Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Journal of Embedded Systems, Security and Intelligent Systems Jurnal Sipakatau
Dewi Fatmarani Surianto
Universitas Negeri Makassar, Indonesia
Religion Arts Humanities Computer Science & IT Engineering Environmental Science Health Professions Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Nursing Physics Social Sciences Veterinary Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Transfer Learning-Based CNN for Guava Fruit Disease Detection and Classification Azir Zuldani Pratama; Mustari Lamada; Dewi Fatmarani Surianto
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 3 (2025): September 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i3.10153

Abstract

Guava (Psidium guajava L.) is a tropical plant from the Myrtaceae family and the Psidium genus that is susceptible to diseases such as anthracnose and scab, especially in humid environmental conditions. To accurately detect and classify these diseases, digital image-based technology is needed. However, previous studies still have limitations in dataset size, method variation, and model optimization. Therefore, a study was conducted with the title Guava Fruit Disease Detection and Classification System Using a Convolutional Neural Network (CNN) Based Transfer Learning Model. This study tested four Transfer Learning models, namely MobileNetV2, DenseNet169, VGG16, and EfficientNetV2B5. Based on the test results, the MobileNetV2 model with a combination of activation functions and optimizers (Swish, Swish, Adam) showed the best performance, having the fastest computation time, namely 10 minutes 17 seconds. This proves that the model built is not only superior in accuracy, but also efficient in execution time and can be applied to guava fruit disease detection and classification systems. These findings provide valuable insights into the MobileNetV2 method, combined with Swish, Swish, and Adam, as the best choice for classifying or detecting guava fruit disease levels compared to other methods. This approach can also lead to the development of a widely applicable web-based system for plant disease identification. This offers several benefits for farmers, including faster and more accurate disease detection, efficiency, and cost savings.
EduTech Acceleration: Strengthening Teacher Competencies through AI-Based Learning Media Training Dewi Fatmarani Surianto; Muhammad Fajar B; Ayu Hasnining; Andi Akram Nur Risal; Haekal Febriansyah Ramadhan; Dewi Fatmawati Surianto
Jurnal Sipakatau: Inovasi Pengabdian Masyarakat Vol. 3 No. 1 (2025): Jurnal Sipakatau
Publisher : PT. Global Research Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66314/sipakatau.v3i1.265

Abstract

The rapid adoption of Generative Artificial Intelligence (GenAI) in education requires teachers to strengthen their competencies in producing accurate, ethical, and safe learning media. This community engagement program was conducted in a secondary education institution to enhance teachers’ AI literacy and ability to apply structured prompting using the CRISP-EDU framework. The training emphasized fact-checking, credible source attribution, bias mitigation, and student data protection principles. Evaluation results demonstrate improvements across all competency dimensions: understanding of CRISP-EDU fundamentals (+42%), AI licensing and ethics (+32%), classroom AI-related standard operating procedures and risk awareness (+26%), generative AI utilization (+15%), and practical application of CRISP-EDU (+23.66%). These findings indicate a shift in teachers’ roles from passive users to critical and ethical content curators capable of producing safe and contextually appropriate AI-based learning materials.
Beyond Advice: Training Mentors in Ethics, Boundaries, and Trustworthy Mentoring Dewi Fatmarani Surianto; Asmaul Husnah Nasrullah; Ayu Hasnining; Fhatiah Adiba
Jurnal Sipakatau: Inovasi Pengabdian Masyarakat Vol. 2 No. 4 (2025): Jurnal Sipakatau
Publisher : PT. Global Research Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61220/jsipakatau.v2i4.2525

Abstract

The Community Service Program aims to improve ethical competency among student mentors through a structured training program that focuses on five key areas: confidentiality, ethical communication, communication style, professional boundaries, and respecting mentee diversity. A total of 31 mentors participated in pre- and post-test assessments, allowing for a measurable analysis of knowledge development. The training was delivered online using Zoom and included interactive discussions, scenario analysis, and self-reflection sessions. Results showed significant improvements in all five indicators, particularly in understanding ethical communication (from 32.3% to 77.4% selecting the highest score), and appropriate communication style (from 41.9% to 80.6%). Even dimensions with high baseline scores, such as confidentiality (74.2%), experienced positive growth. The findings confirm that the training successfully improved participants’ ethical sensitivity, practical communication skills, and preparedness for real-world mentoring situations. This initiative contributed to the development of a responsible mentoring culture that aligns with the values ​​of empathy, professionalism, and inclusion. Future programs should consider expanding to include peer mentors from other faculties and provide ongoing support mechanisms to strengthen ethical mentoring practices.
PKM Pelatihan Figma untuk Meningkatkan Kualitas User Interface Project Mahasiswa Demi Mendukung Hasil Project-Based Learning Kurnia Prima Putra; Dewi Fatmarani Surianto; Wahyu Hidayat; Jasruddin Jasruddin; Ridwan Daud Mahande
Jurnal Sipakatau: Inovasi Pengabdian Masyarakat Vol. 1 No. 3 (2024): Jurnal Sipakatau
Publisher : PT. Global Research Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61220/jsipakatau.v1i3.247

Abstract

In the era of project-based learning (PjBL), the quality of student learning is a primary concern. However, often the quality of user interface (UI) in these projects is neglected. Therefore, we conducted intensive training using Figma to enhance UI quality in PjBL projects. With a practical approach, students were encouraged to become more engaged and understand UI design concepts better. The results were surprising: there was a significant improvement in the quality of student project UIs. Not only were they more actively involved, but they were also able to apply good design principles. These findings offer new hope in curriculum development and teaching practices for the future, reinforcing Figma's contribution to enhancing student learning quality.
Co-Authors Andi Akram Nur Risal Asmaul Husnah Nasrullah Ayu Hasnining Azir Zuldani Pratama Dewi Fatmawati Surianto Fhatiah Adiba Haekal Febriansyah Ramadhan Jasruddin Jasruddin Kurnia Prima Putra Muhammad Fajar B Mustari Lamada Ridwan Daud Mahande Wahyu Hidayat