• Dr. N.SADHASIVAM
• Dr. C.VEERAMANI
• Dr.M. PANDI

Traffic information can be derived from various sources for developing traffic prediction techniques, which in turn improve navigation of the route, traffic regulation and urban area planning. One key challenge for predicting traffic is how much to depend on prediction models that are constructed using historical data in real time traffic situations which may differ from that of the historical data and change over time. Existing approach is used for predicting traffic models that are learned offline or they are retrained after long periods and thus they cannot adapt to dynamically changing traffic situations. To overcome this problem, online traffic prediction with Big Data: A Naive Bayesian Classification algorithm has been proposed. From the current traffic situations in real time, future traffic can be predicted by matching the current traffic situations to the most effective prediction model trained using historical data. When real time traffic data arrives the traffic context space is adaptively partitioned using machine learning algorithm in order to efficiently estimate the effectiveness of each base predictor in different situations. The proposed approach also obtains and proves both short term and long term performance for online algorithm. The proposed algorithm also works effectively in scenarios like, when the true labels are missing or become available with delay

Naïve Bayesian classification; Machine Learning; Traffic Prediction.

"Online Traffic Prediction with Big Data: A Naive Bayesian Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.753-756, April-2019, Available :http://www.jetir.org/papers/JETIR1904R15.pdf

"Online Traffic Prediction with Big Data: A Naive Bayesian Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp753-756, April-2019, Available at : http://www.jetir.org/papers/JETIR1904R15.pdf