MRT Demand Prediction through Social Media
碩士 === 國立臺灣大學 === 土木工程學研究所 === 103 === With the technological improvements of mobile devices and the increasing number of social media posts, there are more and more data on human mobility based on which information could potentially be extracted. Current research related to social media are mostly...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2015
|
Online Access: | http://ndltd.ncl.edu.tw/handle/08325576544480906430 |
id |
ndltd-TW-103NTU05015034 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-103NTU050150342016-11-19T04:09:44Z http://ndltd.ncl.edu.tw/handle/08325576544480906430 MRT Demand Prediction through Social Media 基於社群網路資料之捷運運量預測 Chuan-Heng Lin 林泉亨 碩士 國立臺灣大學 土木工程學研究所 103 With the technological improvements of mobile devices and the increasing number of social media posts, there are more and more data on human mobility based on which information could potentially be extracted. Current research related to social media are mostly focused on inter-person behaviors. Conversely, related topics on system level performances are rarely discussed. This thesis applies feature extraction methods on quantitative, textual, and image data to retrieve useful features from social media. In addition, a machine learning pipeline based on support vector machine, random forest and stochastic gradient boosting is constructed for a short-term transportation demand forecast. Furthermore, real-world datasets from Instagram together with the demand data of the Taipei Metro Rapid Transit system are demonstrated in this work. Validation results show that social media has the potential to enhance the forecasting accuracy. Albert Y. Chen 陳柏華 2015 學位論文 ; thesis 45 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣大學 === 土木工程學研究所 === 103 === With the technological improvements of mobile devices and the increasing number of social media posts, there are more and more data on human mobility based on which information could potentially be extracted. Current research related to social media are mostly focused on inter-person behaviors. Conversely, related topics on system level performances are rarely discussed. This thesis applies feature extraction methods on quantitative, textual, and image data to retrieve useful features from social media. In addition, a machine learning pipeline based on support vector machine, random forest and stochastic gradient boosting is constructed for a short-term transportation demand forecast. Furthermore, real-world datasets from Instagram together with the demand data of the Taipei Metro Rapid Transit system are demonstrated in this work. Validation results show that social media has the potential to enhance the forecasting accuracy.
|
author2 |
Albert Y. Chen |
author_facet |
Albert Y. Chen Chuan-Heng Lin 林泉亨 |
author |
Chuan-Heng Lin 林泉亨 |
spellingShingle |
Chuan-Heng Lin 林泉亨 MRT Demand Prediction through Social Media |
author_sort |
Chuan-Heng Lin |
title |
MRT Demand Prediction through Social Media |
title_short |
MRT Demand Prediction through Social Media |
title_full |
MRT Demand Prediction through Social Media |
title_fullStr |
MRT Demand Prediction through Social Media |
title_full_unstemmed |
MRT Demand Prediction through Social Media |
title_sort |
mrt demand prediction through social media |
publishDate |
2015 |
url |
http://ndltd.ncl.edu.tw/handle/08325576544480906430 |
work_keys_str_mv |
AT chuanhenglin mrtdemandpredictionthroughsocialmedia AT línquánhēng mrtdemandpredictionthroughsocialmedia AT chuanhenglin jīyúshèqúnwǎnglùzīliàozhījiéyùnyùnliàngyùcè AT línquánhēng jīyúshèqúnwǎnglùzīliàozhījiéyùnyùnliàngyùcè |
_version_ |
1718394019484008448 |