Analysing the Train Accident Injuries using Mining Techniques
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2017, Vol 5, Issue 4
Abstract
Rail accidents describe a significant safety concern for the transportation industry in multiple countries. To better understand the contributors to these extreme accidents, the Federal Railroad Administration has established the railroads involved in accidents to submit reports that contain both fixed function entries and narratives that explain the characteristics of the accident. While a number of studies have noticed the fixed fields, nothing has done an extensive analysis of the narratives. This project describes the use of mining with a combination of techniques to automatically discover accident characteristics that can confess a better understanding of the contributors to the accidents. The results show that predictive accuracy for accident costs significantly improves on the use of features found by mining and predictive accuracy also improves through the use of modern ensemble methods. Importantly, this study furthermore shows through case examples how the findings from mining of the narratives can improve understanding of the contributors to rail accidents in ways not possible on only fixed field analysis of the accident reports.
Authors and Affiliations
CH. Nireesha, N. Vijay Kumar, V. Babu
Keywords
Related Articles
- EP ID EP23913
- DOI http://doi.org/10.22214/ijraset.2017.4207
- Views 264
- Downloads 9
An Automatic Close Loop Embedded System for Real Time Monitoring of Speed and Torque of Motor
The system proposed in this project aims at monitoring the torque and efficiency in induction motors in real time by employing wireless sensor networks (WSNs). An embedded system is employed for acquiring electrical sig...
Prediction of Corrosion Rates in Structural Steel Using Artificial Neural Networks
A phenomenal outcome for the prediction of corrosion in steel was proposed with the learning ability of artificial neural network using MATLAB software. The prediction of corrosion rate has become an important challenge...
Mechanical Properties of Waste Plastic Reinforced Epoxy Matrix Composites
Management and treatment of plastic waste can mitigate adverse impacts on environment process and human health. The aim of the present study was to develop and characterise polymeric composite waste plastic pellets by m...
slugA Novel Approach for the Development of Metadata Editors in Web-based Applications
Metadata is the data about data which describes how and when particular data was collected and how the data should be formatted. Metadata Standards that support a number of defined functions, and specify elements which...
Implementation of Document Envelope Rest APIS for B2B Sterling Integrator
a document envelope consists of control information that enables organizations to effectively exchange documents. The document envelope takes the original document, assigns a control number, and packages header and trai...