cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Seno Darmawan Panjaitan
Contact Email
-
Phone
-
Journal Mail Official
jurnal.elkha@untan.ac.id
Editorial Address
Department of Electrical Engineering, Faculty of Engineering, Universitas Tanjungpura, Jl. Prof. Dr. Hadari Nawawi, Pontianak 78124
Location
Kota pontianak,
Kalimantan barat
INDONESIA
ELKHA : Jurnal Teknik Elektro
Published by Universitas Tanjungpura
ISSN : 18581463     EISSN : 25806807     DOI : http://dx.doi.org/10.26418
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Industrial & Manufacturing Engineering
The ELKHA publishes high-quality scientific journals related to Electrical and Computer Engineering and is associated with FORTEI (Forum Pendidikan Tinggi Teknik Elektro Indonesia / Indonesian Electrical Engineering Higher Education Forum). The scope of this journal covers the theory development, design and applications on Automatic Control, Electronics, Power and Energy Systems, Telecommunication, Informatics, and Industrial Engineering.
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 11 Documents
 1   2 
Search results for , issue "Vol. 18 No.1 April 2026" : 11 Documents clear
Automatic Daily Medication Reminder Tool Using an IoT-Based ESP532 Sensor
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.103145

Abstract

Patient compliance with medication schedules remains a major challenge, especially for individuals with chronic diseases requiring long-term and routine treatment. Missed or delayed doses frequently occur due to forgetfulness or the absence of monitoring. This study presents the design of an IoT-based daily medication consumption monitoring system using an ESP32 microcontroller. The system integrates a limit switch to detect the opening of a medicine box as an indicator of medication intake, and is supported by an LED, buzzer, and 16×2 LCD for local reminders and status display. An Android application is included for configuring schedules and receiving real-time notifications. A key methodological difference from previous ESP32-based medication reminder studies is that earlier systems rely mainly on time-based alerts without verifying whether the user actually responds. In contrast, the proposed approach employs sensor-based event detection to confirm physical interaction with the medication box, enabling behavioral verification rather than simple reminder delivery. IoT provides an unprecedented approach in the field of instrumentation and measurement, namely enabling instruments to detect, characterize, and analyze physical phenomena continuously and in real time. This allows the system to log actual user compliance in real time via Firebase. System development involves hardware design, Arduino-based ESP32 programming, and HTTP data communication using JSON processing. Experimental results show that the system reliably detects user actions, triggers reminders, and uploads consumption data. The system has been proven to provide timely notifications via LEDs and buzzers with 100% accuracy. Overall, the system offers a more accurate and responsive method for supporting daily medication adherence.
XAI Implementation for Inverter-Level Underperformance Analysis of the PV Power Plant from Actual Operational Data
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.104850

Abstract

Photovoltaic (PV) power plants installed on uneven terrain often experience spatially non-uniform operating conditions that lead to performance disparities among inverters, which may not be detected through conventional system-level monitoring. This study presents an inverter-level performance analysis of the Nusa Penida PV power plant using one year of operational data with a 30-minute resolution. A data-driven framework integrating Extreme Gradient Boosting (XGBoost) classification and explainable artificial intelligence was developed to detect underperforming inverters and interpret the contributing factors affecting system performance. The analysis identified significant performance variations among the 18 inverters, with seven units categorized as underperforming based on a relative performance ratio threshold of 0.80 compared to the highest-performing inverter at the same timestamp. The proposed XGBoost classification model achieved an AUC of approximately 0.79 on the test dataset, indicating reliable discrimination between normal and underperforming inverter conditions. Further analysis shows that the detected underperformance corresponds to annual energy losses ranging from approximately 81,000 kWh to 119,000 kWh per inverter when compared with the best-performing reference unit. Explainable analysis using SHapley Additive exPlanations (SHAP) reveals that irradiance and temporal variables are the dominant contributors affecting inverter performance, while persistent negative feature contributions in several inverters indicate location-related constraints beyond natural environmental variability. These results demonstrate that inverter-level monitoring combined with interpretable machine learning provides deeper diagnostic insight than aggregated performance indicators and can support more effective identification of structural performance limitations in PV power plants installed on non-uniform terrain.
WSN-Based IoT Water Tank Monitoring with Accuracy and QoS Evaluation
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.104648

Abstract

This study presents a Wireless Sensor Network (WSN)-based Internet of Things (IoT) water tank monitoring system designed to provide reliable real-time monitoring and performance evaluation. The proposed system utilizes NodeMCU ESP8266 modules and ultrasonic sensors to measure water levels across multiple tanks within a distributed WSN architecture. Previous studies on IoT-based water monitoring have largely focused on system implementation, conceptual frameworks, or application-oriented solutions, while comprehensive experimental validation of sensing accuracy and network communication performance is often limited. In particular, integrated evaluation approaches that simultaneously assess sensor measurement accuracy and network Quality of Service (QoS) performance in multi-node WSN deployments remain relatively underexplored. To address this gap, this study applies an integrated evaluation framework that combines ultrasonic sensing accuracy testing and QoS delay analysis, based on the Telecommunication and Internet Protocol Harmonization Over Networks (TIPHON) standard. Experimental results show that the system achieved average measurement accuracies of 96.59%, 97.21%, and 97.37% for Tanks 1, 2, and 3, respectively. Network performance evaluation under non-Line-of-Sight (non-LoS) indoor conditions produced an average transmission delay of 28.75 ms, which falls within the “very good” category according to TIPHON QoS criteria. These results demonstrate that the proposed WSN–IoT architecture provides reliable sensing performance and stable communication for domestic water tank monitoring applications.
Predicting Breakdown Voltage of Transformer Oil under Copper/Iron Contamination: A Comparative Study of Gradient vs Metaheuristic Training
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.101026

Abstract

Transformer oil functions as an insulating and cooling medium in high-voltage power systems, whose dielectric condition degrades over service life due to thermal aging, moisture ingress, and metallic contamination, leading to reduced Breakdown Voltage (BDV) and increased insulation failure risk that may necessitate oil regeneration, replacement, or indicate transformer end-of-life. Unlike Dissolved Gas Analysis (DGA), which evaluates transformer faults based on gas decomposition products, BDV directly reflects the dielectric strength of insulating oil and is more sensitive to particulate contamination such as Cu and Fe, making it more suitable for material-level insulation degradation assessment. This study investigates the influence of copper (Cu) and iron (Fe) particle contamination on BDV and compares three Artificial Neural Network (ANN) training strategies for BDV prediction: gradient-based training (DFFNN-Pure), Genetic Algorithm optimization (DFFNN-GA), and Grey Wolf Optimizer-based training (DFFNN-GWO), using experimental data from 36 transformer oil samples obtained in accordance with IEC 60156:2018. The comparison represents a before–after modeling perspective in terms of training strategy rather than repeated physical testing. The results show that DFFNN-Pure achieved the highest prediction accuracy (R² = 0.996, RMSE = 0.296 kV, MAE = 0.238 kV), while DFFNN-GWO demonstrated stable convergence with competitive accuracy (R² = 0.971, RMSE = 0.886 kV), whereas DFFNN-GA exhibited unstable convergence and poor generalization. Unlike previous studies that primarily focus on transformer remaining useful life estimation at the system level, this work emphasizes material-level BDV prediction of transformer oil under metallic contamination and provides a systematic comparison between gradient-based and metaheuristic training within the same DFFNN framework, supporting non-destructive condition monitoring and predictive maintenance.
Spatial Clustering of Electricity Consumption Patterns in Indonesian Higher Education Institutions
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.104516

Abstract

Higher education institutions represent a significant contributor to electricity consumption in the public sector, particularly in developing countries such as Indonesia. This study aims to identify spatial patterns and provincial disparities in electricity consumption across Indonesian higher education institutions. This research method uses spatial autocorrelation analysis with Moran's I and hierarchical clustering based on Ward’s method. The results show that the observed Moran’s I (0.5129679) is higher than the expected Moran’s I (-0.03030303), and the spatial pattern of electricity consumption by higher education institutions is clustered. This result is confirmed by the negligible p-value (0.0003618787 < 0.05), indicating a strong clustered spatial pattern. Hierarchical clustering was used to identify three groups of provinces representing the level of electricity consumption. The findings highlight significant regional disparities in electricity consumption patterns and provide a quantitative basis for energy management strategies and sustainable higher education policy planning in Indonesia.
Early Lightning Event Detection System Using the LSTM–GRU Architecture at Supadio Airport, Pontianak
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.104281

Abstract

Frequent thunderstorm activity around Supadio Airport, Pontianak, highlights the need for reliable lightning forecasting to support aviation safety and airport operations. In practice, most lightning systems are still used for detection rather than prediction, while many previous forecasting studies have relied on a single deep learning model, which may limit the ability to capture temporal patterns in meteorological data. Therefore, this study applied a hybrid Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) model to predict lightning occurrences using historical meteorological data from Supadio Airport. The main contribution of this study lies in the development of a hybrid LSTM–GRU framework for airport-scale lightning prediction using station-based historical meteorological data. This setting has received limited attention in previous studies and combined LSTM and GRU within a single framework to improve sequence learning while maintaining computational efficiency, in contrast to previous single-model approaches. The experimental results show that the proposed model achieved a testing accuracy of 0.6716, with an F1-score of 0.71 and a Recall of 0.78 for the dominant lightning class. Although the model still showed limited performance in detecting rare lightning events due to class imbalance, the overall results indicate that the LSTM–GRU model has strong potential as a basis for an airport-scale early warning system and may help support safer, more reliable flight operations.
Adaptive Low-Power LoRa WSN for Real-Time Soil Monitoring in Remote Oil Palm Plantations
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.100568

Abstract

Oil palm plantations in remote regions such as Sebatik, North Kalimantan, face significant challenges in sustainable soil management due to limited infrastructure and dynamic peat soil conditions. Conventional monitoring methods lack real-time capability and energy efficiency. To address this, this research proposes a novel adaptive low-power LoRa-based Wireless Sensor Network (WSN) that dynamically adjusts sensing and transmission frequency based on real-time soil parameters—specifically, moisture, temperature, and pH. Unlike fixed-interval systems, the proposed architecture implements edge-based logic on ESP32 nodes to escalate sampling during critical events (e.g., pH ≤ 4.5) and reduce activity during stable periods, optimizing energy use without cloud dependency. The system integrates LoRa SX1278 modules, a RAK2245 gateway, ChirpStack for secure data routing, and OpenRemote for visualization and alerts. Field testing over 7 days in three micro-zones (roadside, plantation center, drainage) demonstrated robust performance with average Packet Delivery Ratios of 97.2%, 82.5%, and 88.3%, respectively, and a communication range of up to 2.8 km. Crucially, the adaptive strategy reduced daily power consumption to 7.8 mAh—58% lower than a fixed 10-minute schedule—extending theoretical battery life from 6–8 months to over 14 months. Sensor accuracy remained high (moisture error: 1.68%; temperature: 3.09%; pH: 1.47 units), enabling timely agronomic interventions such as targeted liming. This work contributes an environment-responsive WSN architecture that balances energy efficiency and event responsiveness, offering a scalable, deployable model for precision agriculture in tropical peripheral regions with acidic soils and intermittent connectivity.
IoT-Integrated PLC-SCADA Architecture for Energy Optimization in Material Processing
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.96402

Abstract

Despite the extensive studies on industrial automation and energy monitoring, most existing works focus on either PLC–SCADA automation or IoT-based monitoring separately. Only limited studies have experimentally integrated IoT, PLC, and SCADA into a unified architecture specifically for real-time energy optimization in material processing systems. The novelty of this research lies in three main contributions. First, this study proposes an integrated IoT–PLC–SCADA architecture specifically designed for adaptive energy management in material processing systems. Second, the proposed system implements real-time energy monitoring combined with adaptive PLC control logic to dynamically adjust process operation based on real-time sensor data. The results showed that the system succeeded in reducing average energy consumption by 12.2%, increasing process time efficiency by 9%, and recording a system uptime of 97.3%. The statistical test yielded a p-value of 0.0012, indicating that the energy reduction was statistically significant. In addition, the system proved to be accurate and reliable with sensor measurement deviations below 5%. Third, the proposed framework is experimentally validated through a quantitative pretest–posttest approach combined with statistical hypothesis testing to verify the significance of energy efficiency improvements. Therefore, this study contributes both technically and experimentally by providing a validated implementation model of intelligent industrial energy optimization based on IoT-integrated PLC–SCADA architecture.
Design and Implementation of Voice Control System for Mecanum Robot Using Whisper and Albert Pipeline on Raspberry Pi Platform
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.102212

Abstract

This study presents the design and implementation of a fully embedded offline voice control system for a Mecanum wheel robot integrating Whisper-based automatic speech recognition and ALBERT-based natural language understanding on a Raspberry Pi 4 platform. The proposed system supports parameterized motion commands with numerical value and unit extraction, enabling precise kinematic mapping without reliance on cloud services. The voice processing pipeline consists of audio acquisition, preprocessing, voice activity detection, speech transcription, intent classification, parameter extraction, kinematic transformation, and motor actuation. The system was trained on a custom dataset of 500 Indonesian navigation command samples spoken by five native speakers and evaluated on a separate test set of 200 commands. Experimental results demonstrate command recognition accuracy exceeding 95 percent and word error rates below 7.5 percent under moderate noise conditions. The system achieved an average end-to-end latency of 1.23 seconds. Motion execution errors remained below 5 percent within optimal parameter ranges, demonstrating sufficient precision for navigation tasks. Environmental robustness and reliability testing confirm stable performance in typical indoor environments. These results indicate that transformer-based speech and language models can be effectively deployed on resource-constrained embedded robotic platforms to enable practical real-time human–robot interaction. Specifically, the system addresses latency and privacy concerns associated with cloud-dependent solutions. The implementation demonstrates feasibility for educational and light industrial applications requiring offline capability.
System Testing and Performance Evaluation of an MQTT-Based IoT Monitoring System for Crop Cultivation
ELKHA : Jurnal Teknik Elektro Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v%vi%i.98306

Abstract

Agriculture is a crucial component of Indonesia's economy and food security. However, farmers have been using conventional techniques, such as planting according to a fixed timetable that is unaffected by weather or temperature. This will negative effect on the quality and yields of crops. Thus, a device is needed that can provide information about the weather or temperature. The message queuing telemetry transport (MQTT) is very helpful because it send data from the microcontroller to the display. This research aims to develop a prototype that displays measurement data utilizing MQTT and Node-RED, along with performance evaluations including latency, packet loss, and energy efficiency. This study employs an experimental approach that starts with a schematic design, followed by the installation and evaluation of a monitoring system. The outcome of this research indicates that the prototype worked performed well in an open farming field. System performance was assessed in terms of latency, packet loss, and energy efficiency. The results demonstrate stable operation during a 10-day field deployment, with an average latency of approximately 1.3 s, a packet loss rate of 1.38% and average power consumption of 1.25 W over 24 hours of continuous operation. These findings indicate that the proposed system is suitable for real-time agricultural monitoring under open-field conditions. The study emphasizes deployment feasibility and system-level performance rather than detailed agronomic analysis providing insights into the use of MQTT-based IoT solutions for open-field precision agriculture

Page 1 of 2 | Total Record : 11

 1   2 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 18 No.1 April 2026 Vol. 17 No.2 October 2025 Vol. 17 No.1 April 2025 Vol. 16 No.2 October 2024 Vol. 16 No.1 April 2024 Vol. 15 No.2 October 2023 Vol. 15 No.1 April 2023 Vol. 14 No. 2 October 2022 Vol. 14 No. 1 April 2022 Vol. 13 No. 2 October 2021 Vol. 13 No. 1 April 2021 Vol. 12 No. 2 October 2020 Vol. 12 No. 1, April 2020 Vol.11 No.2, October 2019 Vol. 11 No. 1, April 2019 Vol. 10 No. 2, October 2018 Vol. 10 No. 1, March 2018 Vol. 9 No. 2, October 2017 Vol. 9 No.1, March 2017 Vol 8, No 2 (2016): Edisi Bulan Oktober 2016 Vol 8, No 1 (2016): Edisi Bulan Maret 2016 Vol 7, No 2 (2015): Edisi Oktober 2015 Vol 7, No 1 (2015): Edisi Bulan Maret 2015 Vol 6, No 2 (2014): Edisi Bulan Oktober 2014 Vol 6, No 1 (2014): Edisi Bulan Maret 2014 Vol 5, No 2 (2013): Edisi Bulan Oktober 2013 Vol 5, No 1 (2013): Edisi Bulan Maret Vol 4, No 2 (2012): EDISI BULAN OKTOBER Vol 4, No 1 (2012): Edisi Bulan Maret Vol 3, No 2 (2011): Edisi Bulan Juli Vol 3, No 1 (2011): Edisi Bulan Maret Vol 2, No 3 (2010): Edisi Bulan November Vol 2, No 2 (2010): Edisi Bulan Juli Vol 2, No 1 (2010): Edisi Bulan Maret Vol 1, No 5 (2009): Edisi Bulan November Vol 1, No 4 (2009): Edisi Bulan Juli Vol 1, No 3 (2009): Edisi Bulan Maret Vol 1, No 2 (2008): Edisi Bulan November Vol 1, No 1 (2008): Edisi Bulan Juli More Issue