Mohammad Badri
Universitas Islam Negeri Sumatera Utara, Medan

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi Algoritma Backpropagation Neural Networks Untuk Memprediksi Hasil Kinerja Dosen Samsudin Samsudin; Ali Ikhwan; Raissa Amanda Putri; Mohammad Badri
Journal of Information System Research (JOSH) Vol 4 No 2 (2023): January 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v4i2.2685

Abstract

In improving the quality of education in tertiary institutions, one of the efforts made to make it happen is to place qualified and professional educators or lecturers at these universities. A lecturer must have the ability to carry out the tridharma of higher education. A lecturer must also be able to follow the development of science and always be able to develop himself and have good teaching skills according to his field of knowledge, from planning, implementation to evaluation of learning. To predict the performance of lecturers using the Backpropagation Neural Networks algorithm. The design of the application to predict the performance of lecturers with the Backpropagation Neural Networks algorithm is done by determining the number of units for each layer. After the network is formed, training is carried out from the patterned data. Tests were carried out using Matlab software with several forms of network architecture. The architecture with the best configuration consists of 24 input layers, 20 hidden layers and 5 output layers. The results obtained from the test are predictions of lecturer performance which consist of Very Poor, Less, Enough, Good, Very Good. This assessment serves to evaluate the performance of lecturers in each semester at higher education institutions. with a test accuracy of 95%.