Application of an improved neural network algorithm in spam filtering
Wang Ming-l · Information technology newsletter · 2015
Since spam has been increasingly threatening our information security,how to increase the spam control technically so as to maintain network security has become a hot issue in study. With the adaptive feature,artificial neural networks have a significant advantage in dealing with the spam problem which is changing all the time. But the traditional algorithms have the problem of being inefficient. This paper puts forward an improved BP neural network algorithm with the combination of genetic algorithm and fuzzy theory. The efficiency of the algorithm is improved to a certain extent. Through the experimental analysis of Chinese e-mail classification,the results indicate that the efficiency of the proposed algorithm is superior to the traditional algorithm,and has high recognition accuracy.