CLASSIFICATION AND FEATURE SELECTION IN MEDICAL DATA PREPROCESSING
In this article, the issues such as medical data preprocessing, reclassification of training sets and determining the importance of classes, forming reference tables, selecting a set of informative features that differentiate between class objects, formed by medical professionals, were solved based on Fisher criterion using algorithms for an estimate calculation. As a result of data preprocessing, three objects were formed: 1) Ischemic heart disease. Unstable angina pectoris; 2) Ischemic heart disease. Acute myocardial infarction; 3) Ischemic heart disease. Arrhythmic form. Further, the issues such as classifying, selecting a set of informative features that differentiate between class objects were solved using Fisher criterion, and algorithms for an estimate calculation as well as software programs for them were developed. As a result of data preprocessing, reference classes were formed. Objects that had fallen outside of their class during the formation process were excluded from the training set. A classification and a set of informative features were selected using established classes. Initially, three class objects, each containing 62 features, were provided by medical professionals, and as a result of data preprocessing, three sets consisting of 131, 115, and 40 objects, respectively, in the three classes were used to form a reference table.
. Yu.I.Zhuravlev, â€œSelected scientific worksâ€, â€“ M: â€œMagistrâ€ Publishing house, 420 p., 1998.
. L.Yu, H.Liu. â€œEfficient Feature Selection via Analysis of Relevance and Redundancyâ€. â€“ J. Mach. Learn. Res., Vol. 5, pp. 1205-1224, No Oct. 2004.
. L.Yu, â€œToward Integrating Feature Selection Algorithm for Classification and Clusteringâ€, IEEE Transaction on Knowledge and Data Engineering 17(4), 491-502.
. K.Yan, D.Zhang, â€œFeature Selection and Analysis on Correlated Gas Sensor Data with Recursive Feature Eliminationâ€, Sensors Actuators, B Chem., Vol. 212, pp. 353-363, Jun 2015.
. A.Kh.Nishanov, Kh.A.Turakulov, Kh.V.Turakhanov, â€œA decision rule for identification of eye pathologiesâ€, Biomedical Engineering, 33(4) 178-179, 1999.
. A.Kh.Nishanov, Kh.A.Turakulov, Kh.V.Turakhanov, â€œA decisive rule in classifying diseases of the visual systemâ€, Meditsinskaia tekhnika, (4) 16-18, 1999.
. F.Xiang, W.Lina, â€œFeature Selection Based on Fisher Criterion and Sequential Forward Selection for Intrusion Detectionâ€, Revista de la Facultad de IngenierÃa U.C.V., Vol. 32, NÂ° 1, pp.498-503, 2017.
. S.Linhui, F.Sheng and F.Wang, â€œDecision tree SVM model with Fisher feature selection for speech emotion recognitionâ€, Sun et al. EURASIP Journal on Audio, Speech, and Music Processing https://doi.org/10.1186/s13636-018-0145-5, 2019.
. X.Yan, M.Tan, Y.Yan, M.LÃ¼, â€œResearch on Hidden Markov Model-Based And Neural Network-Based Intrusion Detectionsâ€, Computer Applications and Software, 29(2), 294â€“297, 2012.
. X.Jing, H.Wang, K.Nie, Z.Luo, â€œFeature Selection Algorithm Based on IMGA and MKSVM to Intrusion Detectionâ€, Computer Science, 39(7), 96â€“100, 2012.
. K.Koushal, S.B.Jaspreet, â€œNetwork Intrusion Detection with Feature Selection Techniques using Machine-Learning Algorithmsâ€, International Journal of Computer Applications (0975 â€“ 8887) Volume 150 â€“ No.12, 1-13, September-2016.
. A.Kh.Nishanov, G.P.Djurayev, M.A.Khasanova, â€œImproved algorithms for calculating evaluations in processing medical dataâ€, COMPUSOFT: An International Journal of Advanced Computer Technology, India, Vol 8, No 6 - 2019.
. M.Kamilov, A.Nishanov, R.Beglerbekov, â€œModified Stages of Algorithms for Computing Estimates in the Space of Informative Featuresâ€, International Journal of Innovative Technology and Exploring Engineering, 8(6), 2019.
. M.Sulaiman, J.Labadin, â€œFeature Selection Based on Mutual Informationâ€, Publisher: Institute of Electrical and Electronics Engineers (IEEE), pp: 1-6, 2015.
. D.Xuelian, L.Yuqing, W.Jian, Z.Jilian, â€œFeature Selection for Text Classification: A reviewâ€ Multimedia Tools and Applications, 1007/s11042-018-6083-5, 2019.
. S.Ma and J.Huang, â€œPenalized Feature Selection and Classification in Bioinformaticsâ€, Briefings in Bioinformatics. doi: 10.1093/bib/bbn027, 2008.
. L.Sun, , S.Fu and F.Wang, 2019) â€˜Decision Tree SVM Model with Fisher Feature Selection for Speech Emotion Recognitionâ€™, Eurasip Journal on Audio, Speech, and Music Processing, doi: 10.1186/s13636-018-0145-5, (1)2019.
. R. S. B.Krishna and M.Aramudhan, â€œFeature Selection Based on Information Theory for Pattern Classificationâ€, in 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies, doi: 10.1109/ICCICCT.2014.6993149, ICCICCT 2014.
. V. V.Mokshin, et al. â€œParallel Genetic Algorithm of Feature Selection for Complex System Analysisâ€, in Journal of Physics: Conference Series. doi: 10.1088/1742-6596/1096/1/012089, 2018.
. S.Solorio-FernÃ¡ndez, J.A.Carrasco-Ochoa and J.F.MartÃnez-Trinidad, â€œA Review of Unsupervised Feature Selection Methodsâ€, Artificial Intelligence Review. doi: 10.1007/s10462-019-09682-y, 2019.
. R.J.Urbanowicz et al. â€œBenchmarking Relief-Based Feature Selection Methods for Bioinformatics Data Miningâ€, Journal of Biomedical Informatics, 85. doi: 10.1016/j.jbi.2018.07.015, 2018.
. J.Cai et al. â€œFeature Selection in Machine Learning: A New Perspectiveâ€, Neurocomputing, 300. doi: 10.1016/j.neucom.2017.11.077, 2018.
. M.Ghaemi and M. R. Feizi-Derakhshi, â€œFeature Selection Using Forest Optimization Algorithmâ€, Pattern Recognition. Elsevier Ltd, 60, pp. 121â€“129. doi: 10.1016/j.patcog.2016.05.012, 2016.
The submitter hereby warrants that the Work (collectively, the “Materials”) is original and that he/she is the author of the Materials. To the extent the Materials incorporate text passages, figures, data or other material from the works of others, the undersigned has obtained any necessary permissions. Where necessary, the undersigned has obtained all third party permissions and consents to grant the license above and has all copies of such permissions and consents.
The submitter represents that he/she has the power and authority to make and execute this assignment. The submitter agrees to indemnify and hold harmless the COMPUSOFT from any damage or expense that may arise in the event of a breach of any of the warranties set forth above. For authenticity, validity and originality of the research paper the author/authors will be totally responsible.