Simultaneously feature selection and parameters optimization by teaching–learning and genetic algorithms for diagnosis of breast cancer
Tóm tắt
Currently, development of early and accurate breast cancer (BC) prediction models using computer-aided tools has proven to be beneficial, which in turn low mortality rate related to this disease. However, feature selection (FS) is a challenging task for the identification and characterization of cancers that increase the susceptibility to common complex multifactorial BC diseases, especially when dealing with clinical treatment. Most of the previous FS techniques does not handle important characterization such as removing irrelevant and/or redundant features separately. According to the past research on FS, several evolutionary algorithms have been proposed to address FS problems, but they have to fail for classifying BC survival types. In order to address before-mentioned issues, numerous hybridized models have been intended for selecting best features in effort to increase the accuracy of breast cancer predictive models. It may be cumbersome to obtain the perfect parameters for optimal performance. To resolve the deficiencies of past diagnostic system, in this paper, hybrid teaching–learning optimization (TLBO) and genetic algorithm (GA)-based is proposed consistent wrapper strategy called TLBOG to improve the reliability of evolutionary algorithms. The aim of using GA here is to tackle slow convergence rate and improve exploitation search capability found by TLBO. Most importantly, goal of our approach is to optimize the parameters of support vector machines to have high accuracy in contrast to other machine learning models and select best features subset simultaneously. From the performance evaluation results, we understand that proposed approach is significantly higher than conventional wrapper techniques in terms of accuracy, sensitivity, precision, and F-measure in the WBCD and WDBC databases.
Từ khóa
Tài liệu tham khảo
C Metta 2023 Improving trust and confidence in medical skin lesion diagnosis through explainable deep learning Int. J. Data Sci. Anal. https://doi.org/10.1007/s41060-023-00401-z
N Arya A Mathur S Saha S Saha 2023 Proposal of SVM utility kernel for breast cancer survival estimation IEEE/ACM Trans. Comput. Biol. Bioinform. 20 2 1372 1383 https://doi.org/10.1109/TCBB.2022.3198879
L Song W Hsu J Xu M Schaar Van Der 2016 Using contextual learning to improve diagnostic accuracy : application in breast cancer screening IEEE J. Biomed. Heal. Inform. 20 3 902 914
S Almutairi S Manimurugan BG Kim MM Aborokbah C Narmatha 2023 Breast cancer classification using Deep Q Learning (DQL) and gorilla troops optimization (GTO) Appl. Soft Comput. 142 110292https://doi.org/10.1016/j.asoc.2023.110292
F Spanhol 2016 A dataset for breast cancer histopathological a dataset for breast cancer histopathological image classification IEEE Trans. Biomed. Eng. 63 1455 1462 https://doi.org/10.1109/TBME.2015.2496264
AM Alaa KH Moon W Hsu M Schaar Van Der 2016 ConfidentCare: a clinical decision support system for personalized breast cancer screening IEEE Trans. Multimed. 18 10 1942 1955 https://doi.org/10.1109/TMM.2016.2589160
P Giudici A Gramegna E Raffinetti 2023 Machine learning classification model comparison Socioecon. Plann. Sci. 87 101560https://doi.org/10.1016/j.seps.2023.101560
M Abd-Elnaby M Alfonse M Roushdy 2021 Classification of breast cancer using microarray gene expression data: a survey J. Biomed. Inform. 117 103764 https://doi.org/10.1016/j.jbi.2021.103764
P Giudici E Raffinetti 2023 SAFE artificial intelligence in finance Financ. Res. Lett. 56 104088 https://doi.org/10.1016/j.frl.2023.104088
R Mendonca-Neto Z Li D Fenyo CT Silva FG Nakamura EF Nakamura 2022 A gene selection method based on outliers for breast cancer subtype classification IEEE/ACM Trans. Comput. Biol. Bioinform. 19 5 2547 2559 https://doi.org/10.1109/TCBB.2021.3132339
N Moustafa B Turnbull KKR Choo 2019 An ensemble intrusion detection technique based on proposed statistical flow features for protecting network traffic of internet of things IEEE Internet Things J. 6 3 4815 4830 https://doi.org/10.1109/JIOT.2018.2871719
PN Silva Da A Plastino F Fabris AA Freitas 2021 A novel feature selection method for uncertain features: an application to the prediction of pro-/anti-longevity genes IEEE/ACM Trans. Comput. Biol. Bioinform. 18 6 2230 2238 https://doi.org/10.1109/TCBB.2020.2988450
B Xue M Zhang S Member WN Browne 2016 A survey on evolutionary computation approaches to feature selection IEEE Trans. Evol. Comput. 20 4 606 626
AS Elkorany M Marey KM Almustafa ZF Elsharkawy 2022 Breast cancer diagnosis using support vector machines optimized by whale optimization and dragonfly algorithms IEEE Access 10 69688 69699 https://doi.org/10.1109/ACCESS.2022.3186021
P Giudici E Raffinetti 2022 Explainable AI methods in cyber risk management Qual. Reliab. Eng. Int. 38 3 1318 1326 https://doi.org/10.1002/qre.2939
CH Yang Y Lin Da LY Chuang HW Chang 2013 Evaluation of breast cancer susceptibility using improved genetic algorithms to generate genotype SNP barcodes IEEE/ACM Trans. Comput. Biol. Bioinform. 10 2 361 371 https://doi.org/10.1109/tcbb.2013.27
RV Rao VJ Savsani DP Vakharia 2011 Teaching learning-based optimization : a novel method for constrained mechanical design optimization problems Comput. Des. 43 3 303 315 https://doi.org/10.1016/j.cad.2010.12.015
S Tuo L Yong F Deng Y Li Y Lin Q Lu 2017 HSTLBO : a hybrid algorithm based on Harmony Search and Teaching-Learning- Based Optimization for complex high- dimensional optimization problems PLoS ONE 12 4 1 23
R Mendes J Kennedy J Neves 2004 The fully informed particle swarm: simpler, maybe better IEEE Trans. Evol. Comput. 8 3 204 210 https://doi.org/10.1109/TEVC.2004.826074
OV Singh P Choudhary 2019 A study on convolution neural network for breast cancer detection Conf. Adv. Comput. Commun. Paradig. ICACCP 2019 1 7 https://doi.org/10.1109/ICACCP.2019.8882993
C Junyue DQ Zeebaree C Qingfeng DA Zebari 2023 Breast cancer diagnosis using hybrid AlexNet-ELM and chimp optimization algorithm evolved by Nelder-mead simplex approach Biomed. Signal Process. Control https://doi.org/10.1016/j.bspc.2023.105053
D Li L Zhang J Zhang X Xie 2023 Convolutional feature descriptor selection for mammogram classification IEEE J. Biomed. Heal. Inform. 27 3 1467 1476 https://doi.org/10.1109/JBHI.2022.3233535
K Thirumoorthy 2023 A two-stage feature selection approach using hybrid quasi-opposition self-adaptive coati optimization algorithm for breast cancer classification Appl. Soft Comput. https://doi.org/10.1016/j.asoc.2023.110704
Z Yang K Li Q Niu 2014 A self-learning TLBO based dynamic economic / environmental dispatch considering multiple plug-in electric vehicle loads J. Mod. Power Syst. Clean Energy 2 4 298 307 https://doi.org/10.1007/s40565-014-0087-6
A Nickabadi MM Ebadzadeh R Safabakhsh 2011 A novel particle swarm optimization algorithm with adaptive inertia weight Appl. Soft Comput. J. 11 4 3658 3670 https://doi.org/10.1016/j.asoc.2011.01.037
D Tripathi B Ramachandra Reddy YCA Padmanabha Reddy AK Shukla RK Kumar NK Sharma 2021 BAT algorithm based feature selection: application in credit scoring J. Intell. Fuzzy Syst. 41 1 10
M Shehab AT Khader MA Al-Betar 2017 A survey on applications and variants of the cuckoo search algorithm Appl. Soft Comput. J. 61 1041 1059 https://doi.org/10.1016/j.asoc.2017.02.034
B Selvakumar K Muneeswaran 2018 Firefly algorithm based feature selection for network intrusion detection Comput. Secur. https://doi.org/10.1016/j.cose.2018.11.005
Butler-Yeoman, T., Xue, B., Zhang, M.: Particle swarm optimisation for feature selection: a hybrid filter-wrapper approach. In: 2015 IEEE Congr. Evol. Comput. CEC 2015 - Proc., pp. 2428–2435, 2015, https://doi.org/10.1109/CEC.2015.7257186
ML Raymer TE Doom LA Kuhn WF Punch 2003 Knowledge discovery in medical and biological datasets using a hybrid bayes classifier/evolutionary algorithm IEEE Trans. Syst. Man Cybern. Part B Cybern. 33 5 802 813 https://doi.org/10.1109/TSMCB.2003.816922
BK Panigrahi VR Pandi S Das 2008 Adaptive particle swarm optimization approach for static and dynamic economic load dispatch Energy Convers. Manag. 49 1407 1415 https://doi.org/10.1016/j.enconman.2007.12.023
Y Xu Z Yang X Li H Kang X Yang 2020 Dynamic opposite learning enhanced teaching–learning-based optimization Knowl.-Based Syst. 188 104966https://doi.org/10.1016/j.knosys.2019.104966
MC Calzarossa P Giudici R Zieni 2023 Explainable machine learning for phishing feature detection Qual. Reliab. Eng. Int. https://doi.org/10.1002/qre.3411
Lu, Q., Zhu, L., Xu, X., Xing, Z., Harrer, S., Whittle, J.: Building the future of responsible AI: a reference architecture for designing large language model based agents, pp. 1–14, 2023, [Online]. Available: https://arxiv.org/abs/2311.13148v2
“Breast cancer.” https://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+(diagnostic)
A Marcano-Cedeño J Quintanilla-Domínguez D Andina 2011 WBCD breast cancer database classification applying artificial metaplasticity neural network Expert Syst. Appl. 38 8 9573 9579 https://doi.org/10.1016/j.eswa.2011.01.167
Q Huang H Ding M MehdiEffatparvar 2023 Breast cancer diagnosis based on hybrid squeezenet and improved chef-based optimizer Expert Syst. Appl. https://doi.org/10.1016/j.eswa.2023.121470
W Elmasry A Akbulut AH Zaim 2020 Evolving deep learning architectures for network intrusion detection using a double PSO metaheuristic Comput. Netw. https://doi.org/10.1016/j.comnet.2019.107042
E Hoz De La E Hoz De La A Ortiz J Ortega A Martínez-Álvarez 2014 Feature selection by multi-objective optimisation: application to network anomaly detection by hierarchical self-organising maps Knowl.-Based Syst. 71 322 338 https://doi.org/10.1016/j.knosys.2014.08.013
LK Singh M Khanna R Singh 2023 Artificial intelligence based medical decision support system for early and accurate breast cancer prediction Adv. Eng. Softw. https://doi.org/10.1016/j.advengsoft.2022.103338
A Kumar S Diwakar TB Ramachandra RD Chandramohan 2019 A study on metaheuristics approaches for gene selection in microarray data : algorithms, applications and open challenges Evol. Intell. https://doi.org/10.1007/s12065-019-00306-6