Claim Missing Document
Check
Articles

Application of Bagging and Boosting Methods for Heart Disease Classification Yehezkiel E.A Parapak; Robet Robet; Jackri Hendrik
Journal of Applied Computer Science and Technology Vol. 6 No. 2 (2025): Desember 2025
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/we9asn06

Abstract

Cardiovascular disease remains a primary contributor to global mortality, underscoring the urgent need for accurate and early diagnostic tools. This study aims to develop a robust classification model for heart disease by conducting a comparative analysis of six ensemble machine learning algorithms, comprising three from the Bagging family (Random Forest, Bagged Decision Tree, Extra Trees) and three from the Boosting family (AdaBoost, Gradient Boosting, XGBoost). The research utilizes the publicly available UCI Cleveland Heart Disease dataset, which exhibits a mild class imbalance. To address this, the Synthetic Minority Over-sampling Technique (SMOTE) was strategically applied to the training data. The performance of each model was rigorously evaluated using accuracy, precision, recall, and F1-score. Experimental results revealed that the Extra Trees algorithm, when combined with SMOTE, achieved the highest overall performance with 90% accuracy, 96% precision, 82% recall, and an 88% F1-score. The primary contribution of this work lies in its comprehensive analysis demonstrating that the randomization strategy of Extra Trees provides a superior and more reliable framework for this classification task compared to other common ensemble techniques, particularly after data balancing. These findings confirm that an integrated approach of ensemble learning and proper data balancing can significantly enhance the development of fair and effective diagnostic tools to support medical professionals.
Akurasi K-Means dengan Menggunakan Cluster dan Titik Grid Terbaik pada Pemetaan Grid Interatif K-Means Johanes Terang Kita Perangin Angin; Ari Rizkita; Robet Robet; Octara Pribadi
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp127-129

Abstract

Traditional K-Means face 2 (two) main problems, namely: Determination of Initial Centroid and poor initial cluster. Determining the initial centroid using random numbers is one of the main problems in classical K-Means which results in low accuracy and long computation time. Likewise, determining the good centroid of each cluster without being accompanied by a process of paying attention to the performance of each cluster can also cause the accuracy value obtained is not good. This study will contribute to how the performance obtained by determining a good initial centroid is combined with the use of a good cluster. Determination of a good initial centroid is done by using the K-Means Grid Mapping which divides the determination of the centroid into several Grid Points. The result of this research is a combination of Iterative K-Means with Grid Mapping K-Means to become Iterative Grid Mapping K-Means which will get a good initial centroid and also a good cluster shown in the table of iris and abalone, comparison of the variables in the iris and abalone affecting the best cluster as a result.
DETEKSI BERITA HOAKS BAHASA INDONESIA MENGGUNAKAN KOMBINASI TF-IDF DAN K-NEAREST NEIGHBOR Ari Rizkita; Johanes Terang Kita Perangin Angin; Robet Robet; Octara Pribadi; Iqbal Giffari Ritonga
Jurnal TIMES Vol 15 No 1 (2026): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51351/jtm.15.1.2026933

Abstract

Penyebaran berita hoaks di media digital Indonesia telah menjadi tantangan serius yang mengancam stabilitas sosial dan ketertiban publik. Berdasarkan data Kementerian Komunikasi dan Informatika, jumlah isu hoaks terus meningkat secara signifikan setiap tahunnya, sehingga diperlukan sistem deteksi otomatis yang cepat dan akurat. Penelitian ini bertujuan untuk mengimplementasikan dan menganalisis performa kombinasi metode ekstraksi fitur Term Frequency-Inverse Document Frequency (TF-IDF) dan algoritma K-Nearest Neighbor (KNN) dalam mengklasifikasikan berita hoaks berbahasa Indonesia. Dataset yang digunakan berjumlah 1.000 entri seimbang yang bersumber dari TurnBackHoax.id sebagai representasi hoaks, serta Antaranews, Kompas, dan Detik sebagai representasi berita valid. Eksperimen dilakukan dengan pembagian data latih dan uji sebesar 80:20 serta pengujian iteratif pada nilai parameter K ganjil (3, 5, 7, 9, dan 11). Hasil penelitian menunjukkan bahwa model mencapai performa maksimal dengan nilai akurasi, presisi, dan recall sebesar 100% pada seluruh skenario nilai K. Hal ini mengindikasikan bahwa pembobotan statistik TF-IDF mampu membedakan pola kosakata antara klarifikasi hoaks dan teks jurnalistik secara sempurna. Kesimpulannya, algoritma KNN terbukti sangat efektif dan efisien secara komputasi untuk digunakan sebagai sistem penyaring misinformasi pada media digital di Indonesia.
PERANCANGAN WEBSITE E-COMMERCE MULTI CABANG PADA PT. PASAR SWALAYAN MAJU BERSAMA MENGGUNAKAN ALGORITMA JACCARD COEFFICIENT Andy Andy; Agus Maringan Siahaan; Satriya Miharja; Robet Robet; Didik Aryanto
Majalah Ilmiah METHODA Vol. 14 No. 1 (2024): Majalah Ilmiah METHODA
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methoda.Vol14No1.pp25-32

Abstract

PT. Pasar Swalayan Maju Bersama is a company engaged in the supermarket sector and has 3 branches, namely Maju Bersama Glugur, Maju Bersama Merak Jingga, and Maju Bersama Marendal. But in practice, PT. Maju Bersama Supermarkets still have not utilized good marketing media, both internally and externally. On the internal side, the company has not been able to properly integrate the sales processes of its three branches. In addition, the main problem is related to the amount of transaction data stored in the company's storage. Transaction data recorded every day will certainly burden storage if it is not used properly to become useful knowledge for the company. From the description of the problem, it is necessary to develop a multi-branch based system that is implemented on an E-Commerce website. This research also implements the Jaccard Coefficient algorithm so that it can process company data which turns a lot of knowledge into product recommendations for customers. The results of the study show that the Jaccard Coefficient algorithm is proven capable of processing company data into knowledge in the form of product recommendations that are relevant to customers.
Implementasi Chatbot Otomatis Akademik Berbasis Web Menggunakan LLM dan Rule-Based System Studi Kasus: STMIK Time Alvin Alvin; Robet Robet; Feriani Astuti Tarigan
JURNAL INFORMATIKA DAN KOMPUTER Vol 9, No 3 (2025): Oktober 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v9i3.2209

Abstract

Perkembangan teknologi kecerdasan buatan (Artificial Intelligence/AI) telah mendorong peningkatan efisiensi layanan informasi melalui penerapan chatbot yang mampu berinteraksi secara alami dengan pengguna. Chatbot merupakan implementasi teknologi berbasis pemrosesan bahasa alami (Natural Language Processing/NLP) yang dirancang untuk memahami dan merespons percakapan manusia. Penelitian ini bertujuan mengembangkan chatbot otomatis layanan akademik STMIK Time berbasis web dengan mengintegrasikan dua pendekatan utama, yaitu Rule-Based System dan Large Language Model (LLM). Metode penelitian meliputi tahap perancangan sistem menggunakan Flowise AI sebagai platform automation workflow, serta pengujian performa sistem melalui dua tahap, yaitu pengujian black box untuk menilai fungsionalitas dan pengujian user experience untuk mengukur persepsi pengguna terhadap kecepatan, akurasi, dan kepuasan. Hasil pengujian menunjukkan bahwa chatbot berfungsi dengan baik dengan capaian kecepatan respons sebesar 51,5%, tingkat akurasi 54,5%, dan tingkat kepuasan pengguna 60,6%. Hasil ini menegaskan bahwa sistem mampu memberikan layanan informasi akademik secara efektif, meskipun aspek kecepatan dan responsivitas masih perlu ditingkatkan. Kesimpulannya, Rule-Based System lebih sesuai untuk percakapan terstruktur, sedangkan Large Language Model (LLM) lebih efektif untuk konteks dinamis. Penelitian ini diharapkan menjadi dasar pengembangan layanan akademik berbasis AI yang lebih adaptif dan responsif di perguruan tinggi.
Improving Resnet Model In Safety Gear Classification Using Finest Optimizer Robet; Johanes Terang Kita Perangin Angin; Edi Wijaya
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.703

Abstract

The Occupational accidents that occur in the work environment are increasing day by day. This is caused by workers' non-compliance with the established work safety equipment. Although the supervision of the use of work safety equipment has been carried out, it is still done manually involving less effective human resources. Therefore, it is necessary to develop an intelligent model that can classify the use of work safety equipment more accurately. This study uses the pre-trained ResNet50 model and is combined with the best optimization model to improve accuracy. The results of the study showed that the RMSProp optimization model has better performance with an accuracy value of 97.01% in the 17th epoch of 50 epochs of data training and with training loss and validation loss values ​​of 0.3268 and 0.145, respectively. Testing of 20 images with each image, 10 images using safety equipment, and 10 images not using safety equipment can be classified correctly.
Optimizing MRI-Based Alzheimer’s Disease Detection Using EfficientNet and Explainable Artificial Intelligence Kohsasih, Kelvin Leonardi; Robet, Robet; Perangin Angin, Johanes Terang Kita; Pribadi, Octara; Hendri, Hendri; Hendrik, Jackri
Jurnal Informatika Vol. 13 No. 2 (2026): October
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/informatika.v13i2.12431

Abstract

Alzheimer’s disease has been difficult to diagnose early because structural changes in the brain often appear subtle and overlap with normal aging. This study aimed to improve the accuracy and interpretability of Alzheimer’s disease detection from structural magnetic resonance imaging by developing a classification framework based on the EfficientNet B3 architecture. The imaging data were processed through grayscale conversion, resizing, contrast enhancement, and normalization, followed by synthetic oversampling to balance the diagnostic categories. The model demonstrated strong performance, achieving an accuracy of 0.9965, high precision and recall across all classes, perfect discrimination scores, and a high Matthews correlation coefficient. Gradient-weighted Class Activation Mapping and Shapley-based explanations revealed that the model focused on neuroanatomical regions consistent with known markers of Alzheimer’s disease. The results showed that the proposed framework met the study objective and produced reliable and clinically relevant predictions. These findings also suggested opportunities for future expansion through multimodal imaging and integration into clinical decision-support systems.