{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T02:30:40Z","timestamp":1772159440579,"version":"3.50.1"},"reference-count":130,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3039064","type":"journal-article","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T16:20:40Z","timestamp":1605716440000},"page":"209964-210005","source":"Crossref","is-referenced-by-count":8,"title":["A Scientific Knowledge Discovery and Data Mining Process Model for Metabolomics"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7502-7978","authenticated-orcid":false,"given":"Ahmed","family":"Banimustafa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9607-2601","authenticated-orcid":false,"given":"Nigel","family":"Hardy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/240455.240464"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0710-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1089\/omi.2008.0019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1347"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1104\/pp.104.058875"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkp356"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprot.2015.01.019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/metabo9100237"},{"key":"ref35","first-page":"79","article-title":"Enhancing learning from imbalanced classes via data preprocessing: A data-driven application in metabolomics data mining","volume":"11","author":"banimustafa","year":"2019","journal-title":"ISC Int J Inf Security"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-0239-3_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/jssc.200900609"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0958-1669(02)00299-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-9422(02)00708-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/mas.20108"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2004.03.007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.mib.2004.04.012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013713905833"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbl012"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0095015"},{"key":"ref26","article-title":"Options for the storage of the results of gas chromotography-mass spectrometry (GC-MS) analysis","author":"fuell","year":"2003"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/336512.336521"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2004-5-6-109"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/4735_2007_0242","article-title":"Reporting standards","volume":"18","author":"hardy","year":"2007","journal-title":"Topics in Current Genetics"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-007-0070-6"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-007-0069-z"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-005-1106-4"},{"key":"ref57","author":"larman","year":"2004","journal-title":"Agile and Iterative Development A Manager s Guide"},{"key":"ref56","article-title":"Data mining and science—Knwoledge discovery in science opposed to business","author":"read","year":"1999","journal-title":"12th ERCIM Workshop on Database Research"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1104\/pp.103.022004"},{"key":"ref54","article-title":"Missing values, outliers, robust statistics & non-parametric methods","author":"burke","year":"2001"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2164-7-142"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.2005.01632.x"},{"key":"ref40","first-page":"82","article-title":"Knowledge discovery and data mining: Toward a unifying framework","author":"fayyad","year":"1996","journal-title":"Proc 1st Intl Conf on Knowledge Discovery and Data Mining (KDD)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/mper-2016-0040"},{"key":"ref3","first-page":"405","article-title":"Data mining process models: A roadmap for knowledge discovery","author":"mendes","year":"2013","journal-title":"Quantitative Modelling In Marketing And Management"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.25046\/aj020376"},{"key":"ref5","first-page":"217","article-title":"A comparative study of data mining process models (KDD, CRISP-DM and SEMMA)","volume":"12","author":"shafique","year":"2014","journal-title":"International Journal of Innovative Research in Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888910000032"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-007-0082-2"},{"key":"ref7","first-page":"182","article-title":"KDD, SEMMA and CRISP-DM: A parallel overview","author":"azevedo","year":"2008","journal-title":"Proc IADIS European Conf Data Mining"},{"key":"ref9","first-page":"92","article-title":"Crisp data mining methodology extension for medical domain","volume":"3","author":"niaksu","year":"2015","journal-title":"Baltic Journal of Modern Computing"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s11306-007-0081-3","article-title":"Proposed minimum reporting standards for data analysis in metabolomics","volume":"3","author":"goodacre","year":"2007","journal-title":"Metabolomics"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/978-1-61779-594-7_18","article-title":"A strategy for selecting data mining techniques in metabolomics","volume":"860","author":"banimustafa","year":"2012","journal-title":"Plant Metabolomics Methods and Protocols"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-281"},{"key":"ref47","article-title":"Introduction to Fourier transform infrared spectroscopy","year":"2007","journal-title":"Thermo Scientific"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/b107408"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1411"},{"key":"ref44","author":"goodacre","year":"2006","journal-title":"Data Analsysis Standards in Metabolomics"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-34351-6_7"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1002\/cem.785"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289588"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/1233321.1233333"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1145\/1289612.1289613","article-title":"Conformance standard for the predictive model markup language","author":"pechter","year":"2006","journal-title":"4th International Workshop on Data Mining Standards Services and Platforms"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"ref71","article-title":"Metabolomics","author":"broeckling","year":"2005"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"ref70","first-page":"37","article-title":"The process of knowledge discovery in data bases: A human centred approach","author":"brachman","year":"1996","journal-title":"Proc AKDDM"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1584\/jpestics.31.300"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.32614\/RJ-2009-010"},{"key":"ref77","author":"trochim","year":"2007","journal-title":"The Research Methods Knowledge Base"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1041"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1002\/cfg.82"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/846170.846172"},{"key":"ref79","author":"ryszad michalski","year":"1998","journal-title":"Machine Learning and Data Mining Methods and Applications"},{"key":"ref60","article-title":"The process of knowledge discovery in databases: A first sketch","author":"ronald brachman","year":"1994"},{"key":"ref62","first-page":"13","article-title":"The CRISP-DM model: The new blueprint for data mining","volume":"5","author":"shearer","year":"2000","journal-title":"J Data Warehousing"},{"key":"ref61","article-title":"CRISP-DM 1.0: Step-by-step data mining guide","author":"chapman","year":"2000"},{"key":"ref63","author":"cios pedrycz swiniarski","year":"2007","journal-title":"Data Mining A Knowledge Discovery Approach"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-739X(97)00023-X"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000737"},{"key":"ref66","first-page":"29","article-title":"CRISP-DM—Towards a standard process model for data mining","author":"wirth","year":"2000","journal-title":"Proc 4th Int Conf Practical Appl Knowl Discovery Data Mining"},{"key":"ref67","first-page":"1","article-title":"Human involovment and interactivity of the next generation’s data mining tools","author":"ankerst","year":"2001","journal-title":"Proc Workshop Res Issues Data Mining Knowl Discovery Workshop Res Issues Data Mining Knowl Discovery"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/2.781634"},{"key":"ref2","article-title":"A knowledge discovery and data mining process model for metabolomics","author":"banimustafa","year":"2012"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1080\/713827122","article-title":"Conceptual knowledge discovery: A human-centred approache","volume":"17","author":"hereth","year":"2003","journal-title":"Appl Artif Intell Int J"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1042\/BST0330520"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1006\/ijhc.1995.1081"},{"key":"ref95","author":"hand","year":"2001","journal-title":"Principles of Data Mining Adaptive Computation and Machine Learning"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2008.62"},{"key":"ref94","article-title":"Data mining and the case for sampling solving business problems using SAS enterprise miner software","author":"milley","year":"1998"},{"key":"ref107","first-page":"53","article-title":"Al-haytham the man of experience, first steps in the science of vision","volume":"2","author":"gorini","year":"2003","journal-title":"Journal of the International Society for the History of Islamic Medicine"},{"key":"ref93","year":"2005","journal-title":"The data mining process"},{"key":"ref106","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1038\/nmeth0409-237","article-title":"Defining the scientific method","volume":"6","author":"carrol","year":"2009","journal-title":"Nature Methods"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/NEUREL.2002.1057967"},{"key":"ref105","first-page":"126","article-title":"Scientific methods in computer science","author":"dodig-crnkovic","year":"2002","journal-title":"Proc Conf Promotion Res IT New Universities at Univ Colleges in Sweden"},{"key":"ref91","article-title":"Modeling the KDD process—A four stage and four elements model","author":"williams","year":"1996"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219768"},{"key":"ref90","first-page":"249","article-title":"Supervised machine learning: A review of classification techniques","volume":"31","author":"kotsiantis","year":"2007","journal-title":"Informatica"},{"key":"ref103","first-page":"36","article-title":"The SDLC and six sigma: An essay on which is which and why","volume":"5","author":"roy boggs","year":"2004","journal-title":"Issues in Inform Syst"},{"key":"ref102","first-page":"38","article-title":"V-model role engineering","volume":"13","author":"constantinescu","year":"2009","journal-title":"Inf Economica"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03915-7_25"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.67"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04747-3_21"},{"key":"ref98","article-title":"Process models in software engineering","author":"scacchi","year":"2001","journal-title":"Encyclopedia of Software Engineering"},{"key":"ref99","article-title":"Software engineering","author":"sommerville","year":"2007","journal-title":"International Computer Science Series"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0054216"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49205-4_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1108\/17410390710725751"},{"key":"ref11","article-title":"A data mining & knowledge discovery process model","author":"?arb\u00e1n","year":"2009","journal-title":"Data Mining and Knowledge Discovery in Real Life Applications"},{"key":"ref12","article-title":"A standardized data mining method in healthcare: A pediatric intensive care unit case study","author":"kari\u0161ik","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2016.07.003"},{"key":"ref14","article-title":"Applications of a novel knowledge discovery and data mining process model for metabolomics","author":"banimustafa","year":"2019","journal-title":"arXiv 1907 03755"},{"key":"ref15","article-title":"Computer-aided data mining: Automating a novel knowledge discovery and data mining process model for metabolomics","author":"banimustafa","year":"2019","journal-title":"arXiv 1907 04318"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/505168.505170"},{"key":"ref16","author":"banimustafa","year":"2019","journal-title":"MeKDDaM-SAGA A Software for Automating and Guiding a Knowledge Discovery and Data Mining Process Model for Metabolomics Version 1 0"},{"key":"ref82","first-page":"1","author":"grossman","year":"2004","journal-title":"Event Based Data Mining Process Models"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2006.0134"},{"key":"ref17","first-page":"92","article-title":"Plant metabolomics","volume":"2","author":"maloney","year":"2004","journal-title":"BioTeach J"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/IITA.2008.26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1289\/ehp.112-1241997"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/2945.981847"},{"key":"ref119","first-page":"295","article-title":"Accuracy vs. Comprehensibility in data mining models","author":"johansson","year":"2004","journal-title":"Proc 7th Int Conf Inf Fusion"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.trac.2004.11.021","article-title":"Metabolomics: Current analytical platforms and methodologies","volume":"24","author":"dunn","year":"2005","journal-title":"Trends Anal Chem"},{"key":"ref83","year":"1999","journal-title":"Introduction to Data Mining and knowledge discovery"},{"key":"ref114","article-title":"Planning to learn with a knowledge discovery ontology","author":"\u017e\u00e1kov\u00e1","year":"2008","journal-title":"Planning to Learn Workshop (PlanLearn 2008) at ICML"},{"key":"ref113","first-page":"23","article-title":"Meta-learning with kernels and similarity functions for planning of data mining workflows","author":"kalousis","year":"2008","journal-title":"Proc Planing Learn Workshop (PlanLearn)"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btn452"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.025"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-007-0071-5"},{"key":"ref120","author":"kerzner","year":"2003","journal-title":"Project Management A Systems Approach to Planning Scheduling and Controlling"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-59904-887-1"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/BF00337288"},{"key":"ref123","first-page":"831","article-title":"Principles of risk minimization for learning theory","volume":"4","author":"vapnik","year":"1992","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref85","first-page":"23","article-title":"Visual data mining with pixel-oriented visualization techniques","author":"ankerst","year":"2001","journal-title":"ACM SIGKDD Workshop on Visual Data Mining"},{"key":"ref86","author":"kantardzic","year":"2003","journal-title":"Data Mining Concepts Models Methods and Algorithms"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/3.2.134"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2005.18"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09263253.pdf?arnumber=9263253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T13:08:49Z","timestamp":1697116129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9263253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":130,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3039064","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/731844","asserted-by":"object"}]},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}