Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306811865> ?p ?o ?g. }
- W4306811865 endingPage "110024" @default.
- W4306811865 startingPage "110024" @default.
- W4306811865 abstract "Sensor drift has been recognized as the root cause of decreased effectiveness in the gas sensor community. To date, most drift compensation strategies have focused on classification accuracy, while neglecting the labelling cost in the real-world. To simultaneously improve classification accuracy and reduce labelling cost, we propose a novel drift compensation framework for gas sensors, which combines cross-domain subspace learning with balanced distribution and cross-domain adaptive extreme learning machine (CSBD-CAELM). First, in a common subspace, the marginal distribution and conditional distribution between the source domain (clean data) and target domain (drift data) are adaptively aligned, which reduces the distribution divergence between domains. Then, the proposed CSBD-CAELM learns a robust classifier by leveraging the guide samples. Finally, both the subspace and the classifier are optimized continually by iteratively refining the soft labels of the target domain. In this way, a dual drift compensation effect combining the feature level and classifier level is achieved. Compared with the existing methods based on transfer samples, the labelling cost is reduced. The experimental results show that, at the same labelling cost, the CSBD-CAELM can improve the accuracy by 19.5% and 26.4% in the long-term drift scenario and short-term drift scenario, respectively." @default.
- W4306811865 created "2022-10-20" @default.
- W4306811865 creator A5010634498 @default.
- W4306811865 creator A5038606960 @default.
- W4306811865 creator A5044301848 @default.
- W4306811865 creator A5085949847 @default.
- W4306811865 creator A5086406250 @default.
- W4306811865 creator A5089528237 @default.
- W4306811865 date "2023-01-01" @default.
- W4306811865 modified "2023-10-16" @default.
- W4306811865 title "A dual drift compensation framework based on subspace learning and cross-domain adaptive extreme learning machine for gas sensors" @default.
- W4306811865 cites W1965895201 @default.
- W4306811865 cites W1987864869 @default.
- W4306811865 cites W2010910059 @default.
- W4306811865 cites W2022851810 @default.
- W4306811865 cites W2026131661 @default.
- W4306811865 cites W2041105792 @default.
- W4306811865 cites W2048344731 @default.
- W4306811865 cites W2059477850 @default.
- W4306811865 cites W2060365859 @default.
- W4306811865 cites W2061163529 @default.
- W4306811865 cites W2061521613 @default.
- W4306811865 cites W2068733561 @default.
- W4306811865 cites W2101207781 @default.
- W4306811865 cites W2106762334 @default.
- W4306811865 cites W2126950562 @default.
- W4306811865 cites W2139598133 @default.
- W4306811865 cites W2160837819 @default.
- W4306811865 cites W2163472458 @default.
- W4306811865 cites W2166858657 @default.
- W4306811865 cites W2581311652 @default.
- W4306811865 cites W2594570598 @default.
- W4306811865 cites W2607040660 @default.
- W4306811865 cites W2695071295 @default.
- W4306811865 cites W2772818648 @default.
- W4306811865 cites W2901255892 @default.
- W4306811865 cites W2910036515 @default.
- W4306811865 cites W2922105518 @default.
- W4306811865 cites W2956787144 @default.
- W4306811865 cites W3020523979 @default.
- W4306811865 cites W3034932469 @default.
- W4306811865 cites W3100835067 @default.
- W4306811865 cites W3127315601 @default.
- W4306811865 cites W3152723357 @default.
- W4306811865 cites W3198280553 @default.
- W4306811865 cites W3200326076 @default.
- W4306811865 cites W3210899060 @default.
- W4306811865 cites W4284694767 @default.
- W4306811865 cites W4285065294 @default.
- W4306811865 doi "https://doi.org/10.1016/j.knosys.2022.110024" @default.
- W4306811865 hasPublicationYear "2023" @default.
- W4306811865 type Work @default.
- W4306811865 citedByCount "5" @default.
- W4306811865 countsByYear W43068118652023 @default.
- W4306811865 crossrefType "journal-article" @default.
- W4306811865 hasAuthorship W4306811865A5010634498 @default.
- W4306811865 hasAuthorship W4306811865A5038606960 @default.
- W4306811865 hasAuthorship W4306811865A5044301848 @default.
- W4306811865 hasAuthorship W4306811865A5085949847 @default.
- W4306811865 hasAuthorship W4306811865A5086406250 @default.
- W4306811865 hasAuthorship W4306811865A5089528237 @default.
- W4306811865 hasConcept C119857082 @default.
- W4306811865 hasConcept C12267149 @default.
- W4306811865 hasConcept C124101348 @default.
- W4306811865 hasConcept C153180895 @default.
- W4306811865 hasConcept C154945302 @default.
- W4306811865 hasConcept C2780150128 @default.
- W4306811865 hasConcept C32834561 @default.
- W4306811865 hasConcept C41008148 @default.
- W4306811865 hasConcept C50644808 @default.
- W4306811865 hasConcept C60777511 @default.
- W4306811865 hasConcept C89198739 @default.
- W4306811865 hasConcept C95623464 @default.
- W4306811865 hasConceptScore W4306811865C119857082 @default.
- W4306811865 hasConceptScore W4306811865C12267149 @default.
- W4306811865 hasConceptScore W4306811865C124101348 @default.
- W4306811865 hasConceptScore W4306811865C153180895 @default.
- W4306811865 hasConceptScore W4306811865C154945302 @default.
- W4306811865 hasConceptScore W4306811865C2780150128 @default.
- W4306811865 hasConceptScore W4306811865C32834561 @default.
- W4306811865 hasConceptScore W4306811865C41008148 @default.
- W4306811865 hasConceptScore W4306811865C50644808 @default.
- W4306811865 hasConceptScore W4306811865C60777511 @default.
- W4306811865 hasConceptScore W4306811865C89198739 @default.
- W4306811865 hasConceptScore W4306811865C95623464 @default.
- W4306811865 hasLocation W43068118651 @default.
- W4306811865 hasOpenAccess W4306811865 @default.
- W4306811865 hasPrimaryLocation W43068118651 @default.
- W4306811865 hasRelatedWork W2041399278 @default.
- W4306811865 hasRelatedWork W2136184105 @default.
- W4306811865 hasRelatedWork W2160451891 @default.
- W4306811865 hasRelatedWork W2336974148 @default.
- W4306811865 hasRelatedWork W2556319748 @default.
- W4306811865 hasRelatedWork W3013515612 @default.
- W4306811865 hasRelatedWork W3044497914 @default.
- W4306811865 hasRelatedWork W3185179407 @default.
- W4306811865 hasRelatedWork W2187500075 @default.
- W4306811865 hasRelatedWork W2345184372 @default.