cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
,
INDONESIA
Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Published by IAES Indonesia Section and Partners
ISSN : 20893272     EISSN : -     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) is a peer reviewed International Journal in English published four issues per year (March, June, September and December). The aim of Indonesian Journal of Electrical Engineering and Informatics (IJEEI) is to publish high-quality articles dedicated to all aspects of the latest outstanding developments in the field of electrical engineering. Its scope encompasses the engineering of Telecommunication and Information Technology, Applied Computing & Computer, Instrumentation & Control, Electrical (Power), Electronics, and Informatics.
Arjuna Subject : -
Articles 858 Documents
 81   82   83   84   85 
Resolution–Accuracy Trade-offs in UAV-Based Semantic Segmentation for Precision Agricultural Imagery Mohamed Tawhid Amin; Aziza Ibrahim Hussein; Mohamed Mourad Mabrook
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.6512

Abstract

The paper explores resolution-accuracy trade-offs in UAV-based semantic segmentation for precision agricultural imagery, which is an important challenge in achieving computational efficiency while maintaining satisfactory results for semantic segmentation. It is widely believed that higher resolution imagery leads to more accurate results, but it also raises processing expenses and restricts the ability to deploy in real-time systems with unmanned aerial vehicles (UAV). This study comprehensively analyzes the effect of the spatial resolution (also known as Ground Sampling Distance (GSD)) on segmentation performance on a range of agricultural anomaly types. The agriculture-vision dataset is used in experimental runs of three different GSDs (10 cm, 20 cm and 40 cm per pixel) with UAV-acquired images. The standard semantic segmentation metrics (mean Intersection over Union (mIoU), Dice coefficient, and computational time analysis) are adopted to evaluate several deep learning models such as U-Net, R2U-Net, U-Net3+, Attention U-Net and DeepLabV3+. The results show that there is no clear correlation between achieving higher spatial resolution and achieving better segmentation accuracy. Medium resolution imagery (20 cm/pixel) can produce similar or better results for large scale anomalies, including dryness and nutrient deficiency, and at significantly lower computational costs. On the other hand, fine-grained anomalies require more fine-grained resolution to better display the anomalies, which shows that the best resolution depends on the task. Further, multi-scale feature aggregation models have higher robustness to resolution degradation. The findings offer a practical understanding of designing the resolution-aware model, which could lead to more efficient use of UAV for resolution-aware deployment, flight planning, and the implementation of edge-AI in precision agriculture. The study provides a data-driven tool for optimizing the spatial resolution versus accuracy versus efficiency of real-world monitoring systems in agriculture.
Deep Learning-Based Pest Insect Detection for Autonomous Agricultural Systems: Development and Field-Testing of a Custom Convolutional Neural Network Architecture Selim Sürücü; Berk Küçük; Mahammad Karimzade
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7672

Abstract

Global food security is under increasing threat from pest organisms that target agricultural production. The broad-spectrum pesticides traditionally used to combat these pests cause permanent damage to ecosystems, pose risks to human health, and lead to a critical decline in biodiversity. Precision agriculture technologies, as part of the Agriculture 4.0 revolution, offer innovative solutions to these problems. This study focuses on developing a novel artificial intelligence model capable of detecting and classifying pest insects with high accuracy, to serve as the intelligence for autonomous spraying systems. Within the scope of this research, a comprehensive and diverse dataset of over 12,000 images was meticulously compiled, featuring a total of 11 insect species, including 8 economically significant pests and 3 beneficial species for the ecosystem. To enhance the robustness and diversity of the dataset, advanced Generative Adversarial Networks (GANs) such as StyleGAN2-ADA were used alongside traditional data augmentation techniques to generate synthetic images. On this rich dataset, VGG-16 and ResNet152 V2 models, representing the transfer learning approach, were developed and comparatively analyzed against a lightweight Convolutional Neural Network (CNN) architecture custom-designed for resource-constrained edge computing devices. While the ResNet152 V2 model achieved the highest accuracy (92.4%) in laboratory tests, the custom-designed CNN model proved to be the most practical and effective solution in real-world field tests conducted with a Raspberry Pi-based prototype, delivering 82.5% accuracy, a much smaller model size (31 MB), and superior processing speed (7.5 FPS). These results strongly demonstrate that application-specific, lightweight models can exhibit more robust and efficient performance in real-world scenarios compared to complex and large transfer learning architectures. The developed system has the potential to make significant contributions to agricultural sustainability and food security by optimizing pesticide use.
Deep Learning Method for Wafer Flaw Detection in Lab-level Photolithography Subin Lee; Kyunghan Chun
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7975

Abstract

In this paper, we propose a deep learning-based method for wafer flaw detection and classification in lab-label photolithography, known as a core step of the semiconductor manufacturing process. In photolithography, defects due to particles or process errors are critical to product yield and reliability. To detect these flaws, images were collected and efficientnet deep learning method was applied. Data augmentation and model lightweighting techniques were also applied to improve the limitations of the dataset. experimental results showed the relation between model complexity and the amount of training data. For EfficientNetB5, the massive architecture, caused the overfitting problem because of learning even noise in small datasets. But EfficientNetB0, the lightweight model, with batch normalization and early stopping techniques shows improvement of the reliability. In conclusion, this study provides practical guidelines for building and efficient flaw detection method in a data-limited research environment.
Cost-effective Flex Sensor Glove-based Bangla Sign Language (BdSL) Interpreter for Resource-limited Settings Md. Sayzar Rahman Akash; Rethwan Faiz; Mohammad Hasan Imam; G.M. Tanvirul Islam; Sheikh Tanvir Alam; Jhon Dev; Nuzat Nuary Alam
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.6933

Abstract

In Bangladesh, approximately 13 million individuals experience hearing loss, including nearly 3 million with severe to profound impairments, creating significant communication barriers for the deaf and mute community. Most existing Bangla Sign Language (BdSL) interpretation systems rely on image-based approaches. However, these systems are sensitive to environmental conditions, require substantial computational resources, and often involve high implementation costs. To address these limitations, this paper presents a low-cost wearable BdSL interpreter based on flex sensor gloves and inertial sensing. The proposed system utilizes ten flex sensors to capture finger bending and two MPU6050 gyroscope modules to measure hand orientation. Sensor data are processed using a Threshold-Based Rule Classifier (TRC) algorithm running on an Arduino Mega 2560, eliminating the need for computationally intensive machine learning or image-processing techniques. The developed prototype recognizes a total of 25 BdSL gestures, comprising 10 numerals, 10 alphabet letters, and 5 commonly used words. The system provides both text and speech outputs to facilitate communication for hearing and visually impaired users. Experimental evaluation involving five volunteers demonstrated an overall recognition accuracy of 91.2%, with recognition accuracies of 98% for numerical gestures, 80% for alphabetical gestures, and 100% for word-level gestures. Confusion matrix analysis showed macro-F1 and weighted-F1 scores of 0.9798 for numerical gestures and 0.7991 for alphabetical gestures. The complete prototype was developed at a cost of approximately 100 USD using commercially available hardware components sourced from the local market. By avoiding dependence on cameras and high-performance computing platforms, the proposed system provides robust real-time performance under diverse environmental conditions while maintaining affordability and portability. The results demonstrate the potential of low-cost wearable technology to improve accessibility and promote inclusive communication for Bengali-speaking deaf communities in resource-limited settings.
An Electronic System for Woven Fabric Quality Control Based on Image Processing Jean Carlos Carpio; Jorge Calderon; Guillermo Kemper; Luis Ayala; Christian del Carpio
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7498

Abstract

This paper proposes the development of an electronic device that integrates image processing algorithms for quality control of woven fabrics by detecting three defects: holes, bumps, and stains. Although classic and deep learning-based image processing methodologies for detecting fabric defects exist in the literature, these proposals lack hardware integration with the software. The proposed device overcomes this limitation by integrating digital image processing algorithms implemented in Python on a single-board computer, along with control devices for the camera, lighting, and motor, to enable real-time fabric quality control. This adaptable architecture meets the needs of the textile industry and reduces the risks associated with manual inspection. The device was validated with 100 fabric samples evaluated by a textile engineering specialist, yielding a Cohen's Kappa index of 0.959 for light-colored fabrics and 0.869 for dark-colored fabrics, as well as an average inspection speed of 15.68 m/min.
SpineTrace: Auditable Video-Based Scoliosis Screening with Temporal Pose Statistics Teddy Surya Gunawan; Siti Aishah Sofea Asri; Mira Kartiwi; Noreha Abdul Malik; Ahmad Hud Mahfoodz; Mohd Ghaddafi Wahab
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 3: September 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i3.8257

Abstract

Video-derived gait representations may support scalable pre-referral screening for scoliosis, but their evaluation must retain borderline cases, quantify model vulnerability, and distinguish measured performance from clinical or deployment readiness. This study evaluates SpineTrace as an auditable compact engineering baseline rather than a novel learning algorithm or state-of-the-art classifier. The public Scoliosis1K release comprised 1,493 gait sequences reportedly obtained from 1,050 adolescents, including 493 positive, 200 neutral, and 800 negative sequences. The supplied partition of 744 training and 749 test sequences was reproduced exactly. Feature scaling and hyperparameter selection were restricted to five stratified folds within the training partition, with three-class classification designated as the primary task. Among the reproduced RBF-SVM configurations, the highest macro-F1 was obtained using 102 temporal pose features derived from keypoint means and standard deviations. The model achieved 0.737 accuracy, 0.740 balanced accuracy, 0.702 macro-F1, and 0.890 macro one-versus-rest ROC-AUC. Recall was 0.917, 0.619, and 0.685 for negative, neutral, and positive sequences, respectively, demonstrating the greater difficulty of borderline and positive cases. Adding three silhouette and five postural descriptors reduced macro-F1 to 0.656, indicating that semantically plausible handcrafted features did not provide complementary predictive information. Independently retuned PAV-SVM and DTW-kNN baselines achieved macro-F1 scores of 0.545 and 0.473, while a compact ST-GCN adaptation achieved 0.645±0.055 across three optimization seeds. Removing keypoint-confidence features from the full model reduced macro-F1 from 0.656 to 0.618, and coordinate jitter equivalent to 2% of torso length reduced it to 0.287, identifying pose quality as a critical vulnerability. Fixed-test uncertainty was estimated using 2,000 class-stratified sequence bootstraps. Because the local release lacks participant mappings and raw RGB videos, participant independence, cross-estimator transfer, end-to-end latency, and cross-dataset validity could not be established. SpineTrace therefore provides a reproducible sequence-level baseline for auditing feature utility and failure boundaries, not a diagnostic or deployment-ready screening system.
Leveraging Self-Supervised Transformers for Heat Pump Consumption Classification Using the HEAPO Dataset Hoang Thi Thu; Phi Dinh Huynh; Ta Trung Kien; Le Mai Nam; Le Hong Duy; Phan Hong Thing; Nguyen Viet Hung
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 3: September 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i3.7684

Abstract

Heat pumps play a crucial role in reducing carbon emissions in residential heating; however, their electricity consumption varies significantly across households, making large-scale performance assessment challenging. Existing data-driven approaches often rely on fully supervised learning and require extensive labeled data, which are costly to obtain through on-site inspections. This paper investigates whether routinely collected smart meter and weather data can be leveraged to automatically classify household heat pump electricity consumption into three categories: low, normal, and rather high. We propose a self-monitoring transformer framework that combines self-supervised pretraining and supervised fine-tuning for time series classification. A transformer encoder is first pre-trained on multi-day electricity consumption windows from largely unlabeled households using a reconstruction-based objective. The learned representations are then fine-tuned with a lightweight fully connected classifier on a limited labeled subset of the HEAPO dataset. Experimental results demonstrate that the proposed approach consistently outperforms state-of-the-art baselines, including RNN-, CNN-, and transformer-based time series models, achieving approximately 93% classification accuracy, an F1 score above 0.9, and a recovery rate close to 91%. These results indicate that self-supervised representation learning on smart meter data provides an effective and scalable solution for monitoring heat pump electricity consumption and supporting inspection planning.
Self-Interference Cancellation in In-band Full Duplex Systems (IBFD) Using Radial Basis Function Neural Networks (RBFNN) Khaled Gharaibeh
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 3: September 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i3.8090

Abstract

In-band Full Duplex (IBFD) wireless systems have attracted attention for use in emerging wireless systems as they provide significant enhancement to system capacity over traditional techniques. In IBFD, transmission and reception occur simultaneously and on the same frequency band. Thus, the main challenge in system design is self-interference (SI) where the strong transmit signal leaking to the receiver interferes with the weak received signal. SI typically includes a nonlinear component resulting from the transmitter Power Amplifier (PA); therefore, the resulting SI is highly dependent on transmit power. In this paper, an SI cancellation (SIC) scheme for IBFD systems is presented and verified. The proposed nonlinear SIC scheme is based on using a Radial Basis Function Neural Network (RBFNN) to model the nonlinear SI. A practically motivated feature representation which includes instantaneous power of the transmit signal is introduced, enabling efficient modelling of amplitude-dependent and memory-dependent nonlinearities. The proposed RBFNN canceller offers localized approximation capability and inherently stable training structure, making it suitable for addressing the SI dependence on transmit power. Simulation results demonstrate that the RBFNN-based SI canceller outperforms model-based cancellers such as the Memory Polynomial (MP) cancellers by 10 dB across a transmit power range of 30 dB.
Brain Tumor Analysis Using Multi-Scale CNN and Gated DenseNet-169 Ch Muralikrishna; Shanker Chandre
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 3: September 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i3.7233

Abstract

Brain tumors refer to the uncontrolled growth of cells in the human brain, posing a significant risk to human health. Therefore, early detection of these tumors are crucial. However, existing feature extraction approaches often fail to capture the intricate characteristics of tumors, leading to suboptimal classification performance. To address this limitation, a Multi-scale Convolutional Neural Network and Gated Channel Transformation unit-based DenseNet-169 model (MC-GCT-DenseNet-169) is proposed for efficient brain tumor classification. The multi-scale convolutional neural network captures the nonlinear relationships between texture, shape, and intensity in magnetic resonance images (MRI). The GCT function in the DenseNet-169 model enhances the ability to learn subtle variations in MRI such as tumor texture and boundary features, which are essential for accurate classification. Experimental results show that the MC-GCT-DenseNet-169 method attains accuracy of 98.97% on the Figshare dataset, surpassing previous approaches such as Cross-prior Bayesian attention mechanism with a Correlated Inception and Residual Learning Network (CB-CIRL Net).
Solar Drying System Based on Multi-Parameter AI Model Do Van Can; Nguyen Duy Khiem; Nguyen Minh Vuong; Le Thi Ngoc Loan
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 3: September 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i3.7882

Abstract

Agricultural drying strongly affects post-harvest product quality and storage stability. This study develops a smart solar drying system integrating multi-parameter sensing, electrical storage, water-based thermal storage, an Industrial IoT V-box, and a Siemens S7-1200 PLC. Temperature, relative humidity, solar irradiance, airflow, and CO₂ concentration were monitored to characterize the drying environment. A hierarchical Random Forest framework was developed to estimate the chamber temperature, relative humidity, and coffee moisture content. Leave-one-day-out validation yielded pooled R2 values of 0.909 and 0.890 for indoor temperature and relative humidity, respectively. The moisture model achieved R2=0.882, MAE = 0.472 percentage points, and RMSE = 0.740 percentage points against the sensor reference. The Random Forest models were executed on the V-box, while the PLC acquired sensor data and controlled the actuators. The results demonstrate the feasibility of integrating data-driven estimation with PLC-based supervision for solar coffee drying.

Page 83 of 86 | Total Record : 858

 81   82   83   84   85 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 3: September 2026 Vol 14, No 3: September 2026 Vol 14, No 2: June 2026 Vol 14, No 1: March 2026 Vol 13, No 4: December 2025 Vol 13, No 3: September 2025 Vol 13, No 2: June 2025 Vol 13, No 1: March 2025 Vol 12, No 4: December 2024 Vol 12, No 3: September 2024 Vol 12, No 2: June 2024 Vol 12, No 1: March 2024 Vol 11, No 4: December 2023 Vol 11, No 3: September 2023 Vol 11, No 2: June 2023 Vol 11, No 1: March 2023 Vol 10, No 4: December 2022 Vol 10, No 3: September 2022 Vol 10, No 2: June 2022 Vol 10, No 1: March 2022 Vol 9, No 4: December 2021 Vol 9, No 3: September 2021 Vol 9, No 2: June 2021 Vol 9, No 1: March 2021 Vol 8, No 4: December 2020 Vol 8, No 3: September 2020 Vol 8, No 2: June 2020 Vol 8, No 1: March 2020 Vol 7, No 4: December 2019 Vol 7, No 3: September 2019 Vol 7, No 2: June 2019 Vol 7, No 1: March 2019 Vol 6, No 4: December 2018 Vol 6, No 3: September 2018 Vol 6, No 3: September 2018 Vol 6, No 2: June 2018 Vol 6, No 1: March 2018 Vol 5, No 4: December 2017 Vol 5, No 3: September 2017 Vol 5, No 2: June 2017 Vol 5, No 1: March 2017 Vol 4, No 4: December 2016 Vol 4, No 3: September 2016 Vol 4, No 2: June 2016 Vol 4, No 1: March 2016 Vol 3, No 4: December 2015 Vol 3, No 3: September 2015 Vol 3, No 2: June 2015 Vol 3, No 1: March 2015 Vol 2, No 4: December 2014 Vol 2, No 3: September 2014 Vol 2, No 3: September 2014 Vol 2, No 2: June 2014 Vol 2, No 1: March 2014 Vol 1, No 4: December 2013 Vol 1, No 3: September 2013 Vol 1, No 2: June 2013 Vol 1, No 1: March 2013 More Issue