cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dwi Sulisworo
Contact Email
sulisworo@iistr.org
Phone
+6281328387777
Journal Mail Official
esl@journal.iistr.org
Editorial Address
Jalan Sugeng Jeroni No. 36 Yogyakarta 55142, Indonesia
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Engineering Science Letter
Published by Indonesian Institute of Science and Technology Research
ISSN : 29618924     EISSN : 2961872X     DOI : https://doi.org/10.56741/esl.v1i02
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology
Engineering Science Letter is an international peer-reviewed letter that welcomes short original research submissions on any branch of engineering, computer science, and technology, as well as their applications in industry, education, health, business, and other fields. Artificial intelligence, image processing, data mining, data science, bioinformatics, computational statistics, electrical engineering, electronics engineering, telecommunications, hardware systems, industrial automation, industrial engineering, fluids and physics engineering, mechanical engineering, chemical engineering, and their applications are among the engineering and computer science topics covered by the journal. All papers submitted will go through a peer-review process to ensure their quality. Submissions must contain original research and contributions to their field. The manuscript must adhere to the author’s guidelines and have never been published before.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 95 Documents
 6   7   8   9   10 
Performance-Efficiency Tradeoff Analysis of YOLOv8 Variants for Real-Time Multiclass Vehicle Detection in High-Density Traffic Dede Kurniadi; Asri Mulyani; Nuraisah Nuraisah
Engineering Science Letter Vol. 5 No. 01 (2026): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.001702

Abstract

The growing number of vehicles in Indonesia increases the need for an efficient and reliable traffic monitoring system. In Garut Regency, traffic monitoring is still carried out manually without the support of artificial intelligence, thus limiting the effectiveness of real-time traffic analysis. This study develops and evaluates a CCTV image-based vehicle classification model using YOLOv8 with a focus on application in real-world traffic conditions. The development process follows the Machine Learning Life Cycle (MLLC) stages, including data acquisition, preprocessing, training, and model evaluation. The dataset comprises 1,200 CCTV traffic images from 10 locations in Garut Regency, supplemented by 7,426 additional images from the Roboflow platform to enhance the diversity of viewpoints and visual conditions. To address class imbalance, an undersampling technique is applied so that each vehicle category, motorcycle, car, truck, bus, and public transportation, has a balanced number of instances. Three YOLOv8 variants, namely Nano, Small, and Medium, are trained and evaluated using two testing schemes: a 70:20:10 data split and a 5-fold cross-validation method. Performance evaluation was conducted using the mean Average Precision (mAP), precision, recall, and inference speed metrics. The experimental results show that YOLOv8m with the 5-Fold Cross Validation scheme produces the best performance with mAP@50 of 0.947, precision of 0.932, and recall of 0.883, while YOLOv8n excels in terms of inference speed with an average of ±8.77 ms/frame. These findings suggest that the selection of YOLOv8 variants should consider the balance between accuracy and computational efficiency and confirm the potential of YOLOv8 as an initial component of an automated CCTV-based traffic monitoring system in real-world environments with limited resources.
Comparative Thermal Analysis of Single and Double Channel Cold Plates for LiFePO4 Battery Modules Mohamad Yamin; Aldi Gufroni
Engineering Science Letter Vol. 5 No. 01 (2026): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002023

Abstract

Li-ion batteries provide many advantages and are essential components of energy-storage systems for electric automobiles. A crucial aspect of battery operation is the maintenance of optimal temperature levels, which necessitate the implementation of a robust battery thermal management system. This study assessed the efficacy of two cold-plate configurations, a single parallel channel and a double parallel channel, in regulating the temperature of a 7 Ah LiFePO4 battery module comprising of three cells. Employing ANSYS 2023 R1 Academic License, a numerical analysis was performed to evaluate their performance. A battery discharge rate of 5C was used to investigate the changes in the mass flow rates ranging from 0.001 to 0.005 kg/s. The cooling fluid and ambient temperatures were maintained at 25°C. This study shows that double parallel-channel cold plates can be more effective than single parallel-channel cold plates in reducing battery module temperatures. Additionally, the use of double parallel-channel cold plates can result in a lower cooling fluid pressure drop. In addition, the cooling fluid used in the double parallel channel cold plate had a lower heat-transfer coefficient and Nusselt number.
Subject Area Classification of Journal Articles Based on Metadata Using Bag of Words and Naïve Bayes Ainunna’imah; Herman Yuliansyah; Imam Riadi
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002041

Abstract

The rapid growth of scientific publications poses challenges in grouping journal articles based on subject area, especially when using metadata such as titles, abstracts, and keywords. However, differences in feature representation and classification algorithms often result in varying performance, requiring comparative studies to determine the optimal model combination. This study compares four combinations of subject area classification models, namely TF-IDF + Naïve Bayes, TF-IDF + Support Vector Machine, Bag-of-Words + Support Vector Machine, and Bag-of-Words + Naïve Bayes. The research process included text preprocessing, feature extraction, and testing using an 80% training and 20% testing data split scheme in five scenarios. The evaluation was performed using confusion matrices, accuracy, precision, recall, and F1-score. The experimental results showed variations in performance between models, with an average F1-score of 0.8103 for TF-IDF + Naïve Bayes, 0.8494 for TF-IDF + Support Vector Machine, 0.8297 for Bag-of-Words + Support Vector Machine, and 0.8335 for Bag-of-Words + Naïve Bayes as the best performance. These findings indicate that a word frequency-based approach combined with Naïve Bayes is effective for classifying journal article subject areas based on metadata, although challenges remain in subject areas with semantic proximity.
Development of a Non-Invasive Method for Monitoring of HV Circuit Breaker Switching Time Sagar Bhutada
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002082

Abstract

Modern HV circuit breakers may be vulnerable to catastrophic failure as they are designed for higher stress than the earlier CB designs with multiple interrupters per pole. With the advantage of controlled switching, improved performance is obtained for dielectrically well-designed interrupters, which achieve a re-ignition-free window during opening of the CB, in turn minimizing the risk of nozzle puncture. On occasion, asset owners may wish to check whether the CB is performing satisfactorily and whether the controllers are providing reliable and repeatable stress control. Monitoring of voltage waveforms during switching using well-established offline diagnostic methods will provide information about small re-ignitions and re-strikes. However, waveform measurement at moderately high signal frequency would require a CB outage to connect specialized equipment. A non-invasive measurement technique devising re-striking voltage sensors has been developed by the authors to measure high-frequency voltage waveforms occurring during switching operations without the need for an outage. Results of tests performed in the laboratory and 245 kV substation illustrating the capability of this new method to detect re-ignitions are presented in this paper. The proposed diagnostic approach relies on parameters such as operating times, pre-strike characteristics, and restrike detection. Transient electromagnetic emissions have been identified as a promising means to evaluate the above parameters non-intrusively.
Multi-Modal Deep Learning Approach for Waste Management: Integrating Image Classification and Text Mining for Environmental Awareness Santi Prayudani; Ainul Hizriadi; Yuyun Yusnida Lase
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002036

Abstract

Environmental degradation caused by inefficient waste management remains a major global challenge, largely due to the limitations of conventional systems that rely on manual waste sorting and limited utilization of heterogeneous data sources. This study proposes a novel multi-modal deep learning framework that integrates visual and textual information to enhance waste classification performance while simultaneously providing insights into environmental awareness. The proposed framework combines convolutional neural networks (CNNs) for waste image classification and a recurrent neural network with long short-term memory (LSTM) architecture for text analysis. Visual and textual feature representations are integrated through a feature-level fusion strategy using vector concatenation before final classification. The image dataset consists of six waste categories, cardboard, glass, metal, paper, plastic, and trash, while the textual dataset contains waste management descriptions, community feedback, and environmental discourse collected from public and field sources. Environmental awareness was assessed through text mining by identifying dominant themes related to recycling practices, waste sorting behavior, environmental responsibility, and public concern regarding pollution and sustainability issues. Experimental results demonstrate that the proposed multimodal framework achieves an accuracy of 88.9% and an F1-score of 0.89, outperforming image-only and text-only models with accuracies of 78.4% and 81.2%, respectively. This corresponds to absolute performance improvements of 10.5% over the image-based model and 7.7% over the text-based model, while reducing the classification error rate by 40.96%. Furthermore, the multimodal model exhibits superior robustness under degraded data conditions, with only a 4.7% reduction in accuracy compared to larger performance declines observed in unimodal approaches. The main contribution of this study lies in the integration of waste image recognition and environmental-awareness extraction within a unified multimodal learning framework, enabling not only accurate waste categorization but also the generation of behavioral and sustainability-related insights that support more intelligent and sustainable waste management systems.
Ensemble Machine Learning Models for Accurate Prediction of the Carbon Footprint of SCM-Blended Concrete Yulis Widhiastuti; Eko wahyu Abryandoko; Laily Agustina Rahmawati; Ocha Silvia Kencana; Putri Puja Pratiwi
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002078

Abstract

Concrete contributes approximately 8% of global CO₂ emissions. The incorporation of Supplementary Cementitious Materials (SCMs) as partial cement replacements is widely recognized as an effective strategy to reduce the carbon footprint of concrete. However, accurately quantifying the relationship between mix composition and carbon emissions remains challenging. This study develops a machine learning model to predict the carbon footprint of SCM-based concrete using material composition data. A global dataset comprising 1,456 mix designs collected from 136 publications across 27 countries was compiled, resulting in 1,294 valid samples after preprocessing. Four regression algorithms were evaluated: Support Vector Regression (SVR), Random Forest Regression (RFR), Decision Tree Regression (DTR), and Gradient Boosting Regression (GBR), with hyperparameter tuning using 5-fold cross-validation. All models achieved high predictive accuracy (R² > 0.998), with GBR demonstrating the best performance (R² = 0.9996; RMSE = 1.7452 kg CO₂/m³; MAE = 1.2779 kg CO₂/m³). Feature importance analysis identified cement as the dominant contributor (>99.8%) to emissions. Sensitivity analysis confirmed a strong linear relationship between cement content and CO₂ emissions (~0.82 kg CO₂ per kg cement). These findings support emission-reduction strategies in sustainable concrete design.
Taguchi-Based Optimization of Mix Design and Mechanical Properties of Epoxy Polymer Concrete with Recycled Coarse Aggregate Khusnul Aldi Saputra; Eva Arifi; Desy Setyowulan
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002091

Abstract

This study examines the mix design and mechanical properties of epoxy polymer concrete utilizing fully recycled coarse aggregate and fly ash as a mineral filler through a Taguchi-based optimization framework. An L9 orthogonal array including four control factors and three levels was employed to incorporate epoxy resin content, resin–hardener ratio, coarse-to-fine aggregate ratio, and class C fly ash proportion. All mixtures were designed using the absolute-volume method so that the total volume of the constituent materials exactly matched the target specimen volume. The research test object was a 50 × 50 × 50 mm cube that follows the experimental design in method B of the ASTM C 579-96 standard for polymer concrete. Cube specimens tested at seven days for compressive strength and static modulus of elasticity based on the stress–strain response. The compressive strengths varied from around 11.14 to 57.20 MPa, whereas the average static modulus ranged from about 0.58 GPa to nearly 2.95 GPa. Taguchi analysis and ANOVAs conducted on both mean strength and S/N ratios consistently revealed epoxy content, resin–hardener ratio, and coarse-to-fine aggregate ratio as the dominant factors, while fly ash served as a secondary modifier. The optimal combination comprises 25% polymer matrix of the total specimen volume, a resin–hardener ratio of 1.5:1, a balanced coarse-to-fine aggregate ratio of 1:1, and an quantity of fly ash around 30% of the total volume of fine aggregate. According to Taguchi analysis, this optimal combination leads to a predicted compressive strength of approximately 52.89 to 61.23 MPa. An independent confirmation mixture prepared at this optimal combination achieved an average strength of about 57.46 MPa, aligning well with Taguchi predictions. The linear relationship between compressive strength and static modulus of elasticity shows a positive correlation. This linear relationship enables a straightforward empirical formula to determine the stiffness of epoxy polymer concrete with recycled coarse material, predicated on its compressive strength.
Scrum-Driven Task Management for University IT Governance: A Multi-Role Usability Evaluation Muhammad Faried Saputra; Aris Budianto
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002246

Abstract

Task management is an essential aspect of organizational operations that involves coordinating various work activities and facilitating collaboration among team members. However, in many organizations, task management processes are still carried out through informal communication channels such as direct conversations, email, or instant messaging applications, which complicate task monitoring and documentation. This study aims to develop a web-based task management system that supports more structured task management within the Directorate of Information and Communication Technology at Universitas Sebelas Maret. The system was developed through four iterative Scrum sprints over 10 weeks. Functional testing employed the Black-Box Testing method, and usability was assessed using the System Usability Scale (SUS) with 20 purposively selected respondents across four user roles: administrators, sub-directorate heads, section heads, and staff members. The results indicate that all system functions operated successfully, and the system achieved an average SUS score of 75.25 — categorized as Good and exceeding the standard usability benchmark of 68, with scores ranging from 71.0 (section heads) to 81.0 (administrators). These findings suggest that Agile Scrum-based development produces task management systems that are adaptive to organizational needs and well-accepted across hierarchical user roles, with implications for IT governance practice in higher education institutions.
Trade-Off Analysis of Moving Average Filter in Light Sensors Nova Ariyanto; Farid Baskoro; Rifki Firmansyah; Lilik Anifah; Tri Wrahatnolo; Dimas Arya Soeadyfa Fridyatama
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002255

Abstract

Light intensity measurements based on sensors often experience signal quality degradation due to noise interference. Although filtering methods are commonly used to reduce noise, improvements in signal stability are frequently accompanied by changes in dynamic response, resulting in a trade-off between accuracy and response speed that has not been extensively analyzed. This study aims to quantitatively evaluate the effect of Moving Average Filter (MAF) parameters on this trade-off in light sensor systems. The proposed method employs a first-order system simulation with a step input signal contaminated by White Gaussian Noise, which is subsequently processed using the MAF with various window sizes ( = 3, 5, 10, 20, and 40). The evaluation is conducted using Root Mean Square Error (RMSE) and rise time as indicators of estimation accuracy and response speed, respectively. The results demonstrate that increasing the window size significantly reduces the RMSE, decreasing from 0.0156 to 0.0072 under step-up conditions and from 0.0132 to 0.0066 under step-down conditions. Optimal performance is observed within the range of  = 10–20. However, this improvement in accuracy is accompanied by an increase in rise time, from 0.1027 s to 0.1175 s for step-up conditions and from 0.1036 s to 0.1191 s for step-down conditions, indicating a slower dynamic response. These findings confirm the existence of a trade-off between signal accuracy and response speed. Therefore, this study provides a quantitative basis for determining optimal filter parameters by considering the balance between measurement accuracy and system responsiveness in light intensity sensing applications.
Ride-Hailing Quality Gaps and Improvement Priorities: SERVQUAL-Kano Study in Mid-Sized Indonesian City Fadiyah Ghina Salsabila; Achmad Wicaksono; Agus Dwi Wicaksono
Engineering Science Letter Vol. 5 No. 02 (2026): In Press - Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.002289

Abstract

Digitalization has accelerated ride-hailing growth by offering urban commuters convenience and flexibility. In Indonesia, rising usage has intensified competition among platforms such as Grab and its rivals. Despite its extensive reach, Grab continues to face negative perceptions concerning pricing, inconsistent service, and suboptimal user experiences, which erode customer satisfaction and loyalty. Malang City was selected for its high mobility and rapidly growing user base. As a mid-size city with moderate density and growing transport demand, Malang is suitable for studying ride-hailing beyond megacities. This study integrates SERVQUAL and the Kano Model to identify, classify, and prioritize service attributes influencing GrabBike user satisfaction. A purposive sample of 385 respondents completed an online survey (Google Forms) between December 2025 and January 2026. The overall quality ratio (Q) was 0.85, and Tangibles was the lowest performing dimension. RL4 (fare suitability) recorded the largest gap (-1.65), a critical priority. Kano classification yielded 7 Must-Be, 3 One-Dimensional, 3 Attractive, 1 Indifferent, and 1 Reverse attributes. This integrated approach constitutes a novel, data-driven framework for prioritizing service enhancements. The findings provide guidance to remedy dissatisfiers and invest in delight-enhancing attributes, while establishing local quality benchmarks for policymakers.

Page 9 of 10 | Total Record : 95

 6   7   8   9   10 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 02 (2026): In Press - Engineering Science Letter Vol. 5 No. 01 (2026): Engineering Science Letter Vol. 4 No. 03 (2025): Engineering Science Letter Vol. 4 No. 02 (2025): Engineering Science Letter Vol. 4 No. 01 (2025): Engineering Science Letter Vol. 3 No. 03 (2024): Engineering Science Letter Vol. 3 No. 02 (2024): Engineering Science Letter Vol. 3 No. 01 (2024): Engineering Science Letter Vol. 2 No. 03 (2023): Engineering Science Letter Vol. 2 No. 02 (2023): Engineering Science Letter Vol. 2 No. 01 (2023): Engineering Science Letter Vol. 1 No. 02 (2022): Engineering Science Letter Vol. 1 No. 01 (2022): Engineering Science Letter More Issue