Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Agri-Informatika Jurnal INFOTEL
Hardhienata, Medria Kusuma Dewi
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Electrical & Electronics Engineering

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

Found 3 Documents
Search

 1 
Pengelompokan Publikasi Ilmiah Berdasarkan Bidang Kepakaran Menggunakan Latent Dirichlet Allocation dan Normalized PSO-K-means Hayatina, Fina Charisma; Wijaya, Sony Hartono; Hardhienata, Medria Kusuma Dewi
Jurnal Ilmu Komputer dan Agri-Informatika Vol. 10 No. 2 (2023)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.10.2.121-132

Abstract

Salah satu cara untuk memvalidasi klaim kepakaran dosen adalah dengan meninjau dokumen publikasi ilmiah yang tersedia. Namun, menentukan kelompok kepakaran dari sejumlah dokumen memerlukan pengetahuan yang memadai dan waktu yang relatif lama, sehingga menjadi sulit dilakukan. Penelitian ini bertujuan untuk membangun suatu model yang dapat mengelompokkan dokumen berdasarkan bidang kepakaran. Penelitian ini menggunakan algoritma klasterisasi K-means untuk mengelompokkan dokumen berdasarkan bidang kepakaran dosen. Latent dirichlet allocation digunakan untuk mereduksi dimensi data, dan particle swarm optimization digunakan untuk menentukan centroid awal pada algoritma K-means. Hasil penelitian ini berhasil mengelompokkan dokumen publikasi ilmiah dengan nilai koefisien silhouette sebesar 0.42. Selain itu, penggunaan PSO sebagai penentu centroid optimal pada algoritma K-means dapat meningkatkan nilai koefisien silhouette sebesar 5.56%. Model yang dibangun dievaluasi dengan mencocokkan klaster yang dihasilkan dengan klaim yang diberikan. Hasilnya menunjukkan bahwa sebanyak 75% hasil pencocokan sesuai dan 25% tidak sesuai.
Prediksi Performa Akademik Mahasiswa untuk Kelulusan Predikat Cum Laude dengan Pendekatan Machine Learning Indra Kusuma Budiyanto , Firgiawan; Hermadi, Irman; Hardhienata, Medria Kusuma Dewi
Jurnal Ilmu Komputer dan Agri-Informatika Vol. 11 No. 1 (2024)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.11.1.39-49

Abstract

This research aims to develop a predictive model using machine learning techniques to forecast cum laude graduations within a university. Machine learning algorithms are utilized for classification to enable such predictions. The research results demonstrate the effectiveness of the model in predicting cum laude graduation, thereby providing opportunities for the university to enhance the overall quality of graduates and address potential declines in graduation standards. Predictions regarding the number of cum laude students are made in this study to assist decision-making processes among university stakeholders. By leveraging machine learning techniques, institutions can anticipate and support students in achieving cum laude honours, ultimately leading to an improvement in the overall quality of graduates. In this study, three machine learning algorithms—Naïve Bayes, random forest, and C4.5—are compared for predicting student graduation with cum laude honours. The results of the study show that, for the considered case, the best performance was achieved by the Naïve Bayes algorithm with 87.60% accuracy, 86.70% precision, 92.10% recall, and 89.30% F1-score. In addition, the Naïve Bayes algorithm also obtained the lowest computational time compared to other algorithms.
Pembangunan Model Prediksi Potensi Kebakaran Hutan dan Lahan Menggunakan Algoritma Machine Learning Berdasarkan Data Patroli Santoso, Angga Bayu; Sitanggang, Imas Sukaesih; Hardhienata, Medria Kusuma Dewi
JURNAL INFOTEL Vol 16 No 3 (2024): August 2024
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v16i3.1180

Abstract

Indonesia allocates 120 million hectares or 64% of its land area as forest areas. Indonesia's forests continue to experience deforestation; one of the causes is forest and land fires (karhutla). The government conducts forest and land fire prevention through integrated patrols with the Forest and Land Fire Prevention Patrol Information System (SIPP Karhutla) facility for patrol data management. However, the patrol data are still primarily used for data observation and simple spatial analysis in the spatial module. Patrol data has not been used for further forest and land fire prevention studies. Based on these problems, this research aims to build a prediction model of potential forest and land fires using SVM, Random Forest, and XGBoost algorithms and compare model performance to get the best model. The preprocessing stage uses the SMOTE-ENN method to handle data class imbalance, and the k-fold cross-validation stage and hyperparameter tuning use the random search method. The confusion matrix evaluation method to see the model performance in terms of accuracy is XGBoost (94.81%), Random Forest (90.23%), SVM-linear (79.58%), SVM-polynomial model (73.99%), SVM-rbf (74.26%), and SVM-sigmoid (35.04%). Therefore, the best prediction model is XGBoost (94.81%) with boosting technique. The results of this study have implications for helping early prevention of forest and land fires on the islands of Sumatra and Kalimantan.
Co-Authors Hayatina, Fina Charisma Imas Sukaesih Sitanggang Indra Kusuma Budiyanto , Firgiawan Irman Hermadi Santoso, Angga Bayu Sony Hartono Wijaya