Main Article Content

Abstract

Determination of the level of student learning abilities based on the results of the evaluation of the learning process is the most important stage in recognizing the absorbency characteristics of each student. It appears in the response response of the learning process from the lecturers that there is a slow and fast response, so that there needs to be a different action from the lecturer on this matter. The purpose of this study was to determine the classification of assessments of student learning outcomes by using anfis. The study was conducted in class C and E Academic Year 2017/2018 with mathematics and linear & Matrix algebra courses. Type of Quantitative Research using data collection techniques such as interviews, observations, literature studies and documentation. The data taken was tested for normality and homogeneity. The Fuzzy Sugena research results are very suitable for this classification compared to fuzzy mamdani although with fuzzy mamdani there is a smaller error rate of 0.87. Students can be categorized as very good categories of 9 students and a good category of 21 students out of a total of 30 students or can be held very well (30%), and good (70%). After the teaching staff is able to classify students based on the criteria, from that it causes the teaching staff to be able to provide feedback to all students in their class differently. The instructor is able to develop strategies in learning so that what is desired by students who have different criteria can get appropriate treatment Because an educator must be able to understand students who have a diversity of characters that cannot be compared to the way they learn

Keywords

Anfis Assesment Learning Outcomes Article

Article Details

References

  1. Wen Cheng Liu, Wei -Bo-Chen. (2012). "Prediction of Water Temperatur in Subtropical, Subalphine Lake Using an Artifiacial Neural Network and Three Dimensional Circulation Models",Computer and Geoscience .
  2. Zadeh.L.A. (1972), A Fuzzy set Theoretic Interpretation of Linguistik Hedges, Journal of Cybernetics,2,4-42
  3. Kusumadewi,S.,Purnaomo,H, (2009). Aplikasi Logika Fuzzy untuk Pendukung Keputusan. Yogyakarta: Penerbit Andi
  4. Kusrini dan Emha Taufik Luthfi . (2009).Algoritma Data Mining, Yogyakarta: Penerbit Andi.
  5. Suhartono. (2008). Feedforward Neural Network untuk pemodelan runtun waktu. Yogyakarta: Gajah Mada University Indonesia
  6. Jang.J.: (1993). Adaptive Neuro Fuzzy Inference(ANFIS) : Adaptive Network Based Fuzzy Inference System, IEEE Trans System,Man and Cybernetics 23(3),665-684
  7. Jang.J.S.R.,Sun,C.T.,Mizutani,E. (1997). Neuro Fuzzy and Soft Computing : A Computational Approach To Learning And Machine Intelligence.Prentice Hall International.Inc.,New Jersey.
  8. Hindayati Mustafidah dan Dwi Aryanto. (2012). Sistem Inferensi Fuzzy untuk Memprediksi Prestasi Belajar Mahasiswa Berdasarkan Nilai Ujian Nasional, Tes Potensi Akademik, dan Motivasi Belajar. JUITA ISSN: 2086-9398 Vol. II Nomor 1, Mei 2012
  9. Feddy Setio Pribadi. (2009). “Pengklasifikasian siswa berdasarkan prestasi Belajar dengan menggunakan logika Fuzzy clustering” Jurnal Lembaran Ilmu Kependidikan Jilid 39, no. 2, Desember 2009
  10. Agung Budi Purnomo, Daryanto, Henny Wahyu. (2015). Penelitian Di SMP Negeri 1 Glenmore menempatkan kelas sesuai dengan prestasi siswa yang dimiliki. Jurusan Teknik Informatika Fakultas Teknik, Universitas Muhammadiyah Jember