Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955354980> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2955354980 endingPage "216" @default.
- W2955354980 startingPage "204" @default.
- W2955354980 abstract "Abstract Context Software defect prediction is important to ensure the quality of software. Nowadays, many supervised learning techniques have been applied to identify defective instances (e.g., methods, classes, and modules). Objective However, the performance of these supervised learning techniques are still far from satisfactory, and it will be important to design more advanced techniques to improve the performance of defect prediction models. Method We propose a new deep forest model to build the defect prediction model (DPDF). This model can identify more important defect features by using a new cascade strategy, which transforms random forest classifiers into a layer-by-layer structure. This design takes full advantage of ensemble learning and deep learning. Results We evaluate our approach on 25 open source projects from four public datasets (i.e., NASA, PROMISE, AEEEM and Relink). Experimental results show that our approach increases AUC value by 5% compared with the best traditional machine learning algorithms. Conclusion The deep strategy in DPDF is effective for software defect prediction." @default.
- W2955354980 created "2019-07-12" @default.
- W2955354980 creator A5006669765 @default.
- W2955354980 creator A5006966486 @default.
- W2955354980 creator A5036117084 @default.
- W2955354980 creator A5066596896 @default.
- W2955354980 creator A5073736241 @default.
- W2955354980 date "2019-10-01" @default.
- W2955354980 modified "2023-10-14" @default.
- W2955354980 title "Improving defect prediction with deep forest" @default.
- W2955354980 cites W1909497710 @default.
- W2955354980 cites W1964962870 @default.
- W2955354980 cites W1981039744 @default.
- W2955354980 cites W2008338177 @default.
- W2955354980 cites W2008596407 @default.
- W2955354980 cites W2009623562 @default.
- W2955354980 cites W2021688474 @default.
- W2955354980 cites W2043877001 @default.
- W2955354980 cites W2048456683 @default.
- W2955354980 cites W2060374620 @default.
- W2955354980 cites W2064330644 @default.
- W2955354980 cites W2065547122 @default.
- W2955354980 cites W2097883090 @default.
- W2955354980 cites W2101227285 @default.
- W2955354980 cites W2105776892 @default.
- W2955354980 cites W2118283821 @default.
- W2955354980 cites W2127623179 @default.
- W2955354980 cites W2131891947 @default.
- W2955354980 cites W2140785063 @default.
- W2955354980 cites W2143637886 @default.
- W2955354980 cites W2151666086 @default.
- W2955354980 cites W2155653793 @default.
- W2955354980 cites W2158698691 @default.
- W2955354980 cites W2160815625 @default.
- W2955354980 cites W2169152236 @default.
- W2955354980 cites W2289933044 @default.
- W2955354980 cites W2304692780 @default.
- W2955354980 cites W2312398278 @default.
- W2955354980 cites W2316930373 @default.
- W2955354980 cites W2345857495 @default.
- W2955354980 cites W2470944315 @default.
- W2955354980 cites W2474835145 @default.
- W2955354980 cites W2476464413 @default.
- W2955354980 cites W2529722711 @default.
- W2955354980 cites W2617227509 @default.
- W2955354980 cites W2744611928 @default.
- W2955354980 cites W2751688213 @default.
- W2955354980 cites W2760805760 @default.
- W2955354980 cites W285841728 @default.
- W2955354980 cites W2906628499 @default.
- W2955354980 cites W2911964244 @default.
- W2955354980 cites W2912760555 @default.
- W2955354980 doi "https://doi.org/10.1016/j.infsof.2019.07.003" @default.
- W2955354980 hasPublicationYear "2019" @default.
- W2955354980 type Work @default.
- W2955354980 sameAs 2955354980 @default.
- W2955354980 citedByCount "74" @default.
- W2955354980 countsByYear W29553549802019 @default.
- W2955354980 countsByYear W29553549802020 @default.
- W2955354980 countsByYear W29553549802021 @default.
- W2955354980 countsByYear W29553549802022 @default.
- W2955354980 countsByYear W29553549802023 @default.
- W2955354980 crossrefType "journal-article" @default.
- W2955354980 hasAuthorship W2955354980A5006669765 @default.
- W2955354980 hasAuthorship W2955354980A5006966486 @default.
- W2955354980 hasAuthorship W2955354980A5036117084 @default.
- W2955354980 hasAuthorship W2955354980A5066596896 @default.
- W2955354980 hasAuthorship W2955354980A5073736241 @default.
- W2955354980 hasConcept C41008148 @default.
- W2955354980 hasConceptScore W2955354980C41008148 @default.
- W2955354980 hasFunder F4320321001 @default.
- W2955354980 hasLocation W29553549801 @default.
- W2955354980 hasOpenAccess W2955354980 @default.
- W2955354980 hasPrimaryLocation W29553549801 @default.
- W2955354980 hasRelatedWork W2093578348 @default.
- W2955354980 hasRelatedWork W2096946506 @default.
- W2955354980 hasRelatedWork W2350741829 @default.
- W2955354980 hasRelatedWork W2358668433 @default.
- W2955354980 hasRelatedWork W2376932109 @default.
- W2955354980 hasRelatedWork W2382290278 @default.
- W2955354980 hasRelatedWork W2390279801 @default.
- W2955354980 hasRelatedWork W2748952813 @default.
- W2955354980 hasRelatedWork W2766271392 @default.
- W2955354980 hasRelatedWork W2899084033 @default.
- W2955354980 hasVolume "114" @default.
- W2955354980 isParatext "false" @default.
- W2955354980 isRetracted "false" @default.
- W2955354980 magId "2955354980" @default.
- W2955354980 workType "article" @default.