Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses
Computational graphs (CGs) have been widely utilized in numerical analysis and deep learning to represent directed forward networks of data flows between operations. This paper aims to develop an explainable learning framework that can fully integrate three major steps of decision support: Synthesis...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/10/2254 |
| _version_ | 1798003502203535360 |
|---|---|
| author | Jianping Sun Jifu Guo Xin Wu Qian Zhu Danting Wu Kai Xian Xuesong Zhou |
| author_facet | Jianping Sun Jifu Guo Xin Wu Qian Zhu Danting Wu Kai Xian Xuesong Zhou |
| author_sort | Jianping Sun |
| collection | DOAJ |
| description | Computational graphs (CGs) have been widely utilized in numerical analysis and deep learning to represent directed forward networks of data flows between operations. This paper aims to develop an explainable learning framework that can fully integrate three major steps of decision support: Synthesis of diverse traffic data, multilayered traffic demand estimation, and marginal effect analyses for transport policies. Following the big data-driven transportation computational graph (BTCG) framework, which is an emerging framework for explainable neural networks, we map different external traffic measurements collected from household survey data, mobile phone data, floating car data, and sensor networks to multilayered demand variables in a CG. Furthermore, we extend the CG-based framework by mapping different congestion mitigation strategies to CG layers individually or in combination, allowing the marginal effects and potential migration magnitudes of the strategies to be reliably quantified. Using the TensorFlow architecture, we evaluate our framework on the Sioux Falls network and present a large-scale case study based on a subnetwork of Beijing using a data set from the metropolitan planning organization. |
| first_indexed | 2024-04-11T12:08:33Z |
| format | Article |
| id | doaj.art-8025d06fe1f941fa8afa3f98c9cd4506 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:08:33Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8025d06fe1f941fa8afa3f98c9cd45062022-12-22T04:24:40ZengMDPI AGSensors1424-82202019-05-011910225410.3390/s19102254s19102254Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect AnalysesJianping Sun0Jifu Guo1Xin Wu2Qian Zhu3Danting Wu4Kai Xian5Xuesong Zhou6School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Sustainable Engineering and the Built Environment, Arizona State University, Tempe, AZ 85281, USASchool of Transportation and Logistics, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaBeijing Transport Institute, Beijing 100073, ChinaBeijing Transport Institute, Beijing 100073, ChinaComputational graphs (CGs) have been widely utilized in numerical analysis and deep learning to represent directed forward networks of data flows between operations. This paper aims to develop an explainable learning framework that can fully integrate three major steps of decision support: Synthesis of diverse traffic data, multilayered traffic demand estimation, and marginal effect analyses for transport policies. Following the big data-driven transportation computational graph (BTCG) framework, which is an emerging framework for explainable neural networks, we map different external traffic measurements collected from household survey data, mobile phone data, floating car data, and sensor networks to multilayered demand variables in a CG. Furthermore, we extend the CG-based framework by mapping different congestion mitigation strategies to CG layers individually or in combination, allowing the marginal effects and potential migration magnitudes of the strategies to be reliably quantified. Using the TensorFlow architecture, we evaluate our framework on the Sioux Falls network and present a large-scale case study based on a subnetwork of Beijing using a data set from the metropolitan planning organization.https://www.mdpi.com/1424-8220/19/10/2254computational graphtraffic demand estimationcongestion mitigationmarginal analysesTensorFlow |
| spellingShingle | Jianping Sun Jifu Guo Xin Wu Qian Zhu Danting Wu Kai Xian Xuesong Zhou Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses Sensors computational graph traffic demand estimation congestion mitigation marginal analyses TensorFlow |
| title | Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses |
| title_full | Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses |
| title_fullStr | Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses |
| title_full_unstemmed | Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses |
| title_short | Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses |
| title_sort | analyzing the impact of traffic congestion mitigation from an explainable neural network learning framework to marginal effect analyses |
| topic | computational graph traffic demand estimation congestion mitigation marginal analyses TensorFlow |
| url | https://www.mdpi.com/1424-8220/19/10/2254 |
| work_keys_str_mv | AT jianpingsun analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT jifuguo analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT xinwu analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT qianzhu analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT dantingwu analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT kaixian analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses AT xuesongzhou analyzingtheimpactoftrafficcongestionmitigationfromanexplainableneuralnetworklearningframeworktomarginaleffectanalyses |