Introduction to Applying Data Mining In Prediction And Classification Of Urban Traffic:
Applying data mining in prediction and classification of urban traffic project is implemented in java platform. Progress and development of computer science and usage of modern hardware technologies in sampling data causes generating a huge amount of data to gather and process in most of the fields. Although more sample data can help more accurate decisions, in most cases dilatory methods of analysis and process make it impossible to use this amount of data. As well as appearing high-tech devices of sampling data, new algorithms and software technologies have been developed to survey and analyze the sampled data.
Data mining presents different methods and algorithms that can help us in mining knowledge from data, clustering and classifying data, predicting future status and decision making. Utilizing apparatuses like sensors, networks (cable or wireless), cameras and high speed computers in current traffic systems open a new field for data mining to demonstrate its capabilities. Prediction of traffic and making decision for it are two of the most important benefits of employing data mining in traffic management; there are many other instances to proof applying data mining in traffics. Moreover numerous quantity of gathered data and on the other hand frequent income of acquired data makes the manual analyzing impossible. Therefore employing data mining techniques becomes necessary.
In some cases all data is ready and the quantity of it is known; we will use algorithms which are called static data mining algorithms. Therefore the pattern is stable so, it is enough to run the learning algorithm once and then use the resulted pattern algorithm on the rest of data. On the other hand there are situations that algorithm could not have all the data at the beginning and system will receive new data during its process. Algorithms which are working on these kinds of data are called Stream data mining algorithms. In these cases it is possible that the pattern changes during the time, so running the learning algorithm just once at the beginning and utilizing mined knowledge for all new data which are entering the system is not a reasonable method. In stream data mining we should refresh the pattern by running the learning algorithm in specified periods of time with new sets of learning data. In other words the old knowledge should be removed and recent knowledge driven from new stream of data must replace it.
We proposed another way of processing stream data, new learning data are used to update the former knowledge hence available knowledge of system will become compatible with the change of the data pattern by time. The traffic issue and its concerning data have stream nature. This data is collected in time and its pattern may change in relation with season, oil price, and holydays. Thus to analyse traffics we have to use stream data mining methods.
In this research we use data mining for learning effect of special parameters on traffic, and then we will employ this knowledge to predict the traffic state and make decisions about it. Classification is one of the data mining branches that can be used in interference learning, knowledge mining, prediction and decision making. In classification cases a learning set is defined to result a classifier algorithm. Each sample in learning set has some variable fields and a class number which indicates its class. Completed the learning and test phase, classifier predicts the class of incoming new data.
Download Applying Data Mining In Prediction And Classification Of Urban Traffic from this link.