Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : jeti

Implementasi Tata Kelola Teknologi Informasi Menggunakan Framework Cobit 5 Pada Penyelenggaraan Haji dan Umrah Kementerian Agama Kota Lhokseumawe Nova Amalia
Jurnal Elektronika dan Teknologi Informasi Vol 4 No 2 (2023): September 2023
Publisher : LPPM-UNIKI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5201/jet.v4i2.416

Abstract

Hajj and Umrah Organizer, Office of the Ministry of Religion, Lhokseumawe City, as the institution responsible for organizing the Hajj and Umrah, is faced with complex challenges related to information and technology management. This research determines the process domain of Control Objectives using the COBIT 5 Framework and analysis of Capability Levels in Agencies. Based on the results of this research, it was found that the COBIT 5 domain processes used were EDM (Evaluate, Direct and Monitor), APO (Align, Plan and Organize), and MEA (Monitor Evaluate and Assess). The research results show that the agency's capability level is 2.29, which means it is still at level 2 (managed process), meaning the process has been carried out regularly, there is planning and supervision. Therefore, recommendations are needed for target levels to be achieved at level 3 by improving documentation of information technology management processes and developing requirements, classifications and priorities in providing services and handling incidents.
Application of the Random Forest Algorithm for Predicting Hajj Registration Numbers at Kemenag Lhokseumawe Nova Amalia
Jurnal Elektronika dan Teknologi Informasi Vol 5 No 2 (2024): September 2024
Publisher : LPPM-UNIKI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5201/jet.v5i2.487

Abstract

Ransomware is a type of malware that blocks access to computer systems or data until a ransom is paid by the victim. Ransomware attacks typically occur due to malicious files that are unknowingly downloaded and installed by the victim onto their computer system. Given the threats and potential losses posed, methods for detecting and classifying ransomware continue to be developed, one of which utilizes the Random Forest machine learning algorithm. Random Forest is chosen for its advantages in handling large datasets, short training time, high prediction accuracy, and its ability to reduce the risk of overfitting. Using 1380 ransomware samples from a dataset with 54 features, 10 best features were selected through Feature Selection where the built Random Forest model successfully predicted ransomware files with an accuracy of 98.79%.