cover
Contact Name
Muhammad Yusuf Mappeasse
Contact Email
jurnal.mediaelektrik@unm.ac.id
Phone
+6281355296513
Journal Mail Official
jurnal.mediaelektrik@unm.ac.id
Editorial Address
Electrical Engineering Education Department Building, 2nd Floor, Faculty of Engineering, Universitas Negeri Makassar.
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Media Elektrik
ISSN : 19071728     EISSN : 27219100     DOI : 10.59562/metrik
Publications in the areas of Electrical Engineering, Information and Computer Engineering, and Control include research articles and reviews of the literature.
Articles 213 Documents
Tuning the Alpha Hyperparameter in the Multires U-Net Architecture for Segmentation of Bali Pendet Dance Images Darmawan Bakti, Lalu; Nasirudin Karim, Muh; Imran, Bahtiar
Jurnal Media Elektrik Vol. 23 No. 2 (2026): MEDIA ELEKTRIK
Publisher : Jurusan Pendidikan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/metrik.v23i2.11944

Abstract

Bali’s traditional Pendet dance represents an important cultural heritage that requires preservation. To support dance recognition, this study applied semantic segmentation to Pendet dance images using the Multires U-Net architecture with alpha hyperparameter tuning. Specifically, three optimization methods Particle Swarm Optimization (PSO), Grid Search, and Random Search were evaluated using the Jaccard Index, Dice Coefficient, and Mean Squared Error (MSE). The results demonstrate that Grid Search produced the optimal alpha value of 1.45, achieving average Jaccard and Dice scores of 98.5002 and 99.2439, respectively. These results outperform previous research (98.4746; 99.2309), PSO (98.4883; 99.2378), and Random Search (98.4837; 99.2352). For MSE, the prior study reported the best score of 7.608E-04, followed by Grid Search (7.659E-04), PSO (7.663E-04), and Random Search (7.765E-04). These findings highlight the effectiveness of Grid Search in optimizing the alpha hyperparameter for the Multires U-Net architecture and demonstrate a significant performance improvement compared to earlier studies.
Development of a Forward Chaining Expert System for Early Diagnosis of Eye Diseases at Padang Eye Center Hospital Afriyani, Risti; Ramanda, Febri; Bunga Ramadhan, Anggun; Bayu Setiaji, Muhammad
Jurnal Media Elektrik Vol. 23 No. 2 (2026): MEDIA ELEKTRIK
Publisher : Jurusan Pendidikan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/metrik.v23i2.11945

Abstract

Objective: The inefficiency of the manual medical check-up process at the Rumah Sakit Mata Padang Eye Center, characterized by paper-based recording, long waiting times, inconsistent symptom documentation, and heavy reliance on limited ophthalmologists, motivated this study. The objective was to develop a web-based expert system that enables patients to perform preliminary self-diagnosis of common eye diseases through interactive yes/no symptom consultation while integrating the forward chaining method with patient data management to support early detection and reduce specialist workload. Method: This study adopted a Research and Development (R&D) approach using the sequential linear (waterfall) model. Data were collected through field observations, interviews with ophthalmologists and staff, questionnaires, and a literature review at Padang Eye Center. The system was implemented using PHP and MySQL, incorporating decision trees, Data Flow Diagrams, and production rules with a Certainty Factor. Results: Functional testing on 50 test cases revealed that the prototype achieved 92% diagnostic accuracy, 94% precision, and an average processing time of 0.82 seconds, representing an 85% reduction in consultation time compared to the manual process. The system successfully generated consistent diagnoses with treatment and prevention recommendations for conditions such as eyelid edema, blepharitis, and trichiasis. Novelty: The novelty of this study lies in the seamless integration of forward chaining inference, symptom weighting, and modular web interfaces specifically designed for real clinical workflows in an Indonesian eye hospital, features rarely combined with previous standalone prototypes. This study provides both practical improvements in service efficiency and theoretical contributions to accessible, explainable rule-based expert systems in ophthalmology.
UML-Based Web Information System for Indonesian Migrant Worker Recruitment: A Case Study at PT Dewi Pengayom Bangsa Ramanda, Febri; Afriyani, Risti; Sella, Puspita Sari; Ardika, Kevin
Jurnal Media Elektrik Vol. 23 No. 2 (2026): MEDIA ELEKTRIK
Publisher : Jurusan Pendidikan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/metrik.v23i2.11947

Abstract

Objective: Private Indonesian migrant worker placement agencies, such as PT Dewi Pengayom Bangsa in Pati Regency, still rely on paper-based and inefficient manual recruitment processes. These processes face issues such as slow data retrieval, excessive physical storage demands, and document accumulation. This study aimed to develop a web-based information system to digitize the recruitment workflow of Indonesian migrant workers (Calon TKI) in Taiwan, Hong Kong, and Singapore. Method: A systems development approach using the waterfall model was employed. Data were collected through on-site observation and semi-structured interviews with agency staff and management, complemented by secondary data from the literature on information systems and migrant labor policies. The system was designed using UML diagrams and implemented using PHP and MySQL. The evaluation included black-box testing and usability assessments. Results: The system integrated eight core modules: online registration, candidate management, automated examination, interview recording, and real-time PDF reporting. Testing showed a 100% success rate in black-box testing and an average usability score of 82.3. Efficiency improvements were substantial: registration time was reduced by 82%, data retrieval improved by 95%, and data entry errors dropped by 92%. Novelty: This study introduces a UML-modeled web-based recruitment system tailored for private TKI agencies at the regency level, offering significant efficiency gains and supporting Indonesia’s BP2MI policies.