{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T06:58:26Z","timestamp":1763017106467,"version":"build-2065373602"},"reference-count":55,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2011,4,28]],"date-time":"2011-04-28T00:00:00Z","timestamp":1303948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Classification is one of the data mining problems receiving enormous attention in the database community. Although artificial neural networks (ANNs) have been successfully applied in a wide range of machine learning applications, they are however often regarded as black boxes, i.e., their predictions cannot be explained. To enhance the explanation of ANNs, a novel algorithm to extract symbolic rules from ANNs has been proposed in this paper. ANN methods have not been effectively utilized for data mining tasks because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by human experts. With the proposed approach, concise symbolic rules with high accuracy, that are easily explainable, can be extracted from the trained ANNs. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the accuracy. The effectiveness of the proposed approach is clearly demonstrated by the experimental results on a set of benchmark data mining classification problems.<\/jats:p>","DOI":"10.3390\/s110504622","type":"journal-article","created":{"date-parts":[[2011,4,28]],"date-time":"2011-04-28T10:20:20Z","timestamp":1303986020000},"page":"4622-4647","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["A New Data Mining Scheme Using Artificial Neural Networks"],"prefix":"10.3390","volume":"11","author":[{"given":"S. M.","family":"Kamruzzaman","sequence":"first","affiliation":[{"name":"Department of Electronics Engineering, Hankuk University of Foreign Studies, 89 Wangsan-ri, Mohyeon-myon, Yongin-si, Kyonggi-do, 449-791, Korea"}]},{"given":"A. M. Jehad","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Department of Digital Information Engineering, Hankuk University of Foreign Studies, 89 Wangsan-ri, Mohyeon-myon, Yongin-si, Kyonggi-do, 449-791, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2011,4,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, L, and Sui, TZ (2007, January 21\u201325). Application of data mining technology based on neural network in the engineering. Shanghai, China.","DOI":"10.1109\/WICOM.2007.1358"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Nirkhi, S (2010, January 26\u201328). Potential use of artificial neural network in data mining. Singapore.","DOI":"10.1109\/ICCAE.2010.5451537"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0950-7051(96)81920-4","article-title":"Survey and critique of techniques for extracting rules from trained artificial neural networks","volume":"8","author":"Andrews","year":"1995","journal-title":"Knowl. Based Syst"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1162\/neco.1997.9.1.205","article-title":"Extracting rules from neural networks by pruning and hidden-unit splitting","volume":"9","author":"Setiono","year":"1997","journal-title":"Neural Comput"},{"key":"ref_5","unstructured":"Darbari, A Rule Extraction from Trained ANN: A Survey, Technical Report;."},{"key":"ref_6","unstructured":"Biryulev, C, Yakymiv, Y, and Selemonavichus, A (2010, January 20\u201323). Research of artificial neural networks usage in data mining and semantic integration. Lviv, Ukraine."},{"key":"ref_7","first-page":"381","article-title":"Research of data mining based on neural networks","volume":"39","author":"Ni","year":"2008","journal-title":"World Academy Sci Eng Tech"},{"key":"ref_8","first-page":"427","article-title":"Neural networks in data mining","volume":"49","author":"Vesely","year":"2003","journal-title":"Agric. Econ"},{"key":"ref_9","first-page":"37","article-title":"Neural networks in data mining","volume":"5","author":"Singh","year":"2009","journal-title":"J. Theo. and App. Inf. Tech"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1287\/mnsc.49.3.312.12739","article-title":"Using neural network rule extraction and decision tables for credit-risk evaluation","volume":"49","author":"Baesens","year":"2003","journal-title":"Manage. Sci"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1162\/0899766053630350","article-title":"Rule extraction from recurrent neural networks: A taxonomy and review","volume":"17","author":"Jacobsson","year":"2005","journal-title":"Neural Comput"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1016\/j.eswa.2007.11.024","article-title":"Rule extraction from trained adaptive neural networks using artificial immune systems","volume":"36","author":"Kahramanli","year":"2009","journal-title":"Expert Syst. Appl"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.ejor.2007.09.022","article-title":"A note on knowledge discovery using neural networks and its application to credit screening","volume":"192","author":"Setiono","year":"2009","journal-title":"Eur. J. Operation. Res"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1109\/72.728352","article-title":"The truth will come to light: Directions and challenges in extracting the knowledge embedded within trained artificial neural networks","volume":"9","author":"Tickle","year":"1998","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1023\/A:1008307919726","article-title":"FERNN: An algorithm for fast extraction of rules from neural networks","volume":"12","author":"Setiono","year":"2000","journal-title":"Appl. Intell"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1109\/2.485895","article-title":"Symbolic representation of neural networks","volume":"29","author":"Setiono","year":"1996","journal-title":"IEEE Comput"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"020","DOI":"10.1016\/j.neunet.2008.01.003","article-title":"Greedy rule generation from discrete data and its use in neural network rule extraction","volume":"21","author":"Odajima","year":"2008","journal-title":"Neural Netw"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1109\/69.553163","article-title":"Effective data mining using neural networks","volume":"8","author":"Setiono","year":"1996","journal-title":"IEEE Trans. Knowl. Data En"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0167-739X(97)00022-8","article-title":"Using neural networks for data mining","volume":"13","author":"Craven","year":"1997","journal-title":"Future Gener. Comput. Syt"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Anbananthen, SK, Sainarayanan, G, Chekima, A, and Teo, J (2006, January 24\u201328). Data mining using pruned artificial neural network tree (ANNT). Damascus, Syria.","DOI":"10.1109\/CCSP.2005.4977180"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Saito, K, and Nakano, R (1988, January 24\u201327). Medical diagnosis expert system based on PDP model. San Diego, CA, USA.","DOI":"10.1109\/ICNN.1988.23855"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/BF00993103","article-title":"Extracting refined rules from knowledge-based neural networks","volume":"13","author":"Towell","year":"1993","journal-title":"Mach. Learn"},{"key":"ref_23","unstructured":"Fu, L Rule learning by searching on adapted nets. Anaheim, CA, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/0004-3702(94)90105-8","article-title":"Knowledge-based artificial neural networks","volume":"70","author":"Towell","year":"1994","journal-title":"Artif. Intell"},{"key":"ref_25","unstructured":"Liu, H, and Tan, ST (1995, January 22\u201325). X2R: A fast rule generator. Vancouver, BC, Canada."},{"key":"ref_26","first-page":"15","article-title":"A family of efficient rule generators","volume":"39","author":"Liu","year":"1998","journal-title":"Encyclopedia of Computer Science and Technology"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1109\/72.839020","article-title":"Extracting M-of-N rules from trained neural networks","volume":"11","author":"Setiono","year":"2000","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_28","first-page":"41","article-title":"An algorithm to extract rules from artificial neural networks for medical diagnosis problems","volume":"12","author":"Kamruzzaman","year":"2006","journal-title":"Int. J. Inf. Tech"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1109\/TSMCC.2008.919172","article-title":"Pareto-based multiobjective machine learning: An overview and case studies","volume":"38","author":"Jin","year":"2008","journal-title":"IEEE Trans. Syst. Man Cybern. C Appl. Rev"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, J, Zhang, W, Qin, B, and Shi, W (2010, January 14\u201315). Research on rules extraction from neural network based on linear insertion. Beidaihe, Hebei, China.","DOI":"10.1109\/ICIE.2010.103"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/72.572102","article-title":"Constructive algorithms for structured learning in feedforward neural networks for regression problems","volume":"8","author":"Kwok","year":"1997","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/TNN.2003.813832","article-title":"A constructive algorithm for training cooperative neural network ensembles","volume":"14","author":"Islam","year":"2003","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/72.839013","article-title":"Constructive neural network learning algorithms for pattern classification","volume":"11","author":"Parekh","year":"2000","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1080\/09540098908915647","article-title":"Dynamic node creation in backpropagation networks","volume":"1","author":"Ash","year":"1989","journal-title":"Connect. Sci"},{"key":"ref_35","first-page":"524","article-title":"The cascade-correlation learning architecture","volume":"2","author":"Fahlman","year":"1990","journal-title":"Adv. Neural Inf. Proc. Syst"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1109\/72.363426","article-title":"Use of quasi-Newton method in a feedforward neural network construction algorithm","volume":"6","author":"Setiono","year":"1995","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_37","unstructured":"Kamruzzaman, SM, Hasan, AR, Siddiquee, AB, and Mazumder, MEH (2004, January 28\u201330). Medical diagnosis using neural network. Dhaka, Bangladesh."},{"key":"ref_38","unstructured":"Islam, MM, Akhand, MAH, Rahman, MA, and Murase, K (2002, January 27\u201328). Weight freezing to reduce training time in designing artificial neural networks. Dhaka, Bangladesh."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sietsma, J, and Dow, RJF (1988, January 24\u201327). Neural net pruning-why and how?. San Diego, CA, USA.","DOI":"10.1109\/ICNN.1988.23864"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/0893-6080(92)90008-7","article-title":"Improving the convergence of backpropagation algorithm","volume":"5","author":"Ooyen","year":"1992","journal-title":"Neural Netw"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/72.248452","article-title":"Pruning algorithms-A survey","volume":"4","author":"Reed","year":"1993","journal-title":"IEEE Trans. Neural Netw"},{"key":"ref_42","unstructured":"Jiawei, H, and Kamber, M (2001). Data Mining: Concepts and Techniques, Morgan Kaufmann."},{"key":"ref_43","unstructured":"Kaufman, L, and Rousseeuw, PJ (2005). Finding Groups in Data: An Introduction to Cluster Analysis, John Wiley & Sons."},{"key":"ref_44","unstructured":"Raymond, TN, and Han, J (1994, January 12\u201315). Efficient and effective clustering methods for spatial data mining. Santiago de Chile, Chile."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1016\/S0893-6080(01)00075-2","article-title":"A new algorithm to design compact two hidden-layer artificial neural networks","volume":"4","author":"Islam","year":"2001","journal-title":"Neural Netw"},{"key":"ref_46","unstructured":"Quinlan, JR (1993). C45: Programs for Machine Learning, Morgan Kaufmann."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1109\/69.250074","article-title":"Database mining: A performance perspective","volume":"5","author":"Agrawal","year":"1993","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"ref_48","unstructured":"Yen, S-J, and Chen, ALP (1995, January 11\u201313). An efficient algorithm for deriving compact rules from databases. Singapore."},{"key":"ref_49","unstructured":"Murphy, PM, and Aha, DW Available online: http:\/\/archive.ics.uci.edu\/ml\/ (accessed on 12 April 2011)."},{"key":"ref_50","unstructured":"Prechelt, L (1994). PROBEN1-A Set of Neural Network Benchmark Problems and Benchmarking Rules, Fakultat fur Informatik, Universitat Karlsruhe. Technical Report 21\/94;."},{"key":"ref_51","unstructured":"Setiono, R (1998, January 16\u201320). Techniques for extracting rules from artificial neural networks. Iizuka, Japan."},{"key":"ref_52","unstructured":"Breiman, L, Friedman, J, Olshen, R, and Stone, C Classification and Regression Trees."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/S0957-4174(99)80008-6","article-title":"RULES: A simple rule extraction system","volume":"8","author":"Pham","year":"1995","journal-title":"Expert Syst. Appl"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/0954-1810(93)90011-4","article-title":"An algorithm for automatic rule induction","volume":"8","author":"Pham","year":"1994","journal-title":"Artif. Intell. Eng"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/S0020-7373(87)80003-2","article-title":"PRISM: An algorithm for inducting modular rules","volume":"27","author":"Cendrowska","year":"1987","journal-title":"Int. J. Man Mach. Stud"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/11\/5\/4622\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:55:57Z","timestamp":1760219757000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/11\/5\/4622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4,28]]},"references-count":55,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2011,5]]}},"alternative-id":["s110504622"],"URL":"https:\/\/doi.org\/10.3390\/s110504622","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2011,4,28]]}}}