Classification of Network Status in Academic Information Systems using Naive Bayes Algorithm Method

Academic Information System is a system used for academic data management with the application of computer technology, both hardware and software. Operating an academic information system requires an adequate server and good network quality. Dynamic Host Configuration Protocol (DHCP) server is a service that allows devices to distribute IP address to host in a network automatically. The DHCP server provides IP addresses, DNS, Default Gateway, and various TCP / IP information. The operating systems that support the DHCP server are Linux, GNU, Windows Net Server, Windows 2003 server. The method used in this research is the Naive Bayes algorithm, a machine learning method that utilizes probability and statistical calculations. Classification is carried out on data protocols which have low, medium and high categories. The results in this study were the throughput on the server was 38.8% in the medium category, the delay on the server was 2.80 ms in the very good category, and the packet loss was 0% in the very good category. The results of classification on the protocol have two confidence, that is producing an average accuracy value that is right for classification on the long protocol of 94.92% and the protocol counting of 81.35%.