O‘pka saratoniga chalinganlar ulushi onkologik kasallik turlari orasida eng katta ko‘rsatkichlarni tashkil etmoqda. Ushbu tur saraton kasalligiga chalingan bemorlar o‘limi onkologik kasalliklar tufayli vafot etayotganlarning 18 foizini tashkil etayotganligi bu borada tadqiqot olib borish zarurligini ko‘rsatmoqda. Mamlakatimizda ham yildan-yilga o‘pka saratoniga chalingan bemorlar hamda mazkur kasallik asoratlaridan vafot etayotganlar soni ortib borayotgani buning yaqqol misolidir. Mazkur maqolada tayanch vektorlar usuli yordamida bemorlardagi o‘pka saratoni kasalligiga chalinish darajasini tasniflash masalasi ko‘rib chiqilgan. O‘quv tanlanma uchun kaggle.com saytidan olingan etalon ma’lumotlardan foydalanilgan. Tadqiqot usuli sifatida tanlangan tayanch vektorlar usulining asosiy bosqichlari atroflicha yoritilgan. Kasallikka chalinish darajalarining tasniflash natijalari jadval va grafiklar asosida keltirilgan. Xulosa o‘rnida tayanch vektorlar usuli nafaqat turli sohalar, balki tibbiyot sohasida ham qo‘llanilishi ijobiy yechim bo‘la olishi isbotlangan. Bundan tashqari, tadqiqotda foydalanilgan o‘quv tanlanma ham real jarayonga tatbiq etishga loyiqligi ta’kidlangan.
Среди онкологических заболеваний рак лёгкого имеет наибольшую долю. Тот факт, что смертность больных этим видом рака составляет 18 % от смертности из всех онкологических заболеваний, показывает актуальность проведения исследований в этом направлении. Убедительным примером этого является и то, что в нашей стране с каждым годом растёт количество больных раком лёгкого, в том числе и умирающих от осложнений этого заболевания. В данной статье рассмотрена задача классификации заболеваний рака лёгкого у пациентов при помощи метода опорных векторов. В качестве обучающей выборки использовались эталонные данные, полученные Kaggle.com. Подробно описаны основные этапы метода опорных векторов, выбранного в качестве метода исследования. Результаты классификации заболеваний поясняются с помощью таблиц и графиков. Было доказано, что метод опорных векторов может быть эффективным решением при применении в медицине. Кроме того, подчёркивается, что использованная в исследовании обучающая выборка вполне применима в реальном процессе.
O‘pka saratoniga chalinganlar ulushi onkologik kasallik turlari orasida eng katta ko‘rsatkichlarni tashkil etmoqda. Ushbu tur saraton kasalligiga chalingan bemorlar o‘limi onkologik kasalliklar tufayli vafot etayotganlarning 18 foizini tashkil etayotganligi bu borada tadqiqot olib borish zarurligini ko‘rsatmoqda. Mamlakatimizda ham yildan-yilga o‘pka saratoniga chalingan bemorlar hamda mazkur kasallik asoratlaridan vafot etayotganlar soni ortib borayotgani buning yaqqol misolidir. Mazkur maqolada tayanch vektorlar usuli yordamida bemorlardagi o‘pka saratoni kasalligiga chalinish darajasini tasniflash masalasi ko‘rib chiqilgan. O‘quv tanlanma uchun kaggle.com saytidan olingan etalon ma’lumotlardan foydalanilgan. Tadqiqot usuli sifatida tanlangan tayanch vektorlar usulining asosiy bosqichlari atroflicha yoritilgan. Kasallikka chalinish darajalarining tasniflash natijalari jadval va grafiklar asosida keltirilgan. Xulosa o‘rnida tayanch vektorlar usuli nafaqat turli sohalar, balki tibbiyot sohasida ham qo‘llanilishi ijobiy yechim bo‘la olishi isbotlangan. Bundan tashqari, tadqiqotda foydalanilgan o‘quv tanlanma ham real jarayonga tatbiq etishga loyiqligi ta’kidlangan.
Among all cancers, lung cancer accounts for the largest proportion of patients. The fact that the mortality rate of patients with this type of cancer makes 18% of the number of deaths from oncologic diseases, shows relevance of the research in this area. A clear evidence of this is the fact that in our country, statistics of lung cancer patients and those who die from its implications, is increasing every year. This paper reviews the issue of classifying the level of lung cancer in patients using the support vector method. The benchmark data obtained from kaggle.com was used as a training set. The main stages of the support vector method chosen as the research method are being closely described. Findings from classification of morbidity levels are being explained using tables and graphs. The study proves that the support vector method can serve as a positive solution for application in various fields including the medical practice. Moreover, it is being emphasized that the training set used in the study is worthy of applying in the real process.
№ | Имя автора | Должность | Наименование организации |
---|---|---|---|
1 | Xudayberdiyev M.X. | professor | Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti, “Axborot texnologiyalarining dasturiy ta’minoti” kafedrasi |
2 | Achilov B.S. | assistent | Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti, “Axborot texnologiyalarining dasturiy ta’minoti” kafedrasi |
3 | Alimqulov N.M. | tayanch doktorant | Zahiriddin Muhammad Bobur nomidagi Andijon davlat universiteti |
№ | Название ссылки |
---|---|
1 | Agarwal, D., Singh, P., & El Sayed, M. (2023). The Karush–Kuhn–Tucker (KKT) optimality conditions for fuzzy-valued fractional optimization problems. Mathematics and Computers in Simulation, 205, 861-877. |
2 | Battineni, G., Chintalapudi, N., & Amenta, F. (2019). Machine learning in medicine: Performance calculation of dementia prediction by support vector machines (SVM). Informatics in Medicine Unlocked, 16, 100200. |
3 | Bhat, A. (2021). Kaggle. Retrieved from https://www.kaggle.com/datasets/mysarahmadbhat/lung-cancer |
4 | Davies, M., Takahiro, S., Haitham, A., Liping, H., Triantafillos, L., Yang, R., & Field, J. (2023). Plasma protein biomarkers for early prediction of lung cancer. eBioMedicine, Volume 93, 104686. |
5 | Ibragimov, S. (2023). Raqamli dasturiy mahsulot yaratish asosida onkoepidemiologik holatni kompleks baholash [Comprehensive assessment of the oncoepidemiological situation based on the creation of a digital software product]. Tashkent. |
6 | IQAIR. (2024). Air quality in Tashkent. Air quality index (AQI) and PM2.5 air pollution in Tashkent. (Keystone, IQAIR). Retrieved from IQAIR: https://www.iqair.com/ru/uzbekistan/toshkent-shahri/tashkent |
7 | Keerthana, D., Venugopal, V., Nath, M., & Mishra, M. (2023). Hybrid convolutional neural networks with SVM classifier for classification of skin cancer. Biomedical Engineering Advances, 5, 100069. |
8 | Khudayberdiev, M., Ibragimov, S., Alimkulov, N., & Djanklich, S. (2023). Solving tasks of oncoepidemiology prediction using least squares and SVR algorithms. В T. &. Group (Ed.), Artificial Intelligence, Blockchain, Computing and Security Volume 2 (pр. 595-602). London: CRC Press. |
9 | Kumar, K., Srikanth, V., Prasad, G., Hazela, B., & Tamrakar, A. (2023). Fault detection on the 3-D printed objective surface by using the SVM algorithm. Materials Today: Proceedings. |
10 | Lan, Y., Zhang, Y., & Lin, W. (2023). Diagnosis algorithms for indirect bridge health monitoring via an optimized AdaBoost-linear SVM. Engineering Structures, 275(Part A), 115239. |
11 | Liu, J., & Liu, Y. (2014). Non-integer norm regularization SVM via Legendre–Fenchel duality. Neurocomputing, 144, 537-545. |
12 | Nasser, I.M.; Abu-Naser, S.S. (2019). Lung Cancer Detection Using Artificial Neural Network. International Journal of Engineering and Information Systems, 3(3), 17-23. |
13 | Qiang, Y., Guo, Y., Li, X., Wang, Q., Chen, H., & Cuic, D. (2007). The Diagnostic Rules of Peripheral Lung Cancer Preliminary Study Based on Data Mining Technique. Journal of Nanjing Medical University, 190-195. |
14 | Rikta, S., Uddin, K., Biswas, N., Mostafiz, R., Sharmin, F., & Dey, S. (2023). XML-GBM lung: An explainable machine learning-based application for the diagnosis of lung cancer. Journal of Pathology Informatics, 14, 100307. |
15 | Tillyashaykhova, M., Ibragimova, S., & Dzhanklich, S. (2023). Sostoyaniye onkologicheskoy pomoshchi naseleniyu Respubliki Uzbekistan v 2022 godu [The state of cancer care for the population of the Republic of Uzbekistan in 2022]. Tashkent: Khalk Publ. |
16 | Vankdothu, R., & Hameed, M. (2022). Brain tumor segmentation of MR images using SVM and fuzzy classifier in machine learning. Measurement: Sensors, 24, 100440. |
17 | Wu, Y., & Li, S. (2022). Damage degree evaluation of masonry using optimized SVM-based acoustic emission monitoring and rate process theory. Measurement, 190, 110729. |
18 | Yang, M., Lim, M., Qu, Y., Li, X., & Ni, D. (2023). Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction. Expert Systems with Applications, 213(Part A). |