{"id":"https://openalex.org/W1978860892","doi":"https://doi.org/10.1109/cibcb.2014.6845517","title":"Multiclass unbalanced protein data classification using sequence features","display_name":"Multiclass unbalanced protein data classification using sequence features","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1978860892","doi":"https://doi.org/10.1109/cibcb.2014.6845517","mag":"1978860892"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb.2014.6845517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2014.6845517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038964029","display_name":"K. Vani","orcid":"https://orcid.org/0000-0003-4608-6308"},"institutions":[{"id":"https://openalex.org/I2802823369","display_name":"ASA College","ror":"https://ror.org/039h3aa75","country_code":"US","type":"education","lineage":["https://openalex.org/I2802823369"]},{"id":"https://openalex.org/I116891498","display_name":"Siddhartha Medical College","ror":"https://ror.org/058pt1w78","country_code":"IN","type":"education","lineage":["https://openalex.org/I116891498"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"K. Suvarna Vani","raw_affiliation_strings":["Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, Andhra Pradesh, IN","Department of Computer Science & Engineering, V R Siddhartha Engineering College, Vijayawada, India"],"affiliations":[{"raw_affiliation_string":"Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, Andhra Pradesh, IN","institution_ids":["https://openalex.org/I2802823369"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, V R Siddhartha Engineering College, Vijayawada, India","institution_ids":["https://openalex.org/I116891498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113535137","display_name":"T. D. Sravani","orcid":null},"institutions":[{"id":"https://openalex.org/I116891498","display_name":"Siddhartha Medical College","ror":"https://ror.org/058pt1w78","country_code":"IN","type":"education","lineage":["https://openalex.org/I116891498"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"T.D. Sravani","raw_affiliation_strings":["Department of Computer Science and Engineering, V.R. Siddhartha Engineering College, Vijayawada, Andhra Pradesh, India","Department of Computer Science & Engineering, V R Siddhartha Engineering College, Vijayawada, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, V.R. Siddhartha Engineering College, Vijayawada, Andhra Pradesh, India","institution_ids":["https://openalex.org/I116891498"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, V R Siddhartha Engineering College, Vijayawada, India","institution_ids":["https://openalex.org/I116891498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038964029"],"corresponding_institution_ids":["https://openalex.org/I116891498","https://openalex.org/I2802823369"],"apc_list":null,"apc_paid":null,"fwci":0.1394,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51831259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6996832489967346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972901821136475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6898363828659058},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.672026515007019},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.6097867488861084},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5839917659759521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5787534713745117},{"id":"https://openalex.org/keywords/c4.5-algorithm","display_name":"C4.5 algorithm","score":0.570223331451416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5311861038208008},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4668577015399933},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4527166783809662},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.43615129590034485},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.43437063694000244},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"Multiclass classification","score":0.42031121253967285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3343909978866577},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.3316522240638733}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6996832489967346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972901821136475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6898363828659058},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.672026515007019},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.6097867488861084},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5839917659759521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5787534713745117},{"id":"https://openalex.org/C52003472","wikidata":"https://www.wikidata.org/wiki/Q1022655","display_name":"C4.5 algorithm","level":4,"score":0.570223331451416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5311861038208008},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4668577015399933},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4527166783809662},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.43615129590034485},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.43437063694000244},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.42031121253967285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3343909978866577},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.3316522240638733},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb.2014.6845517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2014.6845517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W273955616","https://openalex.org/W1536368332","https://openalex.org/W1570448133","https://openalex.org/W1576259574","https://openalex.org/W1993220166","https://openalex.org/W2006782375","https://openalex.org/W2024046085","https://openalex.org/W2095985063","https://openalex.org/W2107432340","https://openalex.org/W2109109045","https://openalex.org/W2118347512","https://openalex.org/W2126232612","https://openalex.org/W2148143831","https://openalex.org/W2153150899","https://openalex.org/W2169712481","https://openalex.org/W2315549826","https://openalex.org/W3004732066","https://openalex.org/W4212883601","https://openalex.org/W4235848672","https://openalex.org/W4285719527","https://openalex.org/W6610017368","https://openalex.org/W6699167161"],"related_works":["https://openalex.org/W3102090019","https://openalex.org/W4390338302","https://openalex.org/W2793442578","https://openalex.org/W4232572698","https://openalex.org/W2911792412","https://openalex.org/W4221072066","https://openalex.org/W2161389817","https://openalex.org/W2106647409","https://openalex.org/W2952448206","https://openalex.org/W744859113"],"abstract_inverted_index":{"Protein":[0],"fold":[1,22,167],"classification":[2,23,130,168],"is":[3,28,45,56,100,119,131,177],"one":[4],"of":[5,14,20,59,95,127,159],"the":[6,18,52,88,104,125,134,144,148,156,166,174,183,188,193,199,203,211],"challenging":[7],"problems":[8],"in":[9,84,202],"bioinformatics.":[10],"The":[11,129,150],"main":[12],"objective":[13],"this":[15,81],"work":[16],"addresses":[17],"problem":[19,31,169],"protein":[21,137,184],"using":[24,170],"sequence":[25],"features":[26,50,126,171,180],"which":[27,64,197,222],"a":[29,70,73],"multi-class":[30,74],"having":[32],"unbalanced":[33],"classes.":[34,149],"A":[35],"simple":[36,157],"and":[37,107,186,220],"computationally":[38],"inexpensive":[39],"algorithm":[40,44,91],"called":[41],"feature":[42,190,205],"extraction":[43],"proposed":[46],"to":[47,72,86,102,121,161,178,192,209],"extract":[48,179],"novel":[49],"from":[51,69,124,173],"primary":[53],"sequences.":[54,128],"It":[55],"found":[57],"that":[58],"Support":[60],"Vector":[61],"Machine":[62],"(SVM)":[63],"can":[65],"be":[66],"effectively":[67],"extended":[68],"binary":[71],"classifier":[75,118],"does":[76],"not":[77],"perform":[78],"well":[79,141],"on":[80,165,182],"problem.":[82],"Hence":[83],"order":[85,208],"boost":[87],"performance,":[89],"boosting":[90,160,216],"like":[92,113,218],"SMOTE":[93],"technique":[94],"Chawla":[96],"et":[97],"al.":[98],"[17]":[99],"applied":[101],"rebalance":[103],"data":[105],"set":[106,191],"then":[108],"apply":[109,187],"different":[110,145,215],"classifiers":[111],"methods":[112],"J48":[114],"[15]":[115],"decision":[116],"tree":[117],"used":[120],"classify":[122],"folds":[123,146],"performed":[132],"across":[133],"four":[135],"major":[136],"structural":[138],"classes":[139],"as":[140,142],"among":[143],"within":[147],"results":[151],"obtained":[152],"are":[153],"promising":[154],"validating":[155],"methodology":[158],"obtain":[162],"improved":[163,194],"performance":[164],"derived":[172],"sequences":[175,185],"alone":[176],"based":[181],"extracted":[189,204],"oversampling":[195],"method":[196],"reduces":[198],"imbalance":[200],"present":[201],"set.":[206],"In":[207],"tackle":[210],"multi-classes":[212],"we":[213],"use":[214],"algorithms":[217],"Adaboost":[219],"Logitboost":[221],"handle":[223],"multi-datasets":[224],"effectively.":[225]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}