Claim Missing Document
Check
Articles

Found 5 Documents
Search

Enhancing Predictive Models in System Development Using Machine Learning Algorithms Muhammad Hatta; Wahyu Nur Wahid; Faisal Yusuf; Farhan Hidayat; Nesti Anggraini Santoso; Qurotul Aini
International Journal of Cyber ​​and IT Service Management (IJCITSM) Vol. 4 No. 2 (2024): October
Publisher : International Institute for Advanced Science & Technology (IIAST)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/ijcitsm.v4i2.159

Abstract

Predictive models play a crucial role in system development, enabling more informed decision making and improving system efficiency. However, traditional predictive models often struggle with scalability and accuracy in complex environments. This paper explores the use of Machine Learning (ML) algorithms to enhance predictive models, offering more accurate and scalable solutions. By leveraging key ML techniques such as decision trees, regression models, and neural networks, the study demonstrates how these algorithms can improve predictive accuracy and system performance. The methodology involves data collection, model training, and performance evaluation using various metrics to assess the effectiveness of ML enhanced predictive models. The results indicate a significant improvement in model accuracy and scalability, making ML a valuable tool in advancing system development processes. By incorporating ML frameworks specifically tailored to the unique demands of system development, this research offers new methodological adaptations designed to optimize scalability and performance. This study diverges from previous research by implementing and tailoring ML techniques uniquely suited for complex system development environments, enhancing both predictive accuracy and scalability.
Enhancing Predictive Models in System Development Using Machine Learning Algorithms Muhammad Hatta; Wahyu Nur Wahid; Faisal Yusuf; Farhan Hidayat; Nesti Anggraini Santoso; Qurotul Aini
International Journal of Cyber and IT Service Management Vol. 4 No. 2 (2024): October
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/ijcitsm.v4i2.159

Abstract

Predictive models play a crucial role in system development, enabling more informed decision making and improving system efficiency. However, traditional predictive models often struggle with scalability and accuracy in complex environments. This paper explores the use of Machine Learning (ML) algorithms to enhance predictive models, offering more accurate and scalable solutions. By leveraging key ML techniques such as decision trees, regression models, and neural networks, the study demonstrates how these algorithms can improve predictive accuracy and system performance. The methodology involves data collection, model training, and performance evaluation using various metrics to assess the effectiveness of ML enhanced predictive models. The results indicate a significant improvement in model accuracy and scalability, making ML a valuable tool in advancing system development processes. By incorporating ML frameworks specifically tailored to the unique demands of system development, this research offers new methodological adaptations designed to optimize scalability and performance. This study diverges from previous research by implementing and tailoring ML techniques uniquely suited for complex system development environments, enhancing both predictive accuracy and scalability.
Exploration of the Impact of Social Media on Children's Learning Mechanisms Emily Smith; Nesti Anggraini Santoso; Musyfiq amrullah Ar Romdhoni; Nur Azizah; Eka Dian Astuti
CORISINTA Vol 1 No 1 (2024): February
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/v1n1.21

Abstract

In this study, we investigated the complex relationship between social media and children's learning processes during childhood. Although research on student responses to e-learning platforms in pediatric contexts continues to grow, there remains significant confusion regarding the factors that shape acceptance of e-learning conducted via social media applications. To fill this gap, our study analyzes the influence of social media practices, especially in the context of knowledge sharing, features, motivation, and social media use, on how children respond to e-learning systems. In this effort, we expanded the existing Technology Acceptance Model (MPT) to accommodate these factors. We also conducted a comprehensive survey involving 100 children and their parents as research participants. They participate by answering questionnaires, which provide valuable empirical data. Using the powerful SMART-PLS analysis technique, we perform a careful analysis of the extended model. The results of our empirical data analysis confirm that social media practices have a significant positive impact on Perceived Effectiveness (PU) and Perceived Ease of Use (PEOU) in the context of children's learning mechanisms. Our main findings emphasize the central role of PU and PEOU in influencing how children receive e-learning systems. In other words, this paper highlights the potential changes that social media practices can bring about in shaping the acceptance of e-learning systems, while contributing to our understanding of the interactions between social media, MPT factors, and e-learning acceptance in the context of educational programs children.
Evaluating the Impact of VR, AR, and Wearable Devices on Outcome-Driven Learning in Engineering Education Sandy Setiawan; Michael Surya Gunawan; Terra Saptina Maulani; Noah Rangi; Nesti Anggraini Santoso
International Transactions on Education Technology (ITEE) Vol. 4 No. 1 (2025): International Transactions on Education Technology (ITEE)
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/itee.v4i1.962

Abstract

The integration of immersive technologies such as Virtual Reality (VR), (AR), and wearable devices has transformed the landscape of engineering education, offering new possibilities for interactive and outcome driven learning. This study aims to evaluate the impact of these technologies on students’ learn- ing performance, engagement, and skill acquisition within engineering learn- ing environments. Employing a quantitative research design, data were col- lected from 180 engineering students across three universities through structured pre and post tests, supported by validated engagement and usability question- naires. Statistical analyses, including paired tests and regression models, were conducted to measure the effectiveness of technology assisted learning inter- ventions compared to traditional instructional methods. The results reveal a significant improvement in students’ cognitive performance, practical task effi- ciency, and overall motivation when VR, AR, and wearable technologies were integrated into the curriculum. Moreover, students reported enhanced spatial understanding and problem solving capabilities, indicating that immersive tools foster deeper experiential learning and higher knowledge retention. The find- ings suggest that the systematic implementation of immersive technologies can significantly enhance learning outcomes, bridging the gap between theoretical knowledge and hands on engineering practice. This research highlights the criti- cal role of technology driven innovation in promoting outcome based education, providing valuable insights for educators and policymakers aiming to optimize the use of emerging technologies in engineering education.
Decentralized File Sharing Infrastructure with IPFS for Censorship Resistance in Blockchain Ecosystems Nesti Anggraini Santoso; Palma Juanta; Sabda Maulana; Kerimbekov Toktar; Aulia Khanza
Blockchain Frontier Technology Vol. 5 No. 1 (2025): Blockchain Frontier Technology
Publisher : Indonesian Association of Higher Education in Informatics and Computing (APTIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/bfront.v5i1.835

Abstract

Traditional file sharing systems that rely on centralized servers face various challenges. problems such as vulnerability to censorship, blocking, and server failures.This research focuses on the need for file sharing technology that is more secure, censorship-resistant, and does not rely on a single central authority. Challenge the main challenge in developing a new file sharing system is how to overcome the limitations of network scale, slow access speed, and lack of incentives for node providers. Research purposes this is to analyze the role of the InterPlanetary File System (IPFS) in building a censorship-resistant file sharing infrastructure and evaluate its benefits and constraints compared to conventional file sharing systems. Findings from the literature study show that IPFS has advantages in data decentralization, increasing information availability, and strengthening resistance to censorship. Research results also revealed that although IPFS is able to overcome many weaknesses of traditional systems, further development is still needed in terms of network efficiency and user incentives. In conclusion, IPFS has great potential to become the main foundation in a future digital ecosystem that is more open, secure, and free from third-party intervention.