{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T04:02:10Z","timestamp":1749528130593,"version":"3.41.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04049-3","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T11:28:45Z","timestamp":1749468525000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Data Augmentation Affects Evolutionary Algorithms in Feature Selection: An Experimental Study"],"prefix":"10.1007","volume":"6","author":[{"given":"Emanuele","family":"Nardone","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiziana","family":"D\u2019Alessandro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio","family":"De Stefano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3242-0179","authenticated-orcid":false,"given":"Francesco","family":"Fontanella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"4049_CR1","doi-asserted-by":"crossref","unstructured":"Cordella LP, De\u00a0Stefano C, Fontanella F, Scotto Di\u00a0Freca A. A weighted majority vote strategy using Bayesian networks. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics) 8157 LNCS(PART 2). 2013. pp. 219\u201328.","DOI":"10.1007\/978-3-642-41184-7_23"},{"key":"4049_CR2","doi-asserted-by":"crossref","unstructured":"De\u00a0Stefano C, Fontanella F, Folino G, Scotto Di\u00a0Freca A. A Bayesian approach for combining ensembles of gp classifiers. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics) 6713 LNCS. 2011. pp. 26\u201335.","DOI":"10.1007\/978-3-642-21557-5_5"},{"key":"4049_CR3","doi-asserted-by":"crossref","unstructured":"De\u00a0Stefano C, Fontanella F, Scotto Di\u00a0Freca A. A novel Naive Bayes voting strategy for combining classifiers. In: 2012 international conference on frontiers in handwriting recognition. 2012. pp. 467\u201372.","DOI":"10.1109\/ICFHR.2012.166"},{"key":"4049_CR4","doi-asserted-by":"crossref","unstructured":"Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, Liu H. Feature selection: a data perspective. ACM Comput Surv. 2017;50(6).","DOI":"10.1145\/3136625"},{"issue":"1","key":"4049_CR5","first-page":"3","volume":"19","author":"B Venkatesh","year":"2019","unstructured":"Venkatesh B, Anuradha J. A review of feature selection and its methods. Cybern Inf Technol. 2019;19(1):3\u201326.","journal-title":"Cybern Inf Technol"},{"key":"4049_CR6","doi-asserted-by":"crossref","unstructured":"Cilia ND, De\u00a0Stefano C, Fontanella F, Freca A. Variable-length representation for ec-based feature selection in high-dimensional data. In: Applications of evolutionary computation: 22nd international conference, evoapplications 2019, held as part of EvoStar 2019, Leipzig, Germany, April 24\u201326, 2019, Proceedings 22. Springer; 2019. pp. 325\u201340.","DOI":"10.1007\/978-3-030-16692-2_22"},{"issue":"4","key":"4049_CR7","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1109\/TEVC.2015.2504420","volume":"20","author":"B Xue","year":"2016","unstructured":"Xue B, Zhang M, Browne WN, Yao X. A survey on evolutionary computation approaches to feature selection. IEEE Trans Evol Comput. 2016;20(4):606\u201326.","journal-title":"IEEE Trans Evol Comput"},{"key":"4049_CR8","doi-asserted-by":"crossref","unstructured":"De\u00a0Falco I, Tarantino E, Della\u00a0Cioppa A, Fontanella F. A novel grammar-based genetic programming approach to clustering. In: Proceedings of the 2005 ACM symposium on applied computing. 2005. pp. 928\u201332.","DOI":"10.1145\/1066677.1066891"},{"key":"4049_CR9","doi-asserted-by":"crossref","unstructured":"De\u00a0Falco I, Tarantino E, Della\u00a0Cioppa A, Fontanella F. An innovative approach to genetic programming\u2013based clustering. In: Applied soft computing technologies: the challenge of complexity. Springer; 2006. pp. 55\u201364.","DOI":"10.1007\/3-540-31662-0_4"},{"key":"4049_CR10","first-page":"285","volume-title":"A GA-based feature selection algorithm for remote sensing images","author":"C De Stefano","year":"2008","unstructured":"De Stefano C, Fontanella F, Marrocco C. A GA-based feature selection algorithm for remote sensing images. Berlin: Springer; 2008. p. 285\u201394."},{"key":"4049_CR11","doi-asserted-by":"crossref","unstructured":"Cordella LP, De\u00a0Stefano C, Fontanella F, Marrocco C, Freca A. Combining single class features for improving performance of a two stage classifier. In: 20th international conference on pattern recognition (ICPR 2010). IEEE Computer Society. 2010. pp. 4352\u20135.","DOI":"10.1109\/ICPR.2010.1058"},{"key":"4049_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119062","volume":"641","author":"A-D Li","year":"2023","unstructured":"Li A-D, Xue B, Zhang M. Multi-objective particle swarm optimization for key quality feature selection in complex manufacturing processes. Inf Sci. 2023;641: 119062.","journal-title":"Inf Sci"},{"key":"4049_CR13","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.asoc.2013.09.018","volume":"18","author":"B Xue","year":"2014","unstructured":"Xue B, Zhang M, Browne WN. Particle swarm optimisation for feature selection in classification: novel initialisation and updating mechanisms. Appl Soft Comput. 2014;18:261\u201376.","journal-title":"Appl Soft Comput"},{"key":"4049_CR14","doi-asserted-by":"publisher","unstructured":"Al-Yaseen WL, Idrees AK, Almasoudy FH. Wrapper feature selection method based differential evolution and extreme learning machine for intrusion detection system. Pattern Recognit. 2022;132:108912. https:\/\/doi.org\/10.1016\/j.patcog.2022.108912.","DOI":"10.1016\/j.patcog.2022.108912"},{"issue":"7","key":"4049_CR15","doi-asserted-by":"publisher","first-page":"4579","DOI":"10.1109\/TCYB.2021.3128540","volume":"53","author":"P Wang","year":"2023","unstructured":"Wang P, Xue B, Liang J, Zhang M. Multiobjective differential evolution for feature selection in classification. IEEE Trans Cybern. 2023;53(7):4579\u201393. https:\/\/doi.org\/10.1109\/TCYB.2021.3128540.","journal-title":"IEEE Trans Cybern"},{"key":"4049_CR16","volume-title":"Deep learning. Adaptive computation and machine learning series","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning. Adaptive computation and machine learning series. Cambridge: MIT Press; 2016."},{"key":"4049_CR17","volume-title":"Deep learning for computer vision: expert techniques to train advanced neural networks using TensorFlow and Keras","author":"R Shanmugamani","year":"2018","unstructured":"Shanmugamani R, Moore SM. Deep learning for computer vision: expert techniques to train advanced neural networks using TensorFlow and Keras. Birmingham: Packt Publishing; 2018."},{"key":"4049_CR18","volume-title":"Feature engineering for machine learning: principles and techniques for data scientists","author":"A Zheng","year":"2018","unstructured":"Zheng A, Casari A. Feature engineering for machine learning: principles and techniques for data scientists. 1st ed. Sebastopol: O\u2019Reilly Media Inc; 2018.","edition":"1"},{"key":"4049_CR19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-031-02462-7_22","volume-title":"Applications of evolutionary computation","author":"S Pereira","year":"2022","unstructured":"Pereira S, Correia J, Machado P. Evolving data augmentation strategies. In: Jim\u00e9nez Laredo JL, Hidalgo JI, Babaagba KO, editors. Applications of evolutionary computation. Cham: Springer; 2022. p. 337\u201351."},{"key":"4049_CR20","doi-asserted-by":"crossref","unstructured":"Mertes S, Baird A, Schiller D, Schuller BW, Andr\u00e9 E. An evolutionary-based generative approach for audio data augmentation. In: 2020 IEEE 22nd international workshop on multimedia signal processing (MMSP). 2020. pp. 1\u20136.","DOI":"10.1109\/MMSP48831.2020.9287156"},{"key":"4049_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2022.105937","volume":"146","author":"X Zhang","year":"2022","unstructured":"Zhang X, Yu L, Yin H, Lai KK. Integrating data augmentation and hybrid feature selection for small sample credit risk assessment with high dimensionality. Comput Oper Res. 2022;146: 105937.","journal-title":"Comput Oper Res"},{"key":"4049_CR22","doi-asserted-by":"crossref","unstructured":"Daniel T, Casenave F, Akkari N, Ryckelynck D. Data augmentation and feature selection for automatic model recommendation in computational physics. Math Comput Appl. 2021;26(1).","DOI":"10.3390\/mca26010017"},{"key":"4049_CR23","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/978-3-031-56852-7_25","volume-title":"Applications of evolutionary computation","author":"T D\u2019Alessandro","year":"2024","unstructured":"D\u2019Alessandro T, De Stefano C, Fontanella F, Nardone E. Integrating data augmentation in evolutionary algorithms for feature selection: a preliminary study. In: Smith S, Correia J, Cintrano C, editors. Applications of evolutionary computation. Cham: Springer; 2024. p. 397\u2013412."},{"key":"4049_CR24","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/A:1012487302797","volume":"46","author":"I Guyon","year":"2002","unstructured":"Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. J Mach Learn Res. 2002;46:389\u2013422.","journal-title":"J Mach Learn Res"},{"key":"4049_CR25","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-540-77226-2_19","volume-title":"Intelligent Data engineering and automated learning\u2014IDEAL 2007","author":"N S\u00e1nchez-Maro\u00f1o","year":"2007","unstructured":"S\u00e1nchez-Maro\u00f1o N, Alonso-Betanzos A, Tombilla-Sanrom\u00e1n M. Filter methods for feature selection\u2014a comparative study. In: Yin H, Tino P, Corchado E, Byrne W, Yao X, editors. Intelligent Data engineering and automated learning\u2014IDEAL 2007. Berlin, Heidelberg: Springer; 2007. p. 178\u201387."},{"key":"4049_CR26","doi-asserted-by":"crossref","unstructured":"Jain R, Ramakrishnan A. Modality-specific feature selection, data augmentation and temporal context for improved performance in sleep staging. IEEE J Biomed Health Inform. 2023.","DOI":"10.1109\/JBHI.2023.3339713"},{"issue":"1","key":"4049_CR27","doi-asserted-by":"publisher","first-page":"204","DOI":"10.3390\/s22010204","volume":"22","author":"P Zhao","year":"2021","unstructured":"Zhao P, Zheng Q, Ding Z, Zhang Y, Wang H, Yang Y. A high-dimensional and small-sample submersible fault detection method based on feature selection and data augmentation. Sensors. 2021;22(1):204.","journal-title":"Sensors"},{"issue":"18","key":"4049_CR28","doi-asserted-by":"publisher","first-page":"6750","DOI":"10.3390\/en16186750","volume":"16","author":"S Pohlmann","year":"2023","unstructured":"Pohlmann S, Mashayekh A, Kuder M, Neve A, Weyh T. Data augmentation and feature selection for the prediction of the state of charge of lithium-ion batteries using artificial neural networks. Energies. 2023;16(18):6750.","journal-title":"Energies"},{"key":"4049_CR29","doi-asserted-by":"crossref","unstructured":"Fujita K, Kobayashi M, Nagao T. Data augmentation using evolutionary image processing. In: 2018 digital image computing: techniques and applications (DICTA). 2018. pp. 1\u20136.","DOI":"10.1109\/DICTA.2018.8615799"},{"key":"4049_CR30","doi-asserted-by":"crossref","unstructured":"Mehta K, Kobti Z, Pfaff K, Fox S. Data augmentation using ca evolved gans. In: 2019 IEEE symposium on computers and communications (ISCC). 2019. pp. 1087\u201392.","DOI":"10.1109\/ISCC47284.2019.8969638"},{"key":"4049_CR31","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-031-50320-7_12","volume-title":"Dynamics of information systems","author":"ST Marc","year":"2024","unstructured":"Marc ST, Belavkin R, Windridge D, Gao X. An evolutionary approach to automated class-specific data augmentation for image classification. In: Moosaei H, Hlad\u00edk M, Pardalos PM, editors. Dynamics of information systems. Cham: Springer; 2024. p. 170\u201385."},{"key":"4049_CR32","doi-asserted-by":"crossref","unstructured":"Velasco JM, Garnica O, Contador S, Lanchares J, Maqueda E, Botella M, Hidalgo JI. Data augmentation and evolutionary algorithms to improve the prediction of blood glucose levels in scarcity of training data. In: 2017 IEEE congress on evolutionary computation (CEC). 2017. pp. 2193\u2013200.","DOI":"10.1109\/CEC.2017.7969570"},{"key":"4049_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2022.101173","volume":"75","author":"Z Liu","year":"2022","unstructured":"Liu Z, Wang H. A data augmentation based kriging-assisted reference vector guided evolutionary algorithm for expensive dynamic multi-objective optimization. Swarm Evol Comput. 2022;75: 101173.","journal-title":"Swarm Evol Comput"},{"key":"4049_CR34","first-page":"2171","volume":"13","author":"F-A Fortin","year":"2012","unstructured":"Fortin F-A, De Rainville F-M, Gardner M-A, Parizeau M, Gagn\u00e9 C. DEAP: evolutionary algorithms made easy. J Mach Learn Res. 2012;13:2171\u20135.","journal-title":"J Mach Learn Res"},{"key":"4049_CR35","doi-asserted-by":"crossref","unstructured":"Cilia ND, De\u00a0Stefano C, Fontanella F, Molinara M, Scotto Di\u00a0Freca A. Handwriting analysis to support Alzheimer\u2019s disease diagnosis: a preliminary study. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics) 11679 LNCS. 2019. pp. 143\u201351.","DOI":"10.1007\/978-3-030-29891-3_13"},{"key":"4049_CR36","doi-asserted-by":"publisher","unstructured":"Cole R, Fanty M. ISOLET. UCI machine learning repository. 1994. https:\/\/doi.org\/10.24432\/C51G69.","DOI":"10.24432\/C51G69"},{"key":"4049_CR37","doi-asserted-by":"publisher","unstructured":"Duin R. Multiple features. UCI machine learning repository. https:\/\/doi.org\/10.24432\/C5HC70.","DOI":"10.24432\/C5HC70"},{"key":"4049_CR38","doi-asserted-by":"publisher","unstructured":"Zhang K, Fan W, Yuan X. Ozone Level Detection. UCI machine learning repository. 2008. https:\/\/doi.org\/10.24432\/C5NG6W.","DOI":"10.24432\/C5NG6W"},{"key":"4049_CR39","doi-asserted-by":"crossref","unstructured":"Gul S, Rahim F, Isin S, Yilmaz F, Ozturk N, Turkay M, Kavakli IH. Structure-based design and classifications of small molecules regulating the circadian rhythm period. Sci Rep. 2021;11.","DOI":"10.1038\/s41598-021-97962-5"},{"key":"4049_CR40","unstructured":"Herrera CM, MM. CNAE-9 Dataset. 2007. https:\/\/archive.ics.uci.edu\/ml\/datasets\/CNAE-9."},{"issue":"26","key":"4049_CR41","doi-asserted-by":"publisher","first-page":"15149","DOI":"10.1073\/pnas.211566398","volume":"98","author":"S Ramaswamy","year":"2001","unstructured":"Ramaswamy S, Tamayo P, Rifkin R, Mukherjee S, Yeang C-H, Angelo M, Ladd C, Reich M, Latulippe E, Mesirov JP, et al. Multiclass cancer diagnosis using tumor gene expression signatures. Proc Natl Acad Sci. 2001;98(26):15149\u201354.","journal-title":"Proc Natl Acad Sci"},{"issue":"9306","key":"4049_CR42","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/S0140-6736(02)07746-2","volume":"359","author":"EF Petricoin","year":"2002","unstructured":"Petricoin EF, Ardekani AM, Hitt BA, Levine PJ, Fusaro VA, Steinberg SM, Mills GB, Simone C, Fishman DA, Kohn EC, et al. Use of proteomic patterns in serum to identify ovarian cancer. Lancet. 2002;359(9306):572\u20137.","journal-title":"Lancet"},{"key":"4049_CR43","unstructured":"Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL. A public domain dataset for human activity recognition using smartphones. In: 21st European symposium on artificial neural networks, computational intelligence and machine learning, ESANN. 2013."},{"key":"4049_CR44","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining. 2019.","DOI":"10.1145\/3292500.3330701"},{"key":"4049_CR45","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04049-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T11:29:00Z","timestamp":1749468540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04049-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":45,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["4049"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04049-3","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]},"assertion":[{"value":"19 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"536"}}