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 9 Documents
 1 
Search results for , issue "Vol. 1 No. 4 (2025): October Article in Process" : 9 Documents clear
Hybrid K-means, Random Forest, and Simulated Annealing for Optimizing Underwater Image Segmentation Kobra, Mst Jannatul; Rahman, Md Owahedur; Nakib, Arman Mohammad
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.46

Abstract

The process of underwater image segmentation is also very difficult because the data collected by the underwater sensors and cameras is of very high complexity, and much data is generated and in that case, the data is not well seen, the color is distorted, and the features overlap. Current solutions, including K-means clustering and Random Forest classification, are unable to partition complex underwater images with high accuracy, or are unable to scale to large datasets, although the possibility of dynamically optimizing the number of clusters has not been fully explored. To fill these gaps, this paper advises a hybrid solution that combines K-means clustering, Random Forest classification and the Simulated Annealing optimization as a complete end to end system to maximize the efficiency and accuracy of segmentation. K-means clustering first divides images based on pixel intensity, Random Forest narrows its segmentation of images with features like texture, color and shape, and Simulated Annealing determines the desired number of clusters dynamically to segment images with minimal segmentation error. The segmentation error of the proposed method was 30 less than the baseline K-means segmentation accuracy of 65 percent and the proposed method segmentation accuracy was 95% with an optimal cluster number of 10 and a mean error of 7839.22. This hybrid system offers a large-scale, scalable system to underwater image processing that is robust and has applications in marine biology, environmental research, and autonomous underwater system exploration.
Brine Treatment Plant using Hybrid Forward Osmosis–Membrane Distillation (FO–MD) System Al-Rashidi, Aryam Qalit
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.313

Abstract

Brine discharge from seawater reverse osmosis (SWRO) plants poses critical environ-mental and operational challenges, particularly in regions reliant on large-scale desalination. This study proposes a hybrid brine treatment system integrating Forward Osmosis (FO) and Membrane Distillation (MD) to enhance water recovery and minimize ecological impact. The FO stage utilizes a concentrated magnesium chloride (MgCl₂) draw solution to extract water from high-salinity brine without the need for hydraulic pressure, while the MD stage regenerates the draw solution using low-grade solar thermal energy, simultaneously producing high-purity distillate. Mass and energy balance calculations were per-formed to evaluate recovery rates, specific energy consumption, and thermal input requirements. The results indicate that the FO–MD configuration can achieve recovery rates exceeding 80% with significantly reduced brine discharge, while maintaining low energy demand compared to conventional methods. The integration of solar energy further enhances system sustainability, making it suitable for deployment in off-grid or arid regions. This hybrid approach demonstrates strong potential for advancing sustainable desalination practices, aligning with circular water strategies and zero liquid discharge (ZLD) objectives.
GIS-Based Flood Risk Assessment Using the Analytical Hierarchy Process Rakuasa, Heinrich; Rifai, Ahmat
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.43

Abstract

Floods are a common hydrometeorological disaster in Teluk Ambon Sub-district ; therefore, modeling is necessary as a mitigation measure. To address this challenge, Geographic Information System (GIS) and Remote Sensing technologies have proven to be powerful tools in flood disaster analysis and modeling. This study uses 10 variables, including elevation, slope, TWI, NDVI, precipitation, land cover, soil type, drainage density, distance from roads, and distance from rivers. This study uses the Analytical Hierarchy Process (AHP) method. The results show that distance from rivers has the greatest contribution (14.08%) to flooding in Teluk Ambon Sub-district . The level of flood vulnerability in Teluk Ambon Sub-district  is divided into three classes, namely low risk, covering an area of 8,642.26 ha or 64.71%; medium risk, covering an area of 4,066.79 ha or 30.45%; and high risk, covering an area of 646.44 ha or 4.84%. Settlements predicted to be affected by flooding in the low class cover an area of 130.36 ha, or 11.59%; the medium class covers an area of 649.29 ha, or 57.73%; and the high class covers an area of 345.07 ha, or 30.68%. The results of this study are very important in providing a more precise flood risk map to support spatial planning and disaster mitigation in the affected areas.
High-RAP Asphalt Mixtures (>40%): Mechanical Performance, Durability, Sustainability, and Emerging Technologies Abbas, Saifal
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.321

Abstract

Asphalt mixtures that utilize Reclaimed Asphalt Pavement (RAP), particularly at high RAP levels above 40%, are gaining in popularity due to the emphasis on sustainable pavement solutions. This review paper comprehensively evaluates the performance of high RAP asphalt mixtures, focusing on their mechanical characteristics and durability when compared to standard asphalt mixtures. High RAP mixtures perform well in high-traffic scenarios because they have excellent stiffness and resistance to rutting. Still, they have performance limitations that could be remedied through rejuvenators, anti-stripping agents, and premium additives. Durability issues such as moisture susceptibility and long-term aging are investigated, along with the importance of binder blending and rejuvenation on the impacts of aging. The review highlights significant research areas like optimizing rejuvenator formulations, bio-based additives evaluation, and complete life cycle assessments (LCA) to examine the overall sustainability of high-RAP mixtures. The comparison with conventional mixtures highlights high-RAP mixtures' environmental and economic advantages, such as reduced greenhouse gas emissions, decreased energy use, and substantial cost savings. Despite these advantages, variability of RAP content and lack of standard testing are significant challenges. While still in its infancy, new technologies, such as warm-mix asphalt (WMA), and new characterization technologies, such as X-ray computed tomography (CT) and AI, promise to optimize mix design and forecast long-term performance. High-RAP mixes can transform sustainable pavement construction by alleviating these challenges and employing innovative technologies. This article will benefit researchers, engineers, and policymakers looking to facilitate the use of high-RAP mixes in new construction.
Comparative Analysis and Modeling of Single and Three Phase Inverters for Efficient Renewable Energy Integration Emon, Asif Eakball; Molla, Sohan; Shawon, Md; Tabassum, Anika
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.325

Abstract

This work details the hands-on design, simulation, and direct performance comparison of single-phase and three-phase grid-connected photovoltaic (PV) inverters, fully implemented and tested within the MATLAB/Simulink environment. Moving beyond theoretical descriptions, we constructed detailed models incorporating practical elements: a PV array, a DC-DC boost converter with Perturb and Observe (P&O) Maximum Power Point Tracking (MPPT) for real-world energy harvesting, and both single-phase H-bridge and three-phase two-level voltage source inverters (VSIs) feeding the grid through carefully designed LCL filters. We subjected both systems to identical, realistic solar irradiance profiles and rigorously analyzed critical performance metrics side-by-side, including output waveform quality (Total Harmonic Distortion - THD), power conversion efficiency, DC-link voltage stability, and MPPT effectiveness. Our simulation results clearly demonstrate distinct operational characteristics: the three-phase inverter consistently delivered superior efficiency (approximately 97.8% vs. 96.5%), significantly lower output current THD (below 2.0% vs. approximately 3.8%), and reduced DC-link voltage ripple. Conversely, the single-phase topology offers inherent simplicity and lower cost for lower-power applications. This comparative analysis provides concrete, simulation-backed insights into the fundamental trade-offs between complexity, cost, efficiency, and power quality, directly informing the optimal selection of inverter technology—single-phase for standard residential use or three-phase for commercial/industrial systems demanding higher performance.
The Role of Atomic-Scale Disorder in Tailoring the Functional Properties of Crystalline Materials: A Comprehensive Review Rahman, Md Sultanur; Uddin, Md Jasim; Hasan, Rakib; Mia, Md Mehedi Hasan
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.326

Abstract

It has long been believed that crystalline solids will always have atomic-scale disorder, which includes vacancies, interstitials, andesite defects, local strain fields, short-range compositional changes, and amorphous pockets. The functional qualities of materials can be controlled by redefining disorder as a flexible and adjustable design parameter. Across classes of crystalline materials (oxides, chalcogenides, perovskites, semiconductors, and two-dimensional crystals), we synthesize experimental and theoretical advances demonstrate how particular types and distributions of atomic-scale disorder alter charge-carrier dynamics, optical absorption and emission, magnetic ordering, ionic conductivity, thermal transport, and mechanical response. Mechanistic relationships are highlighted, including how correlated defect complexes and local strain mediate polaron generation and carrier mobility, how interface disorder and grain-boundary structure control ion transport and catalytic activity, and how point defects alter electronic band edges and trap states. From total-scattering PDF analysis and advanced spectroscopies to aberration-corrected TEM, atom probe tomography, and scanning probe microscopies, we go over characterization tools and how data-driven models, large-scale molecular dynamics, and first-principles calculations are coming together to predict and direct disorder engineering. Successful methods for improving device performance such as defect-enabled light emission, dopant-activated ionic conductors, and disorder-stabilized phases are highlighted in case studies. We conclude with useful recommendations for intentional disorder design and point out unresolved issues, such as in-operando characterization, multiscale modelling, and controlled defect synthesis, providing a roadmap for utilizing atomic-scale disorder to develop next-generation functional materials.
Ensemble Learning Framework for Image-Based Crop Disease Detection Using CNN Models Betrand, Chidi Ukamaka; Benson-Emenike, Mercy Eberechi; Kelechi, Douglas Allswell; Onukwugha, Chinwe Gilean; Oragba, Nneka Martina
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.330

Abstract

Crop diseases pose a significant threat to global food security, causing substantial yield losses estimated at 10-40% annually. Traditional methods of disease identification, reliant on visual inspection by farmers or experts, are often subjective, time-consuming, and limited by the availability of specialists. This study proposes an ensemble learning framework for robust image-based crop disease detection, specifically designed to address the challenges of heterogeneous, non-Independent and Identically Distributed (non-IID) agricultural datasets in decentralized environments. Utilizing the Plant Village dataset, we implement a stacking ensemble model integrating diverse Convolutional Neural Networks (CNNs) such as VGG (Visual Geometry Group), ResNet, and Inception as base learners, with a meta-learner to optimize prediction fusion. The system employs comprehensive data preprocessing, including resizing, normalization, noise removal, segmentation, and augmentation, to enhance robustness against real-world variability. Transfer learning with ResNet50 was adopted as a baseline model. The baseline ResNet50 achieved 59% test accuracy across seven grape and potato disease classes. The ensemble model improved performance, attaining 63% accuracy with average precision, recall, and F1-scores of 56%, 52%, and 52% respectively. Class imbalance remained a limiting factor for certain categories. The ensemble learning approach outperformed individual models, demonstrating improved generalization across diverse datasets. Although computational demands and imbalance challenges persist, the system provides a promising AI-driven pipeline for accurate crop disease diagnosis, supporting sustainable agricultural practices.
Hybrid Fuzzy–Multi-Objective Particle Swarm Optimization Control for Real-Time Energy Management in PV-Powered Fast Charging Infrastructure for Electric Vehicles Elgammal, Adel
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.339

Abstract

This paper proposes an innovative Fuzzy–Multi-Objective Particle Swarm Optimization (Fuzzy-MOPSO) based hybrid control strategy for real-time energy management in PV-integrated fast charging systems for EVs. The developed approach combines fuzzy logic control and multi-objective optimization algorithm to achieve dynamic balance between charge rate, power quality, grid stability, and cost of energy. This fuzzy controller can be flexibly used in the presence of variable and uncertainty conditions (e.g., fluctuated solar irradiance, changing EV charging request, grid voltage disturbance) since it has gradual control operations by adjusting converter duty ratios and charging current values. The MOPSO algorithm simultaneously optimizes the multiple antagonistic objectives such as minimization of THD, unity PF with less charging time and increased PV utilization efficiency by adjust fuzzy membership functions and rule weights in real-time. Simulation results in MATLAB/Simulink show that the hybrid controller performs better than classical PI controllers or single fuzzy or PSO based control system. The Fuzzy-MOPSO controller also limits the THD 0.995, and charging efficiency enhancement of (8–12%) with stochastic PV and load changes, in conformity to IEEE-519. Excessively generated energy cost are reduced as well by 15% through the optimal control on the power flow between PV generation, storage and grid. The hybridization of fuzzy reasoning and swarm-based optimization provides for fast transient response, renewable intermittency robustness, and grid integration sustainability. These findings validate that the proposed Fuzzy-MOPSO technique is an appropriate approach to intelligent, efficient and eco-friendly FCI of fast charging in REN smart cities.
Incremental Development of a Framework for Mitigating Adversarial Attacks on CNN Models Nisar, Maaz; Fayyaz, Nabeel; Ahmed, Muhammad Abdullah; Shams, Muhammad Usman; Fareed, Bushra
Scientific Journal of Engineering Research Vol. 1 No. 4 (2025): October Article in Process
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i4.2025.349

Abstract

This work explores the vulnerability of Convolutional Neural Networks (CNNs) to adversarial attacks, particularly focusing on the Fast Gradient Sign Method (FGSM). Adversarial attacks, which subtly manipulate input images to deceive machine learning models, pose significant threats to the security and reliability of CNN-based systems. The research introduces an enhanced methodology for identifying and mitigating these adversarial threats by incorporating an anti-noise predictor to separate adversarial noise and images, thereby improving detection accuracy. The proposed method was evaluated against multiple adversarial attack strategies using the MNIST dataset, demonstrating superior detection performance compared to existing techniques. Additionally, the study highlights the integration of Fourier domain-based noise accommodation, enhancing robustness against attacks. The findings contribute to the development of more resilient CNN models capable of effectively countering adversarial manipulations, emphasizing the importance of continuous adaptation and multi-layered defense strategies in securing machine learning systems.

Page 1 of 1 | Total Record : 9

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 1 No. 4 (2025): October Article in Process Vol. 1 No. 3 (2025): July Vol. 1 No. 2 (2025): April Vol. 1 No. 1 (2025): January