Программный каркас для машинного обучения выбору признаков при классификации сердечных заболеваний с использованием улучшенного алгоритма оптимизации методом роя частиц с классификатором метода опорных векторов

 
Код статьиS013234740003049-8-1
DOI10.31857/S013234740003049-8
Тип публикации Статья
Статус публикации Опубликовано
Авторы
Аффилиация: School of Computer Science and Engineering, Vellore Institute of Technology
Адрес: Индия, Веллуру
Аффилиация: School of Computer Science and Engineering, Vellore Institute of Technology
Адрес: Индия, Веллуру
Название журналаПрограммирование
ВыпускВыпуск 6
Страницы52-64
Аннотация

Машинное обучение используется в качестве эффективной вспомогательной системы диагностики состояния здоровья с большим объемом данных. Чаще всего анализ такого большого объема данных требует больше ресурсов и времени на выполнение. Кроме того, не все признаки, присутствующие в наборе данных, способствуют решению данной задачи. Следовательно, необходимо использовать эффективный алгоритм выбора более важных признаков, которые вносят больший вклад в диагностику заболеваний. Оптимизация методом роя частиц (PSO — Particle Swarm Optimization) — один из метаэвристических алгоритмов для поиска наилучшего решения за меньшее время. В настоящее время алгоритм PSO используется не только для выбора более значимых признаков, но и для устранения ненужных и избыточных, присутствующих в наборе данных. Однако традиционный алгоритм PSO имеет проблему выбора оптимального веса для обновления скорости и положения частиц. Для решения этой проблемы в настоящей работе представлена новая функция определения оптимальных весов на основе функции разнообразия множеств и функции настройки. Мы также предложили новую функцию пригодности для PSO с помощью метода опорных векторов (SVM — Support Vector Machine). Цель функции пригодности — минимизировать количество атрибутов и повысить точность. Эффективность предлагаемого алгоритма PSO-SVM сравнивается с различными существующими алгоритмами выбора признаков, такими как прирост информации, хи-квадрат, алгоритм на основе одного атрибута, подмножество совместимости, алгоритм Relief, метод CFS, отфильтрованное подмножество, отфильтрованный атрибут, нормализованный прирост информации и алгоритм PSO. Классификатор SVM также сравнивается с несколькими классификаторами, а именно с наивным байесовским классификатором, случайным лесом и многослойным перцептроном (MLP — Multilayer perceptron).

Ключевые слова
Получено15.12.2018
Дата публикации24.12.2018
Цитировать   Скачать pdf Для скачивания PDF необходимо авторизоваться
Размещенный ниже текст является ознакомительной версией и может не соответствовать печатной.

всего просмотров: 1012

Оценка читателей: голосов 0

1. Imran Kurt, Mevlut Ture, et al., Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease, J. Expert Syst. Appl., 2008, vol. 34, pp. 366–374.

2. Hongmei Yan, Jun Zheng, et al., Selecting critical clinical features for heart diseases diagnosis with a realcoded genetic algorithm, J. Appl. Soft Comput., 2008, vol. 8, pp. 1105–1111.

3. Carlos Ordonez, Association rule discover with the train and test approach for the heart disease prediction, IEEE Trans. Inf. Technol. Biomed., 2006, vol. 10, no. 2, pp. 334–343.

4. Kusiak, A., Caldarone, Ch.A., et al., Hypo plastic left heart syndrome knowledge discovery with a data mining approach, J. Comput. Biol. Med., 2006, vol. 36, no. 1, pp. 21–40.

5. Babaoglu, I., Kaan Baykan, O., et al., Assessment of exercise stress testing with artificial neural network in determining coronary artery disease and predicting lesion localization, J. Expert Syst. Appl., 2009, vol. 36, pp. 2562–2566.

6. Rajeswari, K., Vaithiyanathan, V., et al., Feature selection in ischemic heart disease identification using feed forward neural networks, Int. Symposium on Robotics and Intelligent Sensors, 2012, vol. 41, pp. 1818–1823.

7. Mu-Jung Huang, Mu-Yen Chen, et al., Integrating data mining with case-based reasoning for chronic diseases prognosis and diagnosis, J. Expert Syst. Appl., 2007, vol. 32, pp. 856–867.

8. Tan, K.C., Teoh, E.J., et al., A hybrid evolutionary algorithm for attribute selection in data mining, J. Expert Syst. Appl., 2009, vol. 36, pp. 8616–8630.

9. Jesmin Nahar, Tasadduq Imam, et al., Association rule mining to detect factors which contribute to heart disease in males and females, J. Expert Syst. Appl., 2013, vol. 40, pp. 1086–1093.

10. Austin, P.C., Tu, J.V., et al., Using methods from the data-mining and machine-learning literature for disease classification and prediction: A case study examining classification of heart failure subtypes, J. Clin. Epidemiol., 2013, vol. 66, pp. 398–407.

11. Kemal Polat and Salih Gunes, A new feature selection method on classification of medical datasets: Kernel Fscore feature selection, J. Expert Syst. Appl., 2009, vol. 36, pp. 10367–10373.

12. Babaoglu, I., Findik, O., et al., A comparison of feature selection models utilizing binary Particle Swarm Optimization and genetic algorithm in determining coronary artery disease using Support Vector Machine, J. Expert Syst. Appl., 2010, vol. 37, pp. 3177–3183.

13. Jesmin Nahar, Tasadduq Imam, et al., Computational intelligence for heart disease diagnosis: A medical knowledge driven approach, J. Expert Syst. Appl., 2013, vol. 40, pp. 96–104.

14. Setiawan, N.A. et al., A comparative study of imputation methods to predict missing attribute values in coronary heart disease data set, J. Dep. Electr. Electron. Eng., 2009, vol. 21, pp. 266–269.

15. Luukka, P. and Lampinen, J., A classification method based on Principal Component Analysis and differential evolution algorithm applied for prediction diagnosis from clinical EMR heart data sets, J. Comput. Intell. Optimization Adaption, Learn. Optim., 2010, vol. 7, pp. 263–283.

16. Das, R., Turkoglu, I., et al., Effective diagnosis of heart disease through neural networks ensembles, J. Expert Syst. Appl., 2009, vol. 36, pp. 7675–7680.

17. Das, R., Turkoglu, I., et al., Diagnosis of valvular heart disease through neural networks ensembles, J. Comput. Methods Programs Biomed., 2009, vol. 93, pp. 185–191.

18. Chang-Sik Son, Yoon-Nyun Kim, et al., Decisionmaking model for early diagnosis of congestive heart failure using rough set and decision tree approaches, J. Biomed. Inf., 2012, vol. 45, pp. 999–1008.

19. Laercio Brito Gon?alves, Marley Maria Bernardes Rebuzzi Vellasco, et al., Inverted hierarchical neurofuzzy BSP system: A novel neuro-fuzzy model for pattern classification and rule extraction in databases, J. IEEE Trans. Syst., Man, Cybernetics, 2006, vol. 36, no. 2.

20. Kemal Polat and Salih Gunes, A hybrid approach to medical decision support systems: Combining feature selection, fuzzy weighted pre-processing and AIRS, J. Comput. Methods Progr. Biomed., 2007, vol. 88, pp. 164–174.

21. Kemal Polat, Seral S. ahan, et al., Automatic detection of heart disease using an Artificial Immune Recognition System (AIRS) with fuzzy resource allocation mechanism and k-nn (nearest neighbor) based weighting preprocessing, J. Expert Syst. Appl., 2007, vol. 32, pp. 625–631.

22. Akin Ozcift and Arif Gulten, Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms, J. Comput. Methods Progr. Biomed., 2011, vol. 104, pp. 443–451.

23. Chih-Lin Chi, Nick Street, W., et al., A decision support system for cost-effective diagnosis, J. Artif. Intell. Med., 2010, vol. 50, pp. 149–161.

24. Yoon-Joo Park, Se-Hak Chun, et al., Cost-sensitive case-based reasoning using a genetic algorithm: Application to medical diagnosis, J. Artif. Intell. Med., 2011, vol. 51, pp. 133–145.

25. Debabrata Pal, Mandana, K.M., et al., Fuzzy expert system approach for coronary artery disease screening using clinical parameters, J. Knowl. Based Syst., 2012, vol. 36, pp. 162–174.

26. Kahramanli, H. and Allahverdi, N., Design of a hybrid system for the diabetes and heart diseases, J. Expert Syst. Appl., 2008, vol. 35, pp. 82–89.

27. Vahid Khatibi and Gholam Ali Montazer, A fuzzyevidential hybrid inference engine for coronary heart disease risk assessment, J. Expert Syst. Appl., 2010, vol. 37, pp. 8536–8542.

28. Goekmen Turan, R. Bozdag, I., et al., Improved functional activity of bone marrow derived circulating progenitor cells after intra coronary freshly isolated bone marrow cells transplantation in patients with ischemic heart disease, J. Stem Cell Rev. Rep., 2011, vol. 7, pp.646–656.

29. Karsdorp, P.A., Kindt, M., et al., False heart rate feedback and the perception of heart symptoms in patients with congenital heart disease and anxiety, Int. J. Behav. Med., 2009, vol. 16, pp. 81–88.

30. Carlosnasillo/Hybrid-Genetic-Algorithm, 2017. GitHub. https://github.com/carlosnasillo/HybridGenetic-Algorithm. Retrieved October 22, 2017.

31. Muthukaruppan, S. and Er, M.J., A hybrid Particle Swarm Optimization based fuzzy expert system for the diagnosis of coronary artery disease, J. Expert Syst. Appl., 2012, vol. 39, pp. 11657–11665.

32. Anooj, P.K., Clinical decision support system: Risk level prediction of heart disease using weighted fuzzy rules, J. Comput. Inf. Sci., 2012, vol. 24, pp. 27–40.

33. Tsipouras, M.G., Exarchos, T.P., et al., Automated diagnosis of coronary artery disease based on data mining and fuzzy modeling, J. IEEE Trans. Inf. Technol. Biomed., 2008, vol. 12, no. 4.

34. Paredesa, S. et al., Long term cardiovascular risk models’ combination, J. Comput. Methods Progr. Biomed., 2011, vol. 101, pp. 231–242.

35. Swati Shilaskar et al., Feature selection for medical diagnosis: Evaluation for cardiovascular diseases, J. Expert Syst. Appl., 2013, vol. 40, pp. 4146–4153.

36. UCI Machine Learning Repository: Heart Disease Data Set. Archive.ics.uci.edu. http://archive.ics.uci. edu/ml/datasets/Heart+Disease. Retrieved October 22, 2017.

37. Zhao, M., Fu, C., Ji, L., Tang, K., and Zhou, M., Feature selection and parameter optimization for Support Vector Machines: A new approach based on genetic algorithm with feature chromosomes, Expert Syst. Appl., 2011, vol. 38, no. 5, pp. 5197– 5204.

38. Li-Na Pu, Ze Zhao, et al., Investigation on cardiovascular risk prediction using genetic information, J. IEEE Trans. Inf. Technol., Biomed., 2012, vol. 16, no. 5.

39. Pfister, R., Barnes, D., et al., Individual and cumulative effect of type 2 diabetes genetic susceptibility variants on risk of coronary heart disease, J. Diabetologia, 2011, vol. 54, pp. 2283–2287.

40. Nazri Mohd Nawi, Rozaida Ghazali, et al., The development of improved back-propagation neural networks algorithm for predicting patients with heart disease, in Proceedings of the First International Conference ICICA, 2010, vol. 6377, pp. 317–324.

41. Jae-Hong Eom, Sung-Chun Kim, et al., AptaCDSS-E: A classifier ensemble-based clinical decision support system for cardiovascular disease level prediction, J. Expert Syst. Appl., 2008, vol. 34 2465, p. 2479.

42. Iftikhar, S., Fatima, K., Rehman, A., Almazyad, A.S., and Saba, T., An evolution based hybrid approach for heart diseases classification and associated risk factors identification, Biomed. Res., 2017, vol. 28, no. 8.

43. Shah, S.M.S., Batool, S., Khan, I., Ashraf, M.U., Abbas, S.H., and Hussain, S.A., Feature extraction through parallel probabilistic Principal Component Analysis for heart disease diagnosis, Phys. A: Statistical Mechanics and Its Applications, 2017, vol. 482, pp. 796–807.

44. Arabasadi, Z., Alizadehsani, R., Roshanzamir, M., Moosaei, H., and Yarifard, A.A., Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm, Comput. Methods Progr. Biomed., 2017, vol. 141, pp. 19–26.

45. Li, Q., Chen, H., Huang, H., Zhao, X., Cai, Z., Tong, C., and Tian, X., An enhanced grey wolf optimization based feature selection wrapped kernel extreme learning machine for medical diagnosis, Comput. Math. Methods Med., 2017.

46. Vivekanandan, T. and Iyengar, N.C.S.N., Optimal feature selection using a modified differential evolution algorithm and its effectiveness for prediction of heart disease, Comput. Biol. Med., 2017, vol. 90, pp. 125–136.

47. Jabbar, M.A., Deekshatulu, B.L., and Chandra, P., Prediction of heart disease using random forest and feature subset selection, in Innovations in Bio-Inspired Computing and Applications, Cham.; Springer, 2016, pp. 187–196.

48. Paul, A.K., Shill, P.C., Rabin, M.R.I., and Akhand,M.A.H., Genetic algorithm based fuzzy decision support system for the diagnosis of heart disease, in Informatics, Electronics and Vision (ICIEV), 2016 5th International Conference, IEEE, 2016, pp. 145–150.

49. Inbarani, H.H., Azar, A.T., and Jothi, G., Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis, Comput. Methods Progr. Biomed., 2014, vol. 113, no. 1, pp. 175–185.

50. Tomar, D. and Agarwal, S., Feature selection based Least Square Twin Support Vector Machine for diagnosis of heart disease, Int. J. Bio-Sci. BioTechnol., 2014, vol. 6, no. 2, pp. 69–82.

51. Reddy, G.T. and Khare, N., An efficient system for heart disease prediction using hybrid OFBAT with rule-based Fuzzy Logic Model, J. Circuits, Syst. Comput., 2017, vol. 26, no. 04, p. 1750061.

52. Pimentel, A., Coronary heart disease prognosis using machine-learning techniques on patients with type 2 Diabetes Mellitus, in Ubiquitous Machine Learning and Its Applications, IGI Global, 2017, pp. 89–112.

Система Orphus

Загрузка...
Вверх