Implementation of K-Means Clustering Method to Lecturers Based on Publications of National Journals and Accredited Sinta

Lecturer research or scientific results published both nationally and with Sinta accreditation. This is done to determine the level of publication of lecturer research results that have been published so that they can be easily disseminated so that the knowledge gained influences knowledge in general and has an impact on people's lives. The problem in this research is how to apply the K-Means clustering method with reference to the results of lecturer research publications based on national journals and sinta accredited journals. In this study, the researchers used the K-Means method, which has the goal of minimizing the objective function that has been set in the clustering process and maximizing the variation of data in other clusters. So researchers will look for the best number of clusters in the K-means method. The discussion is carried out based on the data that has been collected in the form of national journal weights and sinta accredited journal weights by utilizing Matlab R2013b software. From the results of system testing, lecturer clustering was obtained related to the results of journal weights, namely lecturers with high national scores and no sinta accreditation weights, lecturers with quite high national weights and high sinta accreditation weights, moderate national weights and low sinta accreditation weights, low national weights and high weights with low Sinta accreditation. This study resulted in the conclusion that the data was processed through several stages, starting with calculating the weight value of each issue of the national journal and sinta accredited journal. Then the results of these weights are recapitulated based on each lecturer so that it can be seen the total value of the lecturers' weights in publishing research results in the form of journals that have been published both in the form of national publications and sinta publications.