cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jamaluddin
Contact Email
hengkitamando26@gmail.com
Phone
+6281397181985
Journal Mail Official
publication.aptikomsumut@gmail.com
Editorial Address
Jl. Alumni No.3, Padang Bulan, Kec. Medan Baru, Kota Medan, Sumatera Utara 20155
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer Science and Research
Published by Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer Provinsi Sumatera Utara
ISSN : -     EISSN : 29862337     DOI : -
Core Subject : Economy, Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Library & Information Science
Journal of Computer Science and Research (JoCoSiR) is aimed to publish research articles on theoretical foundations of information and computation, and of practical techniques for their implementation and application in computer systems. Journal of Computer Science and Research (JoCoSiR) published quarterly and is a peer reviewed journal covers the latest and most compelling research of the time. Journal of Computer Science and Research (JoCoSiR) is managed and published by APTIKOM Wilayah 1 Sumatera Utara.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 63 Documents
 1   2   3   4   5 
Development of quantum machine learning for protein structure prediction Bianco, Nimbe Qureshi; Miyashita, Sierra-Sosa; Pathak, Pathak
Journal of Computer Science and Research (JoCoSiR) Vol. 1 No. 4 (2023): Oct: Computing Quantum and Related Fields
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v1i4.31

Abstract

Quantum Machine Learning (QML) holds immense potential in revolutionizing the prediction of protein structures, a critical challenge in computational biology. This research explores the application of quantum states, including superposition and entanglement, to capture the intricate and uncertain nature of protein conformations. Quantum gates and Fourier transforms are investigated as tools to manipulate and enhance quantum states, showcasing their ability to discern features essential for accurate predictions. The integration of hybrid quantum-classical models addresses the current limitations of quantum hardware, combining classical and quantum computing strengths. Quantum error correction is identified as a pivotal aspect for ensuring the reliability of predictions in the quantum domain. A numerical example is presented to illustrate the probabilistic nature of quantum states and the potential for obtaining optimized outcomes through quantum machine learning. The findings highlight the need for continued interdisciplinary collaboration between quantum physicists, computer scientists, and computational biologists to advance the field. While the exploration of QML for Protein Structure Prediction is in its early stages, the research emphasizes the transformative potential of quantum computing in unraveling the complexities of molecular structures.
Development of quantum neural networks for complex data classification Savvas, Asgari; Lizarralde, Mian Snell; Marsoit, Patrisia Teresa
Journal of Computer Science and Research (JoCoSiR) Vol. 1 No. 4 (2023): Oct: Computing Quantum and Related Fields
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v1i4.32

Abstract

This research explores the development of Quantum Neural Networks (QNNs) as a transformative approach for complex data classification. Utilizing a numerical example, we illustrate the foundational quantum principles of superposition and entanglement within QNNs. The hybrid quantum-classical processing paradigm is introduced, emphasizing the seamless integration of quantum and classical components, acknowledging the challenges of quantum error correction and noise in Noisy Intermediate-Scale Quantum (NISQ) devices. While the example is deliberately simple, it serves as a starting point for understanding the unique advantages and challenges associated with QNNs. Our findings highlight the potential of quantum computation for parallel processing but also underscore the need to address current limitations for practical applications. Future research directions include investigating sophisticated quantum circuits, exploring error mitigation strategies, and assessing QNN performance across diverse datasets. Collaboration between quantum computing and machine learning communities is essential for the advancement of QNNs, and developments in quantum hardware will play a pivotal role in realizing their full potential. This study contributes to the evolving discourse at the intersection of quantum computing and machine learning, providing foundational insights and laying the groundwork for further exploration in this rapidly advancing field.
Optimizing Convolutional Neural Networks for Image Classification Harahap, Muhammad Khoiruddin; Xu, Chlap Min; Zhu, Kong Huang
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 1 (2024): Jan: CNN and Artificial
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i1.33

Abstract

This research explores the optimization of Convolutional Neural Networks (CNNs) for image classification through a numerical experiment. A simplified CNN architecture is trained on a small dataset comprising 100 randomly generated images with a resolution of 28×28. The model incorporates key components such as convolutional layers, batch normalization, max-pooling, and dense layers. Training involves 10 epochs using the Adam optimizer and sparse categorical cross-entropy loss. The results reveal promising training accuracy of 85%, but the validation accuracy, a crucial metric for generalization, lags at 60%. The discussion emphasizes the limitations of the small and synthetic dataset, underscoring the importance of real-world, diverse datasets for meaningful experimentation. The example serves as a foundation for understanding CNN training dynamics, with implications for refining models in more realistic image classification scenarios. The conclusion calls for future research to focus on advanced techniques, larger datasets, and comprehensive validation processes to enhance the reliability and applicability of CNN models in practical applications.
Integrating barcode technology into warehouse management systems for enhanced efficiency and inventory accuracy Deepali, Charumati; Monika, Priyankan; Dharmendra, Sonali
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 1 (2024): Jan: CNN and Artificial
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i1.34

Abstract

This research explores the integration of barcode technology into Warehouse Management Information Systems (WMS) to optimize warehouse operations. Through a comprehensive review of literature, case studies, and industry practices, the study investigates the benefits, challenges, and best practices associated with barcode-based WMS implementation. Key findings reveal the transformative impact of barcode technology on operational efficiency, inventory accuracy, and order processing speed in warehouses. A framework for designing barcode-based WMS is developed, providing practical guidance for organizations seeking to leverage technology to enhance warehouse management practices. The implications of the research extend to businesses, employees, customers, and supply chain partners, highlighting opportunities for cost savings, productivity improvement, and customer satisfaction.
Enhancing Disaster Resilience: Leveraging Raspberry Pi Technology for Natural Disaster Management Information Systems Harukap, Kayo; Shizuka, Takara
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 1 (2024): Jan: CNN and Artificial
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i1.35

Abstract

Natural disasters pose significant threats to human lives, infrastructure, and ecosystems, necessitating effective disaster management strategies to mitigate their impacts. In this research, we explore the design and implementation of a Natural Disaster Management Information System (NDMIS) using Raspberry Pi technology. The NDMIS leverages Raspberry Pi's versatility, affordability, and scalability to collect, process, and analyze real-time data, enabling stakeholders to make informed decisions and take proactive measures during disaster events. Through interdisciplinary collaboration and community engagement, the research demonstrates the transformative potential of Raspberry Pi in democratizing access to critical information and resources, empowering communities to build resilience and enhance disaster response capabilities. The findings underscore the importance of technological innovation, community empowerment, and interdisciplinary collaboration in advancing disaster management practices. Furthermore, the research identifies future research directions, including algorithm optimization, interoperability, and human-centered design, aimed at further enhancing the effectiveness and scalability of NDMIS solutions. This research represents a significant step towards leveraging Raspberry Pi technology for building more resilient, adaptive, and sustainable communities in the face of natural disasters.
Enhancing Electoral Decision-Making: A Social Learning Network Election Decision Support System Utilizing AHP and PROMETHEE Methods Alesha, Aisyah; Simbolon , Romasinta; Batubara, Juliana; Panjaitan, Firta Sari
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 1 (2024): Jan: CNN and Artificial
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i1.36

Abstract

This In today's digital age, the intersection of technology, democracy, and citizen participation has become increasingly prominent. This research explores the development and application of a Social Learning Network Election Decision Support System (SLNEDSS) using Analytic Hierarchy Process (AHP) and Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) methods to enhance electoral decision-making processes. By leveraging social learning networks as platforms for information dissemination and deliberative discourse, SLNEDSS empowers citizens to make informed choices that reflect their values, aspirations, and preferences. The integration of AHP and PROMETHEE methods within SLNEDSS provides users with structured frameworks for evaluating electoral alternatives, synthesizing stakeholder preferences, and facilitating transparent and systematic decision-making processes. Through empirical studies, the effectiveness of SLNEDSS in enhancing the quality and inclusivity of electoral outcomes is demonstrated, highlighting its transformative potential in shaping the future of democratic governance. The research also identifies challenges and limitations associated with SLNEDSS, such as algorithmic biases and user adoption, and suggests directions for future research to address these shortcomings. Ultimately, this research contributes to advancing the frontiers of knowledge and innovation in the field of electoral decision support systems, paving the way for a more informed, inclusive, and responsive democracy in the digital age.
A Decision Support System for Selecting the Best Private Universities in Yogyakarta Using MARCOS Method Nasyuha, Asyahri Hadi
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 2 (2024): April: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i2.37

Abstract

Decision-making in higher education often involves evaluating multiple and sometimes conflicting criteria, particularly in regions such as Yogyakarta, Indonesia, which hosts more than one hundred private universities. Selecting the best institution is therefore a critical and complex task for students, parents, and policymakers. Traditional decision support system (DSS) methods such as SAW, TOPSIS, and AHP are widely applied but remain prone to sensitivity in weight assignment and rank reversal, which may compromise reliability. This study proposes the use of the MARCOS (Measurement of Alternatives and Ranking according to Compromise Solution) method, a recent multi-criteria decision-making (MCDM) technique introduced in 2019, to overcome these shortcomings. MARCOS simultaneously considers both ideal and anti-ideal solutions to achieve more stable rankings. A DSS model was developed and applied to five private universities in Yogyakarta UII, UMY, UAJY, USD, and UTDI evaluated across six criteria: accreditation, doctoral lecturers, research publications, facilities, tuition fees, and graduate employability. The results revealed that Universitas Islam Indonesia (UII) obtained the highest utility score (f(Ki)=0.7404 and ranked first, followed by Universitas Muhammadiyah Yogyakarta (0.6931), Universitas Atma Jaya Yogyakarta (0.6498), Universitas Sanata Dharma (0.6126), and Universitas Teknologi Digital Indonesia (0.5831). Sensitivity analysis further demonstrated that the ranking of UII remained unchanged across weight variations, confirming the robustness of MARCOS. Comparisons with TOPSIS also showed fewer rank reversals, reinforcing the stability of MARCOS in multi-criteria decision-making. This research contributes a novel application of MARCOS in higher education and offers stakeholders a transparent, objective, and data-driven tool for selecting the best private universities in Yogyakarta.
Classification of Health Indicators for Diabetes Mellitus Prediction Using a TabTransformer Model on Clinical Tabular Data Khaidar, Al; Kurnia, Sri
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 2 (2024): April: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i2.54

Abstract

Diabetes mellitus is a non-communicable disease with a continuously increasing global prevalence and impacts quality of life and long-term economic burden; therefore, data-driven early detection is crucial to prevent clinical complications. This study aims to develop a diabetes prediction model using the TabTransformer architecture by utilizing a clinical dataset from Kaggle containing 100,000 patient profiles with more than 35 relevant numerical and categorical attributes. The research stages include preprocessing to remove potential leakage features, target and feature separation, numerical normalization, and categorical feature embedding. The TabTransformer model is applied for binary classification (diagnosed_diabetes) by utilizing a self-attention mechanism to capture latent interactions between tabular features, and is evaluated using accuracy, precision, recall, F1-score, and ROC AUC metrics. The results show competitive performance with an accuracy of 82.55%, a diabetes class F1-score of 0.8527, and a ROC AUC value of 0.9009, indicating the model's discriminatory ability to reliably distinguish diabetic and non-diabetic patients. Based on these results, the TabTransformer architecture has been proven effective for processing large-scale clinical tabular data and is worthy of consideration in the implementation of an artificial intelligence-based medical decision support system for predicting chronic diseases, especially diabetes mellitus.
The Clustering YouTube Videos of SMK Negeri 1 Percut Sei Tuan Based on Views and Likes Using the K-Means Algorithm Asyifaa, Nathania; Iqbal , Muhammad
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 2 (2024): April: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i2.59

Abstract

The increasing use of YouTube as a digital learning and promotional platform has encouraged educational institutions to optimize their content strategies to enhance audience engagement. This study aims to analyze and categorize YouTube videos from SMK N 1 Percut Sei Tuan based on views and likes using the K-Means clustering algorithm. A total of 50 videos were collected and preprocessed using normalization techniques to ensure consistent data scaling. The optimal number of clusters was determined using the Elbow Method, resulting in three distinct engagement groups: high, medium, and low. The clustering process was implemented using Python with the support of the pandas, numpy, scikit-learn, and matplotlib libraries. The results show that videos categorized under high engagement typically consist of school achievements and major institutional events, while low-engagement videos are related to administrative or routine activities with limited public appeal. The clustering outcomes provide valuable insights into audience preferences, allowing educational institutions to improve future content strategies by focusing on video types that generate higher engagement. This research demonstrates that the K-Means algorithm is effective in identifying content patterns and can be used as a decision-support tool for optimizing YouTube channel growth in the educational sector.
A Study on Implementation and Performance Analysis of Basic and Advanced Image Processing Techniques Using Python and OpenCV Lubis, Syaiful Rahman; Iqbal, Muhammad
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 2 (2024): April: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i2.60

Abstract

Abstract— Digital image processing plays a crucial role in artificial intelligence and computer vision, with widespread applications in healthcare, agriculture, security, industry, and transportation. This research focuses on implementing both basic and advanced image processing methods using Python and the OpenCV library within a desktop application. The main problem addressed is the lack of an integrated, structured approach that bridges basic and advanced techniques, limiting users' comprehensive understanding of image processing workflows. The objective is to design a complete system that allows step-by-step processing, starting from grayscale conversion, binarization, arithmetic and logical operations, to convolution and morphological transformations such as Sobel edge detection and erosion. The proposed application utilizes Tkinter for the user interface, enabling users to upload images, apply various processing techniques, and analyze results interactively. The system also includes histogram visualization and equalization to enhance contrast. Findings show that the implemented methods effectively transform images in accordance with theoretical expectations, such as edge enhancement and shape simplification. The integration of these methods into a single, user-friendly platform supports both educational and applied uses. The contribution of this research lies in its practical demonstration of digital image processing techniques, providing a comprehensive and accessible reference for developers, researchers, and students. Despite its achievements, the system lacks advanced segmentation and real-time capabilities, which are suggested for future development through integration of adaptive methods and machine learning techniques.

Page 3 of 7 | Total Record : 63

 1   2   3   4   5 

Filter by Year

2023 2025


Reset
Filter By Issues
All Issue Vol. 3 No. 4 (2025): Research of Biotechnology Vol. 3 No. 3 (2025): July: Health Science Informatic Vol. 3 No. 2 (2025): April: Artificial Intelligence Vol. 3 No. 1 (2025): Jan: Computer Science Vol. 2 No. 4 (2024): October: Artificial Intelligence Vol. 2 No. 3 (2024): July: Artificial Intelligence Vol. 2 No. 2 (2024): April: Computer Science Vol. 2 No. 1 (2024): Jan: CNN and Artificial Vol. 1 No. 4 (2023): Oct: Computing Quantum and Related Fields Vol. 1 No. 3 (2023): July: Computer Science and Research Vol. 1 No. 2 (2023): April: Article Computer Science and Research Vol. 1 No. 1 (2023): January: Article Computer Science and Research More Issue