Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Journal of Information Systems Engineering and Business Intelligence Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Ednawati Rainarli
Universitas Komputer Indonesia
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Simple Logistic Classifier dengan Support Vector Machine dalam Memprediksi Kemenangan Atlet Ednawati Rainarli; Arif Romadhan
Journal of Information Systems Engineering and Business Intelligence Vol. 3 No. 2 (2017): October
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (178.812 KB) | DOI: 10.20473/jisebi.3.2.87-91

Abstract

Abstrak— Prediksi kemenangan atlet adalah hal yang harus dilakukan oleh pelatih ketika memutuskan pemain  yang akan diturunkan dalam suatu pertandingan. Banyaknya faktor-faktor yang mempengaruhi kemenangan atlet membuat keputusan tersebut tidak mudah untuk ditentukan. Dalam penelitian ini akan dilakukan perbandingan dari penggunaan metode Simple Logistic Classifier (SLC) dengan Support Vector Machine (SVM)  dalam memprediksi kemenangan atlet berdasarkan data kesehatan dan data latihan fisik. Data yang digunakan diambil dari 28 cabang olahraga perorangan. Rata-rata akurasi SLC dan SVM masing-masing diperoleh sebesar 80% dan 88%, sedangkan rata-rata kecepatan pemrosesan metode SLC dan SVM adalah 1,6 detik dan 0,2 detik.  Hal ini menunjukkan bahwa penggunaan metode SVM lebih unggul daripada SLC, baik dari segi kecepatan maupun dari nilai akurasi yang dihasilkan. Selain pengujian akurasi, dilakukan pula pengujian terhadap 24 fitur yang digunakan dalam proses klasifikasi.  Hasilnya diketahui bahwa pengurangan fitur melalui tahap seleksi mengakibatkan penurunan nilai akurasi. Berdasarkan hal tersebut disimpulkan bahwa semua fitur yang digunakan dalam penelitian ini adalah fitur yang berpengaruh dalam penentuan prediksi kemenangan atlet. Kata Kunci— Prediksi, Simple Logistic Classifier, Sports Data Mining, Support Vector MachineAbstract— A coach must be able to select which athlete has a good prospect of winning a game.  There are a lot of aspects which influence the athlete in winning a game, so it's not easy by coach to decide it.This research would compare Simple Logistic Classifier (SLC) and Support Vector Machine (SVM) usage applied to predict winning game of athlete based on health and physical condition record.  The data get from 28 sports. The accuracy of SLC and SVM are 80% and 88% meanwhile processing times of SLC and SVM method are 1.6 seconds dan 0.2 seconds.The result shows the SVM usage superior to the SLC both of speed process and the value of accuracy.  There were also testing of 24 features used in the classifications process. Based on the test,  features selection process can cause decreasing the accuracy value. This result concludes that all features used in this research influence the determination of a victory athletes prediction. Keywords— Prediction, Simple Logistic Classifier, Sports Data Mining, Support Vector Machine
Implementasi Q-Learning dan Backpropagation pada Agen yang Memainkan Permainan Flappy Bird Ardiansyah; Ednawati Rainarli
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 6 No 1: Februari 2017
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1479.852 KB)

Abstract

This paper shows how to implement a combination of Q-learning and backpropagation on the case of agent learning to play Flappy Bird game. Q-learning and backpropagation are combined to predict the value-function of each action, or called value-function approximation. The value-function approximation is used to reduce learning time and to reduce weights stored in memory. Previous studies using only regular reinforcement learning took longer time and more amount of weights stored in memory. The artificial neural network architecture (ANN) used in this study is an ANN for each action. The results show that combining Q-learning and backpropagation can reduce agent’s learning time to play Flappy Bird up to 92% and reduce the weights stored in memory up to 94%, compared to regular Q-learning only. Although the learning time and the weights stored are reduced, Q-learning combined with backpropagation have the same ability as regular Q-learning to play Flappy Bird game.
Co-Authors Ardiansyah Arif Romadhan