東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Exploration of Location-Aware Machin...

Chowdhury, Kanchan,

Linked to FindBook

Google Book

Amazon

博客來

Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets // Kanchan Chowdhury.
Author:	Chowdhury, Kanchan,
Description:	1 electronic resource (137 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
Contained By:	Dissertations Abstracts International86-02B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31485231
ISBN:	9798383607404

Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets /
Chowdhury, Kanchan,

Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets /Kanchan Chowdhury. - 1 electronic resource (137 pages)

Source: Dissertations Abstracts International, Volume: 86-02, Section: B.

Geospatial machine learning (ML) models and their applications have recently gained significant attention due to the rising availability of raster and spatiotemporal datasets. Three important limitations in ML for the geospatial domain are the following. Firstly, real-world geospatial datasets are often too large, and many geospatial ML algorithms represent the geographical region in terms of a grid. If the granularity of the grid is too fine, it results in a large number of grid cells, leading to long training time and high memory consumption issues during the model training. Secondly, current machine learning systems are mainly designed for text, image, audio, and video data, and they often fall short of adequately supporting geospatial datasets. This is because machine learning and data preprocessing techniques in this domain fail to capture the spatial autocorrelation property, a key characteristic available in geospatial datasets. Thirdly, many real-world inference workflows in this domain involve preprocessing steps that join data from multiple data silos to assemble feature vectors. Often, these geospatial joins are expensive and become bottlenecks in the inference process. In this dissertation, I will discuss novel solutions to these three major concerns of spatiotemporal machine learning. In particular, the dissertation includes three main research components. The first one presents a machine learning-aware technique for re-partitioning geospatial data to shorten the training duration of spatial machine learning models; the second component introduces an end-to-end framework for deep learning and data preprocessing with spatiotemporal vector and raster dataset; the third solution presents a strategy to co-optimize a preprocessing and inference pipeline consisting of costly join queries and model inferencing. Additionally, I will present experimental evaluation results using a variety of real-world datasets to demonstrate the effectiveness of all three solutions.

English

ISBN: 9798383607404Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Database systems

Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets /
LDR:03545nmm a22004573i 4500 001 2428464
005 20250410083506.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383607404
035 $a (MiAaPQD)AAI31485231
035 $a AAI31485231
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Chowdhury, Kanchan, $e author. $3 3815694
245 1 0 $a Exploration of Location-Aware Machine Learning for Spatiotemporal Vector and Raster Datasets / $c Kanchan Chowdhury.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (137 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: 86-02, Section: B.
500 $a Advisors: Sarwat, Mohamed; Zou, Jia Committee members: Davulcu, Hasan; Bryan, Chris.
502 $b Ph.D. $c Arizona State University $d 2024.
520 $a Geospatial machine learning (ML) models and their applications have recently gained significant attention due to the rising availability of raster and spatiotemporal datasets. Three important limitations in ML for the geospatial domain are the following. Firstly, real-world geospatial datasets are often too large, and many geospatial ML algorithms represent the geographical region in terms of a grid. If the granularity of the grid is too fine, it results in a large number of grid cells, leading to long training time and high memory consumption issues during the model training. Secondly, current machine learning systems are mainly designed for text, image, audio, and video data, and they often fall short of adequately supporting geospatial datasets. This is because machine learning and data preprocessing techniques in this domain fail to capture the spatial autocorrelation property, a key characteristic available in geospatial datasets. Thirdly, many real-world inference workflows in this domain involve preprocessing steps that join data from multiple data silos to assemble feature vectors. Often, these geospatial joins are expensive and become bottlenecks in the inference process. In this dissertation, I will discuss novel solutions to these three major concerns of spatiotemporal machine learning. In particular, the dissertation includes three main research components. The first one presents a machine learning-aware technique for re-partitioning geospatial data to shorten the training duration of spatial machine learning models; the second component introduces an end-to-end framework for deep learning and data preprocessing with spatiotemporal vector and raster dataset; the third solution presents a strategy to co-optimize a preprocessing and inference pipeline consisting of costly join queries and model inferencing. Additionally, I will present experimental evaluation results using a variety of real-world datasets to demonstrate the effectiveness of all three solutions.
546 $a English
590 $a School code: 0010
650 4 $a Computer science. $3 523869
650 4 $a Geographic information science. $3 3432445
653 $a Database systems
653 $a Deep learning
653 $a Geospatial data
653 $a Neural networks
653 $a Spatial machine learning
653 $a Spatiotemporal data
690 $a 0984
690 $a 0370
690 $a 0800
710 2 $a Arizona State University. $b Computer Science. $e degree granting institution. $3 3815405
720 1 $a Sarwat, Mohamed $e degree supervisor.
720 1 $a Zou, Jia $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-02B.
790 $a 0010
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31485231