{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T13:36:05Z","timestamp":1770384965112,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Simple neural network classification tasks are based on performing extraction as transformations of the set simultaneously with optimization of weights on individual layers. In this paper, the <jats:italic>Representation 7<\/jats:italic> architecture is proposed, the primary assumption of which is to divide the inductive procedure into separate blocks \u2013 transformation and decision \u2013 which may lead to a better generalization ability of the presented model. Architecture is based on the processing context of the typical neural network and unifies datasets into a shared, generically sampled space. It can be applicable in the case of difficult problems \u2013 defined not as imbalance or streaming data but by low-class separability and a high dimensionality. This article has tested the hypothesis that \u2013 in such conditions \u2013 the proposed method could achieve better results than reference algorithms by comparing the R7 architecture with state-of-the-art methods, raw mlp and <jats:italic>Tabnet<\/jats:italic> architecture. The contributions of this work are the proposition of the new architecture and complete experiments on synthetic and real datasets with the evaluation of the quality and loss achieved by R7 and by reference methods.<\/jats:p>","DOI":"10.1007\/s10489-023-04878-w","type":"journal-article","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T01:02:22Z","timestamp":1692234142000},"page":"26050-26066","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Neural network architecture with intermediate distribution-driven layer for classification of multidimensional data with low class separability"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2426-9541","authenticated-orcid":false,"given":"Weronika","family":"Borek-Marciniec","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8395","authenticated-orcid":false,"given":"Pawel","family":"Ksieniewicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"issue":"1","key":"4878_CR1","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s11634-009-0037-8","volume":"3","author":"A Jamain","year":"2009","unstructured":"Jamain A, Hand DJ (2009) Where are the large and difficult datasets? ADAC 3(1):25\u201338","journal-title":"ADAC"},{"key":"4878_CR2","unstructured":"Dua D, Graff C (2017) UCI Machine Learning Repository. https:\/\/archive.ics.uci.edu\/ml. Accessed 15 Apr 2023"},{"key":"4878_CR3","doi-asserted-by":"crossref","unstructured":"Shand C, Allmendinger R, Handl J, Webb A, Keane J (2019) Evolving controllably difficult datasets for clustering. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp 463\u2013471","DOI":"10.1145\/3321707.3321761"},{"issue":"2","key":"4878_CR4","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.ijforecast.2020.07.007","volume":"37","author":"CS Bojer","year":"2021","unstructured":"Bojer CS, Meldgaard JP (2021) Kaggle forecasting competitions: An over-looked learning opportunity. Int J Forecast 37(2):587\u2013603","journal-title":"Int J Forecast"},{"key":"4878_CR5","first-page":"255","volume":"17","author":"J Derrac","year":"2015","unstructured":"Derrac J, Garcia S, Sanchez L, Herrera F (2015) Keel data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework. J Mult Valued Logic Soft Comput 17:255\u2013287","journal-title":"J Mult Valued Logic Soft Comput"},{"issue":"10","key":"4878_CR6","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1038\/s41592-021-01256-7","volume":"18","author":"BJ Heil","year":"2021","unstructured":"Heil BJ, Hoffman MM, Markowetz F, Lee S-I, Greene CS, Hicks SC (2021) Reproducibility standards for machine learning in the life sciences. Nat Methods 18(10):1132\u20131135","journal-title":"Nat Methods"},{"key":"4878_CR7","doi-asserted-by":"crossref","unstructured":"Komorniczak J, Zyblewski P, Ksieniewicz P (2021) Prior probability estimation in dynamically imbalanced data streams. In: 2021 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1\u20137","DOI":"10.1109\/IJCNN52387.2021.9533795"},{"key":"4878_CR8","doi-asserted-by":"publisher","first-page":"109380","DOI":"10.1016\/j.knosys.2022.109380","volume":"252","author":"J Komorniczak","year":"2022","unstructured":"Komorniczak J, Zyblewski P, Ksieniewicz P (2022) Statistical drift detection ensemble for batch processing of data streams. Knowl-Based Syst 252:109380","journal-title":"Knowl-Based Syst"},{"issue":"5","key":"4878_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3347711","volume":"52","author":"AC Lorena","year":"2019","unstructured":"Lorena AC, Garcia LP, Lehmann J, Souto MC, Ho TK (2019) How complex is your classification problem? a survey on measuring classification complexity. ACM Comput Surv (CSUR) 52(5):1\u201334","journal-title":"ACM Comput Surv (CSUR)"},{"key":"4878_CR10","doi-asserted-by":"crossref","unstructured":"Assefa SA, Dervovic D, Mahfouz M, Tillman RE, Reddy P, Veloso M (2020) Generating synthetic data in finance: opportunities, challenges and pitfalls. In: Proceedings of the First ACM International Conference on AI in Finance, pp 1\u20138","DOI":"10.1145\/3383455.3422554"},{"key":"4878_CR11","doi-asserted-by":"crossref","unstructured":"Ardabili S, Mosavi A, V\u00e1rkonyi-K\u00f3czy AR (2020) Advances in machine learning modeling reviewing hybrid and ensemble methods. In: International Conference on Global Research and Education, Springer, pp 215\u2013227","DOI":"10.1007\/978-3-030-36841-8_21"},{"issue":"6","key":"4878_CR12","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1037\/h0071325","volume":"24","author":"H Hotelling","year":"1933","unstructured":"Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417","journal-title":"J Educ Psychol"},{"key":"4878_CR13","doi-asserted-by":"publisher","first-page":"100378","DOI":"10.1016\/j.cosrev.2021.100378","volume":"40","author":"F Anowar","year":"2021","unstructured":"Anowar F, Sadaoui S, Selim B (2021) Conceptual and empirical comparison of dimensionality reduction algorithms (pca, kpca, lda, mds, svd, lle, isomap, le, ica, t-sne). Comput Sci Rev 40:100378","journal-title":"Comput Sci Rev"},{"issue":"4","key":"4878_CR14","doi-asserted-by":"publisher","first-page":"104","DOI":"10.3390\/computation8040104","volume":"8","author":"LAS Cardona","year":"2020","unstructured":"Cardona LAS, Vargas-Cardona HD, Navarro Gonz\u00e1lez P, Cardenas Pe\u00f1a DA, Orozco Guti\u00e9rrez \u00c1\u00c1 (2020) Classification of categorical data based on the chi-square dissimilarity and t-sne. Computation 8(4):104","journal-title":"Computation"},{"key":"4878_CR15","unstructured":"Liu C, Gao C, Xia X, Lo D, Grundy J, Yang X (2020) On the replicability and reproducibility of deep learning in software engineering. arXiv preprint arXiv:2006.14244"},{"issue":"4","key":"4878_CR16","doi-asserted-by":"publisher","first-page":"2236","DOI":"10.1214\/18-AOS1746","volume":"47","author":"M Gerber","year":"2019","unstructured":"Gerber M, Chopin N, Whiteley N (2019) Negative association, ordering and convergence of resampling methods. Ann Stat 47(4):2236\u20132260","journal-title":"Ann Stat"},{"key":"4878_CR17","doi-asserted-by":"crossref","unstructured":"Borek W, Ksieniewicz P (2022) Inductive parallel learning for multiple classification problems. In: 2022 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN55064.2022.9892319"},{"issue":"1","key":"4878_CR18","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/TEVC.2021.3099289","volume":"26","author":"N Zhang","year":"2021","unstructured":"Zhang N, Gupta A, Chen Z, Ong Y-S (2021) Evolutionary machine learning with minions: A case study in feature selection. IEEE Trans Evol Comput 26(1):130\u2013144","journal-title":"IEEE Trans Evol Comput"},{"issue":"7","key":"4878_CR19","first-page":"3614","volume":"44","author":"S Vandenhende","year":"2021","unstructured":"Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L (2021) Multi-task learning for dense prediction tasks: A survey. IEEE Trans Pattern Anal Mach Intell 44(7):3614\u20133633","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4878_CR20","doi-asserted-by":"crossref","unstructured":"Hu R, Singh A (2021) Unit: Multimodal multitask learning with a unified transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1439\u20131449","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"4878_CR21","unstructured":"Lin X, Zhen H-L, Li Z, Zhang Q-F, Kwong S (2019) Pareto multi-task learning. Advances in neural information processing systems 32"},{"key":"4878_CR22","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac PH, Healy G, Smeaton AF (2020) Contrastive representation learning: A framework and review. IEEE Access 8:193907\u2013193934","journal-title":"IEEE Access"},{"key":"4878_CR23","doi-asserted-by":"crossref","unstructured":"Hinton GE (1990) Connectionist learning procedures, 555\u2013610","DOI":"10.1136\/jcp.43.7.610-b"},{"key":"4878_CR24","doi-asserted-by":"crossref","unstructured":"James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning (Vol. 112, p. 18). New York: springer.","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"4878_CR25","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li Z, Liu F, Yang W, Peng S, Zhou J (2021) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst 33:6999\u20137019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4878_CR26","first-page":"23928","volume":"34","author":"A Kadra","year":"2021","unstructured":"Kadra A, Lindauer M, Hutter F, Grabocka J (2021) Well-tuned simple nets excel on tabular datasets. Adv Neural Inf Proces Syst 34:23928\u201323941","journal-title":"Adv Neural Inf Proces Syst"},{"issue":"3","key":"4878_CR27","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1177\/1473871620909485","volume":"19","author":"M Espadoto","year":"2020","unstructured":"Espadoto M, Hirata NST, Telea AC (2020) Deep learning multidimensional projections. Inf Vis 19(3):247\u2013269","journal-title":"Inf Vis"},{"key":"4878_CR28","doi-asserted-by":"crossref","unstructured":"Khalid S, Khalil T, Nasreen S (2014) A survey of feature selection and feature extraction techniques in machine learning. In: 2014 Science and Information Conference, IEEE, pp 372\u2013378","DOI":"10.1109\/SAI.2014.6918213"},{"key":"4878_CR29","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.7717\/peerj-cs.1061","volume":"8","author":"J Zheng","year":"2022","unstructured":"Zheng J, Qu H, Li Z, Li L, Tang X, Guo F (2022) A novel autoencoder approach to feature extraction with linear separability for high-dimensional data. PeerJ Comput Sci 8:1061","journal-title":"PeerJ Comput Sci"},{"issue":"6","key":"4878_CR30","first-page":"734","volume":"26","author":"M Topolski","year":"2020","unstructured":"Topolski M (2020) The modified principal component analysis feature extraction method for the task of diagnosing chronic lymphocytic leukemia type b-cll. J Univ Comput Sci 26(6):734\u2013746","journal-title":"J Univ Comput Sci"},{"issue":"1","key":"4878_CR31","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1166\/jctn.2020.8648","volume":"17","author":"M Sewak","year":"2020","unstructured":"Sewak M, Sahay SK, Rathore H (2020) An overview of deep learning architecture of deep neural networks and autoencoders. J Comput Theor Nanosci 17(1):182\u2013188","journal-title":"J Comput Theor Nanosci"},{"key":"4878_CR32","unstructured":"Guyon I (2003) Design of experiments of the nips 2003 variable selection benchmark. In: NIPS 2003 Workshop on Feature Extraction and Feature Selection 253:40"},{"key":"4878_CR33","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 (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"4878_CR34","doi-asserted-by":"publisher","first-page":"6679","DOI":"10.1609\/aaai.v35i8.16826","volume":"35","author":"S\u00d6 Arik","year":"2021","unstructured":"Arik S\u00d6, Pfister T (2021) Tabnet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence 35:6679\u20136687","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04878-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-04878-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04878-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T14:28:34Z","timestamp":1698071314000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-04878-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":34,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["4878"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-04878-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,17]]},"assertion":[{"value":"7 July 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}