Garuda - Garba Rujukan Digital

RANCANG BANGUN SISTEM INFORMASI STUDI KASUS PENDATAAN TABUNG GAS PADA PT. UTAMA GAS MULTIPERKASA Najmuddin Najmuddin; Gugun Gunawan; Memed Saputra; Adith Aulia Rahman
DESANTA (Indonesian of Interdisciplinary Journal) Vol. 3 No. 1 (2022): September 2022
Publisher : Desanta Publisher

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

Salah satu tujuan pembuatan rancang bangun sistem informasi ini bertujuan untuk meningkatkan efisiensi dalam melakukan pengolahan data. Karena segala informasi yang dihasilkan dapat menjadikan sebuah keputusan oleh pihak Perusahaan. PT. Utama Gas Multiperkasa merupakan salah satu bentuk badan usaha yang bergerak dalam bidang usaha memproduksi dan mendistribusikan berbagai gas-gas industri ke beberapa Perusahaan yang membutuhkan jenis-jenis gas seperti Oksigen (O2), Nitrogen (N2), Argon (Ar), Asetilen (C2H2), Hidrogen (H2), Karbondioksida (CO2), Nitrous Oksida (N2O), dan lain-lain. Dengan adanya sistem baru yang akan dibuat maka PT. Utama Gas Multiperkasa dapat melakukan pencatatan data-data transaksi mulai dari permintaan hingga pengiriman yang diperlukan dengan lebih mudah dan cepat.

Application of Machine Learning in Computer Networks: Techniques, Datasets, and Applications for Performance and Security Optimization Memed Saputra; Fegie Yoanti Wattimena; Davy Jonathan
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 1 (2025): APRIL 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i1.3989

This study designs and tests a network security system based on a combined Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) framework. In this study, distributed processing and reinforcement learning methods in combination with differential privacy are introduced into the proposed system to enhance attack detection and network management. The evaluation results show significant improvements; 97.3% detection accuracy, 34% more efficient bandwidth utilization and 45% less latency than the previous system. The 16-node linear scalability of the distributed architecture has a throughput of 1.2 million packets per second. It is defended against adversarial attacks by maintaining accuracy above 92% and provides a total energy saving of 38% using dynamic batch processing. Three months of testing in an operational environment detected 99.2% of 1,247 threats, including 23 new attack types, with an average detection time of 1.8 seconds. Sensitivity analysis was performed to preserve the privacy of sensitive data while maintaining network performance. The results show that the hybrid solution is reliable, scalable and secure for today's network management.

Development of a Financial Prediction System Based on Machine Learning: A Case Study on Financial Data Management Using Time Series Analysis Davy Jonathan; Memed Saputra
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5052

Due to intense volatility, complex nonlinear dynamics, and scant historical data, predicting financial prices in emerging markets is extremely difficult. This paper presents a hybrid ARIMA+LSTM model for stock price forecasting in the Indonesian market and tests it. The model effectively combines traditional econometric techniques with advanced deep learning methodologies. Walk-forward validation on over five years of data from various Indonesian stocks (BBRI, ALFMART, UNVR, BSIM) is applied. The hybrid model achieves a Root Mean Square Error of 112.54, Mean Absolute Percentage Error of 2.21%, and Directional Accuracy of 68.9% for one-day ahead predictions. This performance exceeds that of pure ARIMA by 22.5% and is statistically significant (p < 0.001, Cohen's d = 1.18). The model consistently shows good results over many prediction horizons (1, 5, and 10 days) and several Indonesian stocks from different sectors with a standard deviation of only 8.3 during the test period. A cloud-based deployment architecture is planned to reach about 1,500 predictions per second at a latency of 45ms which will be suitable for real-time institutional trading systems. Sensitivity analysis reveals optimal hyperparameters (60-day window; between 50 to 25 LSTM units with a dropout rate of 0.2) as well as confirming strong performance across parameter variations. SHAP analysis plus attention visualization results show that the model keeps interpretability even though deep learning is complicated; recent prices (lag-1 and lag-2) hold about 70% of the prediction variance. This work validates hybrid ARIMA+LSTM modeling in an emerging market like Indonesia through rigorous walk-forward validation methodology and practical insights into generating actionable trading signals with a win rate of 68.9% which supports portfolio management integrated within risk frameworks as well as limitations that include dependency on historical data, exclusion of transaction costs, and single asset focus yet significantly contributes methodological rigor and empirical validation to machine learning literature in financial forecasting specifically regarding emerging markets

The Use of Digital Data and Artificial Intelligence in Recruitment: An Analysis of Business Candidates’ Perceptions of Organizational Attractiveness Haryanto Haryanto; Najmuddin Najmuddin; Mohammad Fauzan Nawawi; Andri Cahyo Purnomo; Memed Saputra
Prosperia: Journal of Economic Development, Accounting, and Global Markets Vol. 1 No. 3 (2026): : August: Prosperia: Journal of Economic Development, Accounting, and Global Ma
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/0b6erk57

This study examines the causal relationships between artificial intelligence implementation, digital data sourcing practices, and candidates' perceptions of organizational attractiveness within the contemporary talent acquisition landscape. Adopting a rigorous empirical research design, a scenario based vignette survey experiment was conducted with a sample of 413 final year undergraduate university students in major Indonesian metropolitan areas. The econometric analyses, executed using paired Student's t-tests, reveal that increasing automation levels enhances corporate innovation signals but severely reduces perceived social environment viability and applicant intentions to apply. Furthermore, the utilization of personal online digital data significantly damages procedural fairness evaluations compared to professional tracking frameworks. Individual technology trust serves as a critical moderating variable, determining the magnitude of intention shifts among prospective business and engineering applicants. These findings suggest that organizations must strategically balance automated processing efficiency with candidate privacy boundaries to protect employer brand value. Navigating this sociotechnical dynamic allows recruiting organizations to leverage predictive talent analytics while maintaining high organizational attractiveness for top tier talent.

IMPLEMENTATION OF CLOUD COMPUTING IN THE DEVELOPMENT OF DISTRIBUTED COMPUTER SYSTEMS Memed Saputra; Davy Jonathan; Aribowo Aribowo
Journal of Computer Science Advancements Vol. 3 No. 2 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i2.2253

The rapid evolution of information technology has driven a significant shift from centralized to distributed computing architectures. One of the most transformative innovations in this domain is cloud computing, which offers scalable, flexible, and cost-effective solutions for managing large-scale distributed systems. This study investigates the implementation of cloud computing in the development of distributed computer systems, focusing on its impact on performance, resource utilization, and system scalability. The objective of this research is to analyze the effectiveness of cloud-based infrastructures in supporting distributed applications and to identify best practices for optimizing system architecture within a cloud environment. A mixed-method approach was employed, combining qualitative system analysis with quantitative performance metrics derived from cloud-deployed prototypes. Various case studies across different sectors—education, healthcare, and business—were used to illustrate real-world applications. The findings reveal that cloud computing significantly enhances the operational efficiency and adaptability of distributed systems. Key improvements include dynamic resource allocation, simplified maintenance, and increased fault tolerance. In conclusion, the integration of cloud computing into distributed systems presents a robust framework for modern computing needs. It not only reduces operational complexity but also facilitates innovation by enabling seamless scalability and rapid deployment. Future research is encouraged to explore hybrid cloud models and edge computing integration to further enhance distributed system performance in latency-sensitive environments.

Development of a Financial Prediction System Based on Machine Learning: A Case Study on Financial Data Management Using Time Series Analysis Davy Jonathan; Memed Saputra
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5052

Due to intense volatility, complex nonlinear dynamics, and scant historical data, predicting financial prices in emerging markets is extremely difficult. This paper presents a hybrid ARIMA+LSTM model for stock price forecasting in the Indonesian market and tests it. The model effectively combines traditional econometric techniques with advanced deep learning methodologies. Walk-forward validation on over five years of data from various Indonesian stocks (BBRI, ALFMART, UNVR, BSIM) is applied. The hybrid model achieves a Root Mean Square Error of 112.54, Mean Absolute Percentage Error of 2.21%, and Directional Accuracy of 68.9% for one-day ahead predictions. This performance exceeds that of pure ARIMA by 22.5% and is statistically significant (p < 0.001, Cohen's d = 1.18). The model consistently shows good results over many prediction horizons (1, 5, and 10 days) and several Indonesian stocks from different sectors with a standard deviation of only 8.3 during the test period. A cloud-based deployment architecture is planned to reach about 1,500 predictions per second at a latency of 45ms which will be suitable for real-time institutional trading systems. Sensitivity analysis reveals optimal hyperparameters (60-day window; between 50 to 25 LSTM units with a dropout rate of 0.2) as well as confirming strong performance across parameter variations. SHAP analysis plus attention visualization results show that the model keeps interpretability even though deep learning is complicated; recent prices (lag-1 and lag-2) hold about 70% of the prediction variance. This work validates hybrid ARIMA+LSTM modeling in an emerging market like Indonesia through rigorous walk-forward validation methodology and practical insights into generating actionable trading signals with a win rate of 68.9% which supports portfolio management integrated within risk frameworks as well as limitations that include dependency on historical data, exclusion of transaction costs, and single asset focus yet significantly contributes methodological rigor and empirical validation to machine learning literature in financial forecasting specifically regarding emerging markets

The Effect of Using Digital Learning Applications on Student Achievement in Elementary Schools Ngr. Putu Raka Novandra Asta; Aribowo Aribowo; Memed Saputra; Najmuddin Najmuddin; Pahmi Pahmi
Journal Emerging Technologies in Education Vol. 2 No. 1 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jete.v2i1.735

Background. Every digital technology will be able to influence its users. The response to incoming digital technology has pros and cons. The use of technology in education can no longer be avoided. The use of learning media in the form of applications will have a new impact on the world of education. Learning sometimes has to be done online due to some natural conditions that cannot be denied. Therefore, it is important to be able to use learning applications for education today. Purpose This study aims to determine the benefits of using learning applications. It is also useful to measure how influential the use of digital learning applications is on student achievement in elementary schools. The use of digital learning applications at the education level will have a significant impact on the success of education. Method. The method used in this research is a qualitative method. Qualitative method is a data that will be presented in the form of numbers. Data collection is in the form of distributing questionnaires to teachers and also parents whose children are at the elementary school level. In this case the statement is presented in google from. The statement contains matters relating to the influence of the use of digital learning applications on student achievement in education. This research is more focused on the elementary school level. Results. The results of this study explain that positive effects are obtained in the use of digital learning applications. However, there are also obstacles in using digital applications for learning at the elementary school level. Students who are still classified as underage must be extra supervised so as not to make mistakes in the use of technology. In addition, the use of technology that is influenced by the internet will also affect. This is due to some areas that are constrained by internet networks. In fact, there are still students in whose homes there is no digital technology. Conclusion This research can be concluded that the use of digital technology will have a significant and effective effect on student achievement at the elementary school level if done with the right method. Other supports are the internet and also tools as a medium to facilitate the use of learning applications. Every influence will certainly also experience challenges and obstacles as well as negative influences in its use.

Integrating Augmented Reality with Management Information Systems for Enhanced Data Visualization in Retail Ngr. Putu Raka Novandra Asta; Setiawan Setiawan; Memed Saputra; Najmuddin Najmuddin; Kddour Guettaoi Bedra
Journal of Social Science Utilizing Technology Vol. 2 No. 2 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jssut.v2i2.964

Background. Effective data management and visualization are essential for fast and informed decision-making in the retail industry. However, traditional data visualization methods are often less interactive and need help comprehensively conveying information. Augmented Reality (AR) offers great potential to improve visualizing data, allowing users to interact with data more intuitively and dynamically. Purpose. This research aims to integrate Augmented Reality technology with Management Information Systems (MIS) in retail, focusing on improving data visualization. The main objective is to evaluate the effectiveness of AR in presenting complex data more clearly and interactively to enhance the quality of decision-making in retail management. Method. The research method used is application development and testing. First, an AR application integrated with MIS is developed using an iterative software development approach. Once the application is created, testing is done in a retail environment. Qualitative and quantitative data were collected through observations, interviews, and surveys to evaluate the effectiveness and acceptability of this technology. Results. Research results show that integrating AR with MIS significantly improves how retail managers visualize and understand data. AR applications enable more interactive and easy-to-understand data visualization, which helps managers analyze trends and make better decisions. Users report improvements in decision-making efficiency and accuracy after using this app. Conclusion. Integration of Augmented Reality with Management Information Systems in retail has proven effective in improving data visualization. This technology not only makes data more accessible and understandable but also enhances user interaction with the data, leading to more informed decision-making. This research suggests a more comprehensive application of AR technology in the retail industry to support better and more efficient management.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search