|
香港科技大学可视化实验室积极参与国家和香港的重大研发项目,累计主持或参与的资助金额在千万级别的项目6项,涉及的范围非常广泛,包括在线教育,智慧城市,大数据等。
主持:
HKUST-MIT Consortium ITF project "An Open Learning Design, Data Analytics and Visualization Framework for E-Learning" (时间: 2016-2020; 金额: 一千六百万港币)
研究内容:
該項目的目標是為 MOOC 教師、教學設計師、機構負責課程的領導和學習科家開發一個開放性的框架。該框架將集成三個主要的電子學習技術組件:1)學 習和評估設計的模型和工具,用以指導并支持電子學習課程的設計,以及具體學 習分析和評估要求的提前規劃; 2)对學習行為分析和預測的分析方法,用以促進 個性化在線學習并提高MOOC課程的保留率; 3)用於理解MOOC平臺所搜集 的海量數據以及數據分析結果的可視化界面。我們將基於該框架實現一套開放源 碼系統,並使用該系統對香港科技大學、麻省理工學院、和香港大學的多個實際 的 MOOC 課程和混合型課程進行試點研究。 該項目的成果將包括:可用於電子 學習課程設計的新型方法與工具套件;經過驗證的可用於電子學習的教學方法和 評估設計的模型;可用於學習行為分析和預測的新型數據分析與可視化方法;一 套詳盡的用於 MOOC 課程設計和數據分析的開源系統;以及基於多所大學試點 研究得到的關於電子學習的新發現。
参与:
国家973计划项目: “网络信息空间大数据计算理论” (PI: 怀进鹏;时间:2014-2018; 金额:三千万人民币)
研究内容:国家973计划项目“网络信息空间大数据计算理论”由北京航空航天大学牵头,怀进鹏院士任首席科学家。本项目围绕网络信息空间大数据计算中“近似处理、增量计算、多源归纳”的计算属性,归纳为大数据计算的“3I”特征,即近似性(Inexact)、增量性(Incremental)和归纳(Inductive),进而聚焦三个关键科学问题:(1)多源异构数据的量化表示问题;(2)动态数据处理算法的量效均衡问题;(3)大数据计算架构的存算联动问题。本项目拟在这三个科学问题的研究上取得突破,建立大数据计算的易解类复杂性与算法理论,突破多源异构大数据的量化表示方法、大数据计算的模型与算法设计、大数据计算的系统架构与核心机制、大数据分析与挖掘处理等关键技术,研制大数据分析与挖掘处理系统,产生一批在国际上具有重大影响力的原创成果,并通过两种典型应用示范,显著提高我国网络信息空间大数据挖掘处理的综合能力和水平,培养一批从事大数据计算研究和工程技术的创新人才,为国家安全和经济社会发展做出实质贡献。
本项目由北京航空航天大学联合中国科学院软件研究所、上海交通大学、中国人民解放军国防科学技术大学、广州市香港科大霍英东研究院、华为技术有限公司、国家计算机网络与信息安全管理中心、北京百度网讯科技有限公司等单位共同承担
香港政府主题研究计划: “大數據為本智能及個人化空氣污染監測和健康管理“ (PI: 李安國; 时间:2018-2022; 金额:五千万港币)
Big Data for Smart and
Personalized Air Pollution Monitoring and Health Management
Project Coordinator: Prof Victor On-kwok
LI (HKU)
研究内容:每個人都有權享受清潔環境並有尊嚴地生活。借助大數據技術,可以收集複雜,多樣化,高分辨率,個人化和同步的城市空氣污染,個人活動,健康狀況,幸福感和行為數據,從而產生智能(實時和互動)及個人化健康提示和建議,以改善公民健康和幸福感,為香港及其他地區的資訊科技和健康產業創造嶄新商機和競爭優勢。此項研究有五項挑戰。第一,城市空氣質量數據稀疏,難以及時提供個人化的提示和建議。第二,收集到的數據,尤其涉及人為輸入的,如個人健康評估,往往出現錯漏。第三,收集到的數據往往多樣化,複雜,不容易理解,不便利個人或集體根據數據直接作決策。第四,有關香港的年輕哮喘病患者和年輕健康公民的個人空氣污染物暴露(尤其是直徑小於或等於2.5微米和1.0微米顆粒物)與個人健康狀況和健康生活質素(幸福感)的因果關係尚未確立。第五,提供智能資訊及相關建議是否能影響個人生活行為有待確立。要克服這些挑戰,此研究第一項創新是創建一個深度學習大數據框架,以此提供智能個人化空氣質量估算。第二個創新是採用移動污染傳感器平台,大幅度提高估算和預測空氣質量的精準度;以及收集個人活動,健康狀況和健康評估數據,並矯正人為輸入數據。第三個創新是設計可視化工具,將個人污染暴露及其他四種個人數據相連結,以容易理解的指標呈視用者,以提供及時和個人化的空氣污染,健康和出行活動提示建議。第四個創新是向香港250名年輕哮喘病患者及250名年輕健康市民進行臨床研究,確定個人污染物暴露,即個人受直徑小於或等於2.5微米和1.0微米顆粒物和二氧化氮暴露,和個人健康狀況及個人健康生活質素評估之間的因果關係。從250名香港年輕哮喘病患者收集到的真實數據將用作暴露模型的開發,訓練和驗證,以進一步向香港九成哮喘病患者展開人口時間序列健康研究。第五個創新是智能資訊介入性研究,以確定我們提出之大數據系統所提供的智能數據是否能引發個人行為轉變。此嶄新大數據技術及分析方法為個人化空氣污染監測和電子健康質素管理創造獨特跨學科框架模型,隨時可轉用於其它領域及城市。
We are all entitled to live with dignity
in a clean environment. With big data
technologies, it is possible to collect
complex, heterogeneous, high resolution,
personalized, and synchronized urban air
pollution, human activity, health
condition, well-being, and behavioral
data, enabling the generation of smart
(real-time and interactive), personal
alert and advice to improve the health and
well-being of individual citizens,
creating new business opportunities and
competitive advantage for the IT and
health industry in HK and beyond. There
are five major challenges. FIRST, urban
air quality data is sparse, rendering it
difficult to provide timely personalized
alert and advice. SECOND, collected data,
especially those involving human inputs,
such as health perception, are often
missing and erroneous. THIRD, data
collected are heterogeneous, and highly
complex, not easily comprehensible to
facilitate individual or collective
decision-making. FOURTH, the causal
relationships between personal air
pollutants exposure (specifically
PM(2.5,1.0) and NO2) and personal health
conditions, and health (well-being)
perception, of young asthmatics and young
healthy citizens in HK, are yet to be
established. FIFTH, one must determine if
information and advice provided can effect
behavioral change. To overcome these
challenges, our FIRST novelty is to
develop a big data framework based on deep
learning to estimate smart personalized
air quality. Our SECOND novelty includes
the deployment of mobile pollution sensor
platforms to substantially improve the
accuracy of estimated and forecasted air
quality data, and the collection of
activity, health conditions and perception
data, accounting for human in the loop.
Our THIRD novelty is the development of
visualization tools, and comprehensible
indexes which correlate personal exposure
with four other types of personal data, to
provide timely, personalized pollution,
health and travel alerts and advice. Our
FOURTH novelty is determining causal
relationship, if any, between personal
pollutants, PM(2.5,1.0), NO2 exposure and
personal health conditions, and also
personal health perceptions, based on
clinical experiments of 250 young
asthmatics and 250 young healthy citizens
in HK. An exposure model is developed,
trained and verified with real data
collected by 250 young asthmatics to
further conduct population-based time
series health study on 90% of asthmatics
in HK. Our FIFTH novelty is an
intervention study to determine if smart
data, presented via our proposed system,
will induce personal behavioral change.
Our novel big data technologies and
analytical approaches create a unique
framework for personalized air pollution
monitoring and e-health management, easily
transferrable to and applicable in other
domains and countries.
香港政府主题研究计划:數碼世代公民素養的學習和評估 (PI: 羅陸慧英;时间:2017-2021; 金额:两千万港币)
長久以來,人們都認為掌握了3R(閱讀,寫作和算術)便具有足以應付在社會上生活的基本技能。然而,數碼技術的出現,不僅加速了社會、經濟、政治和文化變革的步伐,同時也壓縮了時空距離。社交媒體、社交網絡技術和數碼移動技術的普及化已經改變了人們的工作和休閒生活,並為我們的福祉帶來了新的可能性和新的挑戰。為了確保能夠有效參與社交和工作,以及有關個人和社會利益的事情,21世紀公民需要具備(1)數碼資訊素養(包括流暢利用數碼技術、新媒體素養和網絡安全的能力); (2)合作解難的能力(包括利用批判性思維、創造力、協作和溝通能力,解決現實生活遇到的問題); (3)自我調節; (4)承擔風險的意願。我們假設這四種能力是 數碼公民素養的標誌。
雖然我們不難可以找到建基於研究結果,適用於不同時年齡段的3R課程、教學法和評估基準,有關數碼公民素養的研究卻非常匱乏。本項目將有助於我們理解數碼公民素養差異背後的因素,以及家庭和學校因素對其發展的影響。我們還會提供一個網上電子學習、數據收集和評估的平台,推動數碼公民素養研究的持續發展。協作解難(CPS)是數碼公民素養的關鍵能力;為此重點,我們會開發一個在線嚴肅遊戲的門戶網站,為評估及研究CPS的有效學習設計兩個目標服務。
Project Title: Learning and Assessment for Digital Citizenship
Project Coordinator: Prof Nancy Wai-ying LAW (HKU)
The project aims are to develop a research programme to (1) establish the key dimensions and indicators, as well as assessment instruments, for the establishment of developmental milestones for digital citizenship from childhood to young adulthood (age 7 to 22); (2) develop an online role play simulation game platform for fostering and assessing digital literacy and collaborative problem solving (two key digital citizenship competencies) for adolescents and young adults; (3) develop pedagogical theory and design principles for fostering digital citizenship based on massive empirical e-learning and assessment data; and (4) identify the family and school factors that contribute to the development of digital citizenship.
Mastery of the 3 Rs (Reading, wRiting and aRithmetic) has long been considered adequate for competent functioning in society. However, the advent of digital technology has not only accelerated the pace of social, economic, political and cultural changes, but also led to space-time compression. The emergence of social media and social networking technologies and increasing accessibility of digital mobile technologies have changed the worlds of work and leisure, and brought about new solutions and new challenges to our well-being. To ensure effective participation in the workplace, as well as personal and social well-being, citizens in the 21st century need to possess (i) digital literacy (technological fluency, media literacy and cyber-wellness); (ii) collaborative problem-solving ability (the holistic exercise of critical-thinking, creativity, collaboration and communication skills to address real-life problems through self-directed inquiry); (iii) self-regulation; and (iv) willingness to take risks. We assume that these four competencies are the hallmarks of digital citizenship.
Although there are research-informed, age-appropriate curricula, pedagogy and benchmarks for the 3Rs, there is a dearth of research on digital citizenship. This project will contribute to our basic understanding of developmental differences in the competencies that underlie digital citizenship and the family and school factors that contribute to their development. We will also deliver an online e-learning, data-collection and assessment platform for sustained research on digital citizenship. Collaborative problem solving (CPS), a key dimension of digital citizenship, is selected for focused study. An online serious game portal will be developed to serve the dual purpose of assessing CPS and investigating the effectiveness of different learning designs to support CPS development in diverse learners.
汇丰银行150周年项目:Personalised real-time air quality informatics system for exposure - Hong Kong (PRAISE-HK) (PI: Alexis Lau; 时间:2017-2021;金额:四千六百万港币)
香港科技与创新项目 (ITF): 異構數據下的大數據平臺及其在智能交通中的應
用 (PI: 杨强和宗福季;时间2015-2017;金额:一千万港币)
Big data platform for smart transportation applications with heterogeneous data sources
We plan to carry out research and development to build a big data platform toaddress some critical problems in Hong Kong’s transport industry. Today, HongKong faces increasing demand in transporting people across the city safely and efficiently. Two particular problems present themselves: (1) how to effectively monitor and control the crowds in transport stations so that early warnings can be given on potential dangers as a result of crowd buildup, and (2) how to ensure smooth operation of the transport system by forecasting potential major equipment failure? We plan to solve these two problems using solutions supported by a big-data platform that is specially tailored for smart transport applications.
Big data is characterized by the data complexities related to volume,
variety,velocity. In Hong Kong’s transportation system, various data
sources are available, ranging from surveillance videos to twitter chats. These
heterogeneous data arrive in in an amazing speed and in great volume. The
big data platform will be designed and developed to integrate these data and
transform them into structure and easy-to-query formats. Then, a suite of
analytic tools will be applied to elicit useful patterns and information from the
data. Finally, specific application-drive models are applied to automatically
monitor the current situations and make forecasts. A closed-loop optimization
module is also designed for decision support.
Our proposed approach is unique in that the big-data platform fuses together many state-of-the-art big-data research topics such as data fusion, data analytics, human factors, optimization/visualization, transfer learning, simulation and operations research. It is also unique in that, in this project, academia, industry and government will work closely together to build an interdisciplinary and cross-domain solution for problems pertinent to Hong Kong. The Big Data platform will help build smart transport solutions for operators in moving people and goods efficiently and safely, and enhancingcitizen’s quality of living in a smart city.
Archiver|手机版|科学网 ( 京ICP备07017567号-12 )
GMT+8, 2024-9-1 14:27
Powered by ScienceNet.cn
Copyright © 2007- 中国科学报社