Abstract
Dynamic traffic management (DTM) systems are used to reduce the negative
externalities of traffic congestion, such as air pollution in urban areas. They
require traffic and environmental monitoring infrastructures. In this paper we
present a prototype of a low-cost Internet of Things (IoT) system for monitoring
traffic flow and the Air Quality Index (AQI). The computation of the traffic
flows is based on processing video in the compressed domain. Only using motion vectors as input, traffic flow is computed in real-time over an embedded architecture.
An estimation of the AQI is supported by machine learning regression
techniques, using different feature data obtained from the IoT device. These
automatic learning techniques overcome the need for complex calibration and
other limitations of embedded devices in making the needed measurements of
the pollutant gases for the computation of the actual AQI. The experimentation
with the data obtained from different cities representing different scenarios with
a variety of climate and traffic conditions, allows validating the proposed architecture.
As regressors, Linear Regression (LR), Gaussian Process Regression
(GPR) and Random Forest (RF) are compared using the performance metrics
R2, MSE, MAE and MRE resulting in a relevant improvement of the AQI estimations of our proposal.
externalities of traffic congestion, such as air pollution in urban areas. They
require traffic and environmental monitoring infrastructures. In this paper we
present a prototype of a low-cost Internet of Things (IoT) system for monitoring
traffic flow and the Air Quality Index (AQI). The computation of the traffic
flows is based on processing video in the compressed domain. Only using motion vectors as input, traffic flow is computed in real-time over an embedded architecture.
An estimation of the AQI is supported by machine learning regression
techniques, using different feature data obtained from the IoT device. These
automatic learning techniques overcome the need for complex calibration and
other limitations of embedded devices in making the needed measurements of
the pollutant gases for the computation of the actual AQI. The experimentation
with the data obtained from different cities representing different scenarios with
a variety of climate and traffic conditions, allows validating the proposed architecture.
As regressors, Linear Regression (LR), Gaussian Process Regression
(GPR) and Random Forest (RF) are compared using the performance metrics
R2, MSE, MAE and MRE resulting in a relevant improvement of the AQI estimations of our proposal.
| Original language | English |
|---|---|
| Article number | 108282 |
| Pages (from-to) | 1-48 |
| Number of pages | 48 |
| Journal | Applied Soft Computing Journal |
| Volume | 115 |
| Early online date | 10 Dec 2021 |
| DOIs | |
| Publication status | Published (in print/issue) - 31 Jan 2022 |
Bibliographical note
Funding Information:Grants TRA2016-76914-C3-2-P and PID2020-112967GB-C32 funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe.
Funding Information:
The research of Martín-Baos has been supported by the FPU Predoctoral Program of the Spanish Ministry of Universities with reference FPU18/00802.
Publisher Copyright:
© 2021 Elsevier B.V.
Keywords
- air quality index
- regression modelling
- video motion vectors
- embedded systems
- Embedded systems
- Air Quality Index
- Video motion vectors
- Regression modelling
