Pembobotan Atribut PSO Untuk Klasifikasi Data Kinerja Akademik Mahasiswa
Abstract
An educational database containing information about students is useful for predicting student academic performance. Mujiyono, Sri in 2017 has proven that PSO improves SVM performance for predicting student academic performance. This study aims to prove that PSO can improve the performance of the NBC, C4.5, SVM and NN classification methods for the classification of student academic performance. The results of this study prove that PSO can improve the performance of all the classification methods used. With PSO optimization, NN defeats the accuracy of SVM.References
Peraturan BAN-PT No 4 Tahun 2017 tentang Instrumen Akreditasi.
Kabakchieva, D., (2013). Predicting student performance by using data mining methods for classification. Cybernetics and information technologies, 13(1), pp.61-72.
Huang, S., & Fang, N. (2013). Predicting student academic performance in an engineering dynamics course: A comparison of four types of predictive mathematical models. Computers & Education, 61, 133-145.
Ahmad, F., Ismail, N. H., & Aziz, A. A. (2015). The prediction of students’ academic performance using classification data mining techniques. Applied Mathematical Sciences, 9(129), 6415-6426.
Ghamisi, P., & Benediktsson, J. A. (2015). Feature selection based on hybridization of genetic algorithm and particle swarm optimization. IEEE Geoscience and Remote Sensing Letters, 12(2), 309-313.
Chen, L. F., Su, C. T., Chen, K. H., & Wang, P. C. (2012). Particle swarm optimization for feature selection with application in obstructive sleep apnea diagnosis. Neural Computing and Applications, 21(8), 2087-2096.
Mujiyono, Sri. “Optimasi Klasifikasi Data Kinerja Akademik Mahasiswa Menggunakan SVM Berbasis PSO†Tesis Magister Ilmu Komputer. Universitas Dian Nuswantoro, 2017
