Open AccessKlasterisasi Tingkat Kehadiran Dosen Menggunakan Algoritma K-Means Clustering
Author(s) -
Ismail Virgo,
Sarjon Defit,
Y Yuhandri
Publication year - 2020
Publication title -
jurnal sistim informasi dan teknologi
Language(s) - English
Resource type - Journals
ISSN - 2686-3154
DOI - 10.37034/jsisfotek.v2i1.17
Subject(s) - civil servant , civil servants , attendance , servant , cluster analysis , psychology , engineering , political science , computer science , artificial intelligence , law , politics , software engineering
Non-Civil Servant Lecturers of Batusangkar State Islamic Institute (IAIN) are still manual in recording the presence of non-civil servant lecturers. This study aims to use an application to record the number of meetings conducted during the teaching and learning process by non civil servant lecturers who are able to study courses. The meeting data will be an assessment of the performance of non civil servant lecturers. Higher education quality assurance institutions can classify non-civil servant lecturer meeting data using Knowledge Discovery in Database (KDD). The next stage is to do data mining with the K-Means Clustering Algorithm. The results of this study grouping lecturers into 3 groups: 72 subjects taught by non-civil servant lecturers in the group rarely meet (4,7650%), 69 courses that are taught by non-civil servant lecturers in the group are in meetings (4,5665%), and 1370 subjects taught by lecturers non civil servants in the diligent group meeting (90.6684%). Based on the results of the study it was concluded that the academic year 2017/2018 odd semester and even non-civil servant lecturers supporting certain subjects diligently entered at each meeting with attendance rates of 12-16 times meetings per semester.