CoreID Journal

Comparison of Classification Models for Predicting Admission Outcomes of Prospective Students with Disabilities

2026-03-16T06:02:58+00:00

Students with disabilities are a group that requires special attention in the admission process at universities, especially at State Islamic Higher Education Institutions (PTKIN). Although inclusive policies have been implemented, challenges in implementation in the field are still quite significant, especially in terms of equal access and the readiness of educational institutions. This study aims to analyze the opportunities and challenges of accepting students with disabilities at PTKIN through a machine learning approach to predict the factors that influence selection graduation. The research data consists of 80 prospective students with disabilities who participated in the PTKIN selection, covering variables such as gender, province of origin, previous education, school accreditation, and type of disability. The research process included data cleaning, feature engineering (including categorical encoding and recategorization of disability variables), and data balancing using the SMOTE method. Next, model training was carried out using three main algorithms, namely Support Vector Machine (SVM), Random Forest, and XGBoost, as well as model combination (ensemble voting classifier) for performance comparison. The results show that the SVM (RBF kernel) model provides the best performance with an accuracy of 80% and an F1-score of 0.88 for the “Pass” class. This model outperforms Random Forest and XGBoost, which have an accuracy of 65% each. The most influential factors for graduation are the province of origin, disability category, and previous form of education. These findings indicate that the acceptance of students with disabilities at PTKIN is still influenced by geographical factors and educational background, so affirmative policies need to be directed at expanding access for people with disabilities from certain regions and backgrounds. The machine learning approach has proven to be effective as a tool for analyzing inclusive education policies in the PTKIN environment.

Comparison of Long Short-Term Memory and Recurrent Neural Network For Stock Market Price Movement Classification in Islamic Bank Finance

2026-03-26T04:08:03+00:00

This study addresses the importance of accurate stock price prediction in the Islamic finance sector, where reliable forecasting supports better investment decisions and market stability. Despite the growing use of deep learning methods, comparative studies on sequential models in this domain remain limited. Therefore, this research compares the performance of Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) models for classifying stock price movement direction of Islamic banks in Indonesia. The dataset was sourced from two Islamic banks in Indonesia, covering the period from 2022 to mid-2024, with features such as Open, High, Low, Close, Adjusted Close, and Volume. The CRISP-DM method was applied for data processing, and testing was performed with data splits of 60:40, 70:30, and 80:20, as well as epoch variations (30, 50, 80). Results indicate that RNN outperforms LSTM, with the highest accuracy of 58% for RNN and 53% for LSTM. Evaluation metrics also included precision, recall, and F1-score. In conclusion, RNN performs better for stock movement classification direction, while LSTM is more effective for minimizing prediction error.

Multi-Layer PHP Source Code Protection Model Using Encoding with Integrity Hashing and Anti-Reverse Engineering

2026-03-25T09:40:39+00:00

Unprotected PHP source code is vulnerable to reverse engineering, piracy, and illegal modifications. This research aims to design and develop a multi-layer PHP source code protection model that combines obfuscation techniques, multi-layer encoding, AES-256 encryption, and hashing mechanisms with anti-tamper capabilities to maintain code confidentiality and integrity. The system is also equipped with auto-restore features and panic notification via Telegram Bot that automatically restores original files and sends security warnings when illegal changes are detected. The methodology used is Research and Development (R&D), with stages including literature review, system design, prototype development, security experiments, and performance benchmarking. The expected results show that the multi-layer model can hinder reverse engineering, accurately detect file changes, and provide rapid responses via auto-restore and Telegram notifications, significantly improving PHP source code security compared to conventional encoders. The security experiments demonstrated superior protection against deobfuscation attacks, with benchmark results showing acceptable performance overhead (an average execution-time increase of 15-20ms, a CPU load increase of 8-12%, and a memory usage increase of 5-8 MB) compared to commercial encoders.

Information System Audit of Learning Management System Using COBIT 5 Army Staff and Command School

2026-03-27T09:09:20+00:00

In today’s digital era, information technology has become an integral part of education, with Learning Management System (LMS) serving as a key innovation supporting online teaching and learning processes. The Army Staff and Command School (Seskoad) uses LMS to enhance the effectiveness and efficiency of its educational programs. However, no audit of the LMS information system has been conducted at Seskoad, potentially exposing the system to operational and security risks, such as non-compliance with regulations and vulnerability to cyber attacks. This study aims to audit the LMS using the COBIT 5 framework to evaluate the Maturity Level of IT governance and information system management. The methodology includes observation, interviews, questionnaires, and triangulation of data. The audit results indicate that the LMS Maturity Level is at Level 2 (Managed) across all seven evaluated sub-domains (APO9, DSS01, DSS04, DSS05, DSS06, MEA01, MEA02), with deficiencies in documentation, risk management, and security governance. Recommended improvements include developing SOPs, conducting user training, and performing regular security audits. With systematic implementation over five years, it is expected that Seskoad’s LMS can reach Level 4 (Quantitatively Managed), enhancing effectiveness and efficiency of education and training in the military environment.

Performance Analysis of MQTT and HTTP Protocols on Low-Power ESP32 Devices for IoT Applications

2026-04-08T07:23:58+00:00

The choice of communication protocol is crucial in determining the efficiency and service life of low-power Internet of Things (IoT) devices such as those based on the ESP32, particularly in Smart Home applications. This study aims to conduct a Systematic Literature Review to analyze and compare the performance of MQTT and HTTP on low-power ESP32 microcontrollers, with a primary focus on energy efficiency, latency, and data overhead. By analyzing and synthesizing findings from various empirical studies, the results of this review are expected to confirm that MQTT, through its lightweight publish–subscribe architecture and minimal data overhead, offers significantly lower power consumption and better latency compared to the verbose request–response model of HTTP. The conclusions drawn from this analysis will provide strong recommendations for developers in selecting the most efficient communication protocol for resource-constrained IoT applications.