Garuda - Garba Rujukan Digital

XGBOOST HYPERPARAMETER OPTIMIZATION USING RANDOMIZEDSEARCHCV FOR ACCURATE FOREST FIRE DROUGHT CONDITION PREDICTION Alamsyah, Nur; Budiman, Budiman; Yoga, Titan Parama; Alamsyah, R Yadi Rakhman
Jurnal Pilar Nusa Mandiri Vol. 20 No. 2 (2024): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v20i2.5569

Climate change and increasing global temperatures have increased the frequency and intensity of forest fires, making fire risk evaluation increasingly important. This study aims to improve the accuracy of predicting forest fuel drought conditions (Drought Code) by using the XGBoost algorithm optimized with RandomizedSearchCV. The research methods include collecting data related to forest fires, preprocessing data to ensure quality and consistency, and using RandomizedSearchCV for XGBoost hyperparameter optimization. The results showed that the optimized XGBoost model resulted in a decrease in Mean Squared Error (MSE) and an increase in R-squared value compared to the default model. The optimized model achieved an MSE of 0.0210 and R2 of 0.9820 on the test data, indicating significantly improved prediction accuracy for forest fuel drought conditions. These findings emphasize the importance of hyperparameter optimization in improving the accuracy of predictive models for forest fire risk assessment.

COMPARISON LINEAR REGRESSION AND RANDOM FOREST MODELS FOR PREDICTION OF UNDERGROUND DROUGHT LEVELS IN FOREST FIRES Alamsyah, Nur; Budiman, Budiman; Yoga, Titan Parama; Alamsyah, R Yadi Rakhman
Jurnal Techno Nusa Mandiri Vol. 21 No. 2 (2024): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v21i2.5237

The increase in forest fires poses a significant risk due to its impact on underground dryness, which can cause long-term environmental damage and challenge fire suppression efforts. This research aims to develop a prediction model for underground drought levels in the context of forest fires using machine learning techniques. The methodology used in this research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework, which includes the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. This study analyzes a forest fire dataset, applies encoder labels to transform categorical variables, and uses linear regression and random forest models to predict underground drought levels. The goal is to create a predictive model that can help inform wildfire risk management strategies by anticipating underground drought levels. The results showed that the random forest model achieved higher prediction accuracy than the linear regression, with an R-squared value of 0.97. This suggests that the random forest model is a more robust tool for predicting underground drought levels, providing valuable insights for forest fire management. This research contributes to the understanding of underground drought levels, aiding the development of effective wildfire risk management strategies.

Pengembangan Perangkat Lunak Pengelolaan Layanan Perbaikan Komputer Titan Parama Yoga; Marwondo Marwondo; Wahyu Kurnianto
SisInfo Vol 2 No 1 (2020): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2366.214 KB)

Pengolahan Layanan Perbaikan Komputer adalah pengolahan perbaikan yang terkomputerisasi yang dikembangkan untuk mempermudah dalam proses pengolahan perbaikan komputer pada Sistem Informasi Rumah Sakit RSUP Dr. Hasan Sadikin Bandung.Pengolahan Layanan Perbaikan Komputer ini memiliki kemampuan untuk mempercepat proses pencarian data permintaan dan perbaikan, dapat merancang basis data yang diharapkan dapat menyimpan secara terorganisir dengan baik, untuk mempermudah dan mempercepat menampilkan data laporan perbaikan yang masih dalam proses perbaikan ataupun telah terselesaikan oleh teknisi SIRS RSHS.Dalam pengelolaan perbaikan komputer di RSUP Dr. Hasan Sadikin Bandung saat ini, proses permintaan hingga perbaikan belum terorganisir dengan baik. Hal itu terjadi karena masih banyak proses yang dilakukan secara manual, diantaranya pencatatan pada buku, pencarian data perbaikan, dan pembuatan laporan-laporan perbaikan yang belum terkomputerisasi dengan baik. Pengolahan Layanan Perbaikan Komputer lebih mudah untuk dioperasikan sehingga dapat mempermudah dan mempercepat dalam pengelolaan perbaikan komputer. Selain itu Pengolahan Layanan Perbaikan Komputer

Audit Manajemen Resiko Teknologi Informasi Pospay Menggunakan Framework COBIT 5 M Nurdin Afgani; Titan Parama Yoga; Chairul Habibi
SisInfo Vol 6 No 1 (2024): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37278/sisinfo.v6i1.800

Perkembangan teknologi informasi menuju era digital merupakan suatu inovasi yang mengubah sistem dan mempengaruhi perilaku juga harapan masyarakat terhadap tersedianya berbagai layanan informasi dan fitur layanan elektronik. salah satu nya adalah layanan pospay yang mempermudah pelanggan dalam melakukan pembayaran berbagai macam tagihan seperti listrik, telepon, air, kredit motor, dan kartu kredit. Pospay menggunakan Sistem Online Payment Point (SOPP) dan diterapkan di PT. Pos Indonesia sehingga dengan menggunakan layanan Pospay masyarakat tidak lagi repot untuk membayar beberapa tagihan di tempat yang berbeda, cukup dengan satu loket yang berada di salah satu cabang kantor pos maka pelanggan dapat merasakan kemudahan dalam melakukan beberapa tranksaksi pembayaran yang dilakukan secara online. Namun pada proses layanan Pospay tidak lepas dari resiko yang pasti akan dihadapi, oleh karena itu tujuan dari penelitian yang dilakukan antara lain yaitu melaksanakan audit manajemen resiko teknologi informasi pada Pospay dengan menggunakan framework COBIT 5. Berdasarkan hasil penelitian yang telah dilakukan melalui kuisioner dengan menggunakan framework COBIT 5 dengan domain EDM03 dan APO12 didapatkan hasil bahwa capability existing level 2 dengan capability yang diharapkan yaitu level 5. Oleh karena itu, capability gap yang diperoleh pada kondisi tersebut yaitu 3 level.

Analisis Faktor-Faktor yang Mempengaruhi Behavioral Intention dan Use Behavior Pada Pengguna Aplikasi Mobile Banking BRImo Menggunakan Model UTAUT 2 (Unified Theory of Acceptance an Use of Technology 2) Ludi Priyadi; Arnold Ropen Sinaga; Titan Parama Yoga
SisInfo Vol 7 No 1 (2025): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37278/sisinfo.v7i1.1110

This research is based on the problem of users who complain or are less comfortable in using services on BRImo Mobile Banking. Although BRImo Mobile Banking is recognized as having a good ability to provide information, the inconvenience from the user's side can reduce user confidence in the service. This study aims to determine the intention and use of digital services of BRImo Mobile Banking application in Bandung using behavioral intention and use behavior as factors that influence the technology acceptance model (UTAUT2). The research method is quantitative, analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with 249 research respondents. The results showed that the performance expectancy variable on behavioral intention had a positive and insignificant effect. Other variables such as effort expectancy, social influence, facilitating conditions and habit on behavioral intention have a positive and significant effect. There are also facilitating conditions, habit and behavior intention variables on use behavior, which have a positive and significant effect.

I-Pos Information System Security Audit Using Framework Control Objectives for Information and Related Technologies 2019 And Information Technology Infrastructure Library 4 Titan Parama Yoga; Habibi, Chairul; Aziz, Nizar Hizbi Abdul
Jurnal Computech & Bisnis (e-journal) Vol. 17 No. 2 (2023): Jurnal Computech & Bisnis (e-Journal)
Publisher : LPPM STMIK Mardira Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56447/jcb.v17i2.236

Information system security is used to protect against cyber attack crimes. Generally, cyber attacks occur because someone wants to intervene in a system to find out the confidentiality and availability of information. PT. Pos Indonesia is a company under the auspices of SOEs engaged in distributing letters and packages. Both domestic package distribution and overseas package distribution. To facilitate the delivery of packages, PT Pos Indonesia developed an information system called I-POS. Based on the results of the researchers' analysis, the I-POS information system is an information system that aims at mail and package delivery transactions, so using the I-POS information system can facilitate the process of delivery transactions, as well as provide accurate, timely, and relevant information. The purpose of this study is to determine the level of maturity of information system security in the field of I-POS information systems at PT. Pos Indonesia, Analyzing the findings and gaps of the level of maturity of the information system security. Based on the results of research that has been conducted through questionnaires using the COBIT 2019 framework with APO13 and DSS05 domains, it was found that the Existing Capability obtained was at level 2 while the expected Capability Level was at level 5 so the Capability Gap produced in these conditions was 3 levels

PENINGKATAN LITERASI KEUANGAN PADA TINGKAT TK, SD, SMP, SMA DAN MASYARAKAT UMUM DI DESA TUNGGILIS, KECAMATAN KALIPUCANG – KABUPATEN PANGANDARAN Dikdik Purwadisastra; Titan Parama Yoga; Aninditha Putri Kusumawardhani
Journal of Empowerment Community Vol. 5 No. 2 (2023): Oktober 2023
Publisher : Universitas Perjuangan Tasikmalaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36423/jec.v5i2.1472

Literasi keuangan sangat berkaitan dengan kesejahteraan individu. Pengetahuan keuangan dan ketrampilan dalam mengelola keuangan pribadi sangat penting dalam kehidupan sehari-hari. Kesulitan keuangan bukan hanya dipengaruhi dari rendahnya pendapatan. Kesulitan keuangan juga dapat muncul jika terjadi kesalahan dalam pengelolaan keuangan seperti kesalahan penggunaan hutang dan tidak adanya perencanaan keuangan. Keterbatasan finansial dapat menyebabkan stress, dan rendahnya kepercayaan diri. Literasi keuangan sejak dini bertujuan untuk memberikan edukasi literasi keuangan sejak dini karena pengetahuan dan pengalaman keuangan yang ditanamkan akan melekat dalam diri anak sehingga membentuk karakter dan kebiasaan mengelola keuangan mereka di masa depan sebagai suatu budaya baik, seperti mengenal makna uang, kebiasaan menabung, hingga mendahulukan kebutuhan dari pada keinginan. Metode yang digunakan dalam pengabdian kepada masyarakat ini adalah Participatory Action Research (PAR) Metode ini digunakan dalam mengatasi permasalahan mitra melalui tahapan atau langkah-langkah untuk melaksanakan solusi yang ditawarkan. Melihat hasil kegiatan literasi keuangan yang telah dilaksanakan mulai dari tingkat TK, SD, SMP, SMA dan Masyarakat umum, dapat disimpulkan bahwa kegiatan ini sangat bermanfaat dan memberikan edukasi serta pemahaman mengenai pengelolaan keuangan dengan baik dan bijak, mengingat masih kurangnya literasi keuangan yang dimiliki oleh masyarakat desa.

Analisis Sentimen Aplikasi BYOND by BSI di Google Play Store Menggunakan Metode SVM Akbar, Imannudin; Sinaga, Arnold Ropen Sinaga; Yoga, Titan Parama; Hendra, Acep; Setiana, Elia Setiana
Jurnal Accounting Information System (AIMS) Vol. 8 No. 2 (2025)
Publisher : Ma'soem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/aims.v8i2.1583

The BYOND by BSI application has received various user reviews on the Google Play Store, reflecting user perceptions and satisfaction. Sentiment analysis is needed to understand these opinion patterns and support service quality improvement. This study aims to analyze the sentiment of BYOND by BSI user reviews by applying the Support Vector Machine (SVM) method. Review data were collected from the Google Play Store and processed through text preprocessing stages followed by SVM classification modeling. The results show a classification accuracy of 87%, with strong performance in the Positive class (F1-score 0.91) and Negative class (F1-score 0.88), but SVM failed to detect the Neutral class due to data imbalance, where the Neutral class accounted for only 5.85% of the total samples. In conclusion, these findings highlight the importance of handling class imbalance through approaches such as resampling, ensemble algorithms, or class-weight optimization in SVM to improve the accuracy of Neutral sentiment detection.

PENINGKATAN LITERASI KEUANGAN PADA TINGKAT TK, SD, SMP, SMA DAN MASYARAKAT UMUM DI DESA TUNGGILIS, KECAMATAN KALIPUCANG – KABUPATEN PANGANDARAN Dikdik Purwadisastra; Titan Parama Yoga; Aninditha Putri Kusumawardhani
Journal of Empowerment Community Vol. 5 No. 2 (2023): Oktober 2023
Publisher : Universitas Perjuangan Tasikmalaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36423/jec.v5i2.1472

Literasi keuangan sangat berkaitan dengan kesejahteraan individu. Pengetahuan keuangan dan ketrampilan dalam mengelola keuangan pribadi sangat penting dalam kehidupan sehari-hari. Kesulitan keuangan bukan hanya dipengaruhi dari rendahnya pendapatan. Kesulitan keuangan juga dapat muncul jika terjadi kesalahan dalam pengelolaan keuangan seperti kesalahan penggunaan hutang dan tidak adanya perencanaan keuangan. Keterbatasan finansial dapat menyebabkan stress, dan rendahnya kepercayaan diri. Literasi keuangan sejak dini bertujuan untuk memberikan edukasi literasi keuangan sejak dini karena pengetahuan dan pengalaman keuangan yang ditanamkan akan melekat dalam diri anak sehingga membentuk karakter dan kebiasaan mengelola keuangan mereka di masa depan sebagai suatu budaya baik, seperti mengenal makna uang, kebiasaan menabung, hingga mendahulukan kebutuhan dari pada keinginan. Metode yang digunakan dalam pengabdian kepada masyarakat ini adalah Participatory Action Research (PAR) Metode ini digunakan dalam mengatasi permasalahan mitra melalui tahapan atau langkah-langkah untuk melaksanakan solusi yang ditawarkan. Melihat hasil kegiatan literasi keuangan yang telah dilaksanakan mulai dari tingkat TK, SD, SMP, SMA dan Masyarakat umum, dapat disimpulkan bahwa kegiatan ini sangat bermanfaat dan memberikan edukasi serta pemahaman mengenai pengelolaan keuangan dengan baik dan bijak, mengingat masih kurangnya literasi keuangan yang dimiliki oleh masyarakat desa.

A Metaheuristic Wrapper Approach to Feature Selection with Genetic Algorithm for Enhancing XGBoost Classification in Diabetes Prediction Alamsyah, Nur; Budiman; Danestiara, Venia Restreva; Yoga, Titan Parama; Nursyanti, Reni; Kaunang, Valencia
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 4, November 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i4.2366

This study addressed the problem of selecting the most relevant features for improving the accuracy of diabetes classification using health indicator data. The research focused on a binary classification task based on the Behavioral Risk Factor Surveillance System dataset, which comprised over seventy thousand records and twenty-one predictive features related to individual health behaviors and conditions. A metaheuristic wrapper approach was developed by integrating a Genetic Algorithm for feature selection with an XGBoost classifier to evaluate the predictive quality of each feature subset. The fitness function was defined as the average classification accuracy obtained through cross-validation. In addition to feature selection, hyperparameter optimization of the XGBoost model was carried out using a Bayesian-based search strategy to further enhance performance. The proposed method successfully identified a subset of fourteen optimal features that contributed most significantly to the prediction of diabetes. The final model, combining the selected features and optimized parameters, achieved an accuracy of 0.753, outperforming both the baseline models trained on all features and models using features selected through deterministic methods. These results confirmed the effectiveness of combining evolutionary feature selection with model tuning to build efficient and interpretable predictive models for medical data classification. This approach demonstrated a practical solution for managing high-dimensional data in the context of chronic disease prediction.

Title

Found 36 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 36 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 36 Documents
Search