DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Uichin | - |
dc.contributor.advisor | 이의진 | - |
dc.contributor.author | Park, Cheul Young | - |
dc.date.accessioned | 2022-04-27T19:32:33Z | - |
dc.date.available | 2022-04-27T19:32:33Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=964799&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296222 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 지식서비스공학대학원, 2021.2,[iv, 42 p. :] | - |
dc.description.abstract | Accurate recognition of emotions has many applications, but it is challenged by difficulties in collecting emotions in the wild. While naturally occurring emotions are expensive to collect, the inherent bias in their distribution further confounds the issue. The random sampling method frequently employed by researchers fails to overcome these limitations. We propose an adaptive sampling method based on active learning as an alternative to collect emotions with balanced distribution while reducing burdens on users. The effectiveness of adaptive sampling is empirically evaluated with the K-EmoCon, the dataset of continuous emotions and physiological signals collected in the context of naturalistic conversations. The tradeoff between collecting balanced data and querying informative samples is also explored with a parameterized query strategy. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | human-computer interaction▼aaffective computing▼aexperience sampling method▼amachine learning▼aactive learning | - |
dc.subject | 인간-컴퓨터 상호작용▼a감성 컴퓨팅▼a경험 샘플링 방법▼a기계 학습▼a능동 학습 | - |
dc.title | Towards adaptive sampling of emotions in the wild with active learning | - |
dc.title.alternative | 능동 학습을 통한 실시간 감정의 적응적 샘플링 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :지식서비스공학대학원, | - |
dc.contributor.alternativeauthor | 박철영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.