DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Sung-Ju | - |
dc.contributor.advisor | 이성주 | - |
dc.contributor.author | Gong, Taesik | - |
dc.date.accessioned | 2023-06-23T19:34:39Z | - |
dc.date.available | 2023-06-23T19:34:39Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1030593&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309266 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전산학부, 2023.2,[viii, 108 p. :] | - |
dc.description.abstract | Mobile sensing utilizes sensors from mobile devices (e.g., smartphones and wearables) to infer user contexts and provide appropriate services accordingly. Integrated with deep learning, which enables the understanding of multi-dimensional sensory data, mobile sensing has broad applications ranging from human activity recognition to mobile healthcare. However, we found that various factors such as different users, devices, and environments impact the performance of such applications, thus making the domain shift (i.e., distributional shift between the training domain and the target domain) a critical issue in mobile sensing. To overcome the domain shift in mobile sensing, this thesis proposes four approaches. First, we propose a meta-learning-based adaptation framework that utilizes very few data instances from a target user. Second, we propose a similar condition detector that identifies when the unseen condition has similar characteristics to seen conditions and leverages this hint to further improve the accuracy. Third, to eliminate the labeling burden and adapt to gradually changing environments, we propose a test-time adaptation scheme that adapts to a target user's domain during inference without any data collection. Lastly, to reduce the uncertainty of the performance after adaptation, we present a framework that estimates the adaptation performance in a target domain with only unlabeled target data. Our evaluation with real-world datasets indicates that the proposed methods not only outperform the baselines but also significantly reduce computational overhead, which is crucial for resource-constrained mobile devices. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Mobile sensing▼aDeep learning▼aDomain shift▼aDomain adaptation▼aPersonalization | - |
dc.subject | 모바일 센싱▼a딥러닝▼a도메인 변화▼a도메인 적응▼a개인화 | - |
dc.title | Overcoming domain shift in mobile sensing via machine learning | - |
dc.title.alternative | 모바일 센싱에서의 도메인 변화 극복을 위한 기계학습 연구 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 공태식 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.