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 97
- Downloads 0
Multidimensional Performance analysis for Packet delivery and routing overhead in AODV and AOMDV
A Mobile Ad-hoc Network is characterized as a system that is remote and dynamic. It can be outlined with no need for earlier framework where each hub goes about as switch. A versatile Ad hoc Network is a self-arranging a...
Machine Learning: An Effective Technique in Bio-Medical Signal Analysis and Classification
Advancement in the field of digital signal processing and modern machine learning (ML) approaches has witnessed substantial growth in biomedical engineering. The diagnostic power of these machines has grown manifolds mai...
Survey on Security Issues and Concerns in Cloud Computing Technology
Cloud computing is starting a few tremendous changes to individuals' way of life and hindering position recently for its various preferences. Despite, the security of cloud computing is dependably the concentration of he...
Information Processing in Neuron with Exponential Distributed Delay
Artificial intelligence (AI) has been become the primary need in nearly all sectors namely engineering, services, banking, finance, defense, space etc [3], [33]. Artificial intelligence in these sectors can be implemente...
IoT with Big Data Framework using Machine Learning Approach
In future IoT (Internet of Things), big data (BD) & machine learning (ML)disclosure for expansive scale modern robotization application significance of mechanical internet is expanding step by step. The interconnection b...