Context-based probability neural network classifiers realized by genetic optimization for medical decision making
- 82 Downloads
In this paper, we proposed context-based probability neural network (CPNN) classifiers for solving a medical decision making problems. The concept of “contexts” coming from the clustering research area is explored here to construct the second layer of probability neural network classifiers. Furthermore, genetic algorithm is used to optimize the structure parameters when designing the proposed CPNN. In contrast to the known probability neural networks, the proposed CPNN archive a better accuracy classification rate. Several known data sets are utilized to evaluate the performance of CPNN. Experimental results demonstrate that the relationship between the selected features and disease are more apparent in comparison with the conventional neural network models.
KeywordsMedical decision making Extraction of features Probabilistic neural network (PNN) Genetic algorithm
This work was supported by the Foundation of Educational Commission of Tianjin City, China (Grant No. 20140803), supported by the Innovation Foundation for Young Teachers of Tianjin University of Science and Technology, China (Grant No. 2014CXLG30).
- 2.Chen M, Shi X, Zhang Y et al (2017) Deep features learning for medical image analysis with convolutional autoencoder neural network. IEEE Trans Big Data. https://doi.org/10.1109/TBDATA.2017.2717439
- 4.Cheung N (2001) Machine learning techniques for medical analysis. School of Information Technology and Electrical Engineering, B.Sc. Thesis, University of QueenlandGoogle Scholar
- 6.Gadewadikar J, Kuljaca O, Agyepong K, Sarigul E, Zheng Y, Zhang P (2010) Exploring Bayesian networks for medical decision support in breast cancer detection. Afr J Math Comput Sci Res 3(10):225–231Google Scholar
- 12.Huang W, Oh SK, Pedrycz W (2017) Hybrid fuzzy wavelet neural networks architecture based on polynomial neural networks and fuzzy set/relation inference-based wavelet neurons. IEEE Trans Neural Netw Learn Syst:1–11 (In Press)Google Scholar
- 21.Polat K, Sahan S, Kodaz H, Günes S (2015) A new classification method to diagnosis heart disease: supervised artificial immune system (AIRS). In: Proceedings of the Turkish Symposium on Artificial Intelligence and Neural Networks (TAINN)Google Scholar
- 23.Tipping ME (2000) The relevance vector machine. Adv Neural Inf Proces Syst 12:652–658Google Scholar
- 28.Zarinbal M, Fazel Zarandi MH, Turksen IB, Izadi M (2015) A type-2 fuzzy image processing expert system for diagnosing brain tumors. J Med Syst 39(110):1–20Google Scholar