Article Per Year (5 Year)
p-Index From 2021 - 2026
0.961
P-Index
This Author published in this journals
All Journal SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan
Istifa Shania Putri
Telkom University, Indonesia
Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Fine-Tuning Panoptic FPN with ResNet-50 for Maritime Obstacle Detection on the LaRS Dataset Istifa Shania Putri; Sugih Ahmad Fauzan; Mega Fitri Yani; Cindy Muhdiantini
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 3 (2026): July
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20768168

Abstract

Maritime obstacle detection is a critical challenge for Unmanned Surface Vehicles (USVs) operating in complex and dynamic environments. This study investigates the effectiveness of fine-tuning Panoptic FPN, a Mask R-CNN-based architecture augmented with Feature Pyramid Networks, for panoptic segmentation on the LaRS (Lake, River, Seas) dataset. Unlike prior work that explored model comparisons broadly, this research focuses specifically on the impact of hyperparameter tuning and backbone selection on maritime panoptic segmentation performance. Through systematic ablation studies, we demonstrate that adjusting the learning rate to 0.002 and the gamma decay factor to 0.2 yields significant improvements. Our fine-tuned Panoptic FPN with a ResNet-50 backbone achieves a Panoptic Quality (PQ) of 45.31%, surpassing the previous state-of-the-art Mask2Former Swin-B (41.7%) by 3.61 percentage points. Notably, ResNet-50 outperforms the deeper ResNet-101 backbone (36.47% PQ), suggesting that heavier architectures may overfit on domain-specific maritime datasets. Furthermore, Panoptic FPN requires only 8 hours of training compared to approximately 2 days for Mask2Former Swin-L, demonstrating superior computational efficiency. These findings highlight that targeted fine-tuning of lightweight architectures can outperform larger transformer-based models in maritime panoptic segmentation tasks.
A Bibliometric Analysis of Research Trends in AI Integration within Cloud Computing Mega Fitri Yani; Istifa Shania Putri; Cindy Muhdiantini; Farid Munadhil
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 2 (2026): April
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.19927559

Abstract

The integration of Artificial Intelligence (AI) and cloud computing has emerged as a rapidly expanding research area, driven by the need for scalable, elastic, and cost-efficient intelligent systems. Cloud infrastructures enable dynamic resource allocation and pay-as-you-go models, making them ideal environments for AI model training and deployment. Despite the growing volume of publications, a structured mapping of the intellectual landscape of AI–cloud integration remains necessary. This study aims to analyze the research landscape of AI integration in cloud computing using a bibliometric approach. Data were collected from the Scopus database for the period 2021-2026 using the query “Artificial Intelligence” AND “Cloud Computing”, focusing on English-language articles. The analysis was conducted using the Bibliometrix package in R to examine Annual Scientific Production, Countries Collaboration World Map, Most Relevant Affiliations, Co-occurrence Network, Thematic Map, Most Relevant Words, Trend Topics. The findings reveal a significant increase in publications after 2021, indicating accelerating academic interest in AI–cloud convergence. International collaboration is dominated by countries such as India, China, Saudi Arabia, the United States, and the United Kingdom. Thematic analysis shows that artificial intelligence and cloud computing function as foundational themes, with machine learning acting as a key driving force. Emerging topics such as edge computing and real-time systems suggest a shift toward intelligent, distributed, and data-intensive cloud environments.
From Technical Security to Human Awareness: A Bibliometric Review of Cybersecurity Education Research Cindy Muhdiantini; Mega Fitri Yani; Istifa Shania Putri
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 2 (2026): April
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.19897820

Abstract

The rapid advancement of information technology has increased cybersecurity threats, emphasizing the importance of education in building security awareness and human-centered defense capabilities. As research on cybersecurity education continues to grow, a systematic understanding of its research trends and thematic evolution is required. This study analyzes global research trends in cybersecurity education using a bibliometric approach. A total of 189 Scopus-indexed publications from 2020 to 2026 were analyzed using the bibliometrix R package and the Biblioshiny interface. The analysis examines annual publication growth, dominant keywords, evolving research topics, and geographical research contributions. The results indicate a steady increase in scientific production, confirming cybersecurity education as an expanding research domain. While technical topics such as network and data security remain prominent, recent research shows a clear shift toward education, training, and security awareness, highlighting the growing importance of human factors in cybersecurity. In addition, the findings reveal an imbalance in global research contributions and relatively limited international collaboration. This study provides a concise overview of the development and structure of cybersecurity education research and offers insights to support future studies, curriculum development, and policy formulation.
A Bibliometric Analysis of Research Trends in AI Integration within Cloud Computing Mega Fitri Yani; Istifa Shania Putri; Cindy Muhdiantini; Farid Munadhil
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 2 (2026): April
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.19927559

Abstract

The integration of Artificial Intelligence (AI) and cloud computing has emerged as a rapidly expanding research area, driven by the need for scalable, elastic, and cost-efficient intelligent systems. Cloud infrastructures enable dynamic resource allocation and pay-as-you-go models, making them ideal environments for AI model training and deployment. Despite the growing volume of publications, a structured mapping of the intellectual landscape of AI–cloud integration remains necessary. This study aims to analyze the research landscape of AI integration in cloud computing using a bibliometric approach. Data were collected from the Scopus database for the period 2021-2026 using the query “Artificial Intelligence” AND “Cloud Computing”, focusing on English-language articles. The analysis was conducted using the Bibliometrix package in R to examine Annual Scientific Production, Countries Collaboration World Map, Most Relevant Affiliations, Co-occurrence Network, Thematic Map, Most Relevant Words, Trend Topics. The findings reveal a significant increase in publications after 2021, indicating accelerating academic interest in AI–cloud convergence. International collaboration is dominated by countries such as India, China, Saudi Arabia, the United States, and the United Kingdom. Thematic analysis shows that artificial intelligence and cloud computing function as foundational themes, with machine learning acting as a key driving force. Emerging topics such as edge computing and real-time systems suggest a shift toward intelligent, distributed, and data-intensive cloud environments.
From Technical Security to Human Awareness: A Bibliometric Review of Cybersecurity Education Research Cindy Muhdiantini; Mega Fitri Yani; Istifa Shania Putri
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 2 (2026): April
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.19897820

Abstract

The rapid advancement of information technology has increased cybersecurity threats, emphasizing the importance of education in building security awareness and human-centered defense capabilities. As research on cybersecurity education continues to grow, a systematic understanding of its research trends and thematic evolution is required. This study analyzes global research trends in cybersecurity education using a bibliometric approach. A total of 189 Scopus-indexed publications from 2020 to 2026 were analyzed using the bibliometrix R package and the Biblioshiny interface. The analysis examines annual publication growth, dominant keywords, evolving research topics, and geographical research contributions. The results indicate a steady increase in scientific production, confirming cybersecurity education as an expanding research domain. While technical topics such as network and data security remain prominent, recent research shows a clear shift toward education, training, and security awareness, highlighting the growing importance of human factors in cybersecurity. In addition, the findings reveal an imbalance in global research contributions and relatively limited international collaboration. This study provides a concise overview of the development and structure of cybersecurity education research and offers insights to support future studies, curriculum development, and policy formulation.
Fine-Tuning Panoptic FPN with ResNet-50 for Maritime Obstacle Detection on the LaRS Dataset Istifa Shania Putri; Sugih Ahmad Fauzan; Mega Fitri Yani; Cindy Muhdiantini
SITEKNIK: Sistem Informasi, Teknik dan Teknologi Terapan Vol. 3 No. 3 (2026): July
Publisher : RAM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20768168

Abstract

Maritime obstacle detection is a critical challenge for Unmanned Surface Vehicles (USVs) operating in complex and dynamic environments. This study investigates the effectiveness of fine-tuning Panoptic FPN, a Mask R-CNN-based architecture augmented with Feature Pyramid Networks, for panoptic segmentation on the LaRS (Lake, River, Seas) dataset. Unlike prior work that explored model comparisons broadly, this research focuses specifically on the impact of hyperparameter tuning and backbone selection on maritime panoptic segmentation performance. Through systematic ablation studies, we demonstrate that adjusting the learning rate to 0.002 and the gamma decay factor to 0.2 yields significant improvements. Our fine-tuned Panoptic FPN with a ResNet-50 backbone achieves a Panoptic Quality (PQ) of 45.31%, surpassing the previous state-of-the-art Mask2Former Swin-B (41.7%) by 3.61 percentage points. Notably, ResNet-50 outperforms the deeper ResNet-101 backbone (36.47% PQ), suggesting that heavier architectures may overfit on domain-specific maritime datasets. Furthermore, Panoptic FPN requires only 8 hours of training compared to approximately 2 days for Mask2Former Swin-L, demonstrating superior computational efficiency. These findings highlight that targeted fine-tuning of lightweight architectures can outperform larger transformer-based models in maritime panoptic segmentation tasks.
Co-Authors Cindy Muhdiantini Farid Munadhil Mega Fitri Yani Sugih Ahmad Fauzan