Deep Learning of Biomechanical Dynamics with Spatial Variability Mining and Model Sparsifiation
Deep Learning of Biomechanical Dynamics with Spatial Variability Mining and Model Sparsifiation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153107
- ISBN
- 9798346391654
- DDC
- 612.76
- 저자명
- Liu, Ming.
- 서명/저자
- Deep Learning of Biomechanical Dynamics with Spatial Variability Mining and Model Sparsifiation
- 발행사항
- [Sl] : Purdue University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 96 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-05, Section: A.
- 주기사항
- Advisor: Zhang, Qingxue.
- 학위논문주기
- Thesis (Ph.D.)--Purdue University, 2024.
- 초록/해제
- 요약Deep learning of biomechanical dynamics is of great promise in smart health and data-driven precision medicine. Biomechanical dynamics are related to the movement patterns and gait characteristics of human people and may provide important insights if mined by deep learning models. However, efficient deep learning of biomechanical dynamics is still challenging, considering that there is a high diversity in the dynamics from different body locations, and the deep learning model may need to be lightweight enough to be able to be deployed in real-time.Targeting these challenges, we have firstly conducted studies on the spatial variability of biomechanical dynamics, aiming to evaluate and determine the optimal body location that is of great promise in robust physical activity type detection. Further, we have developed a framework for deep learning pruning, aiming to determine the optimal pruning schemes while maintaining acceptable performance. More specifically, the proposed approach first evaluates the layer importance of the deep learning model, and then leverages the probabilistic distribution-enabled threshold determination to optimize the pruning rate. The weighted random thresholding method is first investigated to further the understanding of the behavior of the pruning action for each layer. Afterwards, the Gaussian-based thresholding is designed to more effectively optimize the pruning strategies, which can find out the fine-grained pruning schemes with both emphasis and diversity regulation.Even further, we have enhanced and boosted the efficient deep learning framework, to co-optimize the accuracy and the continuity during the pruning process, with the latter metric - continuity meaning that the pruning locations in the weight matrices are encouraged to not cause too many noncontinuous non-pruned locations thereby achieving friendly model implementation. More specifically, the proposed framework leverages the significance scoring and the continuity scoring to quantize the characteristics of each of pruned convolutional filters, then leverages the clustering technique to group the pruned filters for each convolutional stage. Afterwards, the regularized ranking approach is designed to rank the pruned filters, through putting more emphasis on the continuity scores to encourage friendly implementation. In the end, a dual-thresholding strategy is leveraged to increase the diversity in this framework, during significance & continuity cooptimization.Experimental results have demonstrated promising findings, with enhanced understanding of the spatial variability of the biomechanical dynamics and best performance body location selection, with the effective deep learning model pruning framework that can reduce the model size significantly with performance maintained, and further, with the boosted framework that cooptimizes the accuracy and continuity to all consider the friendly implementation during the pruning process. Overall, this research will greatly advance the deep biomechanical mining towards efficient smart health.
- 일반주제명
- Human mechanics
- 일반주제명
- Exercise
- 일반주제명
- Deep learning
- 일반주제명
- Computer science
- 일반주제명
- Recommender systems
- 일반주제명
- Normal distribution
- 일반주제명
- Clustering
- 일반주제명
- Camcorders
- 일반주제명
- Pattern recognition
- 일반주제명
- Gait
- 일반주제명
- Neural networks
- 일반주제명
- Biomechanics
- 일반주제명
- Accelerometers
- 일반주제명
- Human body
- 일반주제명
- Kinesiology
- 일반주제명
- Information science
- 일반주제명
- Information technology
- 기타저자
- Purdue University.
- 기본자료저록
- Dissertations Abstracts International. 86-05A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164961
■00520250211153107
■006m o d
■007cr#unu||||||||
■020 ▼a9798346391654
■035 ▼a(MiAaPQ)AAI31682035
■035 ▼a(MiAaPQ)Purdue26069641
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a612.76
■1001 ▼aLiu, Ming.
■24510▼aDeep Learning of Biomechanical Dynamics with Spatial Variability Mining and Model Sparsifiation
■260 ▼a[Sl]▼bPurdue University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a96 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-05, Section: A.
■500 ▼aAdvisor: Zhang, Qingxue.
■5021 ▼aThesis (Ph.D.)--Purdue University, 2024.
■520 ▼aDeep learning of biomechanical dynamics is of great promise in smart health and data-driven precision medicine. Biomechanical dynamics are related to the movement patterns and gait characteristics of human people and may provide important insights if mined by deep learning models. However, efficient deep learning of biomechanical dynamics is still challenging, considering that there is a high diversity in the dynamics from different body locations, and the deep learning model may need to be lightweight enough to be able to be deployed in real-time.Targeting these challenges, we have firstly conducted studies on the spatial variability of biomechanical dynamics, aiming to evaluate and determine the optimal body location that is of great promise in robust physical activity type detection. Further, we have developed a framework for deep learning pruning, aiming to determine the optimal pruning schemes while maintaining acceptable performance. More specifically, the proposed approach first evaluates the layer importance of the deep learning model, and then leverages the probabilistic distribution-enabled threshold determination to optimize the pruning rate. The weighted random thresholding method is first investigated to further the understanding of the behavior of the pruning action for each layer. Afterwards, the Gaussian-based thresholding is designed to more effectively optimize the pruning strategies, which can find out the fine-grained pruning schemes with both emphasis and diversity regulation.Even further, we have enhanced and boosted the efficient deep learning framework, to co-optimize the accuracy and the continuity during the pruning process, with the latter metric - continuity meaning that the pruning locations in the weight matrices are encouraged to not cause too many noncontinuous non-pruned locations thereby achieving friendly model implementation. More specifically, the proposed framework leverages the significance scoring and the continuity scoring to quantize the characteristics of each of pruned convolutional filters, then leverages the clustering technique to group the pruned filters for each convolutional stage. Afterwards, the regularized ranking approach is designed to rank the pruned filters, through putting more emphasis on the continuity scores to encourage friendly implementation. In the end, a dual-thresholding strategy is leveraged to increase the diversity in this framework, during significance & continuity cooptimization.Experimental results have demonstrated promising findings, with enhanced understanding of the spatial variability of the biomechanical dynamics and best performance body location selection, with the effective deep learning model pruning framework that can reduce the model size significantly with performance maintained, and further, with the boosted framework that cooptimizes the accuracy and continuity to all consider the friendly implementation during the pruning process. Overall, this research will greatly advance the deep biomechanical mining towards efficient smart health.
■590 ▼aSchool code: 0183.
■650 4▼aHuman mechanics
■650 4▼aExercise
■650 4▼aDeep learning
■650 4▼aComputer science
■650 4▼aRecommender systems
■650 4▼aNormal distribution
■650 4▼aClustering
■650 4▼aCamcorders
■650 4▼aPattern recognition
■650 4▼aGait
■650 4▼aNeural networks
■650 4▼aNatural language processing
■650 4▼aBiomechanics
■650 4▼aAccelerometers
■650 4▼aHuman body
■650 4▼aKinesiology
■650 4▼aInformation science
■650 4▼aInformation technology
■690 ▼a0984
■690 ▼a0648
■690 ▼a0800
■690 ▼a0575
■690 ▼a0723
■690 ▼a0489
■71020▼aPurdue University.
■7730 ▼tDissertations Abstracts International▼g86-05A.
■790 ▼a0183
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164961▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


