GEO-TRAFFIC IDENTIFICATION VIA CENTRALIZED WEB STREAM ANALYSIS

##plugins.themes.bootstrap3.article.main##

Sharmila J Shriram V Vickram R Raveenraj S.K.

Abstract

Social networks can be employed as a source of information for event detection such as road traffic congestion and car accidents. The Existing system present a real-time monitoring system for traffic event detection from twitter. The system fetches tweets from twitter and then; processes tweets using text mining techniques. Lastly performs the classification of tweets. The aim of the system is to assign the appropriate class label to each tweet, whether it is related to a traffic event or not. System employed the support vector machine as a classification model. Road traffic prediction is a critical component in modern smart transportation systems. It provides the basis for traffic management agencies to generate proactive traffic operation strategy for alleviate congestion. Existing work on nearterm traffic prediction (forecasting horizons in the range of 5 minutes to 1 hour) relies on the past and current traffic conditions. However, once the forecasting horizon is beyond 1 hour, i.e., in longer-term traffic prediction, these techniques do not work well since additional factors other than the past and current traffic conditions start to play important roles. To address the above problem, examination is done to check whether it is possible to use the rich information in online social media to improve longer-term traffic prediction. Analysis is done to check the correlation between traffic volume and tweet counts with various granularities. Finally, the classification of tweets is done using the k nearest neighbor algorithm. The aim of the system is to assign the appropriate class label to each tweet, whether it is related to a traffic event or not. The traffic detection system can be employed for real-time monitoring of several areas of the road network, allowing for detection of traffic events almost in real time, often before online traffic news web sites.

##plugins.themes.bootstrap3.article.details##

Section
Articles