Scipediacontent: Scipediacontent moved page Draft Content 250398857 to Shao et al 2018b

2021-02-15T11:27:55Z

Scipediacontent moved page Draft Content 250398857 to Shao et al 2018b

Scipediacontent: Created page with " == Abstract == Machine-learning technology powers many aspects of modern society. Compared to the conventional machine learning techniques that were limited in processing na..."

2021-02-15T11:27:52Z

Created page with " == Abstract == Machine-learning technology powers many aspects of modern society. Compared to the conventional machine learning techniques that were limited in processing na..."

New page

== Abstract ==

Machine-learning technology powers many aspects of modern society. Compared to the conventional machine learning techniques that were limited in processing natural data in the raw form, deep learning allows computational models to learn representations of data with multiple levels of abstraction. In this study, an improved deep learning model is proposed to explore the complex interactions among roadways, traffic, environmental elements, and traffic crashes. The proposed model includes two modules, an unsupervised feature learning module to identify functional network between the explanatory variables and the feature representations and a supervised fine tuning module to perform traffic crash prediction. To address the unobserved heterogeneity issues in the traffic crash prediction, a multivariate negative binomial (MVNB) model is embedding into the supervised fine tuning module as a regression layer. The proposed model was applied to the dataset that was collected from Knox County in Tennessee to validate the performances. The results indicate that the feature learning module identifies relational information between the explanatory variables and the feature representations, which reduces the dimensionality of the input and preserves the original information. The proposed model that includes the MVNB regression layer in the supervised fine tuning module can better account for differential distribution patterns in traffic crashes across injury severities and provides superior traffic crash predictions. The findings suggest that the proposed model is a superior alternative for traffic crash predictions and the average accuracy of the prediction that was measured by RMSD can be improved by 84.58% and 158.27% compared to the deep learning model without the regression layer and the SVM model, respectively.

Document type: Article

== Full document ==
<pdf>Media:Draft_Content_250398857-beopen979-5527-document.pdf</pdf>

== Original document ==

The different versions of the original document can be found in:

* [http://downloads.hindawi.com/journals/jat/2018/3869106.pdf http://downloads.hindawi.com/journals/jat/2018/3869106.pdf] under the license https://creativecommons.org/licenses/by

* [http://dx.doi.org/10.1155/2018/3869106 http://dx.doi.org/10.1155/2018/3869106] under the license cc-by

* [http://downloads.hindawi.com/journals/jat/2018/3869106.pdf http://downloads.hindawi.com/journals/jat/2018/3869106.pdf],
: [http://downloads.hindawi.com/journals/jat/2018/3869106.xml http://downloads.hindawi.com/journals/jat/2018/3869106.xml],
: [http://dx.doi.org/10.1155/2018/3869106 http://dx.doi.org/10.1155/2018/3869106] under the license http://creativecommons.org/licenses/by/4.0

* [http://dx.doi.org/10.1155/2018/3869106 http://dx.doi.org/10.1155/2018/3869106],
: [https://doaj.org/toc/0197-6729 https://doaj.org/toc/0197-6729],
: [https://doaj.org/toc/2042-3195 https://doaj.org/toc/2042-3195] under the license http://creativecommons.org/licenses/by/4.0/

* [https://www.hindawi.com/journals/jat/2018/3869106 https://www.hindawi.com/journals/jat/2018/3869106],
: [http://downloads.hindawi.com/journals/jat/2018/3869106.pdf http://downloads.hindawi.com/journals/jat/2018/3869106.pdf],
: [https://academic.microsoft.com/#/detail/2904042868 https://academic.microsoft.com/#/detail/2904042868]

← Older revision	Revision as of 11:27, 15 February 2021
(No difference)

Shao et al 2018b - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 250398857 to Shao et al 2018b

Scipediacontent: Created page with " == Abstract == Machine-learning technology powers many aspects of modern society. Compared to the conventional machine learning techniques that were limited in processing na..."