基本信息
浏览量:14
职业迁徙
个人简介
Shenhao Wang is a Postdoctoral Associate at MIT Urban Mobility Lab. His research interest is at the interaction of machine learning, decision-making theories, and urban transportation applications. His recent work examines how to extract economic information from the “black box” deep neural networks, improving the interpretability of DNNs and generating mutual insights between deep learning and classical choice modeling. He also works on decision-making under uncertainty with joint machine learning and individual behavioral perspectives. Particularly, he uses classical prospect theory to understand how people respond to the uncertainty in autonomous vehicles (AVs) and uses a robust machine learning framework to reduce the analytical uncertainty for AVs. Currently, he is working on the social justice of transportation policies, integration of urban systems through the machine learning framework, and demand analysis with unstructured data. Shenhao Wang obtained an interdepartmental Ph.D. in Computer and Urban Science from MIT in 2019. He has B.A. in Economics from Peking University and B.A. in architecture and law from Tsinghua University, Master of Science in Transportation, and Master of City Planning from MIT.
Research Projects: SMART, MIT Energy Initiative
Research Interests: Machine Learning, Decision-Making Theory, Transport Policy, Automated Vehicle Analytics, Chinese Urbanization and Motorization
Research Projects: SMART, MIT Energy Initiative
Research Interests: Machine Learning, Decision-Making Theory, Transport Policy, Automated Vehicle Analytics, Chinese Urbanization and Motorization
研究兴趣
论文共 43 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Nature Citiespp.1-10, (2024)
arxiv(2024)
引用0浏览0引用
0
0
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL (2024): 102869
Nature Citiespp.1-13, (2024)
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMSno. 99 (2024): 1-12
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn