Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Teknik ITS TELKOMNIKA (Telecommunication Computing Electronics and Control)
Isye Arieshanti
Institut Teknologi Sepuluh Nopember
Computer Science & IT Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Ovarian Cancer Identification using One-Pass Clustering and k-Nearest Neighbors Isye Arieshanti; Yudhi Purwananto; Handayani Tjandrasa
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 11, No 4: December 2013
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v11i4.1203

Abstract

 The identification of ovarian cancer using protein expression profile (SELDI-TOF-MS) is important to assists early detection of ovarian cancer. The chance to save patient’s life is greater when ovarian cancer is detected at an early stage. However, the analysis of protein expression profile is challenging because it has very high dimensional features and noisy characteristic. In order to tackle those difficulties, a novel ovarian cancer identification model is proposed in this study. The model comprises of One-Pass Clustering and k-Nearest Neighbors Classifier.  With simple and efficient computation, the performance of the model achieves Accuracy about 97%. This result shows that the model is promising for Ovarian Cancer identification.
Comparative Study of Bankruptcy Prediction Models Isye Arieshanti; Yudhi Purwananto; Ariestia Ramadhani; Mohamat Ulin Nuha; Nurissaidah Ulinnuha
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 11, No 3: September 2013
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v11i3.1143

Abstract

 Early indication of Bankruptcy is important for a company. If companies aware of potency of their Bankruptcy, they can take a preventive action to anticipate the Bankruptcy. In order to detect the potency of a Bankruptcy, a company can utilize a model of Bankruptcy prediction. The prediction model can be built using a machine learning methods. However, the choice of machine learning methods should be performed carefully because the suitability of a model depends on the problem specifically. Therefore, in this paper we perform a comparative study of several machine leaning methods for Bankruptcy prediction. It is expected that the comparison result will provide insight about the robust method for further research. According to the comparative study, the performance of several models that based on machine learning methods (k-NN, fuzzy k-NN, SVM, Bagging Nearest Neighbour SVM, Multilayer Perceptron(MLP), Hybrid of MLP + Multiple Linear Regression), it can be concluded that fuzzy k-NN method achieve the best performance with accuracy 77.5%. The result suggests that the enhanced development of bankruptcy prediction model could use the improvement or modification of fuzzy k-NN.
Perbandingan Performa antara Imputasi Metode Konvensional dan Imputasi dengan Algoritma Mutual Nearest Neighbor Azwar Rizal Alfarisi; Handayani Tjandrasa; Isye Arieshanti
Jurnal Teknik ITS Vol 2, No 1 (2013)
Publisher : Direktorat Riset dan Pengabdian Masyarakat (DRPM), ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j23373539.v2i1.2735

Abstract

Missing value adalah sebuah permasalahan yang sering terjadi pada dataset riil. Kekurangan ini biasanya mempengaruhi akurasi saat dilakukan klasifikasi dengan menggunakan dataset tersebut. Salah satu cara menyelesaikan masalah missing value tersebut adalah mengisi nilai baru atau dikenal dengan metode imputasi. Algoritma mutual nearest neighbor (MNN) adalah sebuah algoritma pengenalan pola yang menggunakan tetangga mutual terdekat suatu instance. Dalam studi ini, algoritma MNN digunakan sebagai metode imputasi. Performanya akan dibandingkan dengan metode imputasi konvensional yaitu mengisikan nilai mean atau modus data atribut ke missing value. Berdasarkan hasil uji coba, performa klasifikasi setelah dilakukan imputasi dengan algoritma MNN mengungguli performa klasifikasi dengan metode imputasi konvensional.
Deteksi Penyakit Epilepsi dengan Menggunakan Entropi Permutasi, K-means Clustering, dan Multilayer Perceptron Yunita Ardilla; Handayani Tjandrasa; Isye Arieshanti
Jurnal Teknik ITS Vol 3, No 1 (2014)
Publisher : Direktorat Riset dan Pengabdian Masyarakat (DRPM), ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (277.104 KB) | DOI: 10.12962/j23373539.v3i1.5486

Abstract

Epilepsi didefinisikan sebagai kumpulan gejala dan tanda-tanda klinis yang muncul disebabkan gangguan fungsi otak secara intermiten, yang terjadi akibat lepas muatan listrik abnormal atau berlebihan dari neuron-neuron secara paroksimal dengan berbagai macam etiologi. Banyak pasien yang tidak menyadari adanya gejala epilesi dalam dirinya. Oleh karena itu diperlukan sistem yang bisa memprediksi apakah seseorang menderita epilepsi bebas kejang, atau epilepsi kejang. Dalam artikel ini diimplementasikan perangkat lunak pendeteksi penyakit epilepsi dengan menggunakan entropi permutasi, K-means clustering, dan multilayer perceptron. Hasil model dari algoritma multilayer perceptron akan digunakan dalam proses prediksi. Dataset yang digunakan dalam proses uji coba berisi lima himpunan (A-E) EEG dari manusia sehat dan yang menderita epilepsi yang tersedia online (''Klinik für Epileptologie, Universität Bonn''). Performa terbaik yang dihasilkan oleh model adalah akurasi sebesar 96,5%, specificity sebesar 95,45%, dan sensitivity sebesar 97,97%.
Co-Authors Ariestia Ramadhani Azwar Rizal Alfarisi Handayani Tjandrasa Mohamat Ulin Nuha Nurissaidah Ulinnuha Yudhi Purwananto Yunita Ardilla