Claim Missing Document
Check
Articles

Found 38 Documents
Search

Grouping Education Students at Pusdikjas Institutions of The TNI-AD's Disjasad Using the K-Means Clustering Method Pramudjianto, Imam Wibowo; Ningsih, Ade Kania; Komarudin, Agus
Enrichment: Journal of Multidisciplinary Research and Development Vol. 1 No. 7 (2023): Enrichment: Journal of Multidisciplinary Research and Development
Publisher : International Journal Labs

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55324/enrichment.v1i7.64

Abstract

The Military Physical Education Center, known by the abbreviation Pusdikjasmil, is an implementation body that is directly under the TNI AD. Pusdikjas has the task of providing education in the military physical field to support the duties of the Indonesian Army. At the Pusdikjas agency, student data is obtained from the addition of students attending education each year. The process of admitting students to Pusdikjas institutions produces abundant value data and is repeated every year. By using data mining techniques, abundant student data can be grouped and analyzed to find information that is useful for Pusdikjas agencies. The algorithm used in this research is K-means clustering. The data used from 2018 - 2022 was 1428 data on coaching education students, with the variables used being NRP, attitude & and behavior, knowledge & and skills, and physical. Processed using the JavaScript programming language, this research produces optimal clusters, namely 2 clusters. cluster 1 with a total data of 751 students in cluster 1 describes a very satisfactory category of students, and cluster 2 with total data of 676 students. Cluster 2 describes the satisfactory student category. As for testing the quality of the clusters contained in the system using silhouette with results reaching 0.6543347543126016.
Decision Support System For Determining Food Menu Using Analytical Hierarchy Process (Ahp) Method Maulina, Ninda; Witanti, Wina; Komarudin, Agus
Enrichment: Journal of Multidisciplinary Research and Development Vol. 1 No. 7 (2023): Enrichment: Journal of Multidisciplinary Research and Development
Publisher : International Journal Labs

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55324/enrichment.v1i7.65

Abstract

Food menus in the culinary and restaurant industries often involve various complex features, such as food origin, food category, diet category, ingredients, and time. This study aims to develop a Decision Support System (DSS) based on the AHP method to assist chefs, restaurant managers and food business owners in compiling a diverse menu, meeting nutritional needs, taking into account certain preferences and limitations, and creating a pleasant dining experience. The Analytic Hierarchy Process (AHP) method can be used as a tool in making more effective and structured decisions. The results of this study indicate that the Analytic Hierarchy Process (AHP) method succeeded in producing relative weights for each criterion and sub-criteria, thus enabling priority in preparing food menus. In testing, this system is able to provide the best recommendations based on global priority values for certain types of food, which are expected to increase the variety and quality of food menus and meet consumer preferences and needs. Through experiments conducted using a Decision Support System, a decision model is formed that determines the priority for the weight of all criteria and alternatives. The results show preferences in the process of determining food menus by producing Cold Coffee with a value of 0.30 (29%), Biscuit Dough Donuts with a value of 0.25 (25%), Chicken Dimsum with a value of 0.21 (21%), Succotash with a a value of 0.15 (15%), and Toffee Banana with a value of 0.10 (10%).
Prediksi Kinerja Akademik Siswa Bimbingan Belajar Menggunakan Algoritma Extreme Gradient Boosting (XGBoost) Alfarizi, Muhammad Bayu Ardi; Witanti, Wina; Komarudin, Agus
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7387

Abstract

Improving the quality of education has become a primary focus in addressing the increasingly complex challenges of the educational landscape. One promising approach to support data-driven decision-making is the prediction of students' academic performance using machine learning algorithms. This study aims to develop a classification model for predicting students' academic performance by leveraging the Extreme Gradient Boosting (XGBoost) algorithm. The dataset used was obtained from SMPN 1 Gunung Halu and includes both academic and non-academic attributes of students. Five key features were selected: initial grades, midterm grades, final grades, student behavior, and attendance. Data preprocessing involved feature selection, handling missing values, transforming categorical variables using label encoding, and balancing the classes using the SMOTE method. The XGBoost model was then trained using an 80:20 data split and hyperparameter tuning was performed using Grid Search. Evaluation results showed that the model achieved an accuracy of 84% with balanced F1-scores across all classes. The model outperformed other algorithms such as Bagging and Random Forest. With its strong accuracy and stability, the XGBoost model has the potential to serve as a tool for identifying students who require academic intervention. This study makes a significant contribution to the development of AI-based education systems and provides a foundation for the application of machine learning in improving the quality of secondary-level learning.
Prediksi Penyakit Kanker Payudara Menggunakan Algoritma Synthetic Minority Oversampling Technique dan Categorical Boosting Classifier Mandala, Muhamad Bintang; Witanti, Wina; Komarudin, Agus
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7403

Abstract

Breast cancer remains one of the leading causes of mortality worldwide, with high prevalence rates among women in Indonesia. Accurate and efficient diagnostic models are essential to support early detection and reduce mortality. This study aims to develop a predictive model for breast cancer classification using the CatBoost algorithm, a gradient boosting method known for its ability to natively handle categorical features and reduce overfitting through ordered boosting. The dataset used consists of diagnostic features of breast tumors, which were preprocessed by checking completeness and transforming numerical attributes into categorical bins to capture value distribution more effectively. To address class imbalance between benign and malignant cases, the SMOTE (Synthetic Minority Over-sampling Technique) method was applied, resulting in a balanced training set. Optimal hyperparameters for the CatBoost model were obtained using Bayesian optimization, with key parameters including depth, learning rate, and L2 regularization. The model was then trained and evaluated using recall, accuracy, and F1-score metrics, with a confusion matrix used to assess prediction quality. The results demonstrate that CatBoost achieved high performance with a recall of 1,0, accuracy of 98,6%, and F1-score of 0,99, outperforming or matching other benchmark models such as SVM, Neural Network, and XGBoost. These findings highlight the reliability and effectiveness of CatBoost in supporting medical decision-making for breast cancer diagnosis.
Sistem Monitoring Tanaman Paprika di Greenhouse Menggunakan Internet of Things Al Farisi, Muhammad Farid; Abdillah, Gunawan; Komarudin, Agus
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2437

Abstract

Tanaman paprika (Capsicum annuum var. grossum L.) memerlukan pengawasan lingkungan yang cermat dan terus-menerus. Penelitian ini mengembangkan sistem monitoring berbasis Internet of Things (IoT) dengan mikrokontroler ESP32 untuk mengukur suhu, kelembapan, pH tanah, dan kadar NPK secara otomatis. Data disimpan di Firebase Firestore dan divisualisasikan pada dashboard web berbasis JavaScript. Sistem ini juga mampu mengontrol kipas dan humidifier secara manual dan otomatis jika parameter melebihi ambang batas. Hasil pengujian menunjukkan bahwa sistem berjalan stabil dan responsif dalam kondisi greenhouse skala kecil. Sistem ini diharapkan dapat meningkatkan efisiensi dan akurasi dalam pengelolaan pertanian modern.
Sistem Pendukung Keputusan Penentuan Calon Transmigran Menggunakan Simple Additive Weighting dan Profile Matching Wardani, Mathilda Fitri; Abdillah, Gunawan; Komarudin, Agus
Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi) Vol. 3 No. 1 (2019): PROSIDING SEMNAS INOTEK Ke-III Tahun 2019
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/inotek.v3i1.520

Abstract

Transmigrasi merupakan salah satu program pemerintah dalam mengatasi masalah kepadatan penduduk dengan memindahkan penduduk dari suatu daerah yang padat penduduk ke daerah lain yang jarang penduduk di wilayah Indonesia berlandaskan pada Undang-Undang Nomor 25 tahun 2000 dan Peraturan Pemerintah Nomor 2 Tahun 1999 tentang Penyelenggaraan Transmigrasi. Calon transmigran tidak dapat menentukan sendiri daerah tujuan transmigrasi melainkan harus disesuaikan dengan peraturan yang telah ditetapkan oleh pemerintah, sehingga pemerintah diharuskan untuk dapat memilih daerah tujuan transmigrasi yang tepat sasaran untuk calon transmigran. Penelitian ini telah membangun sistem yang mampu merekomendasikan prioritas calon transmigran beserta daerah tujuan transmigrasi dari segi usia, jumlah anggota keluarga, pekerjaan, pendidikan dan keterampilan dengan bobot yang ditentukan oleh pengguna. Metode yang digunakan adalah Simple Additive Weighting dan Profile Matching. Hasil dari uji coba sistem ini menghasilkan presentase akurasi sistem untuk penentuan calon transmigran sebesar 50% dan akurasi sistem untuk penentuan daerah tujuan transmigrasi sebesar 90%.
SISTEM INFORMASI PENJUALAN SPAREPART DI BENGKEL PRAWIRA BERBASIS WEB Wirajaya Putra, Basudewa; Komarudin, Agus
JURNAL ILMU KOMPUTER, SISTEM INFORMASI, TEKNIK INFORMATIKA Vol 4 No 2 (2025)
Publisher : PT Akom Media Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini berfokus pada bengkel Prawira yang belum mengimplementasikan sistem terkomputerisasi dalam pengecekan persediaan barang. Salah satu masalah utama yang dihadapi adalah kesalahan dalam pencatatan persediaan dan harga barang. Tujuan penelitian ini adalah untuk memahami cara kerja sistem yang ada, mengidentifikasi kelebihan sistem yang diusulkan, serta mempermudah pekerjaan pengguna dalam pengelolaan persediaan. Metode penelitian yang digunakan adalah Metode Waterfall, yang membantu dalam perencanaan dan pengembangan sistem secara terstruktur, serta Framework Bootstrap untuk desain antarmuka. Hasil yang diperoleh adalah sistem persediaan barang berbasis web, yang berfungsi untuk pencatatan dan pengendalian persediaan secara efisien, sehingga mengurangi kesalahan dan meningkatkan produktivitas.
Komparasi Kinerja Model Machine learning Berbasis Metadata Produk untuk Prediksi Popularitas Produk Elektronik pada Marketplace Lazada Indonesia Aziz Apriadi, Eko; Komarudin, Agus; Julianto, Ribut
JURNAL ILMU KOMPUTER, SISTEM INFORMASI, TEKNIK INFORMATIKA Vol 5 No 1 (2026)
Publisher : PT Akom Media Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study explores the use of product metadata to predict the popularity of electronic products in the Lazada Indonesia marketplace. By using machine learning models, including Logistic Regression, Random Forest, and XGBoost, this study shows that simple metadata such as product category, brand, price, and rating are sufficiently informative to build predictive models. The results indicate that although Logistic Regression delivers the lowest performance due to its linear nature, both Random Forest and XGBoost provide significant improvement. XGBoost achieves the best results with the highest accuracy and F1-score, making it the most effective model for predicting product popularity. These findings highlight the complexity of e-commerce data, which requires more flexible models to capture non-linear patterns and interactions among product features. This study contributes to e-commerce management by providing insights into the use of machine learning for inventory management, promotional strategies, and product placement in digital marketplaces