Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal Scientific Journal of Informatics jurnal teknik informatika dan sistem informasi
Kurniati, Neng Ika
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sistem Pakar Untuk Mendiagnosa Penyakit Hewan Peliharaan Menggunakan Metode Certainty Factor Fauziah, Dewi; Mubarok, Husni; Kurniati, Neng Ika
Jurnal Teknik Informatika dan Sistem Informasi Vol 4 No 1 (2018): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1004.313 KB)

Abstract

Many species of a mammal often adopt as a pet animal. Pet healthy is a factor to be considered because pets are prone to disease. Another problem is lack of veterinarian or pet clinic in Tasikmalaya region. Making an expert system to diagnose pet diseases based on its symptoms is an alternative to overcome these problems. This expert system implements certainty factor to manage uncertainty in diagnosing process and uses forward chaining as a strategy for inferring the diagnose process based on rules. One of the results of this research is a set of rules as a knowledge representation for diagnosing pet diseases; there are six rules for diagnosing rabies, parainfluenza, distemper, hepatitis, parvovirus, and coronavirus. Furthermore, the testing of calculation accurately shows that result of manual testing and software testing is the same. The certainty factor in the first trial is 0.8, and for the second one is 0.85, these mean that the certainty value is high enough to accept.
Implementasi Deteksi Warna Pada Game Finding Color Menggunakan Ekstraksi Fitur Warna dan Fuzzy Decision Tree Hasanah, Risna; Hidayat, Eka Wahyu; Kurniati, Neng Ika
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 1 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i1.2388

Abstract

Recognizing color is an ability that must be trained from an early age. But the ability to recognize color in early childhood is still low. One of the most preferred media by children is games. Android mobile games have the advantage of providing interactive multimedia, challenges, and rewards. Finding Color games can be used to help children play actively in exploring and observing colors in the surrounding environment because they can detect colors using the camera. The stages in color detection in games are feature extraction and color classification. Color feature extraction will get the color value at the selected pixel coordinates on the screen. The color classification uses fuzzy decision tree ID3. The test results of the application of color feature extraction produce an accuracy value of 100%. The fuzzy decision tree classification is evaluated using a confusion matrix, resulting in an accuracy value in outdoor light conditions of 94.4%. There is an increase of 4.4% compared to indoor conditions. Keywords— Color Detection; Color Feature Extraction; Fuzzy Decision Tree; Game; Mobile Android
Implementation of Stacking Ensemble Classifier for Multi-class Classification of COVID-19 Vaccines Topics on Twitter Jayapermana, Rama; Aradea, Aradea; Kurniati, Neng Ika
Scientific Journal of Informatics Vol 9, No 1 (2022): May 2022
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v9i1.31648

Abstract

Purpose: However, from the variety of uses of these algorithms, in general, accuracy problems are still a concern today, even accuracy problems related to multi-class classification still require further research.Methods: This study proposes a stacking ensemble classifier method to produce better accuracy by combining Logistic Regression, Random Forest, and Support Vector Machine (SVM) algorithms as first-level learners and using Logistic Regression as a meta-learner for the multi-class classification of COVID-19 vaccine topics on Twitter.Result: Based on the evaluation, the proposed Stacking Ensemble Classifier model shows 86% accuracy, 85% precision, 86% recall, and 85% f1-score.Novelty: The novelty is produce better accuracy by combining Logistic Regression, Random Forest, and Support Vector Machine (SVM) algorithms as first-level learners and using Logistic Regression as a meta-learner.
Co-Authors Aradea Fauziah, Dewi Hasanah, Risna Hidayat, Eka Wahyu Husni Mubarok Jayapermana, Rama