報告人：程濤 英國倫敦大學(xué)學(xué)院 教授

時間：2023年5月12日（周五）,，14:00-16:00

地點：綜合樓二樓國際會議廳

Tao Cheng ([email protected]),，SpaceTimeLab

Department of Civil, Environmental and Geomatic Engineering, University College London

報告摘要

當(dāng)前時空智能(SpaceTimeAI)和地理空間智能(GeoAI)已是熱門的話題, 該研究領(lǐng)域旨在將計算機科學(xué)的最新方法(如深度學(xué)習(xí))應(yīng)用于地理空間問題,。雖然深度學(xué)習(xí)方法因其對柵格數(shù)據(jù)的自然適用性而在圖像處理中取得了巨大成功, 但仍未廣泛應(yīng)用于其他空間和時空數(shù)據(jù)類型,。本演講提出了使用基于網(wǎng)絡(luò)(和圖)的框架作為一般空間結(jié)構(gòu)來表示通常由點,、折線和多邊形表示的時空過程的命題,。我們舉例說明了網(wǎng)絡(luò)和基于圖的SpaceTimeAI,，從基于圖的深度學(xué)習(xí)預(yù)測,，到時空聚類和優(yōu)化,。這些應(yīng)用展示了基于網(wǎng)絡(luò)(圖)的SpaceTimeAI在智慧城市應(yīng)用中的優(yōu)勢,，并介紹其在交通出行、警務(wù)和公共衛(wèi)生等領(lǐng)域的應(yīng)用,。

Abstract

SpaceTimeAI and GeoAI are currently hot topics, applying the latest algorithms in computer science, such as deep learning, to spatiotemporal data. Although deep learning algorithms have been successfully applied to raster data due to their natural applicability to image processing, their applications in other spatial and space-time data types are still immature. This talk sets up the proposition of using a network (& graph)-based framework as a generic spatial structure to present space-time processes that are usually represented by the points, polylines, and polygons. We illustrate network and graph-based SpaceTimeAI, from graph-based deep learning for prediction, to space-time clustering and optimisation. These applications demonstrate the advantages of network (graph)-based SpaceTimeAI for smart cities applications including transport & mobility, crime & policing, and public health.

Reference: http://jggs.chinasmp.com/EN/10.11947/j.JGGS.2022.0309

個人簡介及照片：

程濤教授是倫敦大學(xué)學(xué)院地理信息學(xué)教授,，圖靈研究所研究員，大數(shù)據(jù)分析SpaceTimeLab (www.ucl.ac.uk/spacetimelab)的創(chuàng)始人和主任,。這是一個多學(xué)科研究中心,，旨在從政府、商業(yè)和社會的地理位置和時間戳的數(shù)據(jù)中獲得可操作的見解和遠見,。她的研究興趣包括人工智能和大數(shù)據(jù),、網(wǎng)絡(luò)復(fù)雜性、城市分析（建模,、預(yù)測,、聚類、可視化和模擬）,，及其在交通,、商業(yè)、健康,、社交以及犯罪和自然災(zāi)害預(yù)防等方面的應(yīng)用,。她在英國和歐盟獲得了2500多萬英鎊的研究經(jīng)費，與英國的多個政府機構(gòu)和企業(yè)有深度合作,，包括倫敦交通局(TfL),，倫敦大警察局(London Metropolitan Police) ，英格蘭公共衛(wèi)生部(Public Health England) , 奧雅納全球公司(ARUP)等,。她發(fā)表了280多篇研究論文,，并獲得了眾多國際最佳論文獎。

Biography

Tao Cheng (HDR, PhD, FICE, CEng) is a Professor in GeoInformatics, Fellow of Turing Institute, the Founder and Director of SpaceTimeLab for Big Data Analytics (www.ucl.ac.uk/spacetimelab) at University College London, a multi-disciplinary research centre that aims to gain actionable insights and foresights from geo-located and time-stamped data for government, business and society. Her research interests span AI and Big Data, network complexity, urban analytics (modelling, prediction, clustering, visualisation and simulation) with applications in transport and mobility, safety and security, business intelligence, and natural hazards prevention. She has secured more than ￡25M research grants in the UK and EU, working with government and industrial partners in the UK including Transport for London, the London Metropolitan Police Service, Public Health England and Arup, to name a few. She has published over 280 research articles and received numerous international best paper awards.

https://iris.ucl.ac.uk/iris/browse/profile?upi=TCHEN23

航海學(xué)院

國際合作與交流處

2023年5月10日