Search

Your search keyword '"Duan, Ke"' showing total 703 results
Start Over Author "Duan, Ke"
703 results on '"Duan, Ke"'

1. Novelty-based Sample Reuse for Continuous Robotics Control

Author

Duan, Ke, Yang, Kai, Liu, Houde, and Wang, Xueqian

Subjects
Computer Science - Robotics, Computer Science - Machine Learning
Abstract

In reinforcement learning, agents collect state information and rewards through environmental interactions, essential for policy refinement. This process is notably time-consuming, especially in complex robotic simulations and real-world applications. Traditional algorithms usually re-engage with the environment after processing a single batch of samples, thereby failing to fully capitalize on historical data. However, frequently observed states, with reliable value estimates, require minimal updates; in contrast, rare observed states necessitate more intensive updates for achieving accurate value estimations. To address uneven sample utilization, we propose Novelty-guided Sample Reuse (NSR). NSR provides extra updates for infrequent, novel states and skips additional updates for frequent states, maximizing sample use before interacting with the environment again. Our experiments show that NSR improves the convergence rate and success rate of algorithms without significantly increasing time consumption. Our code is publicly available at https://github.com/ppksigs/NSR-DDPG-HER.

Published
2024

10. Effect of Audio Prompt on Multistage Lane-Changing Behavior in Work Zone Area

Author

Duan, Ke, Ma, Sheqiang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Wang, Wuhong, editor, Guo, Hongwei, editor, Jiang, Xiaobei, editor, Shi, Jian, editor, and Sun, Dongxian, editor

Published
2024
Full Text
View/download PDF

15. MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis

Author

Zhang, Haodi, Xu, Chenyu, Liang, Peirou, Duan, Ke, Ren, Hao, Cheng, Weibin, and Wu, Kaishun

Subjects
Computer Science - Machine Learning, Computer Science - Symbolic Computation
Abstract

Recent studies show that deep learning models achieve good performance on medical imaging tasks such as diagnosis prediction. Among the models, multimodality has been an emerging trend, integrating different forms of data such as chest X-ray (CXR) images and electronic medical records (EMRs). However, most existing methods incorporate them in a model-free manner, which lacks theoretical support and ignores the intrinsic relations between different data sources. To address this problem, we propose a knowledge-driven and data-driven framework for lung disease diagnosis. By incorporating domain knowledge, machine learning models can reduce the dependence on labeled data and improve interpretability. We formulate diagnosis rules according to authoritative clinical medicine guidelines and learn the weights of rules from text data. Finally, a multimodal fusion consisting of text and image data is designed to infer the marginal probability of lung disease. We conduct experiments on a real-world dataset collected from a hospital. The results show that the proposed method outperforms the state-of-the-art multimodal baselines in terms of accuracy and interpretability.

Published
2022

30. Research on the Mode of the Innovation and Entrepreneurship Education Serving Rural Revitalization Strategy in Colleges and Universities

Author

Duan, Ke, Yang, Xiaolong, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Ali, Ghaffar, editor, Birkök, Mehmet Cüneyt, editor, and Khan, Intakhab Alam, editor

Published
2022
Full Text
View/download PDF

46. Tuning the through-thickness orientation of 1D nanocarbons to enhance the electrical conductivity and ILSS of hierarchical CFRP composites

Author

He Yonglyu, Ju Su, Duan Ke, Tang Jun, Bai Shuxin, Jiang Dazhi, Pei Yingying, and Zhang Jianwei

Subjects
orientation tuning, electrical conductivity, ilss, Materials of engineering and construction. Mechanics of materials, TA401-492
Abstract

In this article, we proposed a novel but simple multilayer resin film infusion-compressive molding (MLRFI-CM) manufacturing process that can harness the resin shear flow to architect hierarchical carbon fiber reinforced polymer (CFRP) composites with tunable 1D nanocarbons orientation. Via this novel process, we demonstrated that the orientation of two typical 1D nanocarbons, namely, the carbon nanotubes (CNTs) and carbon nanofibers (CNFs), can be successfully tuned via altering the infusion time and that the tuning strategy is especially effective toward CNTs. Further, the structure-performance relationships between the electrical conductivity/interlaminar shear strength (ILSS) and filler through-thickness orientation of the hierarchical CFRP composites is explored and compared. In the best case, with only 0.3 wt% of CNTs, the ILSS of CFRP composites revealed an increase of 19.7%, and the through-thickness conductivity demonstrated an increase of 38%.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results