of

Breast cancerdisease preventionconsists of information the importance of objects has been developed;
measurement criteria and algorithms of the importance of
objects in the early diagnosis of diseases. Practical results of the researchconsists of the following.

 Research Methods Breast cancer preventionA software complex has been

In the research process, the methods of information developed that helps to automate medical diagnosis processes
knowledge, intellectual analysis, and the theory of symbol and make a final diagnosis based on information
recognition were used. measurement criteria and algorithms for assessing patients'
disease levels.[9-10].
 Scientific Novelty of the Research –
Consists of:breast cancer preventionheuristic criteria Problems related to early diagnosis were solved as a
and algorithms for determining the importance of objects and result of applying the software complex to solving practical
symbols in the early diagnosis of patients' diseases were problems of the medical field.
analyzed[7-8].
 Scientific and Practical Significance of Research Results.
 The research will develop an algorithm with real-time Scientific significance of research resultsbreast cancer
analysis capabilities, which will allow rapid diagnosis of preventionis a complex research that intersects with different
patients in clinical practice and timely initiation of fields such as signal processing, data science, and artificial
treatment. intelligence. Scientific significance of such studiesbreast
 In the field of combination of methods and algorithms of cancer preventionis to develop and develop algorithms that
intelligent data analysisbreast cancer preventionan can efficiently and perfectly determine the initial indicators
of[11-12].

Table 1 Breast Cancersymptoms

No Breast cancersymptoms (naming characters) Possible values of characters
1. No
Do you have general weakness?
1 2. Light (medium)
3. Strong
1. No disease
2. From 3 to 6 months
2 How long have you been diagnosed with the disease?
3. From 6 months to 1 year
4. From 1 to 3 years
1. No
3 Have you had any diseases in your family (mother-sisters, aunts)?
2. Yes
1. No pain
4 Do you have pain in the lower part of the shoulder? 2. The pain is moderate
3. The pain is intense
1. The same
5 What is your breast size? 2. One is bigger than the other
3. Both are enlarged
1. No
6 Do you have bad habits (Smoking, drinking alcohol, etc.)?
2. Yes

IJISRT24DEC1276 www.ijisrt.com 1536

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219
1. No
7 Do you use household services (manicure, pedicure, piercing, tattoo, etc.)? 2. Rarely
3. Too many
1. No
8 Do you have pain in your breast? 2. Medium
3. Nomadic
1. No
9 Do you have itchy breasts?
2. There is
1. normal (good)
2. Serveset
3. Endocerbicitis
10 Do you have chronic gynecological diseases?
4. Uterine frostbite
5. Ovarian cyst
6. Irregular passage of Hayes
1. No
2. Failure to develop the fetus
11 Have you ever had a series of induced abortions in your lifetime? 3. Forced abortion
4. Miscarriage
5. Causes of TORCH-infections
1. No
12 Have you ever had a breast-related injury in your life?
2. Yes
1. No change
2. Sucker pulled in
13 Are there any changes in your nipples or teats? 3. The teat is not pulled in
4. Wounded change
5. The nipple is cut
1. No
14 Do you notice a lump in your breast?
2. Yes
1. No
15 Does the mammary gland move when you hold it?
2. Yes
1. No
16 Are the boundaries of the tumor in the mammary gland clear?
2. Yes
1. Tumor burden
17 What is the condition of the tumor in the mammary gland 2. The tumor is soft
3. The tumor is solid
To save you regularly contraception or whether you take therapeutic 1. No
18
hormone drugs 2. Yes

II. METHODOLOGY
 Block Diagram of the Formula
 Creating an algorithm 1st block scheme (determining the similarity
coefficients of objects) 𝑚𝑝 = 42 object number,𝑞 = 1 initial
 Formula 1. 𝑥𝑝 the coefficient of similarity of objects is value 𝜔1 𝑢𝑠𝑡𝑢𝑛 For 1st grade
1 𝑚𝑝
∑𝑞=1 (𝑥𝑝, ) =
𝑚𝑝
determined. 1
∑42 [𝑥 + 𝑥2 + ⋯ + 𝑥42 ] So, the following class
𝑚𝑝 42 𝑞=1 1
1 columns are similar𝜔1 , , 𝜔2 , . . , 𝜔18 considered
𝑿𝒑 = ∑ 𝑥𝑝 (1) objects 𝑋1 classare the most common character classes for
𝑚𝑝
𝑞=1 objects. 𝑚𝑝 = 52 object number,𝑞 = 1 initial value
1 𝑚𝑝 1 52
∑ ∑
𝜔1 𝑢𝑠𝑡𝑢𝑛 For 2nd grade 𝑚 𝑞=1(𝑥𝑝, ) = 3 𝑞=1[𝑥1 + 𝑥2 +
𝑝
⋯ + 𝑥52 ]

So the following class columns are

similar𝜔1 , , 𝜔2 , . . , 𝜔18 considered objects 𝑋2classare the most
common character classes for objects. 𝑚𝑝 = 20 object
number,𝑞 = 1 initial value 𝜔1 𝑢𝑠𝑡𝑢𝑛 2 for 3rd
1 𝑚𝑝 1
grade.𝑚 ∑𝑞=1(𝑥𝑝, ) = 3 ∑20 [𝑥
𝑞=1 1 + 𝑥 2 + ⋯ + 𝑥20 ] So
𝑝
𝜔1 = (2 3 2 3 3 2 2 2 1 2 3 2 1 2 2 2 1 2 2) 𝜔1 , , 𝜔2 , . . , 𝜔18

IJISRT24DEC1276 www.ijisrt.com 1537

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219
Similar in the following class columnsconsidered By calculating in the following sequence, we obtain the
objects 𝑋3 classare the most common character classes for following table The following table shows the set of objects
objects. that occur most frequently in the ωu columns of the breast
cancer data objects.

III. RESULTS AND DISCUSSION

Table 2 Set of Most Common Objects

Do you use household services (manicure, pedicure,

Do you have pain in the lower part of the shoulder?
Have you had any diseases in your family (mother-

Have you ever had a series of induced abortions in

Does the mammary gland move when you hold it?

Have you ever had a breast-related injury in your

Are the boundaries of the tumor in the mammary

Do you have chronic gynecological diseases?

Do you regularly take konroceptm hormone

How long have you been diagnosed with the

Do you have bad habits (Smoking, drinking

What is the condition of the tumor in the

Are there any changes in your nipples?

Do you notice a lump in your breast?

Do you have pain in your breast?
Do you have general weakness?

preparations for maintenance?

Do you have itchy breasts?
What is your breast size?

piercing, tattoo, etc.)?

mammary gland
sisters, aunts)?

your lifetime?
alcohol, etc.)?

gland clear?
disease?

life?

X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18

Class 1 (object)
2 3 1 2 2 1 1 2 1 1 1 2 3 1 1 2 3 1
2nd class (object)
2 4 1 1 1 1 1 1 1 1 1 1 1 2 2 2 3 1
3rd class (object)
2 4 1 2 2 1 1 2 1 1 1 1 2 2 2 2 3 1
4th grade (object)
3 3 1 3 2 1 1 3 1 1 1 2 3 2 1 2 3 1
5th grade (object)
2 2 1 2 1 1 1 2 1 1 1 1 2 2 1 2 3 1
6th grade (object)
3 3 1 3 2 1 1 3 1 3 1 2 3 1 1 2 3 1
7th grade (object)
3 3 1 1 1 1 1 1 1 1 1 1 1 2 1 1 3 1
8th grade (object)
3 4 1 3 1 1 1 3 1 1 1 1 1 2 1 1 3 1
9th grade (object)
3 4 1 3 1 1 1 3 1 1 2 1 2 2 2 2 3 1
10th grade (object)
2 3 1 1 2 1 1 1 1 3 1 1 2 2 1 1 3 1
11th grade (object)
2 4 1 2 1 1 1 2 1 1 1 1 1 2 2 2 2 1
12th grade (object)
2 4 1 2 1 1 1 2 1 1 1 1 1 2 1 1 3 1

IJISRT24DEC1276 www.ijisrt.com 1538

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219
 Formula 2. Evaluates the Equality of the Corresponding Components of the Object in Two.

𝑗 𝑗
1 if 𝑥𝑖 = 𝑥𝑘 , 𝑗 = 1, 𝑁.
(𝑥𝑖 , 𝑥𝑘 ) = { (2)
0 else .

For example, let's compare the newly added objects to class 1

1.Newly entered = (2 3 2 3 3 2 2 2 1 2 3 1 1 3 3 2 1 2 1)𝑥1 , 𝑥2 , 𝑥3 , 𝑥4 , 𝑥5 , 𝑥6 , 𝑥7 , 𝑥8 , 𝑥9 , 𝑥10 , 𝑥11 , 𝑥12 , 𝑥13 , 𝑥14 𝑥15 , 𝑥16 , 𝑥17 , 𝑥18

2. most common objects = (2 3 3 3 3 2 1 2 1 2 3 3 1 3 3 3 1 2

1)𝜔1 , 𝜔2 , 𝜔3 , 𝜔4 , 𝜔5 , 𝜔6 , 𝜔7 , 𝜔8 , 𝜔9 , 𝜔10 , 𝜔11 , 𝜔12 , 𝜔13 , 𝜔14 𝜔15 , 𝜔16 , 𝜔17 , 𝜔18 , 𝜔19

𝑥1 = 𝜔1 , 𝑥2 = 𝜔2 , 𝑥3 = 𝜔3 , 𝑥4 = 𝜔4 , 𝑥5 = 𝜔5 , 𝑥6 = 𝜔6 , 𝑥7 = 𝜔7 , 𝑥8 = 𝜔8

𝑥9 = 𝜔9 , 𝑥10 = 𝜔10 , 𝑥11 = 𝜔11 , 𝑥12 = 𝜔12 , 𝑥13 = 𝜔13 , 𝑥14 = 𝜔14 , 𝑥15 = 𝜔15 , 𝑥16 = 𝜔16 , 𝑥17 = 𝜔17 , 𝑥18 = 𝜔18

𝑋𝑢 = {1 1 0 1 1 1 0 1 1 1 1 0 1 1 1 0 1 1 1 }

Here it is if the corresponding components of the object in I kki are equal to each other. So the difference between the
two(𝑥𝑖 , 𝑥𝑘 ) = 1𝑥𝑖 = 𝑥𝑘 𝜇checks a single component,𝜘and size means the number of identical components of objects𝑥𝑖 , 𝑥𝑘 [13-14].

 Formula 3. The optimization problem for identifying an informative character set is as follows:
𝑚𝑝 𝑚𝑝
𝜘(𝑥𝑝 , 𝑥𝑘 ) ∗ 100%
(𝑥𝑝 , 𝑥𝑘 ) = maxℓ ∑ ∑
𝜆∈Λ 𝑁
𝑖≠𝑘=1 𝑘=𝑖+1
𝑁 (3)
𝜆 ∈ Λ = { 𝜆: ∑ 𝜆 = ℓ , 𝜆 ∈ {0,1}, 𝑗 = ̅̅̅̅̅
ℓ 𝑗 𝑗
1, 𝑁} .
{ 𝑗=1

∑ 𝜆𝑗 = ℓ1 + ℓ2, … , ℓ𝑛 = 1 + 1 + 0 + 1 + 1 + 1 + 0 + 1 + 1 + 1 + 1 + 0 + 1 + 1 + 1 + 0 + 1 + 1 + 1 = 15
𝑗=1

Newly introduced objects are compared and aggregated.

𝜘 ∗ 100%
𝑣(𝑥𝑖 , 𝑥𝑘 ) =
𝑁
𝜘 ∗ 100% 15 ∗ 100
(𝑥𝑖 , 𝑥𝑘 ) = = = 78.9%
𝑁 19

The number of parameters is N = 18 through the formula 3 below

Xp = {1 1 0 1 1 1 0 1 1 1 1 0 1 1 1 0 1 1 1 } we perform the following calculations

𝑋𝑝 = {1 1 0 1 1 1 0 1 1 1 1 0 1 1 1 0 1 1 1 }= 1 +1 + 0 + 1 +1 +1 +0 +1+ 1 +1 +1 +0 +1 +1 + 1+ 0+ 1+ 1+ 1 = 15

For example, newly introduced to the 1st gradeFinding the object's percentage of closeness to cash is calculated as follows
𝑚𝑝 𝑚𝑝
𝑋𝑝 ∗ 100% 15 ∗ 100%
𝑿𝒑 = maxℓ ∑ ∑ = = 79 %
𝜆∈Λ 𝑁 18
𝑖≠𝑘=1 𝑘=𝑖+1

𝑋𝑝 our object is 79% percentage, we will make a diagram of the remaining classes using the following formula.

IJISRT24DEC1276 www.ijisrt.com 1539

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219

Fig 2 Interest Shares on Classes

𝑚𝑝
Formula 5. Formula 4 above from these designations
𝑗 𝑗 ̅̅̅̅̅̅̅
𝑎𝑝 = ∑ 𝜌𝑝 (𝑥𝑝, 𝑥𝑞 ), i = 1, mp , 𝑗 = ̅̅̅̅̅̅
1, 𝑁. (4) ieIn recognition of symbols with nominal information 3 - in a
𝑞=1 way that uses a functionalthe issue of choosing informative
signs,𝑋𝑝 in the section of class objectsto solve the following
If we expand this expression, it forms a matrix.(𝑚𝑝 × optimization problem.
𝑁)
𝑚𝑝
In the first row of the matrix there is an estimate of the 1
degree of similarity in the cross-section of the parameters of ∑(𝑎𝑝𝑖 , 𝜆) → 𝑚𝑎𝑥
𝑚𝑝
the objects of the object class, and in the second row there is 𝑖=1
an estimate of the degrees of similarity in the cross-section of 𝑁 (5)
the parameters of the class objects of the second object, and 𝜆 ∈ Λ = { 𝜆: ∑ 𝜆 = ℓ , 𝜆 ∈ {0,1}, 𝑗 = ̅̅̅̅̅
ℓ 𝑗 𝑗
1, 𝑁}
the similarity in the cross-section of the parameters of the { 𝑗=1
class objects of the object The price is located in the cross-
section of levels𝑥𝑝1 𝑋𝑝 𝑥𝑝2 𝑋𝑝 𝑚𝑝 𝑥𝑝𝑚𝑝 𝑋𝑝 [15-16]. By the formula belowobjectsthe largest class in is found
and the newly introduced class belongs to the found class.

Fig 3 (Program Interface)

IJISRT24DEC1276 www.ijisrt.com 1540

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219
IV. CONCLUSIONS [8]. S. Bauer et al. Segmentation of Brain Tumor Images
Based on Integrated Hierarchical Classification and
In conclusion, we can say that based on the above Regularization. IEEE Transactions on Medical
algorithms, the result of the program outputs the class to Imaging, vol. 27, no. 5, 2008.
which the newly entered object belongs, and the software [9]. D. Zikic et al. Decision Forests for Tissue-Specific
displays the result on the screen to determine which class it Segmentation of High-Grade Gliomas in Multi-
belongs to or not to diabetes through the extracted Channel MR. Proceedings of the International
information. shows. Conference on Medical Image Computing and
Computer-Assisted Intervention, 2012.
Early detection of breast cancer significantly increases [10]. E. Panagiotaki et al. Noninvasive Quantification of
the chances of patients recovering. In this process, the Solid Tumor Microstructure using VERDICT MRI.
accuracy of diagnostic algorithms and minimizing errors are Cancer Research, vol. 74, no. 7, 2014.
of great importance. In this study, a new algorithm based on [11]. M. J. Clark et al. The Cancer Imaging Archive
minimizing errors in early detection of breast cancer was (TCIA): Maintaining and Operating a Public
developed and its effectiveness was analyzed. Information Repository. Journal of Digital Imaging,
The algorithm was created by pre-processing data, vol. 26, no. 6, 2013.
selecting important features, training data, and model [12]. S. Bakas et al. Advancing The Cancer Genome Atlas
validation. In particular, several functions were optimized to glioma MRI collections with expert segmentation
minimize errors. The results show that an algorithm based on labels and radiomic features. Scientific Data, vol. 4,
minimizing errors can be effective in early detection of breast 2017.
cancer. This approach can be used as an additional support [13]. Chaddad et al. N4ITK: Improved N3 Bias Correction.
tool for doctors and diagnostic centers. The practical IEEE Transactions on Medical Imaging, vol. 34, no.
application of this algorithm will contribute to the automation 11, 2015.
of the early diagnosis process, cancer prevention, and [14]. R. McKinney et al. Preprocessing Strategies to
improvement of the quality of life of patients. Improve MRS Analysis in Brain Tumors. Magnetic
Resonance Imaging, vol. 27, no. 10, 2009.
In the future, it is necessary to improve this algorithm [15]. D. Lao et al. A Review of Automatic Whole Brain
by involving more databases, using deep learning models, MRI Segmentation Techniques. Journal of
and taking into account the feedback of doctors. Thus, this Neuroimaging, vol. 21, no. 4, 2011.
research has great potential for digitizing and automating [16]. L. Yu et al. Feature Selection and Analysis on
diagnostic processes in the medical field. Correlated Brain Imaging Data. IEEE Transactions on
Biomedical Engineering, vol. 61, no. 2, 2014.
REFERENCES [17]. H. J. Park et al. Feature Extraction and Classification
for Early Diagnosis of Alzheimer's Disease using
[1]. R. Narayanan et al. Feature Selection for Early Resting-State fMRI. Proceedings of the International
Detection of Brain Cancer International. Journal of Conference on Hybrid Artificial Intelligence Systems,
Computer Applications, vol. 70, no. 5, 2013. 2013.
[2]. S. S. Ranjan et al. A Comparative Study of Feature [18]. S. E. Yoon et al. Texture-Based Radiomics Model to
Selection Algorithms for Brain Cancer Classification Predict Early Recurrence in Glioblastoma. Clinical
International Journal of Computer Science and Cancer Research, vol. 23, no. 12, 2017.
Network Security, vol. 13, no. 6, 2013. [19]. L. Chen et al. Multi-Scale Convolutional Neural
[3]. F. Galloway et al. Feature Selection Methods for Early Networks for Lung Nodule Classification.
Prediction of Brain Cancer from Multi-Modal MRI Proceedings of the IEEE Conference on Computer
Proceedings of the IEEE International Conference on Vision and Pattern Recognition, 2017.
Machine Learning and Applications, 2016. [20]. J. van Griethuysen et al. Computational Radiomics
[4]. Dash et al. Feature Selection Methods for Brain System to Decode the Radiographic Phenotype.
Tumor Classification using MRI: A Comprehensive Cancer Research, vol. 77, no. 21, 2017.
Review. Artificial Intelligence Review, vol. 51, no. 2, [21]. Nishanov, A.H., Akbaraliev, B.B., Tajibaev, S.K.
2019. About One Feature Selection Algorithm in Pattern
[5]. K. Zhang et al. Feature Selection in Brain Cancer Recognition. Advances in Intelligent Systems and
Classification using MR Images. Proceedings of the Computing, 2021, 1323 AISC, p.103–112.
IEEE International Conference on Systems, Man, and [22]. Atoev, S., Nishanov, A., Abdirazakov, F. Object
Cybernetics, 2018. Tracking Method Based on Kalman Filter and
[6]. D. Menze et al. The Multimodal Brain Tumor Image Camshift Algorithm for UAV Applications.
Segmentation Benchmark (BRATS). IEEE International Conference on Information Science and
Transactions on Medical Imaging, vol. 34, no. 10, Communications Technologies: Applications, Trends
2015. and Opportunities, ICISCT 2021, 2021.
[7]. Korfiatis et al. MRI Texture Features as Biomarkers
to Predict MGMT Methylation Status in
Glioblastomas. Medical Physics, vol. 43, no. 6, 2016.

IJISRT24DEC1276 www.ijisrt.com 1541

Volume 9, Issue 12, December – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.5281/zenodo.14565219
[23]. Nishanov, A.K., Allamov, O.T., Ruzibaev,
O.B., Abdullaev, A.S., Allamova, S.T. An approach
to finding the most optimal route in a dynamic graph.
International Conference on Information Science and
Communications Technologies: Applications, Trends
and Opportunities, ICISCT 2021, 2021.
[24]. Nishanov, A., Akbaraliev, B., Beglerbekov,
R., Tajibaev, S., Kholiknazarov, R. Analytical method
for selection an informative set of features with
limited resources in the pattern recognition problem.
E3S Web of Conferences, 2021, 284, 04018.
[25]. Nishanov, A.H., Djuraev G.P., Khasanova, M.A.,
Saparov, S.X., Zaripov, F.M. Algorithm of
diagnostics of medical datas based on symptom
complexes. Proceedings Volume 12564, 2nd
International Conference on Computer Applications
for Management and Sustainable Development of
Production and Industry (CMSD-II-2022); 125640W
(2023) https://doi.org/10.1117/12.2669449.

IJISRT24DEC1276 www.ijisrt.com 1542