cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Charis Fathul Hadi
Contact Email
chariselektro@gmail.com
Phone
+6285649231296
Journal Mail Official
chariselektro@gmail.com
Editorial Address
Prodi Teknik Elektro, Fakultas Teknik , Universitas PGRI Banyuwangi Jl.Ikan Tongkol No. 22 Banyuwangi 68416, Jawa Timur
Location
Kab. banyuwangi,
Jawa timur
INDONESIA
Journal Zetroem
Published by Universitas PGRI Banyuwangi
ISSN : 2656081X     EISSN : 2656081X     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering
jurnal zetroem yang dapat dimuat dalam jurnal ini meliputi bidang keilmuan Teknik Elektronika, Teknik Kendali, Sistem Tenaga, Telekomunikasi, Informatika, Sistem Distribusi. Makalah dapat berupa ringkasan laporan hasil penelitian atau kajian pustaka ilmiah. Makalah yang akan dimuat hendaknya memenuhi format yang telah ditentukan.
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 12 Documents
 1   2 
Search results for , issue "Vol 8 No 1 (2026): ZETROEM" : 12 Documents clear
Performance Evaluation of IoT Communication Protocols (LoRa, Wi-Fi and Zigbee) for Smart Environment Fahmi, Arif Fahmi; Indra Kurniawan; Junaedi Adi Prasetyo
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.6414

Abstract

The Internet of Things (IoT) constitutes a core component in the development of Smart Environment systems for real-time environmental monitoring. Selecting an appropriate communication protocol remains a major challenge, particularly in semi-rural areas characterized by limited network infrastructure and heterogeneous geographical conditions. This study aims to evaluate and compare the performance of three IoT communication protocols, namely LoRa, WiFi (ESP32), and Zigbee (XBee), through real-field prototype-based testing conducted in the semi-rural region of Banyuwangi. The evaluated parameters include communication range, transmission latency, and packet delivery ratio (PDR). The experiments were performed by periodically transmitting data packets under multiple distance scenarios. The results indicate that LoRa achieves the longest communication range of approximately ±1750 meters with an average latency of 2.1 seconds, WiFi exhibits the lowest latency of about 0.2 seconds with an effective range of ±200 meters, while Zigbee demonstrates stable transmission performance with a PDR of 100% up to a distance of ±600 meters. The main contribution of this study lies in providing empirical performance data obtained from real-field experiments in a semi-rural Indonesian environment, which can serve as a reference for selecting appropriate IoT communication protocols for Smart Environment implementations.
Comparison of CNN, ResNet50, and Xception for Deepfake Image Detection Rachmat; Mohammad Zainuddin; Handini Arga Damar Rani
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7524

Abstract

This study compares the performance of three deep learning architectures—Convolutional Neural Network , ResNet50, and Xception—for frame-based deepfake image detection and identifies the most effective model in terms of accuracy, precision, recall, F1-score, and generalization. The study followed the Knowledge Discovery in Databases (KDD) framework using the Deepfake Detection Dataset (DFD Entire Original) from Kaggle, which consists of 3,432 videos, including 3,068 fake and 364 real videos. Videos were converted into frames using OpenCV, followed by face detection and cropping using MTCNN. The resulting face images were resized to 224×224 pixels, normalized, augmented, and labeled. To reduce classification bias caused by class imbalance, the training data were balanced using random undersampling, resulting in real frames and  fake frames. The dataset was then split into training, validation, and testing sets using a stratified 60:20:20 ratio. The results show that Xception achieved the best performance among the three models, with an accuracy of 95.21%, precision of 0.95, recall of 0.95, and F1-score of 0.95, followed by ResNet50 with an accuracy of 93.42% and CNN with an accuracy of 87.65%. These findings indicate that transfer learning-based architectures, particularly Xception, are more effective than conventional CNNs for deepfake image detection under a consistent experimental setting. This study is limited to a single dataset and frame-based evaluation, thus future work will explore the potential of hybrid models, such as Vision Transformer (ViT) combined with Capsule Networks , to improve detection performance and address challenges like temporal analysis and cross-dataset validation.
Digital Signal Feature Extraction for Graph-Based Host Classification in VM Placement Hidayat, Taufik; Medriavin Silalahi, Lukman; Hamid, Abdul
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7559

Abstract

This study proposes a host classification methodology based on signal analysis and graph representation as a pre-placement stage for virtual machines (VM) in a cloud computing environment. The Bitbrains dataset is utilized as a source of time-series data representing CPU, memory, disk, and network utilization. Each parameter is modeled as a discrete signal and analyzed in both time and frequency domains. The analysis is conducted using a fixed observation window and frequency-domain transformation to capture workload characteristics across multiple resources. The Fourier transform results indicate the dominance of low-frequency components, suggesting gradual workload variations. Spectral energy is calculated and normalized to identify quantitative differences between host conditions. The results show that the overloaded class contributes 98.9% of the total spectral energy, while the underloaded and balanced classes contribute only 0.7% and 0.4%, respectively. The extracted features are then integrated using a four-node graph model that connects all resource dimensions into a single structure. The aggregated graph score is employed for dynamic percentile-based classification. From a total of 1,239 analyzed hosts, the proposed method classifies 421 hosts as overloaded, 409 as underloaded, and 409 as balanced. These findings demonstrate that spectral characteristics combined with graph integration provide a quantitatively structured and adaptive host segmentation mechanism, where the resulting classification can support VM placement decisions by identifying underloaded, balanced, and overloaded host conditions.
Smart Attendance System: AI Technology for Digital Attendance Using Computer Vision Technology Natsir, Fauzan; Redo Abeputra Sihombing; Triana Dewi Salma; Millati Izzatillah; Ega Shela Marsiani; Farhan Maulana Arramsy; Anuj Kumar
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7569

Abstract

Employee attendance is a crucial aspect of human resource management, particularly in maintaining discipline and ensuring the operational effectiveness of a company. PT KAMM currently uses a fingerprint-based attendance system which, although effective, often encounters issues such as sensor sensitivity to finger conditions, potential device damage caused by continuous physical contact, and employee inconvenience. This research aims to develop a face recognition-based attendance system as a more efficient and hygienic alternative. The dataset comprises 1,400 facial images from 20 PT KAMM employees (20 classes), split into 80% training, 10% validation, and 10% testing data. The method applied combines the Haar Cascade algorithm for face detection and a Convolutional Neural Network (CNN) for face recognition. The CNN architecture consists of four convolutional layers with 32 to 256 filters, ReLU activation, max pooling, flatten, a 512-neuron fully connected layer, dropout of 0.5, and softmax classification. The model was trained for 50 epochs using the Adam optimizer with a learning rate of 0.001 and batch size of 32. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics. Results show the system achieved an accuracy of 95.71%, precision of 95.80%, recall of 95.60%, and an F1-score of 95.70%, with an average inference time of 0.12 seconds/frame in real-time. However, the system has limitations: accuracy drops by up to 12% under extreme lighting conditions and when employees wear masks. This study is expected to serve as a reference for other companies seeking to adopt similar face recognition technology for contactless attendance management systems.
Design and Evaluation of a Virtual Tour–Based Application for the Placement Criteria of the Instrument Landing System (ILS) Rusman; Moch Rifai; Prayitno, Hadi; Artadarma, Nyoman
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7573

Abstract

The Instrument Landing System (ILS) is a critical component of aviation navigation that ensures aircraft landing accuracy and safety. However, public understanding of restricted ILS areas and equipment placement criteria remains limited, as existing informational media—such as regulatory documents or slide presentations—lack interactivity and spatial visualization. This study aims to design and evaluate a Virtual Tour-based ILS Application as an interactive educational medium to visualize and explain the placement criteria of ILS equipment in a three-dimensional (3D) environment. The research used the ADDIE (Analysis, Design, Development, Implementation, Evaluation) instructional design model to systematically develop the application. The content and functional design were derived from the Indonesian Civil Aviation Authority’s SKEP/113/VI/2002 and ICAO Annex 10 Volume I standards. Data collection methods included observation, expert validation, and user testing. The application was evaluated using three quality dimensions of the ISO 25010 software standard: functional suitability, compatibility, and usability. Participants included media experts, subject matter experts, and 20 community members residing near Budiarto Airport, Indonesia. As a result, the Virtual ILS application achieved high evaluation scores across all dimensions—functional suitability (97.5%), compatibility (100%), and usability (90.16%)—indicating excellent performance, ease of use, and educational value. The interactive 3D visualization effectively improved users’ comprehension of ILS restricted zones and equipment placement requirements, compared to conventional informational media.
Development of an Air Quality Classification System Using SMOTE-Based Random Forest and XAI Analysis Arip Kristiyanto; Hirawati Lubis
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7586

Abstract

South Tangerang City is a critical environmental issue that requires an accurate and transparent classification system. This study aims to develop an air quality classification model using a machine learning algorithm integrated with data balancing techniques and model interpretation methods. The methodology used includes pre-processing of Air Pollutant Standard Index (ISPU) data for the 2020–2022 period into three categories: Good, Moderate, and Unhealthy. The dataset used is 1096, Synthetic Minority Over-sampling Technique (SMOTE) is applied to handle class imbalance, and hyperparameter optimization is performed using GridSearchCV. The experimental results show that the Random Forest algorithm outperforms the baseline SVM and KNN models, achieving an accuracy of 0.81 and an F1-Score of 0.75 after SMOTE and tuning. Explainable AI (XAI) analysis using SHAP reveals that sulfur dioxide (SO₂) is the most dominant feature influencing model decisions, and it is spatially correlated with industrial activities and heavy transportation in the South Tangerang area. The final model was then deployed to the Hugging Face Spaces cloud platform via the Gradio interface to provide publicly accessible classification services. This study demonstrates that integrating Random Forests and SHAP produces a classification system that is not only highly performant but also scientifically transparent, supporting air pollution mitigation.
Density-Optimized Lookup Table with Piecewise Linear Interpolation for ESP32 ADC Precision Enhancement Antonius Irianto Sukowati; Linza Mawadda Rahmah
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7602

Abstract

The inherent non-linearity of built-in Analog-to-Digital Converters (ADCs) in low-cost microcontrollers like the ESP32 significantly impacts measurement accuracy, often exceeding 10% error in critical ranges. This research aims to enhance ESP32 ADC precision without expensive external hardware through a novel software-based correction method. The proposed approach combines a density-optimized Lookup Table (LUT) with piecewise linear interpolation. Unlike conventional uniform distribution, this technique strategically concentrates 65% of calibration points in the critical mid-voltage region (0.5–2.5 V) where non-linearity is most pronounced. Experimental validation was conducted using precise input voltages from 0 V to 3.2 V across multiple ESP32 units. Results demonstrate remarkable improvements: the average absolute error was reduced from 0.112 V (3.42% of full scale) to 0.008 V (0.24% of full scale), with Root Mean Square Error (RMSE) decreasing by over 92.5%. The method achieves a sub-1% maximum error while maintaining minimal resource consumption, requiring only 264 bytes of memory and 2.3 ms processing time per measurement. These findings confirm that high-accuracy measurements are achievable using commodity hardware, challenging the notion that precision requires expensive external ADCs. This work offers significant implications for cost-sensitive IoT, environmental monitoring, and healthcare applications requiring reliable data acquisition without increased hardware complexity.
Smart Seismic Intelligence Machine Learning for Spatial Clustering and Earthquake Magnitude Prediction in Indonesia Setya Hadi, Harry; Rauf, Rosnita; Agus Salim; Kevin Maulana Firdaus
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7615

Abstract

Indonesia is located within the Pacific Ring of Fire, one of the most seismically active regions in the world due to the interaction of multiple major tectonic plates. Understanding the spatial distribution of earthquakes and accurately estimating their magnitudes is essential for effective disaster risk assessment and mitigation planning. This study aims to analyze earthquake distribution patterns and develop a machine learning-based approach to predict earthquake magnitude using seismic data from the Meteorology, Climatology, and Geophysics Agency (BMKG). The study employs two machine learning methods: K-Means Clustering to identify spatial groupings of earthquake events and Random Forest Regression to predict magnitude based on spatial and temporal features. The dataset consists of 67 earthquake events recorded in February 2026, including attributes such as latitude, longitude, depth, magnitude, and occurrence time. Clustering results indicate that the optimal number of clusters is k = 4, with a Silhouette Score of 0.3444, suggesting a moderate clustering structure. This implies that spatial patterns are present, although cluster separation is not yet well-defined. The Random Forest model achieved an R² of 0.7382 on training data and 0.0975 on testing data, indicating overfitting likely due to the limited dataset size. Feature importance analysis reveals that longitude contributes the most (43.7%), followed by depth (29.6%), latitude (20.6%), and time (6.0%). These findings highlight the dominant role of spatial factors in Indonesia’s seismic activity. However, the limited dataset restricts model generalization; therefore, future studies should use larger datasets and incorporate additional geophysical parameters to improve predictive performance.
Web-Based Competency Test Information System with Automated Scoring Using the Waterfall Method Damanik, Burhanuddin; Sadarmanis Halawa
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7622

Abstract

The implementation of competency tests in vocational high schools (SMK) is still largely conducted manually, leading to several issues such as delays in score processing, data recording errors, and inefficiencies in managing examination records. This study aims to design and develop a web-based competency test information system using the Waterfall method to improve efficiency, accuracy, and transparency in the examination process. The system was developed using PHP, MySQL, HTML, CSS, and JavaScript, incorporating six main features: user login, participant registration, question management, online examination, automatic scoring, and result reporting. System evaluation was conducted using Black Box Testing to assess functional performance and the System Usability Scale (SUS) to measure user satisfaction. The results show that all system features operated successfully with a functional success rate of 100% across all test scenarios, indicating high system reliability. In addition, usability evaluation involving 30 respondents, consisting of 20 students and 10 teachers, resulted in an average SUS score of 92, which falls into the “excellent” category. The system also significantly improves efficiency by reducing result processing time from 2–3 days to real-time processing, while minimizing data entry errors. Therefore, the developed system not only improves the efficiency and accuracy of competency test implementation but also provides a reliable and user-friendly solution, contributing to the development of educational information systems based on user experience.
Pollutant Monitoring System for Mushroom Factory Liquid Waste using Arduino with 4 Sensor Integration Sigitta H., Rito Cipta; Mubarok, Rizky; Rakhman, Arif; Prastyo, Firman Ardy; Prastyono, Rizki Noor; Arsiandro, Fadly Haris
ZETROEM Vol 8 No 1 (2026): ZETROEM
Publisher : Prodi Teknik Elektro Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/ztr.v8i1.7623

Abstract

Mushroom production requires a specially designed medium for mushroom growth. Factory-scale composting methods utilize several media, which involve water to maintain moisture and chemical/organic fertilizers. The water used for mushroom cultivation contains hazardous substances, which, if dissolved and flowing into sewers, water sources, or community irrigation, can cause several problems, resulting in liquid pollutants. The purpose and main contribution of this research is to develop and implement pollutant monitoring system in mushroom factory liquid waste based on Arduino with the integration of four sensor parameters. The 4D method used includes the stages of define, design, develop, and disseminate. The goal is to develop pollutant monitoring system using four sensors. The feasibility analysis results have a percentage above 80% in the good category and are suitable for use. Accuracy analysis results are >80% in the good category. Temperature and pH also tend to be stable without significant changes. The pH value tends to be stable in the neutral range of 7.2–7.3, which is generally still suitable for supporting the survival of aquatic organisms. The dissolved oxygen (DO) levels in water are generally low, in the range of 2.46 to 3.01 mg/L, which is already below the standard for good water quality (generally >5 mg/L). Meanwhile, the turbidity parameter indicates pollution, marked by very high turbidity reaching 300 NTU. Then it shows a drastic decrease from very high conditions at the beginning of 300 NTU to approaching zero after further distance, indicating an effective natural sedimentation process in improving water clarity.

Page 1 of 2 | Total Record : 12

 1   2 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 8 No 1 (2026): ZETROEM Vol 7 No 2 (2025): ZETROEM Vol 7 No 1 (2025): ZETROEM Vol 6 No 2 (2024): ZETROEM Vol 6 No 1 (2024): ZETROEM Vol 5 No 2 (2023): ZETROEM Vol 5 No 1 (2023): ZETROEM Vol 4 No 2 (2022): ZETROEM Vol 4 No 1 (2022): ZETROEM Vol 3 No 2 (2021): ZETROEM Vol 3 No 1 (2021): ZETROEM Vol 2 No 2 (2020): ZETROEM Vol 2 No 1 (2020): ZETROEM Vol 1 No 2 (2019): ZETROEM Vol 1 No 1 (2019): ZETROEM More Issue