Chemical reaction optimization to disease diagnosis by optimizing hyper-planes classifiers
- 48 Downloads
Early diagnosis of diseases can save and leads to survival. There are several diagnoses techniques which mostly consist of classification and optimization parts. Although these techniques have their specific advantages, they have their significant disadvantages such as sensitivity to the number of features (symptoms) and need to features selection, challenge to detect non-integrated regions of one class and high complexity of their progresses. In this paper to fill up the disadvantages, a novel classification is proposed to disease diagnosis by different numbers of hyper-planes classifiers (HPC) that divides medical data into adequate regions based on assigning binary codes to each region. The HPC can find useful relationships between the symptoms of the diseases by tagging each region with the suitable class label. To optimize the HPC’s coefficients and improve disease diagnosis, chemical reaction optimization (CRO) is adapted based on four reactions on HPC’s coefficients, which are coded as molecular structures. Different numbers of HPCs are performed, and their experimental results are compared together. The interesting point of the results is disease diagnosis error 0.000% by five hyper-planes for test data of all investigated medical data set. Also, the best-obtained results of the CRO-HPC are compared with the best outputs of more than 50 methods of disease diagnosis from the previous state-of-the-art literature. This comparison shows that CRO-HPC’s diagnosis errors can compete with the majority of the other diagnostic methods.
KeywordsHyper-planes classifier Classification of medical data Chemical reaction optimization Disease diagnosis
Compliance with ethical standards
Conflict of interest
The authors of the current manuscript declare that Somayeh Jalayeri is graduated student of Islamic Azad University—Birjand Branch that she affiliated to her university and Majid Abdolrazzagh-Nezhad is Assist. Prof. of Bozorgmehr University of Qaenat as the supervisor of the current research. Except the above-declared conflict interest, the authors claim that there is not any conflict of interest and the research was not founded any grant.
Human participants and/or animals rights
In cases of research involving human participants and/or animals, the article does not contain any studies with human participants and/or animals performed by any of the authors. The investigated medical datasets to disease diagnosis are extracted from UCI (the UC Irvine Machine Learning Repository) that their details are presented in Appendix I.
The authors declare that informed consent was obtained from all individual participants included in the research.
- Anto S, Chandramathi S, Aishwarya S (2016) An expert system based on LS-SVM and simulated annealing for the diagnosis of diabetes disease. Int J Inf Commun Technol 9(1):88–100Google Scholar
- Avci E et al (2018) Performance comparison of some classifiers on chronic kidney disease data. In: 2018 6th international symposium on digital forensic and security (ISDFS). IEEEGoogle Scholar
- Belarouci S, Bekaddour F, Chikh MA (2016) A comparative study of medical data classification based on LS-SVM and metaheuristics approaches. In: 2016 8th international conference on modelling, identification and control (ICMIC). IEEEGoogle Scholar
- Brown G (2004) Diversity in neural network ensembles. University of BirminghamGoogle Scholar
- Chatterjee S et al (2017) Hybrid modified cuckoo search-neural network in chronic kidney disease classification. In: 2017 14th international conference on engineering of modern electric systems (EMES). IEEEGoogle Scholar
- DeCoste D (2003) Anytime query-tuned kernel machines via cholesky factorization. In: Proceedings of the 2003 SIAM international conference on data mining. SIAMGoogle Scholar
- Deoskar P, Singh D, Singh DA (2013) An efficient support based ant colony optimization technique for lung cancer data. Int J Adv Res Comput Commun Eng 2(9):3575–3581Google Scholar
- Eggermont J, Kok JN, Kosters WA (2004) Genetic programming for data classification: partitioning the search space. In: Proceedings of the 2004 ACM symposium on applied computing. ACMGoogle Scholar
- Grossman RL et al (2013) Data mining for scientific and engineering applications, vol 2. Springer, BerlinGoogle Scholar
- Hiesh M-H et al (2013) Classification of schizophrenia using genetic algorithm-support vector machine (GA-SVM). In: 2013 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEEGoogle Scholar
- Hore S, Chatterjee S, Shaw RK, Dey N, Virmani J (2018) Detection of chronic kidney disease: A NN-GA-Based approach. In: Panigrahi B, Hoda M, Sharma V, Goel S (eds) Nature inspired computing. Advances in intelligent systems and computing, vol 652. Springer, SingaporeGoogle Scholar
- Jona J, Nagaveni N (2014) Ant-cuckoo colony optimization for feature selection in digital mammogram. PJBS 17(2):266–271Google Scholar
- Joudaki H et al (2015) Using data mining to detect health care fraud and abuse: a review of literature. Glob J Health Sci 7(1):194Google Scholar
- Kaur G, Sharma A (2017) Predict chronic kidney disease using data mining algorithms in hadoop. In: International conference on inventive computing and informatics (ICICI). IEEEGoogle Scholar
- Kumari A, Mehra R (2014) Design of hybrid method PSO and SVM for detection of brain neoplasm. Int J Eng Adv Technol 3(4):262–266Google Scholar
- Martin JK, Hirschberg DS (1995) The time complexity of decision tree induction. CiteSeer, PrincetonGoogle Scholar
- Michalski RS et al (1986) The multi-purpose incremental learning system AQ15 and its testing application to three medical domains. Proc AAAI 1986:1041–1045Google Scholar
- Polat K, Sentürk U (2018) A novel ML approach to prediction of breast cancer: combining of mad normalization, KMC based feature weighting and AdaBoostM1 classifier. In: 2018 2nd international symposium on multidisciplinary studies and innovative technologies (ISMSIT). IEEEGoogle Scholar
- Saidi M, Chikh MA, Settouti N (2011) Automatic identification of diabetes diseases using a modified artificial immune recognition system2 (MAIRS2). In: Proceedings of 3ème conference internationale sur l ‘informatique et ses applicationsGoogle Scholar
- Sakthivel K, Jayanthiladevi A, Kavitha C (2016) Automatic detection of lung cancer nodules by employing intelligent fuzzy c-means and support vector machine. Biomed Res 27:s123–s127Google Scholar
- Salaken SM et al (2017) Lung cancer classification using deep learned features on low population dataset. In: 2017 IEEE 30th Canadian conference on electrical and computer engineering (CCECE). IEEEGoogle Scholar
- Street WN, Wolberg WH, Mangasarian OL (1993) Nuclear feature extraction for breast tumor diagnosis. In: IS&T/SPIE’s symposium on electronic imaging: science and technology. International society for optics and photonicsGoogle Scholar
- Wu M, Xu Z, Watada J (2012) Memetic algorithm based support vector machine classification. Int J Innov Manag Inf Prod 3(3):99–117Google Scholar