Garuda - Garba Rujukan Digital

THE ROLE OF L1 REGULARIZATION IN ENHANCING LOGISTIC REGRESSION FOR EGG PRODUCTION PREDICTION Nur Alamsyah; Budiman Budiman; Elia Setiana; Valencia Claudia Jennifer
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 4 (2025): JITK Issue May 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i4.6409

Poultry egg productivity is strongly influenced by various environmental factors, such as air and water quality. However, accurately predicting productivity remains a challenge due to the complex interplay of multiple environmental variables and the risk of overfitting in predictive models. This study improves egg productivity prediction using Logistic Regression with L1 regularization, which enhances model generalization by performing automatic feature selection. The research methodology includes data collection of key environmental indicators—Air Quality Index (AQI), Water Quality Index (WQI), and Humidex—followed by data preprocessing, exploratory data analysis (EDA), and model training using L1-regularized Logistic Regression. Model evaluation was performed using classification metrics and learning curve analysis to assess stability and effectiveness. Experimental results indicate that Logistic Regression without regularization achieved an accuracy of 90.7%, with misclassification occurring in the lower production categories. By applying L1 regularization, accuracy increased significantly to 97%, demonstrating its ability to reduce overfitting while improving classification performance. This study also compares its findings with previous research, such as De Col et al. (wheat epidemic prediction, 80–85% accuracy) and Jia Q1 et al. (heart disease prediction, 92.39% accuracy), confirming that our approach outperforms prior Logistic Regression models in similar predictive tasks. These findings suggest that L1 regularization is an effective solution for improving egg productivity prediction, particularly in scenarios with complex environmental influences. Future work will explore advanced ensemble learning techniques and real-time IoT-based monitoring to further enhance prediction accuracy and practical applicability.

Tantangan dan Peluang Gen Z Menjadi Agripreneur di Era Marketplace Digital Setiana, Elia; Budiman; Nur Alamsyah; S.W. Manurip, Atanasius Angga
Jurnal Pengabdian Masyarakat Tapis Berseri (JPMTB) Vol. 4 No. 1 (2025): Jurnal Pengabdian Masyarakat Tapis Berseri (JPMTB) (Edisi April)
Publisher : Pusat Studi Teknologi Informasi Fakultas Ilmu Komputer Universitas Bandar Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36448/jpmtb.v4i1.141

Generation Z, raised in the digital era, holds significant potential to drive transformation in the agricultural sector through agripreneurship. However, alongside the rapid development of technology and digital marketplaces, they also face various notable challenges. This study explores the barriers faced by Gen Z in initiating and developing agribusiness ventures, including limited access to capital, lack of technical agricultural knowledge, and insufficient mentorship from industry players. On the other hand, there are numerous opportunities to seize, such as easier market access through digital platforms, rising consumer demand for healthy and organic products, and increasing government support for agricultural startups. By adopting adaptive, innovative, and collaborative approaches, Gen Z has a promising opportunity to become a key agent of change in building a modern and sustainable agricultural sector. This study aims to provide insights and strategic recommendations for stakeholders to encourage the emergence of young digital-based agripreneurs in Indonesia.

Approximate Bayesian Inference for Bayesian Confidence Quantification in DNA Sequence Classification Using Monte Carlo Dropout Approach Alamsyah, Nur; Budiman, Budiman; Nursyanti, Reni; Setiana, Elia; Danestiara, Venia Restreva
Innovation in Research of Informatics (Innovatics) Vol 7, No 1 (2025): March 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i1.14349

Splice junction classification in DNA sequences is critical for understanding genetic structures and processes, particularly the differentiation between exon-intron (EI), intron-exon (IE), and neither boundaries. Traditional neural network models achieve high accuracy but often lack the ability to quantify uncertainty, which is essential for reliability in sensitive applications such as bioinformatics. This study addresses this limitation by incorporating Bayesian confidence quantification into DNA sequence classification using the Monte Carlo Dropout (MCD) approach. A baseline neural network was first implemented as a reference, achieving a test accuracy of 95.61%. Subsequently, MCD was applied, which not only improved the test accuracy to 96.03% but also provided uncertainty estimation for each prediction by sampling multiple inferences. The uncertainty values enabled the identification of low-confidence predictions, enhancing the interpretability and reliability of the model. Experiments were conducted on a binary-encoded DNA sequence dataset, representing nucleotides (A, C, G, T) and their splice junctions. The results demonstrated that MCD is a robust approach for DNA sequence classification, offering both high predictive performance and actionable insights through uncertainty quantification. This research highlights the potential of Bayesian confidence quantification in genomic studies, particularly for tasks requiring high reliability and interpretability. The proposed approach bridges the gap between accurate predictions and the need for robust uncertainty estimation, contributing to advancements in bioinformatics and machine learning applications in genetic research.

ISOLATION FOREST PARAMETER TUNING FOR MOBILE APP ANOMALY DETECTION BASED ON PERMISSION REQUESTS Kaunang, Valencia Claudia Jennifer; Alamsyah, Nur; Nursyanti, Reni; Budiman, Budiman; Danestiara, Venia R; Setiana, Elia
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): 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.v21i2.6647

Ensuring mobile app security needs the capability to detect apps that request excessive or inappropriate permissions. This research proposes an anomaly detection approach using Isolation Forest, enhanced through hyperparameter tuning, to identify suspect apps based on permission request patterns. The dataset is processed into binary features, followed by exploratory data analysis (EDA) to examine the distribution and highlight sensitive permissions. The Isolation Forest model is then optimized by tuning parameters such as contamination level, number of estimators, and sample size. The fine-tuned model achieved a more accurate separation between normal and anomaly applications, detecting 10 anomalies out of 200 applications, with anomaly applications averaging 125.10 permits compared to 42.76 in normal applications. These anomalies often requested permissions related to network, storage, contacts and microphone, indicating potential privacy risks. The results show that parameter tuning improves the detection performance of Isolation Forest, providing a practical solution for mobile security monitoring. After tuning, the number of false positives decreased by 50%, and the model successfully reduced detected anomalies from 20 to 10, increasing the precision of anomaly detection from 70% to 90%. Future work could include improving feature selection and integration into real-time detection systems.

Optimizing Heart Disease Prediction : A Comparative Study of Machine Learning Models Using Clinical Data Budiman Budiman; Nur Alamsyah; Elia Setiana; Valencia Claudia Jennifer Kaunang; Syahira Putri Himmaniah
International Journal of Science and Mathematics Education Vol. 1 No. 4 (2024): December: International Journal of Science and Mathematics Education
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijsme.v1i4.96

Cardiovascular disease is a leading cause of death globally, necessitating effective predictive systems. This research aims to analyze the effectiveness of various machine learning (ML) models—Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), Support Vector Classifier (SVC), and K-Nearest Neighbors (KNN)—in predicting heart disease using publicly available health data. The study involved pre-processing data, training models, and evaluating them using accuracy, precision, recall, F1-score, and G-Mean metrics. The results show that KNN is the most reliable model, with the highest accuracy of 92%. Significant health features were identified, such as chest pain type and maximum heart rate. The study contributes to improving clinical decision support systems by identifying optimal ML models for heart disease prediction.

Optimization Of Micro, Small and Medium Enterprise Financial Management Through Android-Based Zazan Mobile Application for Efficiency of Digital Economy Sustainability Yoga, Titan Parama; Setiana, Elia; Hamzah, Encep; Budiman, Budiman; Sarifiyono, Aggi Panigoro
Jurnal Computech & Bisnis (e-journal) Vol. 18 No. 2 (2024): Jurnal Computech & Bisnis (e-Journal)
Publisher : LPPM STMIK Mardira Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56447/95x8j738

In order to sustain and grow a firm, financial management is essential. This procedure is essential for obtaining profit and loss data, preventing employee and business partner fraud, and separating personal and business funds to determine the company's financial situation accurately. Informal MSME actors multitask and operate as small business owners, entrepreneurs, and managers of all business issues. So, there is not enough time to document the financials of a corporation. Making financial records requires basic knowledge, which makes the work feel challenging, intricate, and time-consuming. One way to address this issue is making the Android mobile application "Zazan" to assist in managing the finances of medium-sized, tiny, and microbusinesses. A descriptive strategy was used to gather the data required for this investigation. An integrated application that could record business activity transactions, record business activity schedules, and connect with customers was required, as determined by the analysis and implementation findings. Furthermore, clients can quickly learn more about business players by accessing location information. Interaction between customers and business transaction activities facilitates the automation of business activity recording, enabling the application to complete financial recording. Entrepreneurs will find it easier to manage their financial spending with the help of the company's financial reports. Having employee and multi-store functionalities would be preferable because business actors occasionally have multiple business branches and employees. The implications of this research extend beyond merely providing a tool for financial management; they highlight the necessity of accessible financial solutions for MSMEs. By bridging the gap in financial literacy and time constraints, the "Zazan" application not only empowers business owners to maintain accurate financial records but also fosters better decision-making and strategic planning. This can lead to enhanced business performance, improved relationships with stakeholders, and ultimately, sustainable growth in the competitive market landscape.

Analisis Perancangan Sistem Pakar Pola Latihan Untuk Mencapai Body Goals Menggunakan UML Setiana, Elia; Budiman, Budiman; Rakhman A, R. Yadi; Ramadhan, M. Rizki
INTERNAL (Information System Journal) Vol. 6 No. 2 (2023)
Publisher : Masoem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/internal.v6i2.853

Technological developments and awareness of the importance of health and physical fitness have encouraged people to look for effective solutions in achieving their desired body goals. Expert systems are one potential approach to assist individuals in designing exercise patterns that suit their goals. This system development method uses UML as a tool for analyzing and designing expert system structures. This expert system will utilize expert knowledge in the fields of fitness and nutrition to provide personalized and effective recommendations. Additionally, integration with technology will allow users to monitor their progress in real-time and receive recommendation updates according to their individual progress.The results of this research are architectural designs consisting of Usecase Diagrams, Activity Diagrams, Class Diagrams, Sequence Diagrams, Deployment Diagrams which can then be used as a reference for creating this expert system application system so that it is hoped that the complete system can become a useful tool and can make a contribution. positive in helping users achieve their body goals with a more focused and effective approach.

P Pengujian Perangkat Lunak Metode Black Box Pada Aplikasi Sistem Pakar Pola Latihan dan Asupan Makanan Elia Setiana; Muhammad Rizki Ramadhan; Budiman; R. Yadi Rakhman A4
NUANSA INFORMATIKA Vol. 18 No. 1 (2024): Nuansa Informatika 18.1 Januari 2024
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v18i1.67

Software testing is an important part of expert system application development. This software testing aims to ensure optimal performance and functionality of this application, where the application must be able to run according to a previously created design and application testing must ensure that the program is free from errors. The testing methodology includes a series of steps designed to identify potential bugs, ensure proper integration between components, and verify that the application meets functional and non-functional requirements. Testing is carried out using various functional testing scenarios. Test results show that this application is able to provide accurate and relevant solutions in the context of exercise patterns to achieve the desired body goals. Additionally, application performance is tested to ensure fast response and good user experience, even under high load conditions. The findings from this test provide confidence that the "Exercise Pattern and Food Intake Expert System" is ready for use by end users.

Explainable Deep Transfer Learning for Robust Tomato Leaf Disease Classification Elia Setiana; Mukhammad Restu Febriansyah Putra; Muhammad Fajar Romadhon
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 1 (2025): BIMA November 2025 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i1.4

Automated identification of plant diseases is crucial for advancing precision agriculture and enabling farmers to make informed, timely decisions. This study presents a deep learning-based framework for multi-class classification of tomato leaf diseases using transfer learning with the VGG-19 architecture. A dataset comprising 10,000 images across ten classes, including nine disease categories and one healthy class, was preprocessed and augmented to improve model robustness and generalization. The training strategy employed a two-stage approach: initial feature extraction with frozen, pre-trained layers, followed by selective fine-tuning to adapt the convolutional features to the target domain. Comprehensive evaluation using accuracy, precision, recall, F1-score, and confusion matrices demonstrated the model’s high discriminative capability, achieving an overall accuracy of 93% on the validation set. The results further revealed strong performance in identifying most disease categories, while highlighting classification challenges between visually similar classes, such as Tomato Mosaic Virus and Tomato Target Spot. The contributions of this research include the development of an optimized training pipeline, a reproducible evaluation framework, and insights into the role of transfer learning for agricultural image classification. The findings highlight the potential of deep learning to support automated tomato disease monitoring, with implications for improving crop health management and enhancing agricultural productivity

ISOLATION FOREST PARAMETER TUNING FOR MOBILE APP ANOMALY DETECTION BASED ON PERMISSION REQUESTS Kaunang, Valencia Claudia Jennifer; Alamsyah, Nur; Nursyanti, Reni; Budiman, Budiman; Danestiara, Venia R; Setiana, Elia
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): 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.v21i2.6647

Ensuring mobile app security needs the capability to detect apps that request excessive or inappropriate permissions. This research proposes an anomaly detection approach using Isolation Forest, enhanced through hyperparameter tuning, to identify suspect apps based on permission request patterns. The dataset is processed into binary features, followed by exploratory data analysis (EDA) to examine the distribution and highlight sensitive permissions. The Isolation Forest model is then optimized by tuning parameters such as contamination level, number of estimators, and sample size. The fine-tuned model achieved a more accurate separation between normal and anomaly applications, detecting 10 anomalies out of 200 applications, with anomaly applications averaging 125.10 permits compared to 42.76 in normal applications. These anomalies often requested permissions related to network, storage, contacts and microphone, indicating potential privacy risks. The results show that parameter tuning improves the detection performance of Isolation Forest, providing a practical solution for mobile security monitoring. After tuning, the number of false positives decreased by 50%, and the model successfully reduced detected anomalies from 20 to 10, increasing the precision of anomaly detection from 70% to 90%. Future work could include improving feature selection and integration into real-time detection systems.

Title

Found 21 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 21 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 21 Documents
Search