{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:29:32Z","timestamp":1740122972893,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T00:00:00Z","timestamp":1689465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T00:00:00Z","timestamp":1689465600000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16128-9","type":"journal-article","created":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T04:01:40Z","timestamp":1689480100000},"page":"16623-16655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generic features selection for structure classification of diverse styled scholarly articles"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4563-8951","authenticated-orcid":false,"given":"Muhammad","family":"Waqas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadeem","family":"Anjum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,16]]},"reference":[{"key":"16128_CR1","doi-asserted-by":"publisher","first-page":"167605","DOI":"10.1109\/ACCESS.2019.2953920","volume":"7","author":"M Abdar","year":"2019","unstructured":"Abdar M, Acharya UR, Sarrafzadegan N, Makarenkov V (2019) Ne-nu-svc: A new nested ensemble clinical decision support system for effective diagnosis of coronary artery disease. IEEE Access 7:167605\u2013167620","journal-title":"IEEE Access"},{"key":"16128_CR2","doi-asserted-by":"crossref","unstructured":"Ahmad R, Afzal MT, Qadir MA (2016) Information extraction from PDF sources based on rule-based system using integrated formats. In: Semantic web challenges: third SemWebEval challenge at ESWC 2016, Heraklion, Crete, Greece. May 29-June 2, 2016. Revised selected papers 3.\u00a0Springer International Publishing, pp 293\u2013308","DOI":"10.1007\/978-3-319-46565-4_23"},{"key":"16128_CR3","doi-asserted-by":"crossref","unstructured":"Alam MJ, Kenny P, O\u2019Shaughnessy D (2011) A study of low-variance multi-taper features for distributed speech recognition. In International Conference on Nonlinear Speech Processing, pp 239\u2013245. Springer","DOI":"10.1007\/978-3-642-25020-0_31"},{"key":"16128_CR4","doi-asserted-by":"crossref","unstructured":"Azad HK, Deepak A, Azad A (2022) LOD search engine: a semantic search over linked data. J Intell Inf Syst 1\u201321","DOI":"10.1007\/s10844-021-00687-0"},{"key":"16128_CR5","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.patrec.2022.04.013","volume":"158","author":"HK Azad","year":"2022","unstructured":"Azad HK, Deepak A, Chakraborty C, Abhishek K (2022) Improving query expansion using pseudo-relevant web knowledge for information retrieval. Pattern Recog Lett 158:148\u2013156","journal-title":"Pattern Recog Lett"},{"issue":"6","key":"16128_CR6","doi-asserted-by":"publisher","first-page":"3105","DOI":"10.1016\/j.eswa.2014.11.038","volume":"42","author":"KK Bharti","year":"2015","unstructured":"Bharti KK, Singh PK (2015) Hybrid dimension reduction by integrating feature selection with feature extraction method for text clustering. Expert Syst Appl 42(6):3105\u20133114","journal-title":"Expert Syst Appl"},{"key":"16128_CR7","doi-asserted-by":"crossref","unstructured":"Bowles M (2015) Machine learning in Python: essential techniques for predictive analysis. John Wiley & Sons","DOI":"10.1002\/9781119183600"},{"issue":"1","key":"16128_CR8","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","volume":"40","author":"G Chandrashekar","year":"2014","unstructured":"Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40(1):16\u201328","journal-title":"Comput Electr Eng"},{"key":"16128_CR9","unstructured":"Claesen M, De Smet F, Suykens JAK, De Moor B (2014) Fast prediction with svm models containing rbf kernels. arXiv preprint arXiv:1403.0736.\u00a0Accessed 14 July 2023"},{"key":"16128_CR10","doi-asserted-by":"crossref","unstructured":"Constantin A, Pettifer S, Voronkov A (2013) Pdfx: fully-automated pdf-to-xml conversion of scientific literature. In Proceedings of the 2013 ACM symposium on document engineering, pages 177\u2013180. ACM","DOI":"10.1145\/2494266.2494271"},{"key":"16128_CR11","doi-asserted-by":"crossref","unstructured":"D\u00e9jean H, Meunier JL (2006) A system for converting PDF documents into structured XML format. In: Document analysis systems VII: 7th international workshop, DAS 2006, Nelson, New Zealand, February 13-15, 2006. Proceedings 7,\u00a0Springer Berlin Heidelberg, pp 129\u201314","DOI":"10.1007\/11669487_12"},{"issue":"3","key":"16128_CR12","first-page":"1174","volume":"7","author":"A Dey","year":"2016","unstructured":"Dey A (2016) Machine learning algorithms: a review. Int J Comput Sci Inf Technol 7(3):1174\u20131179","journal-title":"Int J Comput Sci Inf Technol"},{"key":"16128_CR13","doi-asserted-by":"crossref","unstructured":"Dimou A, Di Iorio A, Lange C, Vahdati S (2016) Semantic publishing challenge\u2013assessing the quality of scientific output in its ecosystem. In: Semantic web challenges: third SemWebEval challenge at ESWC 2016, Heraklion, Crete, Greece, May 29-June 2, 2016, Revised selected papers 3. Springer International Publishing, pp 243\u2013254","DOI":"10.1007\/978-3-319-46565-4_19"},{"key":"16128_CR14","doi-asserted-by":"crossref","unstructured":"DoHHN, Chandrasekaran MK, Cho PS, Kan MY (2013) Extracting and matching authors and affiliations in scholarly documents. In Proceedings of the 13th ACM\/IEEE-CS joint conference on Digital libraries, pp 219\u2013228. ACM","DOI":"10.1145\/2467696.2467703"},{"key":"16128_CR15","doi-asserted-by":"crossref","unstructured":"Granitzer M, Hristakeva M, Jack K, Knight R (2012) A comparison of metadata extraction techniques for crowdsourced bibliographic metadata management. In Proceedings of the 27th Annual ACM Symposium on Applied Computing, pp 962\u2013964. ACM","DOI":"10.1145\/2245276.2245462"},{"key":"16128_CR16","doi-asserted-by":"publisher","unstructured":"Guo K, Chen T, Ren S, Li N, Hu M, Kang J (2022) Federated learning empowered real-time medical data processing method for smart healthcare. IEEE\/ACM Trans Comput Biol Bioinforma, 1\u201312. https:\/\/doi.org\/10.1109\/TCBB.2022.3185395","DOI":"10.1109\/TCBB.2022.3185395"},{"key":"16128_CR17","doi-asserted-by":"publisher","unstructured":"Guo K, Shen C, Hu B, Hu M, Kui X (2022) Rsnet: Relation separation network for few-shot similar class recognition. IEEE Trans Multimed, 1\u20131. https:\/\/doi.org\/10.1109\/TMM.2022.3168146","DOI":"10.1109\/TMM.2022.3168146"},{"key":"16128_CR18","unstructured":"Han J, Kamber M, Pei J (2012) Data mining concepts and techniques third edition. University of Illinois at Urbana-Champaign Micheline Kamber Jian Pei Simon Fraser University"},{"key":"16128_CR19","unstructured":"Haryanto AW, Mawardi EK (2018) Influence of word normalization and chi-squared feature selection on support vector machine (svm) text classification. In 2018 international seminar on application for technology of information and communication. IEEE pp. 229\u2013233"},{"issue":"15","key":"16128_CR20","doi-asserted-by":"publisher","first-page":"385","DOI":"10.15623\/ijret.2014.0315076","volume":"3","author":"SB Hiregoudar","year":"2014","unstructured":"Hiregoudar SB, Manjunath K, Patil KS (2014) A survey: research summary on neural networks. Int J Res Eng Technol 3(15):385\u2013389","journal-title":"Int J Res Eng Technol"},{"issue":"10","key":"16128_CR21","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1109\/TKDE.2008.234","volume":"21","author":"L Jiang","year":"2008","unstructured":"Jiang L, Zhang H, Cai Z (2008) A novel bayes model: Hidden naive bayes. IEEE Trans Knowl Data Eng 21(10):1361\u20131371","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"16128_CR22","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1087\/20100308","volume":"23","author":"AE Jinha","year":"2010","unstructured":"Jinha AE (2010) Article 50 million: an estimate of the number of scholarly articles in existence. Learned Publ 23(3):258\u2013263","journal-title":"Learned Publ"},{"key":"16128_CR23","unstructured":"Johnson R, Watkinson A, Mabe M (2018) The STM Report-an overview of scientific and scholarly publishing 2018. STM Association. 5th edn Oct"},{"issue":"4","key":"16128_CR24","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1162\/coli.2006.32.4.485","volume":"32","author":"T Kiss","year":"2006","unstructured":"Kiss T, Strunk J (2006) Unsupervised multilingual sentence boundary detection. Comput Linguist 32(4):485\u2013525","journal-title":"Comput Linguist"},{"issue":"3\u20134","key":"16128_CR25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s00799-014-0115-1","volume":"14","author":"S Klampfl","year":"2014","unstructured":"Klampfl S, Granitzer M, Jack K, Kern R (2014) Unsupervised document structure analysis of digital scientific articles. Int J Digit Libr 14(3\u20134):83\u201399","journal-title":"Int J Digit Libr"},{"issue":"1","key":"16128_CR26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/PL00013570","volume":"4","author":"S Klink","year":"2001","unstructured":"Klink S, Kieninger T (2001) Rule-based document structure understanding with a fuzzy combination of layout and textual features. Int J Doc Anal Recogn 4(1):18\u201326","journal-title":"Int J Doc Anal Recogn"},{"issue":"10","key":"16128_CR27","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1016\/j.patrec.2005.12.018","volume":"27","author":"C Lai","year":"2006","unstructured":"Lai C, Reinders MJ, Wessels L (2006) Random subspace method for multivariate feature selection. Pattern Recog Lett 27(10):1067\u20131076","journal-title":"Pattern Recog Lett"},{"key":"16128_CR28","unstructured":"Mohri M, Rostamizadeh A, Talwalkar A (2018) Foundations of machine learning. MIT press"},{"key":"16128_CR29","doi-asserted-by":"crossref","unstructured":"Olson RS, Bartley N, Urbanowicz RJ, Moore JH (2016) Evaluation of a tree-based pipeline optimization tool for automating data science. In: Proceedings of the genetic and evolutionary computation conference 2016, pp 485\u2013492","DOI":"10.1145\/2908812.2908918"},{"key":"16128_CR30","unstructured":"Preparata FP, Shamos MI (2012) Computational geometry: an introduction. Springer Science & Business Media"},{"issue":"1","key":"16128_CR31","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/1751-0473-7-7","volume":"7","author":"C Ramakrishnan","year":"2012","unstructured":"Ramakrishnan C, Patnia A, Hovy E, Burns GA (2012) Layout-aware text extraction from full-text pdf of scientific articles. Source Code Biol Med 7(1):7","journal-title":"Source Code Biol Med"},{"issue":"12","key":"16128_CR32","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1038\/nrg3337","volume":"13","author":"D Rebholz-Schuhmann","year":"2012","unstructured":"Rebholz-Schuhmann D, Oellrich A, Hoehndorf R (2012) Text-mining solutions for biomedical research: enabling integrative biology. Nat Rev Genet 13(12):829\u2013839","journal-title":"Nat Rev Genet"},{"key":"16128_CR33","unstructured":"Richert, W. (2013). Building machine learning systems with Python. Packt Publishing Ltd."},{"issue":"4","key":"16128_CR34","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s10032-015-0253-z","volume":"18","author":"KC Santosh","year":"2015","unstructured":"Santosh KC (2015) g-dice: graph mining-based document information content exploitation. Int J Doc Anal Recog (IJDAR) 18(4):337\u2013355","journal-title":"Int J Doc Anal Recog (IJDAR)"},{"issue":"1","key":"16128_CR35","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1186\/1471-2105-12-375","volume":"12","author":"P Shi","year":"2011","unstructured":"Shi P, Ray S, Zhu Q, Kon MA (2011) Top scoring pairs for feature selection in machine learning and applications to cancer outcome prediction. BMC Bioinforma 12(1):375","journal-title":"BMC Bioinforma"},{"issue":"3","key":"16128_CR36","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10032-016-0267-1","volume":"19","author":"X Su","year":"2016","unstructured":"Su X, Gao G, Wei H, Bao F (2016) A knowledge-based recognition system for historical mongolian documents. Int J Doc Anal Recog (IJDAR) 19(3):221\u2013235","journal-title":"Int J Doc Anal Recog (IJDAR)"},{"key":"16128_CR37","doi-asserted-by":"crossref","unstructured":"Tkaczyk D, Bolikowski L, Czeczko A, Rusek K (2012) A modular metadata extraction system for born-digital articles. In 2012 10th IAPR international workshop on document analysis systems. IEEE\u00a0 pp. 11\u201316","DOI":"10.1109\/DAS.2012.4"},{"key":"16128_CR38","doi-asserted-by":"crossref","unstructured":"Tsai C-T, Kundu G, Roth D (2013) Concept-based analysis of scientific literature. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, pp 1733\u20131738. ACM","DOI":"10.1145\/2505515.2505613"},{"key":"16128_CR39","doi-asserted-by":"crossref","unstructured":"Tuarob S, Bhatia S, Mitra P, Lee Giles C (2013) Automatic detection of pseudocodes in scholarly documents using machine learning. In 2013 12th International Conference on Document Analysis and Recognition, pages 738\u2013742. IEEE","DOI":"10.1109\/ICDAR.2013.151"},{"issue":"10","key":"16128_CR40","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1109\/TKDE.2019.2913376","volume":"32","author":"S Tuarob","year":"2020","unstructured":"Tuarob S, Kang SW, Wettayakorn P, Pornprasit C, Sachati T, Hassan S-U, Haddawy P (2020) Automatic classification of algorithm citation functions in scientific literature. IEEE Trans Knowl Data Eng 32(10):1881\u20131896. https:\/\/doi.org\/10.1109\/TKDE.2019.2913376","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"16128_CR41","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/959242.959249","volume":"5","author":"T Washio","year":"2003","unstructured":"Washio T, Motoda H (2003) State of the art of graph-based data mining. ACM SIGKDD Explor Newsl 5(1):59\u201368","journal-title":"ACM SIGKDD Explor Newsl"},{"issue":"3","key":"16128_CR42","first-page":"35","volume":"36","author":"J Wu","year":"2015","unstructured":"Wu J, Williams KM, Chen H-H, Khabsa M, Caragea C, Tuarob S, Ororbia AG, Jordan D, Mitra P, Giles CL (2015) Citeseerx: Ai in a digital library search engine. AI Mag 36(3):35\u201348","journal-title":"AI Mag"},{"key":"16128_CR43","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/j.snb.2015.02.025","volume":"212","author":"Ke Yan","year":"2015","unstructured":"Yan Ke, Zhang D (2015) Feature selection and analysis on correlated gas sensor data with recursive feature elimination. Sens Actuators, B Chem 212:353\u2013363","journal-title":"Sens Actuators, B Chem"},{"key":"16128_CR44","doi-asserted-by":"publisher","first-page":"114440","DOI":"10.1109\/ACCESS.2019.2935833","volume":"7","author":"L Zhu","year":"2019","unstructured":"Zhu L, He S, Wang L, Zeng W, Yang J (2019) Feature selection using an improved gravitational search algorithm. IEEE Access 7:114440\u2013114448","journal-title":"IEEE Access"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16128-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16128-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16128-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T08:42:46Z","timestamp":1706690566000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16128-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,16]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16128"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16128-9","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,7,16]]},"assertion":[{"value":"6 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}