cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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
Published by PT. Teknologi Futuristik Indonesia
ISSN : -     EISSN : 31091725     DOI : https://doi.org/10.64539/sjer
Core Subject : Engineering,
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.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 43 Documents
 1   2   3   4   5 
A Novel Wavelet-Based Approach for Transmission Line Fault Detection and Protection Emon, Asif Eakball; Ahammad, Jalal
Scientific Journal of Engineering Research Vol. 2 No. 1 (2026): March
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i1.2026.374

Abstract

The reliable operation of modern power systems is critically dependent on the rapid and accurate isolation of transmission line faults, as failures can trigger cascading outages with severe socioeconomic consequences. While conventional protection schemes like overcurrent and distance relays are widely deployed, they exhibit limitations in speed, selectivity, and performance under high-impedance or evolving fault conditions, representing a significant gap in ensuring grid resilience. To address this, the objective of this research is to design and validate a novel Wavelet Transform Analysis with traditional relaying to enhance fault detection and classification. Through comprehensive modeling and simulation in MATLAB/Simulink, the proposed system demonstrated a mean fault detection time of 11.4 milliseconds and an accuracy of 99.8%, significantly outperforming conventional methods, particularly in challenging scenarios such as high-impedance and intermittent faults. These findings imply that the wavelet-enhanced framework offers a robust, adaptive solution for modern and future power networks, contributing directly to improved system stability, reduced outage times, and a foundational step toward intelligent, self-securing grid infrastructure.
Interpretable Deep Learning for Type 2 Diabetes Risk Prediction in Women Following Gestational Diabetes Prashanthan, Amirthanathan; Prashanthan, Jenifar
Scientific Journal of Engineering Research Vol. 2 No. 1 (2026): March
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i1.2026.376

Abstract

Women with gestational diabetes mellitus (GDM) face a 7-10 times elevated risk of developing Type 2 Diabetes Mellitus (T2DM), yet current predictive models demonstrate limited accuracy (AUC-ROC: 0.70-0.85) and insufficient interpretability for clinical adoption. This study addresses the critical need for accurate, transparent risk prediction tools by developing an interpretable deep learning framework integrating bidirectional long short-term memory (BiLSTM) networks with attention mechanisms and SHapley Additive exPlanations (SHAP). Using a synthetic dataset of 6,000 simulated post-GDM women with 28 clinical risk factors, the BiLSTM-Attention model was evaluated through stratified 10-fold cross-validation against five baseline models. The proposed model achieved exceptional performance with 98.45% accuracy, 98.80% precision, 98.30% recall, 98.55% F1-score, 96.85% MCC, and 0.9968 AUC-ROC, significantly outperforming all baselines (p < 0.05). SHAP analysis identified recurrent GDM history, elevated HbA1c, and impaired glucose tolerance as primary predictors, while highlighting modifiable factors including physical inactivity, dietary habits, and obesity as actionable intervention targets. This proof-of-concept demonstrates the methodological feasibility of combining high-performance deep learning with explainable AI for T2DM risk stratification. However, synthetic data represents a significant limitation; comprehensive real-world clinical validation across diverse populations is essential before clinical implementation. The publicly available computational framework enables future validation studies to advance this approach toward clinical utility.
Real-Time Implementation of Integrated Optical Plus Filtered OFDM 5G Network Parameters for LTE and DVB-T2 Telecommunication Systems Ahmed-Ade, Fatai; Akpan, Vincent Andrew; Ogolo, Emmanuel Omonigho
Scientific Journal of Engineering Research Vol. 2 No. 1 (2026): March
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i1.2026.372

Abstract

Orthogonal Frequency Division Multiplexing (OFDM) technology to deliver mobile broadband and digital television services. This paper presents the real-time implementation of Optical plus Filtered OFDM (O+F OFDM) algorithms for Long Term Evolution (LTE) mobile networks and Digital Video Broadcasting – Second Generation Terrestrial (DVB-T2) systems, with particular focus on deployments in emerging markets. The paper analyzes physical-layer configurations specified in 3GPP TS 36.211 and ETSI EN 302 755, including subcarrier spacing, Fast Fourier Transform (FFT) sizes, cyclic prefix options, modulation schemes, and Multiple-Input Multiple-Output (MIMO) configurations. Field measurements from Nigerian LTE deployments reveal that while theoretical peak rates approach 300 Mbps with 4×4 MIMO on 20 MHz carriers, achieved throughput typically ranges from 15-35 Mbps due to backhaul constraints, interference, and suboptimal network configuration. For DVB-T2, we document parameters enabling 30-50% greater spectral efficiency than first-generation standards through enhanced forward error correction, larger FFT options (up to 32k subcarriers), and rotated constellations. The O+F OFDM implementation demonstrates superior performance characteristics: reduced out-of-band emissions (>45 dB suppression), improved spectral confinement within regulatory masks, and enhanced multipath resilience through optical filtering stages. System-level considerations including adaptive modulation and coding, Quality-of-Service (QoS) bearer management, Self-Organizing Network (SON) algorithms, and carrier aggregation are examined. We strongly recommend Field-Programmable Gate Array (FPGA)-based real-time implementation of O+F OFDM for both MTN's LTE and GOtv's DVB-T2 systems to achieve deterministic signal processing latency below 5 microseconds, support adaptive parameter reconfiguration without hardware modifications, and enable power-efficient operation critical for Nigerian deployment scenarios with unreliable electrical infrastructure.
Soil Erosion Risk Assessment Using Remote Sensing and GIS: An Integrated RUSLE-Frequency Approach Ukah, Chinomso; Adieme, Mmelichukwu Oluebube; Ojukwu, Prosper Chinonso; Ebere, Nwobu Deborah; Udeh, Jennifer Ifeoma
Scientific Journal of Engineering Research Vol. 2 No. 1 (2026): March
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i1.2026.379

Abstract

Soil erosion is a major environmental challenge in tropical regions due to the interaction of intense rainfall, fragile soils, and unsustainable land use. This study assessed soil erosion risk in Agulu-Nanka, southeastern Nigeria, using an integrated GIS, remote sensing, Revised Universal Soil Loss Equation, and Frequency Ratio modeling approach to identify erosion hotspots and validate erosion susceptibility factors. It addresses the lack of localized, high-resolution soil erosion mapping and model validation using observed field erosion features in the study area despite existing regional erosion studies in Anambra State. Multi-source datasets were used to derive Revised Universal Soil Loss Equation factors and produce high-resolution erosion risk maps, which were validated using gully occurrence data. Results indicate extremely high rainfall erosivity (mean R = 110,562.09 MJ-MM/ha-hr-yr) and moderately to highly erodible soils (mean K = 1.39) as key erosion drivers. Steep slopes (LS > 4.00) more than doubled gully occurrence likelihood (FR = 2.21), while poorly vegetated and unmanaged areas recorded high susceptibility (FR > 2.0). Estimated soil loss reached 86.34 t/ha/yr, with high and very high-risk zones covering less than 4% of the area but posing significant threats to land productivity and infrastructure. The study confirms the multi-factorial nature of erosion in Agulu-Nanka and demonstrates the effectiveness of the RUSLE-FR framework for hotspot identification and evidence-based land use planning.
Sustainable Construction Practices: Integrating Renewable Energy for Carbon Footprint Reduction Alabi, Oluwaseyi Omotayo; Laoye, Adeoti Oyegbori
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.386

Abstract

The construction sector is a major contributor to resource depletion and greenhouse gas emissions, underscoring the importance of adopting sustainable practices to meet environmental and climate goals. However, current assessments often underestimate impacts because of narrow system boundaries and insufficiently localized material inventory data, creating a critical research gap in accurately evaluating building sustainability. This study therefore applies to a comprehensive Life Cycle Assessment (LCA) framework to evaluate the environmental performance of key construction materials and to investigate strategies for integrating circular design and renewable energy to reduce carbon footprints. The results reveal that medium-term environmental impacts are approximately 20–30% higher than previously reported, while the Global Warming Potential of conventional brick increases by about 23% when additional life-cycle stages are considered. Furthermore, the analysis demonstrates that design-for-disassembly and recycling-oriented approaches can significantly enhance material recovery and reduce waste. These findings imply that developing harmonized, region-specific material databases and promoting circular construction alongside renewable energy integration are essential for improving LCA accuracy and achieving meaningful reductions in the environmental footprint of buildings.
Federated Temporal Graph Learning for Weakly Supervised Bearing Anomaly Detection Darlami, Khagendra; Awasthi, Lalit
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.413

Abstract

Industrial bearing health monitoring is hindered by four interrelated challenges: high class imbalance, the absence of fault-type annotations, stringent data privacy constraints prohibiting centralized aggregation, and non-independent and identically distributed (non-IID) degradation dynamics across geographically dispersed assets. To address these, we propose Fed-TGCN, a novel weakly supervised federated learning framework grounded in temporal graph neural networks. Each client represents a leave-one-bearing-out fold, comprising two training bearings, one validation bearing, and one held-out test bearing, constructs a hybrid spatio-temporal graph from six physics-informed statistical features derived from raw vibration signals; edges encode both sequential dependencies and feature-space similarity via k-nearest neighbors. Pseudo-anomaly labels are generated locally through adaptive thresholding of a degradation score using exponentially weighted moving average, eliminating reliance on expert annotations. Under a strict leave-one-bearing-out protocol on the NASA IMS dataset (12 bearings), local Temporal Graph Convolutional Networks are trained in isolation and aggregated globally via FedAvg. Our method achieves an Average Precision of 0.675 ± 0.276 and Matthews Correlation Coefficient of 0.636 ± 0.285, maintains stronger performance consistency across heterogeneous bearing conditions than isolated and non-graph baselines (ΔMCC = +0.130, p < 0.01). Ablation studies confirm the necessity of temporal modeling (MCC drops by 0.069 without GRU). To the best of our knowledge, this is the first work integrating weakly supervised, graph-based federated learning for bearing prognostics under, demonstrating that parameter coordination but not the data sharing which enables degradation-invariant representation learning across heterogeneous assets.
Embedded Control Architecture for Multi-Evaporator Industrial Dehumidification Systems Chathumal, Pamodha; Amaratunga, Sanath
Scientific Journal of Engineering Research Vol. 2 No. 1 (2026): March
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i1.2026.435

Abstract

Industrial dehumidification plays a pivotal role in spice processing industries, where precise moisture control directly influences product quality, shelf life, and processing efficiency. However, in many industrial facilities, these systems are operated manually or using basic on-off control methods. Such practices often result in unstable operating conditions, frequent compressor switching, increased energy consumption, and reduced equipment lifespan. This study addresses the lack of affordable, hardware-level automation for multi-evaporator systems by presenting the design and implementation of a dedicated embedded control architecture. The proposed objective was to develop a dual-microcontroller system where a primary controller manages real-time decision-making based on temperature and relative humidity, while a secondary controller is strictly dedicated to safety and time-delay protection. The system was implemented and tested in an industrial spice processing facility. Key findings demonstrate that the autonomous mode reduced outlet air temperature variation to ±1 – 2 oC and relative humidity fluctuation to ±4 – 5%, compared to significantly higher variations in manual operation. Furthermore, the system reduced operator interventions from 1-2 per shift to 0-1 and minimized compressor cycling frequency. Beyond operational efficiency, the stabilization of the drying environment directly contributes to the preservation of critical quality parameters, such as volatile oil retention and color uniformity, which are frequently compromised under manual control regimes. These results imply that low-cost embedded automation can significantly enhance operational stability and safety in agro-industrial processing without requiring expensive infrastructure upgrades.
Numerical and Experimental Investigation of a Vortex Head for Back-Pressure Suppression in Petroleum Pumping Systems Effiom, Samuel Oliver; Enoh, Maria Kaka Etete; Willie, Godwin Effiong; Effiom, Precious-Chibuzo
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.422

Abstract

Back-pressure accumulation and transient pressure surges remain critical operational challenges in petroleum pumping systems, particularly during high-rate product transfer into storage tanks. Conventional mitigation strategies such as pressure relief valves, surge vessels, and bypass lines are largely reactive, energy-intensive, and maintenance-dependent. Despite advances in computational fluid dynamics (CFD), limited research has addressed passive inlet-based hydrodynamic conditioning for petroleum storage tanks with full-scale industrial validation. This study presents a combined numerical and experimental investigation of a passive vortex head (VH) designed to suppress back pressure through vortex-induced flow redistribution at the tank inlet. Three-dimensional CFD simulations were performed using ANSYS Fluent with the realizable k–ε turbulence model to analyze pressure distribution, velocity fields, turbulence characteristics, and vortex formation. Controlled experimental validation was conducted using a prototype system under normalized inlet pressure conditions (0.07 bar) in an industrial petroleum storage facility. The results demonstrate that the vortex head induces a stable swirling flow that promotes gradual momentum dissipation and reduces localized pressure buildup near full capacity. Compared with a conventional straight inlet configuration, the vortex head reduced peak back pressure by approximately 20–30%, while decreasing total tank filling time by about 15% under identical flow conditions. CFD predictions agreed with experimental measurements within ±5%. The findings establish passive vortex-based inlet conditioning as a practical, energy-efficient strategy for preventive back-pressure suppression in petroleum storage infrastructure.
LSKD: Lightweight Self-Knowledge Distillation Framework for Fast and Robust Crowd Counting Raza, Muhammad; Ling, Miaogen; Ur Rahman, Atta; Pallewatta, Pandula; Hersi, Aboubakar Abdinur; Beruwalage, Shehan Maxwell; Kannangara, Deshan Sachintha
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.436

Abstract

Crowd counting plays an important role in the surveillance of the safety of the people, traffic, and intelligent surveillance systems. However, the exact density estimations remain hard to achieve in highly congested scenes due to the tough occlusion, large-scale variance, and complicated background. Although the recent deep-learning methods have high performance, several of them do not need computationally efficient underlying backbone networks, and rather, they employ an external teacher-student distillation architecture, which can limit their use in resource-constrained applications. To avoid this problem, we introduce LSKD, a lightweight self-knowledge distillation network that is density map regression-specific. Unlike other conventional teacher-dependent processes, LSKD can also independently carry out internal multi-level feature alignment within a single small network that is not in need of an external teacher model. The structure integrates a Feature Matching Block (FMB) and a Context Fusion (CoFuse) block to enhance the hierarchical match of features and global awareness of context. The large experiments demonstrate that LSKD obtain competitive performance using the number of parameters as 2.65 million and GFLOPs as 10.23. Particularly, it has 63.17 MAE on ShanghaiTech Part A, 8.94 on ShanghaiTech Part B, 143.7 on UCF-QNRF, and 223.88 on UCF-CC-50, which is a good ratio between the accuracy and the efficiency of the calculations. Such results indicate that LSKD has an implementable and efficient solution to the real-time counting of crowds at the edge devices.
Deep Residual Learning-Based Categorization of Gastric Pathologies: A Knowledge Transfer Framework Win, Ei Phyu Sin
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.429

Abstract

Early detection of gastric pathologies, such as polyps, esophagitis, and ulcerative colitis, plays a pivotal role in improving patient clinical outcomes and long-term treatment efficacy. Despite advancements in medical imaging, manual endoscopic analysis remains a labor-intensive process prone to human error and inter-observer variability, creating a critical research gap for automated diagnostic tools. This research introduces a robust automated classification framework employing the ResNet18 architecture, optimized through a refined Transfer Learning methodology. The study utilizes a comprehensive multi-class dataset, with input data undergoing meticulous preprocessing, including global normalization and strategic data augmentation, to enhance generalization. Empirical evaluations conducted over 50 epochs revealed superior performance, with the proposed model achieving an overall accuracy of 94.05%. Notably, a precision rate of 100% was attained, indicating zero false alarms, while a high sensitivity of 91.67% confirmed the model's effectiveness in distinguishing subtle cancerous features from healthy gastric folds. These quantitative findings underscore the framework's reliability and its potential for seamless integration into clinical decision-support systems. By providing high-fidelity diagnostic assistance, this study contributes to the evolution of computer-aided diagnosis (CAD), offering a scalable solution to reduce clinician workload while significantly increasing the accuracy of early-stage gastric pathology detection.

Page 4 of 5 | Total Record : 43

 1   2   3   4   5 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Vol. 2 No. 2 (2026): June Article in Process Vol. 2 No. 1 (2026): March Vol. 1 No. 4 (2025): December Vol. 1 No. 3 (2025): September Vol. 1 No. 2 (2025): June Vol. 1 No. 1 (2025): March