PREDICTION MODEL FOR POLLUTANTS WITH ONBOARD DIAGNOSTIC SENSORS IN VEHICLES
Journal Title: International Journal of Machine Learning and Networked Collaborative Engineering - Year 2018, Vol 2, Issue 2
Abstract
In this work, a prediction model is developed to illustrate the relationship between the internal parameters of a vehicle and its emissions. Vehicles emit various hazardous pollutants and understanding the influence of in-vehicle parameters is key to reducing their environmental impact. The values of the internal parameters were collected through the On-Board Diagnostics port, while the values of the emissions were measured from the exhaust pipe using Arduino sensors. The observed values were then matched based on the timestamps received from both sources and fit with both linear and polynomial regressions to accurately model the relationship between the internal parameters and pollutants. These models can then be used to estimate vehicle emissions based on the in-vehicle parameters, including vehicle speed, relative throttle position, and engine revolutions per minute. A wide majority of the relationships between various in-vehicle parameters and emissions show no observable correlation. There are observable correlations between carbon dioxide emissions and vehicle speed, as well as carbon dioxide emissions and engine revolutions per minute. These relationships were modelled using linear and polynomial regression with a resulting adjusted R-squared value of approximately 0.1.
Authors and Affiliations
Bryce Maldonado
Keywords
Related Articles
- EP ID EP371005
- DOI 10.30991/IJMLNCE.2018v02i02.002
- Views 88
- Downloads 0
Steganalysis for Reversible Data Hiding Based on Neural Networks and Convolutional Neural Networks
Lossless data hiding techniques is a technique that is very interesting. In which there is a large amount of reversible information hidden technologies. This technique makes it possible to restore the original image afte...
Extracting Knowledge from Large Social Key Valued Data
With advances in computer and information technology, large amount of different types of valuable data are gathered and generate in the present time of huge information from a large range of sources of availability of in...
An Adaptive Approach for AODV Routing Protocol in MANET
Presently a day, Ad-hoc arrange has turned into a resolute part for correspondence for cell phones. A mobile adhoc network (MANET) is a collection of wireless mobile nodes dynamically forming a network topology without t...
A Detailed Analysis of Core NLP for Information Extraction
The amount of unstructured text present in all electronic media is increasing periodically day after day. In order to extract relevant and succinct information, extraction algorithms are limited to entity relationships....
Improvement of Automated Learning Methods based on Linear Learning Algorithms
In recent years, the learning methods are converted to one of the new research area. These researches are divided into two general categories. The first category recognizes the principles of learning the living entities...