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 94
- Downloads 0
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 Load Balancing Queue-Based Resource Allocation Algorithm in Cloud Computing Environment
Load balancing provides a better approach to distribute workloads at different virtual machines in different data center. In cloud computing improves the distributions of workloads across multiple cloud computing resourc...
An Innovative Approach for Quick Shopping Using QR-Code for Indian Precinct
In the present scenario life style became too fast and in this rushing life style shopping become hectic for everyone. In the era of technical achievement, there are multiple advanced ways available for shopping. In whic...
Emerging Trends on Big Data & Cloud Computing
In this paper we focused on the emerging trends and various approaches for carrying out analytics on clouds for Big Data application. It revolves around four important analytics and Big Data. We also discussed about the...
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...