Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer JURNAL MEDIA INFORMATIKA BUDIDARMA
Affandy Affandy
Universitas Dian Nuswantoro, Semarang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 4 Documents
Search

 1 
Analisis Metode Ensemble Pada Klasifikasi Penyakit Jantung Berbasis Decision Tree Mochammad Ilham Aziz; Ahmad Zainul Fanani; Affandy Affandy
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i1.5169

Abstract

Heart disease is one disease that is not easy to predict early on and maybe some people are not aware that they have the disease. Data obtained by WHO More than 17 million people worldwide died of heart attacks in 2016. If thesymptoms of heart disease or heart attack are known, prevention of heart disease can be anticipated and even minimized mortality. Analysis of heart disease aims to reduce mortality from the disease. In writing this research, a decision tree algorithm method is used, the algorithm still has weaknesses in making prediction accuracy. So we need a way to improve the accuracy of the classification learning outcomes. This study aims to improve the learning outcomes of heart disease classification by using ensemble learning methods, namely Boostrap Aggregating (Bagging) and Adaptive Boosting (Adaboost). Both methods were tested by predicting deaths caused by heart disease.
Peningkatan Algoritma C4.5 Berbasis PSO Pada Penyakit Kanker Payudara Rudi Nurcahyo; Ahmad Zainul Fanani; Affandy Affandy; Mochammad Ilham Aziz
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6841

Abstract

Onenof the diseases innthe world that causes deathnin women isncancer. Cancernis a diseasencaused by uncontrolled enlargement of abnormal organs in the body. Cancer diagnosis is made using anthropometric data from routine blood analysis. The data used is the Breast Cancer Coimbra Data Set obtained from the UCI Machine Learning Repository. The C4.5 method is andecision treenalgorithm that is often used in the classification process. The selection of the right features, as well as the selectionnof the right method to overcome the class imbalance in the classification process cannimprove the performancenof the C4.5 algorithm. confusion matrix can benused in the Test to determine Classification accuracy. In this research, the application of PSO as a feature organization.
Optimasi K-means Clustering Dengan Menggunakan Particle Swarm Optimization Untuk Menentukan Jumlah Cluster Pada Kanker Serviks Indrawan Setiaji; Affandy Affandy; Ahmad Zainul Fanani
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 3 (2023): Juli 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i3.6292

Abstract

Cervical cancer is one of the most common cancers among women in the world. It is most common in developing countries. Cervical cancer develops slowly in the body. Clustering is needed so that cervical cancer can be treated quickly. The K-means method was chosen because of its ability to group large amounts of data and fast computation time. The K-means method is also very easy to implement, flexible, and uses simple principles, which can be explained non-statistically. The many advantages that K-means has, also has weaknesses because it uses random clustering numbers and the results are not optimal. The difficulty in accurately determining the amount of clustering in the dataset. The K-means method cannot provide an optimal solution for determining the number of clustering, so it needs to be improved in order to obtain an optimal solution. PSO was chosen because it has several advantages, namely requiring few parameters, easy to implement, fast convergence, more efficient because it requires little computation and is simple. The results showed that the PSO - K-means method can prove to provide a significant contribution by directly obtaining optimum clustering results without having to do repeated experiments with a Silhouette Coefficient value of 0.83 and a Davies Bouldien Index value of 1.91.
Peningkatan Performa Ensemble Learning pada Segmentasi Semantik Gambar dengan Teknik Oversampling untuk Class Imbalance Arie Nugroho; M. Arief Soeleman; Ricardus Anggi Pramunendar; Affandy Affandy; Aris Nurhindarto
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 4: Agustus 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20241046831

Abstract

Perkembangan teknologi dan gaya hidup manusia yang semakin tinggi menghasilkan data-data yang berlimpah. Data-data tersebut dapat berbentuk data yang terstruktur dan tidak terstruktur. Data gambar termasuk dalam data yang tidak terstruktur. Aktifitas dan objek yang terekam dalam suatu gambar beraneka ragam. Secara normal, mata manusia dapat dengan mudah membedakan antara foreground dan background dari suatu gambar, tetapi komputer membutuhkan pembelajaran dalam membedakan keduanya. Segmentasi gambar adalah salah satu bidang dalam computer vision yang membahas bagaimana cara komputer mempelajari dan mengenali segmen dari suatu gambar sesuai label yang ditentukan. Dalam kenyataannya banyak data yang mempunyai class atau label yang tidak seimbang, tentunya akan mempengaruhi tingkat akurasi dari suatu prediksi. Dalam riset ini membahas bagaimana meningkatkan akurasi segmentasi semantik gambar pada metode ensemble learning untuk menangani masalah data yang tidak seimbang dalam segmentasi gambar. Teknik yang digunakan adalah sintetis oversampling sehingga menghasilkan data yang seimbang dan akurasi yang tinggi. Metode ensemble learning yang digunakan adalah Random Forest dan Light Gradien Boosting Machine (LGBM). Dengan menggunakan dataset Penn-Fudan Database for Pedestrian yang mengandung imbalanced class. Penggunaan teknik sintetis oversampling dapat memperbaikki tingkat akurasi pada class minoritas. Pada algoritma random forest mengalami peningkatan akurasi sebesar 37 % sedangkan pada algoritma LGBM meningkat sebesar 41 %. AbstractThe development of technology and the increasingly high lifestyle of humans produce abundant data. These data can be in the form of structured and unstructured data. Image data is included in unstructured data. The activities and objects recorded in a picture are varied. Normally, the human eye can easily distinguish between the foreground and background of an image, but computers need learning to distinguish between the two. Image segmentation is one of the fields in computer vision that discusses how computers learn and recognize segments of an image according to specified labels. In reality, a lot of data has unbalanced classes or labels, of course, it will affect the accuracy of a prediction. This research discusses how to improve the accuracy of image semantic segmentation in the ensemble learning method to deal with the problem of unbalanced data in image segmentation. The technique used is synthetic oversampling so as to produce balanced data and high accuracy. The ensemble learning methods used are Random Forest and Light Gradient Boosting Machine (LGBM). By using the Penn-Fudan Database for Pedestrian dataset which contains a imbalanced class. The use of synthetic oversampling techniques can improve the level of accuracy in minority classes. The random forest algorithm experienced an increase in accuracy by 37% while the LGBM algorithm increased by 41%.
Co-Authors Ahmad Zainul Fanani Arie Nugroho Aris Nurhindarto Indrawan Setiaji M. Arief Soeleman Mochammad Ilham Aziz Ricardus Anggi Pramunendar Rudi Nurcahyo