Claim Missing Document
Check
Articles

Found 6 Documents
Search

COMPASS: Comparative Evaluation of Machine Learning Algorithms for DDoS Detection Using ANOVA F-Value on AISED Dataset Hartinah; Syamsuddin, Irfan; Syarwani, Andi
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8276

Abstract

This study presents COMPASS, a comparative evaluation of ten Machine Learning algorithms for DDoS attack detection using the AISED Dataset on Cloud DDoS Attacks. Feature selection was performed using SelectKBest with ANOVA F-Value, evaluating model performance across varying feature dimensions (K = 10, 15, 20, 25). Experimental results demonstrate that ensemble-based methods, particularly Random Forest, Gradient Boosting, and AdaBoost, achieve near-theoretical maximum AUC scores (>0.998) while maintaining fast training times (<0.1 seconds). K-Nearest Neighbors (KNN) also exhibits robust performance (AUC > 0.98) with minimal computational cost. In contrast, Support Vector Machine (SVM) and Quadratic Discriminant Analysis (QDA) show relatively lower accuracy (AUC > 0.85) and suffer from high computational complexity, with SVM requiring up to 572 seconds to train at K=25. These findings highlight the critical trade-off between classification accuracy and computational efficiency in selecting optimal models for real-time DDoS detection systems. As future work, we propose deploying a lightweight version of COMPASS on edge computing devices and integrating it into federated learning frameworks to enable collaborative, privacy preserving model training.
Women’s Leadership in Educational Institutions: A Qualitative Literature Review on Challenges and Strategic Opportunities Hartinah; Thamrin, Putri Aulia; Ilahi, Muhammad Nur Ilham; Fitriani; Angkananon, Chumphon
Journal of Islamic Education Research Vol. 6 No. 2 (2025): Journal of Islamic Education Research
Publisher : Faculty of Education and Teacher Training, Islamic State University of Kiai Haji Achmad Siddiq Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35719/jier.v6i2.478

Abstract

Women leaders in education continue to face structural and cultural barriers, such as biased recruitment and leadership stereotypes tied to masculinity. However, their collaborative, empathetic, and inclusive leadership style offers unique advantages in building responsive and innovative educational environments. This qualitative literature review explores studies, policies, and best practices related to women's leadership in educational institutions. The findings reveal that gender quotas, leadership training, and mentoring programs effectively increase women’s access to strategic roles. Mentoring also boosts confidence and expands professional networks. To empower women as transformative leaders, institutions must adopt inclusive policies, support mentoring initiatives, and challenge gendered cultural norms. Strengthening women’s leadership can improve institutional equity, innovation, and sustainability. Pemimpin perempuan di bidang pendidikan masih menghadapi hambatan struktural dan kultural, seperti bias dalam rekrutmen serta stereotip bahwa kepemimpinan adalah sifat maskulin. Namun, gaya kepemimpinan perempuan yang kolaboratif, empatik, dan inklusif memiliki keunggulan dalam menciptakan lingkungan pendidikan yang adaptif dan inovatif. Studi pustaka ini menggunakan pendekatan kualitatif untuk menelaah berbagai penelitian, kebijakan, dan praktik terbaik terkait kepemimpinan perempuan. Hasil menunjukkan bahwa kuota gender, pelatihan kepemimpinan, dan program mentoring efektif meningkatkan akses perempuan ke posisi strategis. Mentoring juga memperkuat kepercayaan diri dan jaringan profesional. Untuk memberdayakan perempuan sebagai pemimpin transformatif, institusi perlu menerapkan kebijakan inklusif, mendukung program mentoring, dan menantang norma budaya yang bias gender. Penguatan kepemimpinan perempuan akan mendorong kesetaraan, inovasi, dan keberlanjutan institusi pendidikan.
Synergy Between Spiritual Education and Quality Management in the Modern Era Hartinah; Putra, Fikri Hakim; Maharani, Nur Fitriani; Bodori, Susanti
Journal of Quality Assurance in Islamic Education (JQAIE) Vol. 5 No. 1 (2025): Journal of Quality Assurance in Islamic Education (JQAIE)
Publisher : Institut Agama Islam Negeri Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47945/jqaie.v5i1.1887

Abstract

Education in the modern era faces challenges from rapid technological advancement and globalization. The primary focus is often directed toward developing practical skills and critical thinking abilities, while spiritual and moral values tend to be overlooked. This research aims to integrate spiritual education into quality management to produce academically excellent individuals with strong moral integrity. This study explores the role of spiritual education in shaping individual character and morals and analyzes its impact on the overall quality of education. The method used in this research is a literature review, where the researcher collects and analyzes various literature sources, including books, articles, and relevant academic journals. The results indicate that spiritual education is crucial in helping students understand their identity, achieve inner peace, and enhance their mental and emotional well-being. Spiritual education in quality management has proven to create a positive work culture, strengthen collaboration, and reduce conflicts within the educational environment. This research also finds that individuals with a deep spiritual understanding are better prepared to face life challenges and can make wise decisions. In conclusion, integrating spiritual education and quality management is essential for shaping a generation characterized by integrity, resilience in the face of change, and the ability to contribute to creating a just and prosperous society.
Automated Student Activity Monitoring Based on Spatiotemporal Modeling Using MediaPipe and Long Short-Term Memory Andi Syarwani; Hartinah; Maya Itasari; Nurul Amalia Amri; Annisa Nurfadhilah; Muhdalifah Muhtar
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.v6i3.9371

Abstract

Computer vision-based Human Activity Recognition (HAR) systems hold significant potential for applications in educational settings, particularly for monitoring student activities in laboratories or classrooms. Activities such as typing, smartphone usage, and resting are often visually indistinguishable due to their highly similar seated postures. This study proposes a spatiotemporal modeling approach to automatically and non-invasively recognize such activities. Body poses are extracted from video streams using MediaPipe Pose and represented as sequential feature vectors, which are then analyzed using a Long Short-Term Memory (LSTM) network to capture temporal dynamics. The model is trained on video data of students performing three primary activity classes. Evaluation on validation data demonstrates a classification accuracy of 98.48%, with average precision, recall, and F1-score values of approximately 98%. However, testing on unseen videos shows a decrease in accuracy to around 65%, primarily due to misclassification in segments with minimal movement. These findings suggest that the model is sensitive to subtle pose transitions, which are common in seated activity contexts. Overall, the proposed approach demonstrates promising potential for automated student activity monitoring and provides a foundation for developing pose-based behavioral analysis systems in contextual learning environments.
Penanaman Nilai-Nilai Dakwah Dalam Proses Pembelajaran Agama Di Smp Negeri 4 Filial Kelas Jauh Usaha Jaya Fajrin, Muhammad; Hartinah; Fatima, Siti
Al-Khidmah : Jurnal Pengabdian dan Pendampingan Masyarakat Vol. 2 No. 2 (2022): Al-Khidmah: Jurnal Pengabdian dan Pendampingan Masyarakat
Publisher : LPPM IAIN Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47945/al-khidmah.v2i2.1456

Abstract

In spreading Islam to all corners of the world, da'wah became one of the contributors to spreading this so that Islam became a religion that was embraced and believed in by various nations in all corners of the world. This research aims to review and explain the instillation of da'wah values ​​through the religious learning process at SMP Negeri 4 Filial, Usaha Jaya Class. The method used in this research is a qualitative research method by collecting data through observation. The results of this research show that the cultivation of da'wah values ​​is still high in SMP Negeri 4 Filial, Usaha Jaya Class. The factor causing the high value of da'wah in this area is the early planting carried out by the parents of these students.
Optimized Automated Virtual Private Network Management System Utilizing WireGuard and Redis with Delta Processing on MikroTik RouterOS Ardiansyah; Hartinah; Wahyuddin Saputra
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.v6i3.10044

Abstract

In the contemporary network infrastructures, the pursuit of secure, efficient, and easily manageable connectivity has become a fundamental design requirement. WireGuard, a next-generation Virtual Private Network (VPN) protocol, delivers superior cryptographic efficiency and operational performance compared to traditional protocols such as OpenVPN and IPsec. This study presents the development of an optimized automated VPN management framework built upon WireGuard and integrated into MikroTik RouterOS via a web-based control interface. The proposed system automates user registration, account approval, and configuration generation processes, thereby reducing administrative overhead and minimizing human-induced configuration errors. To further enhance system performance, an optimized traffic logging mechanism was implemented using the Redis in-memory database combined with a Delta Processing algorithm, which records only incremental traffic variations instead of cumulative totals. Experimental validation demonstrates that this integration reduces router CPU utilization by 30% and decreases logging latency by 40% relative to conventional polling-based methods. The results confirm that the proposed solution not only achieves full automation of VPN management but also significantly improves the responsiveness and scalability of real-time traffic monitoring. To the best of our knowledge, this research introduces the first Redis-based Delta Processing integration for VPN optimization on MikroTik platforms, offering a lightweight, scalable, and high-throughput solution for multiuser network environments.