Data-driven approach for instantaneous vehicle emission predicting using integrated deep neural network
This paper details how instantaneous vehicle emissions, namely, CO₂, CO, NOₓ, and HC from light-duty vehicles, can be predicted using the integrated deep neural network method (NNM). The deep-learning algorithms, i.e., short-term memory (LSTM), gated recurrent unit (GRU), and recurrent neural network (RNN) methods, were applied to predict the emissions. Finally, an integrated method using LSTM, RNN, and GRU was used to determine if the integrated method was better at increasing the prediction performance of vehicle emissions. Each model performance was evaluated by calculating the mean squared error (MSE), root mean squared error (RMSE), and normalize root mean squared error (nRMSE) values. The results indicate that the integrated LSTM NNM provided the best overall emission prediction compared to the other methods. This integrated model can help to develop new policies and regulations for vehicle emissions.
- Record URL:
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/13619209
-
Supplemental Notes:
- © 2023 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
-
Authors:
- Howlader, Abdul Motin
- Patel, Dilip
- Gammariello, Robert
- Publication Date: 2023-3
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: 103654
-
Serial:
- Transportation Research Part D: Transport and Environment
- Volume: 116
- Issue Number: 0
- Publisher: Elsevier
- ISSN: 1361-9209
- Serial URL: http://www.sciencedirect.com/science/journal/13619209
Subject/Index Terms
- TRT Terms: Data analysis; Motor vehicles; Neural networks; Pollutants; Predictive models
- Subject Areas: Data and Information Technology; Environment; Vehicles and Equipment;
Filing Info
- Accession Number: 01876592
- Record Type: Publication
- Files: TRIS
- Created Date: Mar 23 2023 10:19AM