| Summary: | 碩士 === 國立雲林科技大學 === 資訊管理系 === 105 === With the progress of information technology, the era of big data, the field of data in various areas has rapidly expanded, and now there are many technologies and equipment every day to produce big data, And because the popularity of intelligent devices, technology continues to improve, the amount of data collected is more and more. These huge amounts of information have valuable information, but it is challenging for machine learning to be applied to large data, because traditional machine learning can not effectively deal with such a big data and immediate analysis. In order to maximize the value of large data, a new method architecture is needed. Therefore, the purpose of this study is to establish a classification model based on automata and execute it in the environment of Hadoop to solve the problem of big data. Automatic classification model, not only can solve the problem of big data and immediate demand, and can accurately predict. Not because of big data or immediate problems and problems. Experimental results the method of this study can successfully establish a classification model for data sets, and compared with a variety of classifiers, the accuracy of this study is high. The accuracy of this study is slightly lower than the traditional support vector machine, but in the execution time is faster than the traditional support vector machine thousands of times the speed.
|
|---|
