cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
sulistiyanto
Contact Email
yantog98@gmail.com
Phone
+6281332986888
Journal Mail Official
jeecom@unuja.ac.id
Editorial Address
https://ejournal.unuja.ac.id/index.php/jeecom/about/editorialTeam
Location
Kab. probolinggo,
Jawa timur
INDONESIA
Journal of Electrical Engineering and Computer (JEECOM)
Published by Universitas Nurul Jadid
ISSN : 27150410     EISSN : 27156427     DOI : -
Core Subject : Science, Engineering,
Control & Systems Engineering Electrical & Electronics Engineering Energy
Journal of Electrical Engineering and Computer (JEECOM) is published by Engineering Faculty of Nurul Jadid University, Probolinggo, East Java, Indonesia. This journal encompasses research articles, original research report, : 1) Power Systems, 2) Signal, System, and Electronics, 3) Communication Systems, 4) Information Technology, etc.
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 248 Documents
 21   22   23   24   25 
Design And Build An Early Warning System For Health Conditions In Climbers Based On Fuzzy Logic Ahlul A'raaf Femas Salsabil; Agus Hayatal Falah; Jamaaluddin Jamaaluddin; Indah Sulistiyowati
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.15028

Abstract

Mountain climbing is currently being popular with the public, both young people and adults. However, there are still many people who are indifferent to the physiological conditions and environmental conditions that exist on the climb. This study aims to combine these two factors, namely physiological factors and environmental factors as an effort to minimize the occurrence of accidents in climbing activities. Physiological factors, namely oxygen saturation and heart rate, are combined with environmental factors of air pressure, which will later be processed with fuzzy logic consisting of 27 rule bases. The test results on the sensor showed high accuracy with an average value of 98.21% for SpO2, 98.01% for heart rate, and 99.10% for air pressure. At the time of the air pressure value of <750 hPa the system is also capable of giving an alarm as a warning. Fuzzy logic testing  is quite effective in determining a climber's health status, where the system consistently assigns a "Normal" status at low altitudes, changes to "Alert" when the air pressure begins to decrease, until it reaches a "Danger" status in extreme conditions. This proves that the system is able to provide an early warning on the condition of a climber.
Design and Development of an IoT-Based Household Electrical Energy Monitoring Application for Energy Efficiency Luluk Suhartini; Fadila Fadila
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16648

Abstract

Electricity consumption in households is often not properly controlled, which can lead to energy waste and higher electricity bills. Therefore, a system is needed to monitor household electricity usage in real time and provide users with clear information to help them take energy-saving actions. This study designs and develops an Internet of Things (IoT)-based household electricity monitoring application using a PZEM-004T sensor connected to a NodeMCU ESP8266 microcontroller. The measured data, including voltage, current, power, and energy consumption, are transmitted wirelessly to a server and displayed on a custom web-based dashboard without relying on third-party IoT platforms. The application features real-time monitoring and historical consumption records, enabling users to track energy usage trends. Test results show that the system can measure and display data accurately with an average transmission delay of 1–2 seconds, and it helps identify energy-intensive household appliances. Thus, this application can be an effective solution to improve energy efficiency in households.
Flower Pollination Algorithm-Based MPPT for PEM Fuel Cells with Interleaved Buck-Boost Converter Pressa Perdana Surya saputra; Zainal Mustakim; Heri Ardiansyah
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16680

Abstract

This study proposes an enhanced maximum power point tracking (MPPT) system for protons exchange membrane fuel cell (PEMFC) by integrating a Flower Pollination Algorithm (FPA)-based controller with an IBBC (interleaved buck–boost converter). The non-linear behavior of electrochemical properties of PEMFCs pose significant challenges to conventional MPPT techniques, which often struggle to maintain accurate and stable power tracking under varying operating conditions. Many existing approaches rely primarily on properties like as membrane water content, hydrogen pressure and cell temperature to regulate converter operation. Proposed FPA-based MPPT method improves tracking accuracy and dynamic performance in response to changes in content of membrane water and temperature. In addition, interleaved buck–boost topology reduces output current ripple and distributes current stress across switching devices, contributing to enhanced efficiency and system stability. Simulation results demonstrate that the proposed strategy achieve convergence faster to maximum power point, lower steady-state oscillations, and improved power extraction efficiency compared with conventional MPPT methods across diverse PEMFC operating scenarios.
Real-Time Monitoring of Solar Battery and Lamp Conditions Using Internet of Things Affan Bachri; Arief Budi Laksono; Eko Wahyu Santoso; Achmad Rifqi Adi Firmansyah
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16851

Abstract

Solar photovoltaic battery systems require continuous observation to prevent unnoticed voltage decline, abnormal temperature, and lamp failure. This study developed a compact Internet of Things monitoring prototype using an ESP32 microcontroller, an INA219 sensor for voltage, current, and power, an LM35 sensor for battery temperature, and a light-dependent resistor for lamp-state detection. Sensor data were shown locally on a 16x2 liquid-crystal display and transmitted through Wi-Fi to a Blynk dashboard at a five-second update interval. The study applied experimental and engineering research procedures covering hardware design, software integration, component validation, and integrated tests under off, three load, and charging conditions. The INA219 achieved average accuracies of 99.69% for voltage, 99.32% for current, and 99.49% for power, while the LM35 reached 97.08% accuracy. The light sensor correctly separated the tested off condition at 3 lux from lamp-on conditions between 230 and 2100 lux. Across all operating modes, the local display and Blynk presented consistent measurements, and negative current reliably indicated charging. The prototype therefore provides accessible real-time monitoring of battery electrical behavior, temperature, charging direction, and lamp status, although long-term data logging and field-scale validation remain necessary.
Hybrid Lexicon and Logistic Regression Sentiment Analysis of YouTube Comments on Suharto’s National Hero Designation Laksmita Dewi Supraba; Andi Sunyoto; Setyo N
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16845

Abstract

This study proposes a hybrid approach to sentiment analysis by combining lexicon and Logistic Regression methods based on TF-IDF features, and using Multinomial Naive Bayes as a benchmark, to classify YouTube comments related to Suharto's appointment as a National Hero. The dataset contains 500 comments TV taken from five YouTube channels: TalkShow tvOne Reload, Kompas Madiun, Tribunnews, Perspektif, and Tempodotco, 100 comments each. The research stages include text pre-processing, lexicon development, automatic labeling, manual validation of annotations, TF-IDF feature extraction, and sentiment classification. The validation results show a 63% agreement between lexicon labels and manual annotations, with a Cohen's Kappa of 0.15 indicating low inter-annotation agreement. The proposed Logistic Regression framework achieved an overall accuracy of 91%, with a weighted average F1 score of 0.87 and a Macro F1 score of 0.43, slightly better than Naïve Bayes Multinomial, which achieved an accuracy of 90% and a weighted F1 score of 0.85. However, the relatively small performance improvement and high accuracy affected the dominance of the neutral class. The Confusion Matrix for the data shows that the model still has difficulty distinguishing between positive and negative comments the recall for the negative class is 0%, and for the positive class is 20%. Therefore, these results are still preliminary and cannot be generalized.
Price-Incentive Distribution Grid Load Scheduling Using Hybrid Grey Wolf Optimization Biobele Alexander Wokoma; Kinba Queen Blue-Jack
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 2 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i2.16815

Abstract

Distribution feeders increasingly require load schedules that respond to time-varying prices while preserving operational limits. This paper presents a Hybrid Grey Wolf Optimizer (HGWO) for 24-hour distribution grid load scheduling underprice incentives. The method augments the leader-guided position update of the conventional Grey Wolf Optimizer with a momentum-based directional term and evaluates candidate schedules through a penalty-aware objective that combines energy price, incentive reward, and constraint violations. The model was implemented in MATLAB and assessed using hourly price, base-load, and incentive data obtained for a representative 11 kV feeder of the Port Harcourt Electricity Distribution Company. Thirty independent runs were conducted and compared with classical GWO. HGWO attained a best objective value of 38,910 ¢, approximately 2.3% below the GWO result, and reached a stable solution in 58 iterations compared with 82 iterations. Its standard deviation decreased from 760 ¢ to 412 ¢, indicating more consistent search performance. Sensitivity tests on penalty coefficient and population size further showed lower and flatter objective responses. The results demonstrate that HGWO can improve convergence speed, robustness, and price-responsive peak-load redistribution for day-ahead feeder scheduling.
Explainable Machine Learning for Predicting Student Dropout and Academic Success Using XGBoost and SHAP Sidik Praptomo; Ahmad Risman; Riko Muhammad Suri
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16978

Abstract

Student dropout is a persistent challenge in higher education, and predictive models can support early identification of students who may require academic or financial intervention. This study develops an explainable multiclass machine learning approach to predict three academic outcomes—Dropout, Enrolled, and Graduate—using the public Predict Students' Dropout and Academic Success dataset containing 4,424 student records. Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) were compared using a stratified 80:20 hold-out design. XGBoost hyperparameters were optimized through randomized search with five-fold stratified cross-validation, and SHapley Additive exPlanations (SHAP) were used to interpret global and class-specific predictions. Random Forest achieved the highest overall accuracy of 77.18%, whereas the optimized XGBoost model produced the highest macro recall of 69.58% and macro F1-score of 70.08%. XGBoost improved recall for the minority Enrolled class to 46.54%, compared with 38.36% for Random Forest and 33.33% for Logistic Regression. SHAP analysis identified the number of curricular units approved in the second and first semesters, tuition-fee status, course, second-semester grade, and age at enrollment among the most influential predictors. Low academic progression and unpaid tuition status contributed strongly toward Dropout predictions, while stronger academic progression shifted predictions toward Graduate. These findings show that explainability complements predictive performance by revealing actionable patterns behind multiclass student-outcome predictions.Student dropout is a persistent challenge in higher education, and predictive models can support early identification of students who may require academic or financial intervention. This study develops an explainable multiclass machine learning approach to predict three academic outcomes—Dropout, Enrolled, and Graduate—using the public Predict Students' Dropout and Academic Success dataset containing 4,424 student records. Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) were compared using a stratified 80:20 hold-out design. XGBoost hyperparameters were optimized through randomized search with five-fold stratified cross-validation, and SHapley Additive exPlanations (SHAP) were used to interpret global and class-specific predictions. Random Forest achieved the highest overall accuracy of 77.18%, whereas the optimized XGBoost model produced the highest macro recall of 69.58% and macro F1-score of 70.08%. XGBoost improved recall for the minority Enrolled class to 46.54%, compared with 38.36% for Random Forest and 33.33% for Logistic Regression. SHAP analysis identified the number of curricular units approved in the second and first semesters, tuition-fee status, course, second-semester grade, and age at enrollment among the most influential predictors. Low academic progression and unpaid tuition status contributed strongly toward Dropout predictions, while stronger academic progression shifted predictions toward Graduate. These findings show that explainability complements predictive performance by revealing actionable patterns behind multiclass student-outcome predictions.
Water Level and Solar Panel Power Monitoring System Based on the Internet of Things (IoT) Affan Bachri; Abdur Rohman Wakhid; Muhammad Aflah Kafabi
Journal of Electrical Engineering and Computer (JEECOM) Vol 7, No 2 (2025)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v7i2.16852

Abstract

Water storage management still requires direct supervision in many household and small-scale applications, while a remote monitoring system also needs a reliable energy supply. This study develops an integrated Internet of Things system that measures water level and photovoltaic electrical parameters in real time. The prototype uses an ESP32, a waterproof JSN-SR04T ultrasonic sensor, two INA219 modules, a 20 Wp solar panel, a PWM solar charge controller, a 12 V battery, ThingSpeak, and a Telegram Bot. Testing covered microcontroller connectivity, distance measurement accuracy, electrical sensing, solar panel output, battery operation, cloud data delivery, and integrated system performance. The JSN-SR04T produced an average reading of 10.16 cm for a 10.00 cm reference, with an average absolute deviation of 0.16 cm. INA219 voltage measurements showed a mean relative error of 2.91% against a multimeter. During integrated testing, the water level remained at 12.0-12.4 cm, solar panel voltage reached 13.44-13.45 V, and panel power reached 4.40-4.41 W. ThingSpeak displayed the measurements continuously, while Telegram delivered synchronized status information. These results show that the proposed system supports remote water-level and energy-source monitoring using an autonomous solar supply.

Page 25 of 25 | Total Record : 248

 21   22   23   24   25 

Filter by Year

2019 2026


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