报告题目: Big Data Driven Human Mobility for Smart Transportation
报告题目：Big Data Driven Mobility to Tackle Urban Traffic and Electric Vehicle Management主讲人：许岩岩（Department of Civil and Environmental Engineering, MIT）报告时间：2017年10月20日3:30pm – 4:30pm报告地点：山东大学 青岛校区振声苑南楼s204摘要：Understanding human mobility has many applications in diverse areas, including spread of diseases, city planning, traffic engineering, financial market forecasting, and nowcasting of economic well-being. In the past years, we have studied problems concerning the use of various sources of large-scale data to better inform human mobility and collective travel behavior in cities. In this presentation, I will introduce two main works on the applications of human mobility: traffic demand management and the Electric Vehicles charging planning. In the first task, our target is to understand the impact of mega events using multiple data resources and design feasible travel demand management strategy for a global mitigation of traffic congestion. In the second one, we simulate the travel behavior of more than 500 million population in San Francisco Bay Area in USA, and assign each vehicle driver a probability of using EV. Then we couple the urban mobility with EV charging plan to alleviate the pressure of power grid from the EV charging. Finally, we shift the arrival and departure times of EV drivers to reduce the peak load of EV energy demand in the working area.报告人简介：Yanyan Xu is a postdoctoral associate in the Human Mobility and Networks Lab, Department of Civil and Environmental Engineering, MIT. He is also a visiting scholar at the Department of City and Regional Planning, University of California, Berkeley. He received PhD in Pattern Recognition and Intelligent Systems from Shanghai Jiao Tong University, China, in 2015. He works in the fields of data mining, human mobility, with a focus on the use of information and communication technology and big data in City problems, including Transportation Systems, Environment, and Urban Planning. Specific projects include urban traffic flow prediction, travel demand management using big data; measuring the air pollution exposure with mobile phone data; and coupling electric vehicle charging with urban mobility, etc. His work has been published in the J. Roy. Soc. Interface, IEEE Trans. ITS, J. Adv. Transp., TRB, among others.
This abstract tells me a lot of stories about itself. Here I want to
discuss two stories about it.
It has demonstrated an excellent job of promoting and abstracting itself to a higher level by playing with words. The work this abstract has done is merely proposing a new land classification system using big data. Essentially, the contribution in this abstract could be nothing new to the scientific literature because a lot of similar work have been done. For example, Soto and Frías-Martínez (2011) conducted an land use identification using mobile phone data, a typical kind of big data. So does Toole et al. (2012). Urban structure, another term which is the other side of urban land use in my opinion, has been also analyzed by many scholars (Long and Liu, 2013; Yuan et al., 2013). But this abstract, by using some philosophical terms in this field, indicated its ‘novelty’ in a very smart way. Let us find that out one by one.
In this abstract, the tile used a term ‘typology’, instead of using the more mediocre term ‘classification’, giving the readers a epistemology-level sense of academic research. In the end of first paragraph, it explained its difference with conventional land use classification which is unit of analysis and the continuity of time and space. Unit of analysis, I suppose, means the basic units this abstract identified are more homogeneous in terms of some characteristics. Thus, as the big data has the time dimension, the new classification using big data did improve its temporal and spatial continuity. All in all, this abstract did not contribute so much as it claimed itself; what it did contribute is just to summarize the implications of this big-data-based land use classification method.
Also, this abstract showed its capability of hiding itself from being probed into. Through the whole abstract, it didn’t say a single word about operationalization and how it is going to do. I guess the author could possibly deleted this operation part which was supposed to be in the second paragraph in this abstract. But, we can not criticize it too much because it is a precaution measure in academic communication scenarios, especially in an academic conference like AAG several thousands of people attended.
Soto, V., & Frías-Martínez, E. (2011). Automated land use identification using cell-phone records. Paper presented at the Proceedings of the 3rd ACM international workshop on MobiArch.
Toole, J. L., Ulm, M., González, M. C., & Bauer, D. (2012). Inferring land use from mobile phone activity. Paper presented at the Proceedings of the ACM SIGKDD International Workshop on Urban Computing.
Long, Y., & Liu, X. (2013). Automated identification and characterization of parcels (AICP) with OpenStreetMap and Points of Interest.
Yuan, J., Zheng, Y., & Xie, X. (2012). Discovering Regions of Different Functions in a City Using Human Mobility and POIs. Paper presented at the ACM KDD, Beijing, China.
Abstract Title: Redefining the Typology of Land Use with Big Data
Author(s): ***永利电玩城网址49696com， - Massachusetts Institute of Technology
Abstract: According to the Wall Street Journal, "check in" was the 12th most popular word of 2010. The underlying picture of this phenomenon is that information sharing and location based services have been so easy in the city. Compared with conventional land use data, these types of big data might tell us much about how urban land is being used in a more dynamic and human-respected way. However there has been few researches focusing on the new opportunities brought by big data onto urban land use classification—the basic "language" of urban geography and planning. In this context, this paper builds a new theoretical framework for urban land use description, and redefines the concept of "land use" in multiple scales of urban geographies. Compared with the conventional land use classification, this new framework is more specific on the key issues of urban geography, such as the unit of analysis and the continuity of time and space.
The new framework of land use typology will challenge our conventional view on land use. Its implication could include but not only: 1) Change the way that land use is defined in the field of urban planning; 2) Develop land use as a language to describe urban activities and settlement; 3) Connect land use typology with broader fields such as travel behavior/transportation analysis, energy consumption of land use, density and urban form and so on.
Keywords: Urban land use; land use categorization; location based big data
永利电玩城，报告简介: Understanding human mobility has many applications in diverse areas, including spread of diseases, city planning, traffic engineering, financial market forecasting, and nowcasting of economic well-being. In the past years, we have studied problems concerning the use of various sources of large-scale data to better inform human mobility and collective travel behavior in cities. In this presentation, I will introduce two works related to human mobility: the Electric Vehicles charging planning using mobile phone data and travel time estimation using deep learning. In the first task, we couple the urban mobility with EV charging plan to alleviate the pressure of power grid from the EV charging, using massive mobile phone data to infer the individual mobility of EVs in San Francisco Bay Area in USA. In the second task, we model the travel delay by learning features from map images using deep learning, and present an end-to-end deep learning framework to estimate the travel time in urban road networks. These results open avenues for smart transportation planning using big data and AI.
报告人简介: 许岩岩是加州大学伯克利分校城市与区域规划系博士后学者。许岩岩分别于2007年和2010年获山东大学信息科学与工程学院学士和硕士学位，于2015年获上海交通大学模式识别与智能系统博士学位，并于2015年至2018年在麻省理工学院土木与环境工程系担任博士后助理。2017年至2018年，任劳伦斯伯克利国家实验室能源分析与环境影响部访问博士后。许岩岩的学术论文发表在Nature Energy, IJCAI, IEEE Trans. ITS, Journal of The Royal Society Interface, CEUS等期刊，是Nature energy, Data Mining and Knowledge Discovery等期刊的审稿人。研究方向包括数据挖掘、人类流动、城市计算等领域，特别强调从跨学科的角度将大量轨迹数据用于智能交通系统、智能城市、环境和能源。