No abstract

No abstract

Knowledge [no more Information] is not only power, but also has significant competitive advantage. Data warehousing is not a new idea. The use of corporate data for strategic decision making, as opposed to the use of data for tracking and enabling operations, has gone on for a computing itself. As the business these days contain huge amounts of data and the users connected to these databases across the globe and round the clock have the necessity for maintaining a separate database for the sake of analysis. This paper proposes one method of feature selection of NB Tree Algorithm. The Proposed algorithm (NB Tree) gives an effective Classification Algorithm for reducing computational time and gives better accuracy results compare with another algorithms. In many applications, however, an accurate ranking of instances based on the class probability is more desirable. The dependence between two attributes is determined based on the probabilities of their joint values that contribute to true and false classification decisions. The paper also evaluates the approach by comparing it with existing feature selection algorithms over 8 datasets from University of California, Irvine (UCI) machine learning databases. The proposed method shows better results in terms of number of selected features, classification accuracy, and running time than most existing algorithms.

Intelligent Transportation Systems (ITS) and AdvancedTraveller Information Systems (ATIS) are the emerging areas of research. They focus with keen interest to solve the issues in traffic management and planning and designing infrastructure to meet the demanding needs of the general public. Many research articles focus on developing video surveillance algorithms for processing video data captured at real-time traffic scenes, but as there is a huge demand for more sophisticated software systems, complexity of the algorithms gets increased in terms of data storage and large scale processing. This research article focuses on refining a framework for large scale video analytics while incorporating the simple, light-weight aspects of a video surveillance algorithm, and makes an insight by adopting blob tracking based video surveillance algorithm for large scale video analytics. The proposed system uses hadoop' map-reduce function to clean and pre-process the hours of traffic video captured in the local site stores. It summarizes and transmits the key frames of the video data to the central computing server to analyses the video frames. The key frame differencing method has been justified as a pronouncing method for data preprocessing and cleaning. Further this system follows the Blob detection, Identification and Tracking using connected components algorithm to determine the correlation between the vehicles moving in the real road scene.

No abstract