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

Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network./
作者:	Hu, Yiqun.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	51 p.
附註:	Source: Masters Abstracts International, Volume: 83-01.
Contained By:	Masters Abstracts International83-01.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28413146
ISBN:	9798516959103

Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network.
Hu, Yiqun.

Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 51 p.

Source: Masters Abstracts International, Volume: 83-01.

Thesis (M.S.)--Northern Illinois University, 2021.

This item must not be sold to any third party vendors.

There have been numerous studies on traffic accidents and their fatality rate. For this challenging machine learning regression problem, Neural Networks (NNs) have produced state-of-the-art data. Despite their success, they are often used in a frequentist scheme, which means they cannot account for uncertainty in their forecasts. BNNs are comprised of a Probabilistic Model and a Neural Network. The aim of such a design is to bring together the benefits of Neural Networks and stochastic modeling. Neural networks have the ability to approximate continuous functions universally. Statistical models allow for the direct definition of a model with known parameter interactions in order to produce results. As a result, both DNNs and BNNs are implemented in this article, and then a model evaluation was performed. The data set used in this paper is U.S. Fatalities data from open source CRAN R package named AER. For the model evaluation, two measures were employed: mean absolute error (MAE) and root mean square error (RMSE). The low MAE and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.

ISBN: 9798516959103Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Neural Networks

Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network.
LDR:02275nmm a2200361 4500 001 2349524
005 20230509091103.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798516959103
035 $a (MiAaPQ)AAI28413146
035 $a AAI28413146
040 $a MiAaPQ $c MiAaPQ
100 1 $a Hu, Yiqun. $3 3688932
245 1 0 $a Traffic Fatality Rate Prediction Based on Deep Neural Network and Bayesian Neural Network.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 51 p.
500 $a Source: Masters Abstracts International, Volume: 83-01.
500 $a Advisor: Ryu, Duchwan.
502 $a Thesis (M.S.)--Northern Illinois University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a There have been numerous studies on traffic accidents and their fatality rate. For this challenging machine learning regression problem, Neural Networks (NNs) have produced state-of-the-art data. Despite their success, they are often used in a frequentist scheme, which means they cannot account for uncertainty in their forecasts. BNNs are comprised of a Probabilistic Model and a Neural Network. The aim of such a design is to bring together the benefits of Neural Networks and stochastic modeling. Neural networks have the ability to approximate continuous functions universally. Statistical models allow for the direct definition of a model with known parameter interactions in order to produce results. As a result, both DNNs and BNNs are implemented in this article, and then a model evaluation was performed. The data set used in this paper is U.S. Fatalities data from open source CRAN R package named AER. For the model evaluation, two measures were employed: mean absolute error (MAE) and root mean square error (RMSE). The low MAE and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.
590 $a School code: 0162.
650 4 $a Statistics. $3 517247
650 4 $a Transportation. $3 555912
650 4 $a Neurons. $3 588699
650 4 $a Fatalities. $3 3681792
650 4 $a Deep learning. $3 3554982
650 4 $a Datasets. $3 3541416
650 4 $a Regression analysis. $3 529831
650 4 $a Random variables. $3 646291
650 4 $a Traffic. $3 3688933
650 4 $a Generalized linear models. $3 3561810
650 4 $a Normal distribution. $3 3561025
650 4 $a Neural networks. $3 677449
650 4 $a Algorithms. $3 536374
650 4 $a Performance evaluation. $3 3562292
653 $a Neural Networks
653 $a Frequentist scheme
653 $a Mean absolute error
690 $a 0463
690 $a 0709
710 2 $a Northern Illinois University. $b Statistics and Actuarial Science. $3 3684928
773 0 $t Masters Abstracts International $g 83-01.
790 $a 0162
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28413146