{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:04:20Z","timestamp":1770354260880,"version":"3.49.0"},"reference-count":34,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T00:00:00Z","timestamp":1648080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Fully connected (FC) layers are used in almost all neural network architectures ranging from multilayer perceptrons to deep neural networks. FC layers allow any kind of symmetric\/asymmetric interaction between features without making any assumption about the structure of the data. However, success of convolutional and recursive layers and findings of many studies have proven that the intrinsic structure of a dataset holds a great potential to improve the success of a classification problem. Leveraging clustering to explore and exploit this intrinsic structure in classification problems has been the subject of various studies. In this paper, we propose a new training pipeline for fully connected layers which enables them to make more accurate classification predictions. The proposed method aims to reflect the clustering patterns in the original feature space of the training dataset to the transformed feature space created by the FC layer. In this way, we intend to enhance the representation ability of the extracted features and accordingly increase the classification accuracy. The Fuzzy C-Means algorithm is employed in this study as the clustering tool. To evaluate the performance of the proposed method, 11 experiments were conducted on 9 benchmark UCI datasets. Empirical results show that the proposed method works well in practice and gives higher classification accuracies compared to a regular FC layer in most datasets.<\/jats:p>","DOI":"10.3390\/sym14040658","type":"journal-article","created":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T23:31:43Z","timestamp":1648164703000},"page":"658","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Improving Classification Performance of Fully Connected Layers by Fuzzy Clustering in Transformed Feature Space"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5706-6455","authenticated-orcid":false,"given":"Tolga Ahmet","family":"Kalayc\u0131","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering, Istanbul Technical University, Ma\u00e7ka, \u0130stanbul 34367, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0838-1421","authenticated-orcid":false,"given":"Umut","family":"Asan","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Istanbul Technical University, Ma\u00e7ka, \u0130stanbul 34367, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1007\/s10115-021-01572-6","article-title":"A study on using data clustering for feature extraction to improve the quality of classification","volume":"63","author":"Piernik","year":"2021","journal-title":"Knowl. Inf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s40708-016-0056-0","article-title":"Fuzzy clustering-based feature extraction method for mental task classification","volume":"4","author":"Gupta","year":"2017","journal-title":"Brain Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1177\/0954410016638874","article-title":"A novel method for spacecraft electrical fault detection based on FCM clustering and WPSVM classification with PCA feature extraction","volume":"231","author":"Li","year":"2017","journal-title":"Proc. Inst. Mech. Eng. Part G J. Aerosp. Eng."},{"key":"ref_4","unstructured":"Srivastava, S., Kawaguchi, K., and Rajan, V. (2022). ExpertNet: A Symbiosis of Classification and Clustering. arXiv."},{"key":"ref_5","first-page":"6487","article-title":"A new fuzzy cluster-aware regularization of neural networks","volume":"39","author":"Kalayci","year":"2020","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1016\/j.patcog.2008.11.029","article-title":"A simultaneous learning framework for clustering and classification","volume":"42","author":"Cai","year":"2009","journal-title":"Pattern Recognit."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TNN.2009.2034741","article-title":"A multiobjective simultaneous learning framework for clustering and classification","volume":"21","author":"Cai","year":"2010","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.1016\/j.patcog.2011.11.027","article-title":"Simultaneous clustering and classification over cluster structure representation","volume":"45","author":"Qian","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.neucom.2015.02.084","article-title":"A new incremental neural network for simultaneous clustering and classification","volume":"169","author":"Hebboul","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.isprsjprs.2020.01.015","article-title":"Collaborative learning of lightweight convolutional neural network and deep clustering for hyperspectral image semi-supervised classification with limited training samples","volume":"161","author":"Fang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_11","unstructured":"Sellars, P., Aviles-Rivero, A., and Sch\u00f6nlieb, C.B. (2020). Two Cycle Learning: Clustering Based Regularisation for Deep Semi-Supervised Classification. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2150036","DOI":"10.1142\/S0218126621500365","article-title":"Imbalanced Data Classification Algorithm Based on Clustering and SVM","volume":"30","author":"Huang","year":"2021","journal-title":"J. Circuits Syst. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chaudhuri, U., Chaudhuri, S., and Chaudhuri, S. (2020, January 10\u201315). GuCNet: A guided clustering-based network for improved classification. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412344"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"108440","DOI":"10.1016\/j.patcog.2021.108440","article-title":"Semantic clustering based deduction learning for image recognition and classification","volume":"124","author":"Ma","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to Deep Learning","volume":"25","author":"Green","year":"2019","journal-title":"Nat. Med."},{"key":"ref_16","unstructured":"Reza Bosagh Zadeh, B.R. (2021, November 14). 4. Fully Connected Deep Networks\u2014TensorFlow for Deep Learning. Available online: https:\/\/www.oreilly.com\/library\/view\/tensorflow-for-deep\/9781491980446\/ch04.html."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.procs.2016.03.014","article-title":"Performance Analysis of Various Fuzzy Clustering Algorithms: A Review","volume":"79","author":"Gosain","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/3477.809032","article-title":"A survey of fuzzy clustering algorithms for pattern recognition\u2014Part I","volume":"29","author":"Baraldi","year":"1999","journal-title":"IEEE Trans. Syst. Man Cybern. Part B Cybern."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/MCI.2018.2881643","article-title":"Fuzzy clustering: A historical perspective","volume":"14","author":"Ruspini","year":"2019","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_20","first-page":"876361","article-title":"Comparison of Fuzzy Clustering Methods and Their Applications to Geophysics Data","volume":"2009","author":"Miller","year":"2009","journal-title":"Appl. Comput. Intell. Soft Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Almeida, R.J., and Sousa, J.M.C. (2006, January 7\u20139). Comparison of fuzzy clustering algorithms for classification. Proceedings of the 2006 International Symposium on Evolving Fuzzy Systems, Ambelside, UK.","DOI":"10.1109\/ISEFS.2006.251138"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3565","DOI":"10.3233\/JIFS-169534","article-title":"A comparison of fuzzy clustering algorithms for bearing fault diagnosis","volume":"34","author":"Li","year":"2018","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ross, T.J. (2010). Fuzzy Logic with Engineering Applications, John Wiley & Sons Ltd.. [3rd ed.].","DOI":"10.1002\/9781119994374"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6292","DOI":"10.1016\/j.eswa.2011.11.063","article-title":"Effective fuzzy c-means clustering algorithms for data clustering problems","volume":"39","author":"Kannan","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1364\/JOSAA.33.001207","article-title":"Enhanced manifold regularization for semi-supervised classification","volume":"33","author":"Gan","year":"2016","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.neucom.2012.08.020","article-title":"Using clustering analysis to improve semi-supervised classification","volume":"101","author":"Gan","year":"2013","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.neucom.2014.06.059","article-title":"Semi-supervised classification learning by discrimination-aware manifold regularization","volume":"147","author":"Wang","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_28","unstructured":"Dua, D., and Graff, C. (2022, January 31). UCI Machine Learning Repository. Available online: http:\/\/archive.ics.uci.edu\/ml."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.ins.2018.04.080","article-title":"On using supervised clustering analysis to improve classification performance","volume":"454\u2013455","author":"Gan","year":"2018","journal-title":"Inf. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.csda.2018.08.015","article-title":"Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification","volume":"131","author":"Abpeykar","year":"2019","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_31","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Greg, S., Corrado, A.D., Dean, J., and Devin, M. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. arXiv."},{"key":"ref_32","first-page":"16","article-title":"Fuzzy C-means in high dimensional spaces","volume":"1","author":"Winkler","year":"2011","journal-title":"Int. J. Fuzzy Syst. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.paid.2016.06.069","article-title":"Effect size guidelines for individual differences researchers","volume":"102","author":"Gignac","year":"2016","journal-title":"Pers. Individ. Dif."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1177\/2515245919847202","article-title":"Evaluating Effect Size in Psychological Research: Sense and Nonsense","volume":"2","author":"Funder","year":"2019","journal-title":"Adv. Methods Pract. Psychol. Sci."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/4\/658\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:42:06Z","timestamp":1760136126000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/4\/658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,24]]},"references-count":34,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["sym14040658"],"URL":"https:\/\/doi.org\/10.3390\/sym14040658","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,24]]}}}