In this study, the EMG signals are processed using 16 time-domain features extraction to classify the finger movement such as thumb, index, middle, ring, and little. The pattern recognition of 16 extracted features are classified using artificial neural network (ANN) with two layer feed forward network. The network utilizes a log-sigmoid transfer function in hidden layer and a hyperbolic tangent sigmoid transfer function in the output layer. The ANN uses 10 neurons in hidden layer and 5 neurons in output layer.
The training of ANN pattern recognition uses Levenberg-Marquardt training algorithm and the performance utilizes mean square error (MSE). At about 22 epochs the MSE of training, test, and validation get stabilized and MSE is very low.There is no miss classification during training process. Based on the resulted overall confusion matrix, the accuracy of thumb, middle, ring, and little is 100%. The confusion of index is 16.7%. The overall confusion matrix shows that the error is 3.3% and overall performance is 96.7%.
ABSTRAK Universitas Islam Negeri (UIN) Sunan Gunung Djati Bandung salah satu institusi perguruan tinggi yang memiliki kualitas yang bagus dan memiliki potensi yang dapat menyerap mahasiswa baru berdasarkan berlimpahnya data awal yang diperoleh dari tahun ajaran 2013/2014 sampai dengan 2016/2017, dengan tahapan seleksi penerimaan yang banyak bahkan mahasiswa baru yang terserap beberapa tahun terakhir mengalami peningkatan dan penurunan.Dalam penelitian dilakukan analisa perbandingan algoritma fuzzy logic metode Tsukamoto, Sugeno dan Mamdani untuk memprediksi jumlah pendaftar untuk tahun kedepan dilihat dari jumlah mahasiswa yang lulus dan registrasi dari tahun sebelumnya dan dalam membandingkan perhitungannya menggunakan nilai rata-rata dari hasil yang diperoleh pada ketiga metode fuzzy tersebut dengan aplikasi berbasis web.Hasil dari penelitian yang telah dihitung bahwa metode fuzzy Mamdani mempunyai tingkat error yang lebih kecil sebesar 19,76% dibandingkan dengan metode Tsukamoto sebesar 39,03% dan Sugeno sebesar 86,41% pada prediksi jumlah pendaftar mahasiswa baru. ABSTRACT State Islamic University (UIN) Sunan Gunung Djati Bandung one of the university institutions that have good quality and has the potential to absorb new students based on the abundance of preliminary data obtained from the academic year 2013/2014 until 2016/2017, with the selection selection stage Which many new students even absorbed in the last few years have increased and decreased. In the research, comparative analysis of fuzzy logic algorithm of Tsukamoto, Sugeno and Mamdani method is used to predict the number of applicants for the next year seen from the number of students who graduated and registration from the previous year and in comparing the calculation uses the average value of the results obtained in the three fuzzy methods with web-based applications. The result of the research has been calculated that the fuzzy Mamdani method has a smaller error rate of 19.76% compared to the tsukamo method To equal to 39.03% and Sugeno equal to 86.41% in predicted number of new student enrollment How to Cite : Irfan, M. Ayuningtias, L.P. Jumadi, J. (2017). ANALISA PERBANDINGAN LOGIC FUZZY METODE TSUKAMOTO, SUGENO, DAN MAMDANI (STUDI KASUS : PREDIKSI JUMLAH PENDAFTAR MAHASISWA BARU FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN GUNUNG DJATI BANDUNG). Jurnal Teknik Informatika, 10(1), 9-16.doi:10.15408/jti.v10i1.6810Permalink/DOI: http://dx.doi.org/10.15408/jti.v10i1.6810
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.