cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Bambang Sumantri
Contact Email
bambang@pens.ac.id
Phone
+62315947280
Journal Mail Official
jeis@journals.pens.ac.id
Editorial Address
Politeknik Elektronika Negeri Surabaya Jalan Raya ITS Sukolilo Kampus PENS Surabaya, 60111, Indonesia
Location
Kota surabaya,
Jawa timur
INDONESIA
Journal of Electrical and Intelligent Systems (JEIS)
Published by Politeknik Elektronika Negeri Surabaya
ISSN : -     EISSN : 31637663     DOI : -
Core Subject :
Journal of Electrical and Intelligent Systems (JEIS) is a peer-reviewed scientific journal that publishes original research articles and review papers in electrical engineering, electronics, and intelligent systems. The journal serves as an interdisciplinary platform for researchers, academics, and practitioners to disseminate innovative theories, methodologies, and applications related to modern electrical and intelligent technologies. JEIS covers a broad range of topics including control, automation, and robotics; electronics, VLSI, and embedded systems; signal, image, and data processing; artificial intelligence and edge computing; sensors and industrial electronics; power systems and smart grid technologies; power electronics and electric drives; renewable energy and energy storage; as well as electric vehicles and transportation electrification. Emphasis is placed on both theoretical developments and practical implementations that address current industrial, societal, and technological challenges. By promoting high-quality research and rigorous peer-review processes, JEIS aims to advance intelligent, sustainable, and efficient electrical and electronic systems while fostering collaboration between academia and industry at the national and international levels.
Arjuna Subject : -
Articles 10 Documents
 1 
Experimental Validation of Enhanced Artificial Rabbit Optimization (ARO)-Based MPPT Method for Photovoltaic Systems Under Partial Shading Conditions Moh. Zaenal Efendi; Ircham Badrus Rahmadani; Muhammad Rizani Rusli
Journal of Electrical and Intelligent Systems Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i1.1

Abstract

Partial shading often introduces multiple local maxima into the power–voltage (P-V) characteristics of photovoltaic (PV) systems, which makes conventional maximum power point tracking (MPPT) methods prone to converging to suboptimal operating points. To overcome this challenge, this study proposes an Enhanced Artificial Rabbit Optimization (ARO)-based MPPT method by incorporating a time-varying adaptive inertia-weight mechanism, enabling more accurate global maximum power point (GMPP) tracking under nonlinear irradiance conditions. The proposed method was experimentally validated on a laboratory-scale PV platform consisting of three series-connected PV modules, a SEPIC converter, and an STM32-based controller tested under four irradiance patterns. The GMPP reference values were determined through direct experimental P-V scanning. The experimental results indicate that the enhanced method consistently performed better than the conventional ARO baseline, achieving a maximum output power of 98.68 W with a tracking accuracy of 99.93%. Across all test cases, the extracted power and tracking accuracy improved by an average of 1.24% and 1.21%, respectively, without a noticeable increase in tracking time.
Development of a UWB-Based Trilateration System for Multi-Mobile Node Indoor Localization Hary Oktavianto; Haniif Mulya Wicaksana; Audra Annisa Zhafirah; Mohammad Syafrudin; Prima Kristalina; Bambang Sumantri
Journal of Electrical and Intelligent Systems Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i1.3

Abstract

Accurate indoor localization is essential for navigation and coordination in multi-agent systems, particularly in environments where Global Positioning System (GPS) signals are unavailable. While ultrawideband (UWB)-based trilateration has been widely studied, most existing works focus on single-node localization and do not explicitly address scalability in terms of computational cost and processing time. This study proposes a scalable multi-mobile node localization framework based on UWB trilateration, with a key contribution in demonstrating linear computational growth with respect to the number of mobile nodes. The system employs UWB DWM1000 modules and the Symmetrical Double-Sided Two-Way Ranging (SDS-TWR) method to estimate distances between mobile nodes and anchor nodes, followed by onboard trilateration for position estimation. Experimental validation is conducted using up to four simultaneous mobile nodes within a 10×10 m indoor environment. The results show that the proposed system maintains centimeter-level accuracy, with RMSE values of 10.08 cm, 11.46 cm, 12.25 cm, and 9.13 cm for nodes 1 to 4, respectively. More importantly, the processing time increases consistently from 55 ms (one node) to 115 ms (four nodes), exhibiting an approximately constant incremental cost of 20 ms per additional node, which confirms the linear scalability of the proposed approach. These findings highlight that the proposed system not only achieves reliable localization accuracy but also ensures predictable and efficient computational performance, making it suitable for real-time multi-node applications such as robot swarm coordination and collaborative autonomous systems.
Automatic Control of Oxygen Flow for Hypoxemia Therapy Based on Fuzzy Method Rika Rokhana; Santi Anggraini; Retno Sukmaningrum; Hary Oktavianto; Paulus Susetyo Wardana; Agrippina Waya Rahmaning; Moch. Rochmad; Kemalasari Kemalasari; Hendhi Hermawan; Zainal Arief
Journal of Electrical and Intelligent Systems Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i1.2

Abstract

Hypoxemia is a serious condition that requires oxygen transfusion. Indiscriminate oxygen administration is a poor strategy that can increase organ damage and even death. This paper describes a system for automatically controlling airflow of an oxygen tubes to a patient based on blood oxygen saturation and respiratory rate measurements. The MAX30102 sensor is used to measure oxygen saturation levels, and the MAX9814 module is used to determine respiratory rate. Both sensor outputs are processed by an STM32F411 microcontroller, and then sent wirelessly to an Arduino Uno microcontroller, which implements the fuzzy logic controller to control oxygen flow. The fuzzy output is used to activate a motor servo that controls the oxygen tube valve opening. The valve opening width (in degrees) is divided into 5 categories. Communication between the microcontroller and the valve actuator uses a 433MHz wireless RF module. The device test results revealed an MAE of 0.40% for oxygen saturation measurements compared to standard hospital measuring instruments and an MAE of 0.47% for respiratory rate measurements compared to manual measurements. Overall system testing produced a valve opening with an MAE of 0.56% compared to simulation results using MATLAB.
Performance Analysis of a Voice-Integrated Overtaking Assistance Application based on LiDAR and Fuzzy Logic Dafit Ody Endriantono; Dedid Cahya Happyanto; Niam Tamami
Journal of Electrical and Intelligent Systems Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i1.4

Abstract

This research aims to enhance driver situational awareness during high-risk overtaking maneuvers by developing Navienta (Navigation Intelligent Assistant), a localized AI-powered navigation assistant. Conventional driver assistance systems often suffer from high latency and cloud dependencies that compromise real-time safety. To address these challenges, we implemented a localized edge-computing architecture utilizing a TF-350 LiDAR sensor and an Intel NUC as a processing hub, specifically designed to facilitate a high-speed, voice-driven interface. The system utilizes an Extended Kalman Filter (EKF) and a Mamdani Fuzzy Inference System (FIS) as the computational core to transform complex environmental dynamics into instantaneous voice instructions, ensuring low-latency feedback for the driver. The scientific contribution of this work lies in the synergistic integration of kinematic smoothing and fuzzy decision-making within a fully localized, high-concurrency architecture, eliminating cloud-dependency for safety-critical maneuvers. Experimental results confirm the system's precision with an average relative distance error of 0.22% and a consistent 50 ms end-to-end latency via a high-concurrency Golang backend. Experimental trials demonstrated that the localized Sherpa-ONNX engine achieved a 95.1% command recognition rate, which directly contributed to a significant 38.8% reduction in driver reaction time (from 1.8s to 1.1s). By maintaining operational integrity without external API dependencies, the Navienta framework provides a robust, cross-platform solution for modern intelligent transportation systems, offering a reliable approach for localized, safety-critical driver assistance.
Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception Gusty Anugrah; Dedid Cahya Happyanto; Eru Puspita
Journal of Electrical and Intelligent Systems Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i1.5

Abstract

Conventional object detection systems in Intelligent Transportation Systems (ITS) commonly operate in a frame-wise manner, leading to temporally inconsistent predictions under dynamic conditions. This paper proposes a motion-consistent object detection framework that integrates velocity-constrained filtering to enforce physical plausibility across consecutive frames. The main contribution of this work lies in explicitly formulating detection validation as a deterministic velocity-bounded constraint problem, enabling direct integration of motion dynamics into the perception pipeline rather than treating motion as auxiliary information. The system employs a lightweight YOLO11s-based detector for visual perception and GPS-based motion estimation to provide real-world velocity constraints. Experiments are conducted on a traffic infrastructure dataset comprising 52,135 images across 33 classes and evaluated on an Intel NUC 13 Pro edge computing platform. Results demonstrate that the proposed method improves temporal stability compared to conventional frame-wise detection while maintaining strong detection performance, achieving an mAP@0.5 of 0.945 at 20 FPS. The findings indicate that incorporating explicit motion constraints enhances detection reliability without introducing significant computational overhead. However, performance may degrade under low-speed GPS noise and challenging visual conditions such as occlusion, highlighting limitations for future improvement.
Driver Fatigue Detection Using YOLOv5 with Genetic- Algorithm-Based Hyperparameter Optimization and Fine-Tuning Strategies Hendri Darmawan; Zulfa Muflihah; Giran Arisdi
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.7

Abstract

Driver fatigue is a major contributor to traffic accidents, injuries, and economic losses. This study proposes a computer-vision-based driver fatigue detection system using YOLOv5s to identify three facial states: normal, eye closed, and yawning. The model is fine-tuned from pre-trained COCO weights and evaluated under multiple training schemes, including full fine-tuning, partial layer freezing, and hyperparameter evolution based on a genetic algorithm. The dataset consists of 5,706 training images and 2,390 testing images compiled from self-recorded and public sources under varied lighting conditions. Experimental results show that the best model without evolution achieves an mAP of 0.887, while the best evolved model reaches an mAP of 0.888 and runs at 30 FPS on a CPU-based device. These findings indicate that the proposed model is sufficiently accurate, lightweight, and practical for early-warning deployment on low- resource edge devices in advanced driver assistance systems.
YOLO-Based Vehicle Detection and Classification for Multi-Lane Free Flow Systems Nihayatus Sa'adah; Faridatun Nadziroh; Rahardhita Widyatra Sudibyo; Haniah Mahmudah; Fitri Fitriah; Hari Wahjuningrat Suparno; Muhammad Hendra Syahputra
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.6

Abstract

Multi-Lane Free Flow (MLFF) systems have emerged as a promising approach to reducing congestion at toll gates by enabling uninterrupted toll transactions without requiring vehicles to stop. To support this implementation, this study proposes a YOLOv9-based vehicle detection and classification system optimized using grid search and the SGD optimizer. The proposed system is designed for edge computing deployment and evaluated in a real multi-lane toll environment using an NVIDIA Jetson AGX Orin device. Experimental results show that the optimized model achieves a mean Average Precision at IoU threshold 0.50 (mAP@50) of 92.6%, an F1-score of 92.0%, and an inference time of 70.8 ms, corresponding to 14.1 FPS. These results indicate that the proposed system provides a balanced trade-off between detection accuracy and computational efficiency for edge-based MLFF applications. Unlike previous studies that primarily evaluated vehicle classification models using offline datasets, this study includes implementation and testing in a real multi-lane toll scenario. The findings demonstrate the potential of YOLO-based vehicle detection and classification to support practical MLFF deployment, although further evaluation under more diverse traffic, lighting, and environmental conditions is still required.
Study of Acoustic Characterization for Reinforcing Steel Using Ultrasonic Waves Thofail Syakirudin; Agus Indra Gunawan; Widita Trisniani; Oskar Natan
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.8

Abstract

The reuse of reinforcing steel bars in construction is a common practice to reduce material costs. However, bending and re-straightening processes may cause changes in mechanical properties and internal defects that are difficult to detect visually. Conventional material evaluation often relies on Destructive Testing (DT), which damages the specimen. Therefore, an accurate evaluation method is needed without damaging the material. This study aims to design and develop a portable and cost-effective Non-Destructive Testing (NDT) device to analyze the serviceability characteristics of reinforcing steel bars using the Ultrasonic Testing (UT) method based on Time of Flight (ToF). The analyzed parameters include ToF and signal amplitude. Tests were conducted on straight, bent, and re-straightening reinforcing bars with a length of 1 m and diameters of 12 mm and 14 mm. The results showed that the ultrasonic wave velocity in straight reinforcing bars was 4973.66 m/s (12 mm) and 4975.37 m/s (14 mm). In bent reinforcing bars, the velocity decreased to 4394.56 m/s (12 mm) and 4216.24 m/s (14 mm). In re-straightened reinforcing bars, the velocity increased to 4774.35 m/s (12 mm) and 4495.96 m/s (14 mm). These results indicate that the straightening process can partially restore the acoustic characteristics of reinforcing bars, making them closer to those of straight reinforcing bars. However, residual deformation still remains in the material.
Design of an IoT-Based Smart Pole for Detecting Manipulation of Plantation Boundary Markers Alwansyah Muhammad Mahardhika Endrawan; Mohammad Syafrudin; Ali Husein Alasiry
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.10

Abstract

Boundary markers are vulnerable to displacement and manipulation, while conventional inspection methods are unable to provide real-time monitoring. This study proposes an Internet of Things (IoT)-based Smart Pole system integrating a uBlox NEO-M8N GNSS module, HMC5883L magnetometer, LoRa EBYTE E32 communication, SIM7600G-H cellular gateway, and a solar-powered subsystem for autonomous boundary marker monitoring. System performance was evaluated through sensor accuracy, communication reliability, and integrated testing. Results showed that the GPS module achieved an average positioning error of 1.60 m (89.33% accuracy), while the HMC5883L achieved an average orientation error of 3.11%, with a maximum MAE of 1.70° and RMSE of 2.05°. The LoRa EBYTE E32 achieved an average PDR of 97.75% with 2.25% packet loss, whereas the SIM7600G-H gateway achieved a 97.0% success rate with 3.0% communication error. The solar subsystem, consisting of a 30 W photovoltaic panel and a 12 V 7.5 Ah SLA battery, provided stable autonomous operation. Integrated testing confirmed reliable detection of displacement and orientation changes, real-time dashboard visualization, and Telegram alert delivery. These results demonstrate that the proposed Smart Pole is a reliable and energy-autonomous solution for real-time plantation boundary marker monitoring.
Performance and Energy Evaluation of Multi-Hop Network Topologies for Water Distribution Monitoring Wilhan Jechovanda Susanto; Agus Indra Gunawan; Rahardhita Widyatra Sudibyo
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.9

Abstract

Real-time monitoring of urban water distribution systems has become a critical requirement in modern smart urbanization, rendering traditional manual monitoring and data recording methods obsolete. To overcome these challenges, this paper presents a comprehensive study on the empirical evaluation of power consumption and communication performance in a low-cost Wireless Sensor Network (WSN) using the NRF24L01+ transceiver. Although natively restricted to basic point-to-point and single-level star topologies, a custom multi-hop routing protocol utilizing an advanced octal addressing scheme was developed to enable multi-tier network scalability. Three network topologies Star, Tree, and Series Tree were implemented and combined with two message scheduling mechanisms: By-Request polling and Round-Robin data aggregation. The system was subjected to rigorous testing under both Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) conditions across complex, obstacle-dense environments including concrete walls and heavy foliage. The experimental results reveal that the proposed multi-hop framework successfully achieves a 0% packet loss rate across seven obstacle zones where traditional Peer-to-Peer (P2P) connections fail entirely. Furthermore, the By-Request scheduling combined with a Series Tree topology demonstrated superior energy efficiency, requiring a minimal total power output of only 91.86 mWh over an operational period of one hour. Balancing data rates between 250 Kbps and 2 Mbps provides optimal real-time monitoring stability and low latency (6 ms per node). These findings provide a scalable, highly cost-effective blueprint for large-scale municipal water asset management.

Page 1 of 1 | Total Record : 10

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 1 No. 2 (2026): September Vol. 1 No. 1 (2026): April