cover
Contact Name
Furizal
Contact Email
sjer.editor@gmail.com
Phone
+6282386092684
Journal Mail Official
sjer.editor@gmail.com
Editorial Address
Jl. Poros Seroja, Kesra, Kepenuhan Barat Sei Rokan Jaya, Kec. Kepenuhan, Kab. Rokan Hulu, Riau
Location
Kab. rokan hulu,
Riau
INDONESIA
Scientific Journal of Engineering Research
ISSN : -     EISSN : 31091725     DOI : https://doi.org/10.64539/sjer
Core Subject : Engineering,
The Scientific Journal of Engineering Research (SJER) is a peer-reviewed and open-access scientific journal, managed and published by PT. Teknologi Futuristik Indonesia in collaboration with Universitas Qamarul Huda Badaruddin Bagu and Peneliti Teknologi Teknik Indonesia. The journal is committed to publishing high-quality articles in all fundamental and interdisciplinary areas of engineering, with a particular emphasis on advancements in Information Technology. It encourages submissions that explore emerging fields such as Machine Learning, Internet of Things (IoT), Deep Learning, Artificial Intelligence (AI), Blockchain, and Big Data, which are at the forefront of innovation and engineering transformation. SJER welcomes original research articles, review papers, and studies involving simulation and practical applications that contribute to advancements in engineering. It encourages research that integrates these technologies across various engineering disciplines. The scope of the journal includes, but is not limited to: Mechanical Engineering Electrical Engineering Electronic Engineering Civil Engineering Architectural Engineering Chemical Engineering Mechatronics and Robotics Computer Engineering Industrial Engineering Environmental Engineering Materials Engineering Energy Engineering All fields related to engineering By fostering innovation and bridging knowledge gaps, SJER aims to contribute to the development of sustainable and intelligent engineering systems for the modern era.
Articles 7 Documents
Search results for , issue "Vol. 2 No. 3 (2026): September (in Process)" : 7 Documents clear
Enhancing the Mechanical Properties of Concrete Using Natural Fiber Reinforcement: A Comparative Study of Bamboo, Banana, and Jute Fibers Rabbani, Md. Liton; Islam, Md. Rashedul; Pulok, Md. Shahoriar; Hasan, Rakibul; Mamun, Md. Shaheen Al; Roy, Dhruboraj; Shiuly, Rafaun Sultana; Hasan, Md. Atiqul
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.458

Abstract

With the construction industry seeking to mitigate its carbon footprint, utilizing agricultural by-products as reinforcement offers a promising pathway toward eco-friendly infrastructure. While previous studies have explored synthetic fibers, there remains a critical research gap in the comparative performance and statistical consistency of diverse natural fibers like banana, jute, and bamboo within a concrete matrix. This study investigates the mechanical properties of concrete mixes incorporating these fibers at varying volume fractions (0.5%–2.0%). The evaluation focuses on compressive, split tensile, and flexural strengths at 7-day and 28-day curing intervals. Key findings reveal that banana fiber at 0.5% achieved the highest absolute compressive and flexural strengths of 37.32 MPa and 6.12 MPa, respectively, after 28 days. However, performance for banana and jute fibers generally declined at higher dosages due to increased porosity. Conversely, bamboo fiber demonstrated superior reliability and consistency, reaching a peak split tensile strength of 5.02 MPa at 2.0% loading and maintaining steady growth across all proportions. This suggests that while banana fiber provides maximum load-bearing capacity at low volumes, bamboo fiber is preferable for applications requiring predictable mechanical scaling. These results provide foundational data for the implementation of natural fiber-reinforced concrete in sustainable structural applications, highlighting a viable strategy for reducing reliance on carbon-intensive materials while enhancing the energy absorption and ductility of cementitious composites.
Nonlinear Prediction with Data Augmentation and Regularization: A Ensembled LSTM–XGBoost Model Funcion, Devine Grace D.; Natividad, Marvee Cheska B.
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.478

Abstract

Nonlinear prediction faces its main challenge in the form of overfitting, which leads to inaccurate predictions. The problem becomes evident when researchers attempt to apply advanced deep learning systems to small agricultural data collections. Researchers use knowledge discovery in databases (KDD) to evaluate regularization methods with ensemble techniques, but have not sufficiently explored how structured data augmentation interacts with MaxNorm regularization. The research explores how a sliding-window transformation, together with bootstrap augmentation methods, works when ElasticNet, Bayesian, and MaxNorm regularization techniques are combined into an LSTM-XGBoost prediction system to predict Tikog grass demand. The research showed that data augmentation techniques helped reduce model overfitting, thereby improving performance on prediction tasks. Among the regularization strategies applied to LSTM, MaxNorm achieved the largest reduction in error, with testing MSE decreasing from 0.060472 to 0.002090 after augmentation. A comparative evaluation further shows that LSTM-XGBoost achieved the highest overall performance (R² = 0.997806), while deep learning models showed greater sensitivity to augmentation and regularization strategies. These findings highlight that structured time-series augmentation combined with norm-based regularization enhances generalization capability, particularly for high-capacity sequence models trained on limited agricultural data.
AVNPR-Net: A Real-Time Deep Learning Framework for Robust Vehicle Number Plate Detection and Recognition Ijaz, Ahmad; Sarfraz, Tayyba; Bibi, Tanzeela; Usman, Muhammad
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.495

Abstract

AVNPR systems are critical in intelligent transportation, monitoring, and law enforcement systems. Nevertheless, the current systems are usually challenged by the issues of dissimilar illumination, obstruction, and the diversity of plate formats, which restrict their practical applicability. To solve these problems, this paper suggests a real-time deep learning-driven AVNPR framework that incorporates effective detection and recognition systems.  The proposed system employs the YOLOv8 object detector model to localize number plates with high accuracy and speed, as well as a lightweight recognition module to identify alphanumeric characters. A custom dataset with different types of vehicles in different environmental conditions was created and improved with the help of preprocessing and data augmentation methods to make the model more robust. In the experiments, the proposed system demonstrated an overall system accuracy of 98.7%, representing the combined number plate detection and character recognition results. The mAP@0.5 is 97%, and mAP 0.5-0.95 is 91%, as well as high precision, recall, and F1-score, which suggests that it shows potential applicability across varying conditions in the assessed dataset and suggests that it may be suitable for real-world applications. The system is also implemented with a Flask-based web application, and it supports image based and real-time webcam detection. The results indicate that the proposed framework provides a viable, efficient, and deployable solution to AVNPR applications. The work will lead to the creation of scalable and real-time intelligent transportation systems and give a basis for future advancement in the improvement of robust vehicle recognition in challenging conditions.
AI-Assisted Design and Control of Smart Electromechanical Devices for Energy-Efficient Applications Akande, Timileyin Opeyemi; Chukwujama, Osinachi Victor; Abdullahi, Monsuru Olalekan; Kalio, Princewill
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.408

Abstract

The growing global demand for sustainable energy has elevated the importance of energy-efficient electromechanical systems in applications such as electric vehicles (EVs), renewable energy conversion, and industrial automation. These systems reduce carbon emissions and operational costs by optimizing power use, aligning with UN Sustainable Development Goals and 2050 net-zero targets. However, traditional control methods like field-oriented control (FOC) and PID controllers struggle with nonlinear dynamics, parameter variations, and variable loads, resulting in suboptimal performance, higher energy losses, and reduced robustness. This paper addresses this gap by proposing an AI-assisted framework for designing and controlling smart electromechanical devices, using permanent magnet synchronous motor (PMSM) drives as a prototype. The approach integrates adaptive neural networks with reinforcement learning to enable real-time optimization of dynamic response, robustness, and energy efficiency. The system was rigorously simulated in MATLAB/Simulink using a d-q reference frame model under nominal, disturbed, and variable-load conditions. Results show significant improvements: transient settling time reduced by 42–58%, overshoot by 60–67%, and energy consumption by 12–18%, achieved through minimized torque ripple and losses. The framework also demonstrated superior disturbance rejection and parameter-variation stability. These advances position the proposed solution as a transformative approach for sustainable applications, enhancing efficiency in EV propulsion, renewable energy integration, and industrial automation, while paving the way for future hardware implementation and scalable AI-driven systems.
A Low-Cost Vision-based Fruit Sorting System for Robotic Applications Afaq, Muhammad; Secco, Emanuele Lindo
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.471

Abstract

Modern robotic systems address complex engineering challenges using artificial intelligence and machine learning techniques. In agricultural robotics, fruit identification and sorting remain challenging due to variations in size, shape, color, orientation, and lighting conditions. This study presents the design and implementation of a vision-based fruit sorting robotic system integrating YOLOv8-based object detection with robotic manipulation. A custom dataset consisting of images of 2 different fruits (namely banana and strawberry images), including single-fruit and multi-fruit scenarios, was used and manually annotated using bounding boxes in CVAT. The dataset was divided into training, validation, and test subsets to enable robust model development under realistic operational conditions. A lightweight YOLOv8 model was trained using CUDA acceleration and optimized for edge deployment by selecting YOLOv8n to balance inference speed and detection accuracy. The trained model was converted to ONNX format and deployed on a Raspberry Pi 5 for real-time inference using live camera input. Evaluation on an independent test dataset achieved a precision of 0.999, recall of 1.000, mAP@0.5 of 0.995, and mAP@0.5:0.95 of 0.963 under controlled experimental conditions with limited object classes. The modular architecture enables low-cost and scalable deployment and provides a foundation for future enhancements, including closed-loop robotic control, additional object categories, and operation in more dynamic environments.
BReMS-Net: Prediction-Guided Coarse-to-Fine Refinement with Boundary-Aware Multi-Scale Dilated Fusion for Robust Breast Mass Segmentation Sarfraz, Tayyba; Ling, Tan; Ijaz, Ahmad
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.489

Abstract

Breast masses in mammograms are important to segment for computer-aided diagnosis (CAD) to enhance early detection and treatment decisions. Current approaches face challenges in segmenting lesions with low lesion-to-tissue contrast and diverse textures, resulting in misclassification or poor segmentation accuracy. To overcome this challenge, this paper introduces BReMS-Net, a multi-stage segmentation network to improve contextual learning and refined boundaries. We used an MBA-Net backbone with two major components: a Multi-scale Hybrid Dilated Convolution (MHD) module to extract multi-scale contextual features, and a Boundary Feature Auxiliary (BFA) module to strengthen boundary representations via coarse-to-fine feature fusion. Furthermore, a lightweight Prediction-Guided Refinement Module (PRM) uses initial predictions to produce attention maps, remove background clutter, and progressively refine boundary areas. The model has been evaluated on a cross-dataset basis, trained on the CBIS-DDSM dataset and tested on the INbreast dataset, and the results show that the BReMS-Net produces a Dice coefficient of 93.12% and an HD95 of 0.9826, which demonstrate competitive performance compared to several state-of-the-art deep learning methods. These results underline its generalization and robustness. Overall, the framework provides a robust and efficient approach to breast mass segmentation and has important implications for the performance and clinical relevance of automatic breast cancer diagnosis systems.
NRCC-LC: Noise-Robust Crowd Counting with Dynamic Label Correction under Noisy Supervision Hersi, Abubakar Abdinur; Ling, Miaogen; Raza, Muhammad; Hassan, Abdirahman Mohamed; Hussien, Idris Aweis
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.494

Abstract

Crowd counting remains a challenge within computer vision due to many factors that affect the performance of available methods such as occlusion, scale variability, and perspective distortion. Additionally, many labels associated with crowd counting systems have high levels of noise caused by various real-world conditions. Although crowd counting methodologies have improved accuracy over recent years, the majority of crowd counting models still rely on clean real-time supervision and lack systems that can correct for dynamically corrupted labels, resulting in low robustness for crowd counting models when deployed in real-world applications. In this work we present a Noise-Robust Crowd Counting with Label Correction (NRCC-LC) framework to obtain reliable density estimates from noisy supervision. To accomplish this, our approach uses a combined CNN-Transformer architecture to capture both locally- and globally-relevant visual information (i.e., image content and context), along with a Noise-Robust Module (NRM) and a Dynamic Label Correction (DLC) mechanism. Our principle experimental results evaluated across four benchmark datasets: ShanghaiTech Part A, ShanghaiTech Part B, NWPU-Crowd, and JHU-Crowd++, indicate that the NRCC-LC exhibits competitive performance with respect to existing state-of-the-art crowd-counting methods; most notably, producing per-image MAEs of 97.8 and 392.3 on NWPU-Crowd. These experimental results additionally have real-world implications for improving public safety and urban planning; thus, through our novel method of noise-aware feature learning combined with iterative label correction, we can establish the potential of automated monitoring systems in complex, real-world environments to be significantly more reliable.

Page 1 of 1 | Total Record : 7