東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges : = Air Pollution Reduction and Traffic Management.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges :/
其他題名:	Air Pollution Reduction and Traffic Management.
作者:	Iyer, Shiva Radhakrishnan.
面頁冊數:	1 online resource (127 pages)
附註:	Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
Contained By:	Dissertations Abstracts International83-10B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28865197click for full text (PQDT)
ISBN:	9798426804944

Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges : = Air Pollution Reduction and Traffic Management.
Iyer, Shiva Radhakrishnan.

Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges :Air Pollution Reduction and Traffic Management. - 1 online resource (127 pages)

Source: Dissertations Abstracts International, Volume: 83-10, Section: B.

Thesis (Ph.D.)--New York University, 2022.

Includes bibliographical references

Data Science and AI-driven solutions are abounding today for a large variety of practical applications. With a continuing focus on urban development and sustainability, in this thesis, I present our attempts in addressing two prominent urban challenges -- urban air pollution control and road traffic congestion management. For both these applications, we have developed novel methods, such as the message-passing recurrent neural network, for predictive analytics and inference in collaboration with economists, public policy experts and ICTD researchers. The city of Delhi has 32 air quality monitors over an area of about 900 sq km, but we do not have information on fine-grained variations in air quality in the city in order to reason about citizen exposure and identify hotspots. We have installed 28 low-cost sensors, many of them concentrated in the south Delhi region. We have identified many hotspots by studying spatio-temporal variations from the data, further motivating the need for fine-grained sensing. And ultimately, we designed a novel model combining geostatistics and deep learning that is able to make spatio-temporal pollution forecasts by the hour with an MAPE of about 10% across all locations.Urban traffic management is another pressing challenge in an era where we observe increasing urbanization and industrialization. Simply building new lanes and larger roads is not enough -- we need to go back to formula and understand how jams happen, and how we can effectively implement traffic control. In the first of our works, we show that road networks can experience traffic jams over prolonged periods, as high as 20 hours sometimes, due to sudden traffic bursts over short time scales. We illustrate this using real data from two different cities -- New York and Nairobi. We provide a formalism for understanding the phenomena of traffic collapse and sudden jams. In the second work, we devise a novel model called the message-passing neural network for modeling the propagation of congestion within a road network and forecasting congestion. The MPRNN achieves the lowest mean error of 0.3 mph when predicting ahead in 10 minute intervals, for up to 3 road segments ahead (message passing across 3 hops). Finally, in the third work, we describe an algorithm for signal control in free-flow road networks, inspired from congestion control in computer networks. Our proposed method significantly enhances the operational capacity of free-flow road networks in the real world by several orders of magnitude (3x-5x) and prevents congestion collapse.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798426804944Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Air pollutionIndex Terms--Genre/Form:

542853
Electronic books.

Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges : = Air Pollution Reduction and Traffic Management.
LDR:04125nmm a2200457K 4500 001 2362318
005 20231027103958.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798426804944
035 $a (MiAaPQ)AAI28865197
035 $a AAI28865197
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Iyer, Shiva Radhakrishnan. $3 3703041
245 1 0 $a Data-Driven Solutions for Addressing Two Pressing Urban Sustainability Challenges : $b Air Pollution Reduction and Traffic Management.
264 0 $c 2022
300 $a 1 online resource (127 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
500 $a Advisor: Subramanian, Lakshminarayanan.
502 $a Thesis (Ph.D.)--New York University, 2022.
504 $a Includes bibliographical references
520 $a Data Science and AI-driven solutions are abounding today for a large variety of practical applications. With a continuing focus on urban development and sustainability, in this thesis, I present our attempts in addressing two prominent urban challenges -- urban air pollution control and road traffic congestion management. For both these applications, we have developed novel methods, such as the message-passing recurrent neural network, for predictive analytics and inference in collaboration with economists, public policy experts and ICTD researchers. The city of Delhi has 32 air quality monitors over an area of about 900 sq km, but we do not have information on fine-grained variations in air quality in the city in order to reason about citizen exposure and identify hotspots. We have installed 28 low-cost sensors, many of them concentrated in the south Delhi region. We have identified many hotspots by studying spatio-temporal variations from the data, further motivating the need for fine-grained sensing. And ultimately, we designed a novel model combining geostatistics and deep learning that is able to make spatio-temporal pollution forecasts by the hour with an MAPE of about 10% across all locations.Urban traffic management is another pressing challenge in an era where we observe increasing urbanization and industrialization. Simply building new lanes and larger roads is not enough -- we need to go back to formula and understand how jams happen, and how we can effectively implement traffic control. In the first of our works, we show that road networks can experience traffic jams over prolonged periods, as high as 20 hours sometimes, due to sudden traffic bursts over short time scales. We illustrate this using real data from two different cities -- New York and Nairobi. We provide a formalism for understanding the phenomena of traffic collapse and sudden jams. In the second work, we devise a novel model called the message-passing neural network for modeling the propagation of congestion within a road network and forecasting congestion. The MPRNN achieves the lowest mean error of 0.3 mph when predicting ahead in 10 minute intervals, for up to 3 road segments ahead (message passing across 3 hops). Finally, in the third work, we describe an algorithm for signal control in free-flow road networks, inspired from congestion control in computer networks. Our proposed method significantly enhances the operational capacity of free-flow road networks in the real world by several orders of magnitude (3x-5x) and prevents congestion collapse.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Sustainability. $3 1029978
650 4 $a Urban planning. $3 2122922
650 4 $a Atmospheric sciences. $3 3168354
650 4 $a Transportation. $3 555912
650 4 $a Public policy. $3 532803
650 4 $a Information science. $3 554358
653 $a Air pollution
653 $a Data science
653 $a Machine Learning
653 $a Road traffic management
653 $a Urban sustainability
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0800
690 $a 0640
690 $a 0630
690 $a 0723
690 $a 0999
690 $a 0725
690 $a 0709
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a New York University. $b Computer Science. $3 1065424
773 0 $t Dissertations Abstracts International $g 83-10B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28865197 $z click for full text (PQDT)