cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dahlan Abdullah
Contact Email
dahlan@unimal.ac.id
Phone
+62811672332
Journal Mail Official
ijestyjournal@gmail.com
Editorial Address
Jl. Tgk. Chik Ditiro, Lancang Garam, Lhokseumawe, Aceh - Indonesia, 24351
Location
Kota lhokseumawe,
Aceh
INDONESIA
International Journal of Engineering, Science and Information Technology
Published by Universitas Malikussaleh
ISSN : -     EISSN : 27752674     DOI : -
Core Subject : Science, Education, Social, Engineering,
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation
The journal covers all aspects of applied engineering, applied Science and information technology, that is: Engineering: Energy Mechanical Engineering Computing and Artificial Intelligence Applied Biosciences and Bioengineering Environmental and Sustainable Science and Technology Quantum Science and Technology Applied Physics Earth Sciences and Geography Civil Engineering Electrical, Electronics and Communications Engineering Robotics and Automation Marine Engineering Aerospace Science and Engineering Architecture Chemical & Process Structural, Geological & Mining Engineering Industrial Mechanical & Materials Science: Bioscience & Biotechnology Chemistry Food Technology Applied Biosciences and Bioengineering Environmental Health Science Mathematics Statistics Applied Physics Biology Pharmaceutical Science Information Technology: Artificial Intelligence Computer Science Computer Network Data Mining Web Language Programming E-Learning & Multimedia Information System Internet & Mobile Computing Database Data Warehouse Big Data Machine Learning Operating System Algorithm Computer Architecture Computer Security Embedded system Coud Computing Internet of Thing Robotics Computer Hardware Information System Geographical Information System Virtual Reality, Augmented Reality Multimedia Computer Vision Computer Graphics Pattern & Speech Recognition Image processing ICT interaction with society, ICT application in social science, ICT as a social research tool, ICT in education
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 593 Documents
 39   40   41   42   43 
Benchmarking Techniques for Real-Time Evaluation of LLMs In Production Systems Chandra, Reena; Bansal, Rishab; Lulla, Karan
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.955

Abstract

Large language models (LLMs) should perform reliably and work efficiently in today's applications that use AI chatbots, copilots, and search systems. Usually, the traditional type of benchmarking deals mainly with understanding linguistics and accurate task performance, while important factors like latency, how much memory is used, and optimisation are ignored. A benchmarking framework is proposed in this study that reviews LLMs using four critical factors: number of tokens processed per second, accuracy, peak memory usage, and Efficiency. Using the Open LLM Performance dataset, 350 open-source models were examined with standardized tools and methods across various families and sizes of parameters. According to the studies, the TinyStories-33M and OPT-19M middle-scale models are ideal for practical use because they handle many words per second without taking up much memory. ONNX Run-time uses less memory than PyTorch, and applying LLM.fp4 quantisation greatly increases throughput without a significant loss in accuracy. Visualisations and ranks are presented to help choose a production model. By following the framework, AI engineers, MLOps teams, and system architects can spot innovative models that can be built, deployed, expanded, and managed within budget. It improves LLM assessment by relating technical measures to practical limitations in real systems so that smarter choices can be made for systems used in actual operations.
Classification Of Outpatient Visit Status Walking at Dr. Zubir Mahmud Hospital Using Algoritma C4.5 Fikria, Putri; Dinata, Rozzi Kesuma; afrillia, Yesy
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.865

Abstract

This study aims to classify the status of outpatient visits at RSUD Dr. Zubir Mahmud into three main categories, namely "Very Urgent", "Urgent", and "Not Urgent”, using the C4.5 algorithm. The web-based system uses the PHP programming language and MySQL database to ensure ease of implementation and efficient data management. The classification process is done by setting threshold parameters, calculating entropy, and the gain ratio to form an accurate and reliable decision tree. The results show that the C4.5 algorithm can classify patient visit data with a reasonably high accuracy rate, which is 93.75% for 2022 data and reaches 100% for 2023 data. In 2022 the “Very Urgent" category had 9 True Positives (TP); in 2023, the number remained consistent. However, in both years, there were also False Negatives in the same category, with 4 cases in 2022 and 5 cases in 2023. The "Urgent" and "Not Urgent" categories show suboptimal classification performance due to uneven data distribution, which causes the precision and recall values in these categories low. Model evaluation was conducted using evaluation metrics such as precision, recall, and F1 score. The evaluation results show that the model works very well in identifying high-priority categories, but further development is needed to improve classification in other categories. This system is expected to be a reliable tool in decision-making in health services, especially in determining the priority of patient services appropriately and efficiently. With further development, this system has the potential to be widely applied in various other hospitals.
Optimizing YOLO-Based Algorithms for Real-Time BISINDO Alphabet Detection Under Varied Lighting and Background Conditions in Computer Vision Systems Hayati, Lilis Nur; Handayani, Anik Nur; Gunawan Irianto, Wahyu Sakti; Asmara, Rosa Andrie; Indra, Dolly; Damanhuri, Nor Salwa
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.948

Abstract

This research explores the optimization of YOLO-based computer vision algorithms for real-time recognition of Indonesian Sign Language (BISINDO) letters under diverse environmental conditions. Motivated by the communication barriers faced by the deaf and hearing communities due to limited sign language literacy, the study aims to enhance inclusivity through advanced visual detection technologies. By implementing the YOLOv5s model, the system is trained to detect and classify correct and incorrect BISINDO hand signs across 52 classes (26 correct and 26 incorrect letters), utilizing a dataset of 3,900 images augmented to 10,920 samples. Performance evaluation employs k-fold cross-validation (k=10) and confusion matrix analysis across varied lighting and background scenarios, both indoor and outdoor. The model achieves a high average precision of 0.9901 and recall of 0.9999, with robust results in indoor settings and slight degradation observed under certain outdoor conditions. These findings demonstrate the potential of YOLOv5 in facilitating real-time, accurate sign language recognition, contributing toward more accessible human-computer interaction systems for the deaf community.
Tracking the Footprints of the Veda Teachings Implementation Study on Hindus in Bali Pastika, Mangku; Ngurah Sudiana, I Gusti; Purnamawati, Sri Putri; D.E, Relin
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.973

Abstract

The Vedic teachings have been the primary foundation of the religious and social life of the Balinese Hindu community. As part of the spiritual heritage of ancient India, these teachings entered Bali through trade routes and cultural migration since the first century AD. Over time, the Vedic teachings have been acculturated with local culture, creating unique and dynamic Balinese Hindu practices. This study examines how the Vedic teachings in Bali are applied in everyday life, social systems, and religious practices, focusing on the concepts of dharma, karma, and moksha, which remain the ethical guidelines of the community. The research method used is qualitative with a descriptive narrative approach, involving interviews with religious figures, direct observation of yadnya rituals, and analysis of historical and religious documents. Through this approach, the study seeks to understand how the Balinese Hindu community internalizes the Vedic teachings in their lives, individually and collectively. Oral traditions and religious rituals are the primary means of preserving the Vedic teachings, which are adapted to the local social and cultural context. The results of the study show that although the Vedic teachings remain the basis of the spiritual life of the Balinese Hindu community, the process of adaptation and acculturation has formed religious practices different from the Vedic teachings that developed in India. Balinese society maintains core values such as dharma and karma. It aligns them with local concepts such as desa, kala, and patra, which allow flexibility in implementing rituals and religious rules. The role of brahmanas as guardians of the Vedic teachings is still vital in the social structure, but changing times bring new challenges to the sustainability of these teachings, especially in the face of modernization and globalization. Modernization and urbanization have given rise to various shifts in religious practices, sometimes leading to the reduction of spiritual meaning and the transformation of rituals into mere formalities. Hindu religious education in Bali can play a role in strengthening the community's understanding and appreciation of the Vedic teachings with methods that are more contextual and relevant to the times. Overall, the Vedic teachings still play a central role in the lives of Balinese Hindu society, although in a form that has undergone modification and acculturation. Academic studies and cultural preservation are strategic steps in maintaining the sustainability of this spiritual heritage amidst changing times. This study emphasizes the importance of preservation efforts through an empirical approach that explores the actual practice of the Vedic teachings and pays attention to how the Balinese Hindu community maintains its religious identity amid globalization.
Creation of a 3D animated film titled "Made and the Lost Spirit" Krishna, Ida Bagus Ista; Dinata, Ramanda Dimas Surya; Jaya, Kadek Prana; Rimbawan, Ari
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.893

Abstract

3D Animation is a form of Animation that uses three-dimensional objects so that the visuals presented look more real and immersive. 3D objects can be rotated and viewed from various perspectives. Bali, with its unique cultural values, should not only be a tourist attraction but can also be the basis for creating multiple creations, especially in animation design, which can be an attraction and introduce Balinese culture to the international arena. In this research, the Animation tells the story of a child named Made who did not have a parental figure from childhood and lived alone with his grandfather in the village. The village where Made lives is not safe; evil demons have destroyed it. This made Made trained by his grandfather to become a strong child worthy of adventure to save the village and find his missing parents. Made's adventure is not alone; Made is accompanied by a good spirit in the form of a barong named Dharma, who will guide Made's journey. Made's efforts are constantly hampered by his older brother, who is an evil spirit with great power, and the only way Made can stop his grandfather is by joining forces with Dharma. The method used in this research is computer graphics with pre-production, production, and post-production stages. This research aims to design an animation entitled Made and The Lost Spirit inspired by the values of the Galungan holiday celebration in Bali. Apart from this, the novelty of this Animation lies in highlighting Balinese culture and ornaments in the visual elements presented in the creation of international standard quality animation with intellectual Property owned by the author.
Cryptocurrency Prospect in the International Market: Pre-sent Value Management and Islamic Perspective Ilham, Rico Nur; Arliansyah, Arliansyah; Juanda, Reza; Sinta, Irada; Ramansyah, Frengki Putra; Multazam, Muhammad
International Journal of Engineering, Science and Information Technology Vol 5, No 1 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i1.1094

Abstract

Cryptocurrency is an investment commodity that can generate returns and already has a license to trade in exchange.  This study aims to examine the prospects of digital cryptocurrency assets more deeply by summarising the results of literature studies in various countries.  As a result of this study, it is known that many countries whose governments make strict regulations on support for legality and allow cryptocurrency transactions include: European Union members, namely Germany and Italy, and non-member countries of the European Union, such as Gibraltar.  Furthermore, in the Americas, there are Canada and Venezuela.  In East Asia and the Asia Pacific, Australia and Japan support the existence of Cryptocurrency.  Meanwhile, in Southeast Asian countries, there are contradictions between several countries, including Indonesia, Malaysia, Vietnam, and the Philippines, that reject cryptocurrency transactions because they are considered threats to money laundering and the problem of terrorism.  Of course, this is a prospect that cryptocurrency transactions can meet the expectations of all users in the world by making regulations regarding the legality of Cryptocurrency so that the transaction model can be integrated between users, both as an asset and a substitute for international payment currencies.
Analysis of Boarding House Feasibility and Satisfaction Using Data Mining with the C4.5 Algorithm Based on Service Quality and Facilities Manik, Aktina; Abdullah, Dahlan; Ar Razi, Ar Razi
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.896

Abstract

This research develops a boarding house eligibility classification system using the C4.5 algorithm based on service quality and available facilities. The system evaluates boarding house eligibility by considering various factors such as management services, cleanliness, security, room facilities, public facilities, internet access, comfort, and price. Each of these factors is given a specific weight based on its importance to the tenants, and they are used to classify boarding houses as luxury, standard, and economical. The classification results show that 43% of luxury boarding houses were deemed eligible, while 57% were not. In the standard boarding house category, 21% were classified as eligible, and 79% as ineligible, while in the economical category, 23% were eligible and 77% were ineligible. Using the Confusion Matrix and Classification Report, model evaluation revealed precision ranging from 0.4 to 1.0, recall from 0.67 to 1.0, and F1-scores from 0.5 to 0.91, demonstrating a reasonably high overall accuracy. Additionally, feature importance analysis revealed that price, water and electricity availability, and room facilities are the most influential factors in determining boarding house eligibility. The system's performance was tested against a dataset of real-world boarding houses, and the results suggest that it can accurately classify boarding houses based on key factors that affect tenant satisfaction. The system has the potential to serve as a valuable decision-making tool for boarding house owners, helping them improve service quality and for prospective tenants, enabling them to make more informed housing choices based on their preferences and needs.
A Hybrid GDHS and GBDT Approach for Handling Multi-Class Imbalanced Data Classification Hartono, Hartono; Zuhanda, Muhammad Khahfi; Syah, Rahmad; Rahman, Sayuti; Ongko, Erianto
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.894

Abstract

Multiclass imbalanced classification remains a significant challenge in machine learning, particularly when datasets exhibit high Imbalance Ratios (IR) and overlapping feature distributions. Traditional classifiers often fail to accurately represent minority classes, leading to biased models and suboptimal performance. This study proposes a hybrid approach combining Generalization potential and learning Difficulty-based Hybrid Sampling (GDHS) as a preprocessing technique with Gradient Boosting Decision Tree (GBDT) as the classifier. GDHS enhances minority class representation through intelligent oversampling while cleaning majority classes to reduce noise and class overlap. GBDT is then applied to the resampled dataset, leveraging its adaptive learning capabilities. The performance of the proposed GDHS+GBDT model was evaluated across six benchmark datasets with varying IR levels, using metrics such as Matthews Correlation Coefficient (MCC), Precision, Recall, and F-Value. Results show that GDHS+GBDT consistently outperforms other methods, including SMOTE+XGBoost, CatBoost, and Select-SMOTE+LightGBM, particularly on high-IR datasets like Red Wine Quality (IR = 68.10) and Page-Blocks (IR = 188.72). The method improves classification performance, especially in detecting minority classes, while maintaining high accuracy.
Optimization of LPG Distribution for a Multiplatform-Based LPG Marketplace Budianto, Herman; Mustaqin, Farhan Faisal Zainul; Setiawan, Esther Irawati; Santoso, Joan
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.994

Abstract

Marketplace applications have become an essential digital solution supporting online transactions, including LPG distribution. The development of this application adopts a multiplatform approach, enabling the application to run on various devices, particularly Android platforms and websites. Using the React Native framework, developers can build applications with a single, efficient codebase for multiple platforms. This study aims to provide users with convenience in purchasing LPG without leaving their homes while offering a more practical and effective user experience. This research includes features for selling, buying, payment, and delivery via courier. The transaction feature facilitates sellers' recording of sales within the application. The results of alpha testing indicate that the Elpijiku marketplace app works well despite some significant errors or bugs. However, acceptance testing results were very positive, with 91% of respondents rating the application and user experience as good. These findings indicate that the Elpijiku application meets user needs in terms of convenience and efficiency and is suitable for use as a digital solution for LPG distribution.
Transformer-Based Tabular Foundation Models: Outperforming Traditional Methods with TabPFN Babu, R Anand; Priya V, Vishwa; Kumar Mishra, Manoj; Ramesh Raja, Inakoti; Kiran Chebrolu, Surya; Swarna, B
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1146

Abstract

Scientific research and commercial applications rely heavily on tabular data, yet efficiently modelling this data has constantly been a problem. For over twenty years, the standard method for machine learning has been based on traditional models, with gradient-boosted decision trees (GBDTs). Despite recent advancements in deep learning, neural networks often fail to provide satisfactory results on compact tabular datasets due to factors such as overfitting, insufficient data intricate feature relationships. The study offers a Tabular Prior data Fitted Network, a foundation model developed by meta-learning on more than one million synthetic datasets generated sequentially, which is constructed on transformers to tackle these limitations. Without retraining or hyperparameter optimization, TabPFN learns to anticipate the best solutions for tabular problems, gaining inspiration from the achievements of GPT-like models in natural language processing. When applied to small to medium-sized datasets, its cutting-edge performance in inference speed accuracy outperforms that of traditional methods. TabPFN redefines efficient and scalable tabular data modelling, including generative capabilities, few-shot learning, rapid adaptation.

Page 41 of 60 | Total Record : 593

 39   40   41   42   43 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol 6, No 1 (2026) Vol 5, No 4 (2025) Vol 5, No 3 (2025) Vol 5, No 2 (2025) Vol 5, No 1 (2025) Vol 4, No 4 (2024) Vol 4, No 3 (2024) Vol 4, No 2 (2024) Vol 4, No 1 (2024) Vol 3, No 4 (2023) Vol 3, No 3 (2023) Vol 3, No 2 (2023) Vol 3, No 1 (2023) Vol 2, No 4 (2022) Vol 2, No 3 (2022) Vol 2, No 2 (2022) Vol 2, No 1 (2022) Vol 1, No 4 (2021) Vol 1, No 3 (2021) Vol 1, No 2 (2021) Vol 1, No 1 (2021) More Issue