中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共24条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Optimal Pedestrian Evacuation in Building with Consecutive Differential Dynamic Programming 会议论文
, Budapest, Hungary, 2019-7-14
作者:  Zhu YH(朱圆恒);  Haibo He;  Dongbin Zhao;  Zhongsheng Hou
Adobe PDF(679Kb)  |  收藏  |  浏览/下载：61/30  |  提交时间：2023/05/22
基于平行学习的多源异构知识协同方法与应用研究 学位论文
, 中国科学院自动化研究所: 中国科学院自动化研究所, 2022
作者:  杨林瑶
Adobe PDF(42420Kb)  |  收藏  |  浏览/下载：192/13  |  提交时间：2022/06/15
平行学习  知识协同  知识图谱  图神经网络  表示学习  
Pedestrian Choice Modeling and Simulation of Staged Evacuation Strategies in Daya Bay Nuclear Power Plant 期刊论文
EEE Transactions on Computational Social Systems, 2020, 卷号: 7, 期号: 3, 页码: 686-695
作者:  Yang, Linyao;  Wang, Xiao;  Zhang, Jun Jason;  Zhou, Min;  Wang, Fei-Yue
Adobe PDF(2409Kb)  |  收藏  |  浏览/下载：149/49  |  提交时间：2022/06/15
Agent-based modeling  exit choice  pedestrian crowd evacuation  random forest (RF)  staged evacuation  
An IVC-Based Nuclear Emergency Parallel Evacuation System 期刊论文
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2021, 卷号: 8, 期号: 4, 页码: 844-855
作者:  Tan, Ke;  Yang, Linyao;  Liu, Xin;  Xu, Yancai;  Lin, Jiazhen;  Wang, Xiao;  Wang, Fei-Yue
Adobe PDF(2418Kb)  |  收藏  |  浏览/下载：259/39  |  提交时间：2021/11/02
Computational modeling  Planning  Optimization  Roads  Mathematical model  Collaboration  Power generation  ACP  intelligent vehicle collaborative system  nuclear evacuation  optimization  parallel intelligence  
Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 卷号: 22, 期号: 6, 页码: 3285-3302
作者:  Song, Xiao;  Chen, Kai;  Li, Xu;  Sun, Jinghan;  Hou, Baocun;  Cui, Yong;  Zhang, Baochang;  Xiong, Gang;  Wang, Zilie
收藏  |  浏览/下载：243/0  |  提交时间：2021/08/15
Trajectory  Predictive models  Neural networks  Force  Mathematical model  Feature extraction  Tensors  Pedestrian behavior  convolution  long short-term memory  neural network  
Optimal Feedback Control of Pedestrian Flow in Heterogeneous Corridors 期刊论文
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2021, 卷号: 18, 期号: 3, 页码: 1097-1108
作者:  Zhu, Yuanheng;  Zhao, Dongbin;  He, Haibo
收藏  |  浏览/下载：184/0  |  提交时间：2021/08/15
Microscopy  Feedback control  Mathematical model  Data models  Dynamic programming  Psychology  Computational modeling  Adaptive dynamic programming (ADP)  heterogeneous corridors  macroscopic pedestrian dynamics  optimal feedback control  pedestrian flow  
Type-2 Fuzzy Control for Driving State and Behavioral Decisions of Unmanned Vehicle 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2020, 卷号: 7, 期号: 1, 页码: 178-186
作者:  Xuanming Zhao;  Hong Mo;  Kefu Yan;  Lingxi Li
浏览  |  Adobe PDF(4151Kb)  |  收藏  |  浏览/下载：161/46  |  提交时间：2021/03/11
Fuzzy comprehensive evaluation  fuzzy control  interval type-2 fuzzy sets  unmanned vehicle  
Parallel Internet of Vehicles: ACP-Based System Architecture and Behavioral Modeling 期刊论文
IEEE INTERNET OF THINGS JOURNAL, 2020, 卷号: 7, 期号: 5, 页码: 3735-3746
作者:  Wang, Xiao;  Han, Shuangshuang;  Yang, Linyao;  Yao, Tingting;  Li, Lingxi
Adobe PDF(3157Kb)  |  收藏  |  浏览/下载：255/25  |  提交时间：2020/06/22
Cyber-physical-social system (CPSS)  parallel intelligence  parallel Internet of Vehicles (PIoV)  
State-of-the-Art Pedestrian and Evacuation Dynamics 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 卷号: 21, 期号: 5, 页码: 1849-1866
作者:  Dong, Hairong;  Zhou, Min;  Wang, Qianling;  Yang, Xiaoxia;  Wang, Fei-Yue
收藏  |  浏览/下载：236/0  |  提交时间：2020/06/22
Mathematical model  Data collection  Data models  Analytical models  Computational modeling  Vehicle dynamics  Dynamics  Pedestrian dynamics  evacuation dynamics  data collection  mathematical modelling  fundamental diagram  
A Recurrent Attention and Interaction Model for Pedestrian Trajectory Prediction 期刊论文
Journal of Automatica Sinica, 2020, 期号: *, 页码: *
作者:  Li Xuesong;  Liu Yating;  Wang Kunfeng;  Wang Fei-Yue
浏览  |  Adobe PDF(5533Kb)  |  收藏  |  浏览/下载：169/47  |  提交时间：2020/06/08
Trajectory prediction  recurrent attention and interaction model  Long Short-Term Memory  deep learning