• D. Venkata Siva Reddy
• Dr. M. Senthil Kumaran

The concept of big Data for intelligent transportation system has been employed for traffic management on dealing with dynamic traffic environments. Big data analytics helps to cope with large amount of storage and computing resources required to use mass traffic data effectively. However these traditional solutions brings us unprecedented opportunities to manage transportation data but it is inefficient for building the next-generation intelligent transportation systems as Traffic data exploring in velocity and volume on various characteristics. In this work, a new framework named Big Data Cloud Driven Computational Framework for Intelligent Transportation System has been architected on employing a new architectures named as deep intelligent network, Increase weighted continuous feature extraction and reinforcement learning. These architectures has been introduced to handle the magnifying and exploring data with hierarchical and spatiotemporal characteristics along location based service by utilizing the Sensor and GPS data of the vehicle in the real time. The proposed framework employs deep learning architecture to predict potential road clusters for passengers on analysing the various characteristics on the attributes of the dataset. In order to perform efficient big data analysis, Feature extraction model has to be structured properly in order to identify high scaling features. Initial methodology of the work is to construct the Increased weighted Continuous feature extraction Algorithm which includes filter, wrapper and hybrid method on efficient feature extraction for classification of road clusters using support vector machine. Reinforcement learning model has been modelled as second architecture for predicting the salient feature on the time varying traffic contexts by approximating non linear data in the dataset. It is injected as recommendation system to passenger in terms of mobile application by employing the agent and feedback function through iterating optimum control policy to control the hardware equipment employment on the vehicle incorporating location based services models to seek available parking slots, traffic free roads and shortest path for reach destination and other services in the specified path etc. The underlying the traffic data is classified into clusters with extracting set of features on it. Finally, deep behavioural network has been architected to processes the traffic data in terms of spatiotemporal characteristics to generate road clusters to produce the traffic forecasting information, vehicle detection, autonomous driving and driving behaviours. In addition, markov model is embedded to discover the hidden features .The experimental results demonstrates that proposed framework achieves better results on the performance measures named as precision, execution time, feasibility and efficiency.

Big Data, Intelligent Transportation System, Deep Learning, Prediction, Spatiotemporal analysis, Location based services

"AN EXTENSIVE RESEARCH ON BIG DATA CLOUD DRIVEN COMPUTATIONAL FRAMEWORK FOR INTELLIGENT TRANSPORTATION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 10, page no.d243-d249, October-2022, Available :http://www.jetir.org/papers/JETIR2210344.pdf

"AN EXTENSIVE RESEARCH ON BIG DATA CLOUD DRIVEN COMPUTATIONAL FRAMEWORK FOR INTELLIGENT TRANSPORTATION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 10, page no. ppd243-d249, October-2022, Available at : http://www.jetir.org/papers/JETIR2210344.pdf