cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josyc@gmail.com
Editorial Address
Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer System and Informatics (JoSYC)
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 27147150     EISSN : 27148912     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Industrial & Manufacturing Engineering
Journal of Computer System and Informatics (JoSYC) covers the whole spectrum of Artificial Inteligent, Computer System, Informatics Technique which includes, but is not limited to: Soft Computing, Distributed Intelligent Systems, Database Management and Information Retrieval, Evolutionary computation and DNA/cellular/molecular computing, Fault detection, Green and Renewable Energy Systems, Human Interface, Human-Computer Interaction, Human Information Processing Hybrid and Distributed Algorithms, High Performance Computing, Information storage, Security, integrity, privacy and trust, Image and Speech Signal Processing, Knowledge Based Systems, Knowledge Networks, Multimedia and Applications, Networked Control Systems, Natural Language Processing Pattern Classification, Speech recognition and synthesis, Robotic Intelligence, Robustness Analysis, Social Intelligence, Ubiquitous, Grid and high performance computing, Virtual Reality in Engineering Applications Web and mobile Intelligence, Big Data
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 443 Documents
 41   42   43   44   45 
Stress Detection Using Hybrid Deep Learning Models with Attention Mechanisms: A Comparative Study of CNN-LSTM, CNN-GRU, and Ensemble Approaches Airlangga, Gregorius
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6284

Abstract

Accurate and reliable stress detection remains a critical challenge in health monitoring due to the multifaceted nature of stress and the difficulty in capturing its temporal and spatial characteristics from physiological data. Existing methods often lack the ability to effectively model these dependencies, leading to suboptimal performance and limited interpretability, which hinder their application in real-world scenarios such as wearable devices and mobile health systems. This study addresses these limitations by investigating hybrid deep learning models with attention mechanisms, specifically focusing on CNN-LSTM, CNN-GRU, and CNN-BiLSTM architectures and their ensemble. Leveraging the complementary strengths of convolutional and recurrent layers, these models aim to capture both spatial and temporal dependencies in stress-related data, while attention layers enhance interpretability by prioritizing relevant features. Experimental results reveal that the CNN-LSTM with Attention model achieved the best performance, with the lowest Mean Squared Error (MSE) and Mean Absolute Error (MAE), demonstrating its suitability for complex stress prediction tasks. The CNN-GRU model also performed well, offering a balance between computational efficiency and accuracy, while the CNN-BiLSTM model showed limitations, suggesting that additional model complexity may lead to overfitting. The ensemble model, combining predictions from all three architectures, delivered stable performance across metrics, underscoring the value of ensemble approaches in improving robustness and mitigating model-specific biases. These findings have significant implications for practical applications, such as wearable devices and mobile health systems, where accurate, interpretable, and reliable stress monitoring is essential for timely interventions. Future work should focus on optimizing these models for real-time deployment, exploring adaptive learning for personalized stress detection, and validating across diverse datasets to enhance generalizability. This research highlights the importance of hybrid architectures and attention mechanisms in addressing the challenges of stress detection, paving the way for responsive and user-centered health monitoring systems.
Implementasi Metode Vikor Dalam Perekrutan Pegawai Tetap dan Cadangan Pada Mandali Packaging Lubis, Farhan Rusdy Asyhary; Kurniawan, Rakhmat
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6290

Abstract

Today's technological advances are rapidly expanding, which opens up a huge opportunity for entrepreneurs to implement and develop a recruitment system for prospective employees as an effective and efficient means of promoting performance. Decision-making using technology makes the decision-making process run faster and more accurate. Mandali Packaging is a business model that moves in the field of creative industries, precisely in the sablon service that still implements the recruitment process of staff manually. The aim of this research is to implement and develop a decision support system using the VIKOR method to improve the effectiveness and objectivity of the recruitment process in Mandali Packaging. The method is used because it has the ability to solve multi-criterion problems, provide optimal solutions based on the preference of the established criteria, and also help reduce the bias of subjectivity that often occurs in manual decision-making. The ranking results show that Ali Imron Lubis received the 1st rank with the lowest score of 0 because in the VIKOR method, the lower the score, the higher the rank. This research demonstrates that the VIKOR method has the potential to provide more accurate and objective recommendations.
A Hybrid Machine Learning Framework for Enhanced Tsunami Prediction Using Ensemble Models and Neural Networks Airlangga, Gregorius
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6291

Abstract

Tsunami prediction is a critical task for mitigating risks associated with natural disasters, yet achieving accurate and reliable predictions remains a significant challenge due to the inherent complexity and uncertainty in earthquake-related data. Traditional predictive models often struggle to capture the intricate relationships between earthquake features, such as magnitude, latitude, longitude, depth, and instrumental intensities, leading to suboptimal performance and unreliable predictions. To address these challenges, this research proposes a hybrid machine learning framework that integrates ensemble models and neural networks to enhance both accuracy and robustness in tsunami prediction. The dataset undergoes rigorous preprocessing, including the removal of missing values, normalization, and shuffling, to improve data quality. The framework employs a diverse set of ensemble models such as Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost alongside a neural network with three hidden layers for predictive modeling. Predictions from these models are aggregated into meta-features and passed to a logistic regression meta-classifier for final decision-making. Using ten-fold stratified cross-validation, the framework is evaluated on key metrics, including precision, recall, F1-Score, accuracy, and ROC-AUC. Results demonstrate that the hybrid model significantly outperforms individual models, effectively addressing the challenges of low accuracy and instability in traditional approaches. By leveraging the complementary strengths of ensemble models and neural networks, the proposed framework offers a scalable and adaptable solution for tsunami prediction, contributing to enhanced disaster preparedness and risk mitigation strategies.
The Determination of Availability Path Planning in Natural Tourist Attractions using Dijkstra's Algorithm and Ant Colony Optimization Gustami, Heri; Rizal, Muhammad; Fajri, Riyadhul
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6336

Abstract

The research on determining Availability Path Planning for natural tourist attractions using Dijkstra and Ant Colony algorithms aims to identify the most efficient routes in terms of time, distance, and environmental conditions. This is achieved by combining the Dijkstra and Ant Colony Optimization algorithms, each with its respective advantages and disadvantages, to create a system for finding the shortest, fastest, and safest paths to natural tourist destinations in Bireuen Regency. The methodology employed in this study is the waterfall model, which encompasses stages from analysis to application development, integrating both Dijkstra and Ant Colony Optimization algorithms. The research findings reveal that the shortest route to the Ceuraceu Waterfall destination can be accessed via the Samagadeng Village road in Pandrah District, while the longest route can be accessed through the city center of Bireuen Regency. Furthermore, for the Krueng Simpo River Bathing Tourism, the shortest route is via the Gayo Bireuen road, while the longest route is through the KKA Aceh Utara road. Lastly, the shortest route to the Kuala Jangka Beach tourist attraction is via the Jangka road from the Matangglumpang Dua area, while the longest route can be accessed through the Kuala Bireuen road.
Perbandingan Kinerja RNN dan CNN Dalam Klasifikasi Sentimen Ulasan Pengguna Aplikasi di Play Store Saputra, Satria Nugraha; Setiaji, Galet Guntoro; Widiyanto, Max Teja Ajie Cipta
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6408

Abstract

The public frequently shares their thoughts and opinions on various topics, such as products, public figures, or government policies, through online platforms. The process of analyzing review data is referred to as sentiment analysis. This study aims to compare the performance of two deep learning models Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) in classifying user sentiments across five review categories from the Google Play Store: design, photography, gaming, social media, and streaming. Choosing the right algorithm is essential to achieving optimal accuracy, given the variations in language and expression patterns within reviews. The dataset used in this study consists of 50,000 reviews with an imbalanced distribution of positive and negative sentiments. To address this imbalance, oversampling techniques were applied using the Synthetic Minority Oversampling Technique (SMOTE). The evaluation process measured each model's accuracy and loss levels. The results show that CNN consistently outperformed RNN across most categories. For the design category, CNN achieved the highest accuracy of 85% with a loss value of 0.41, compared to RNN, which achieved 83% accuracy and a loss of 0.53. On the other hand, the streaming category showed the lowest performance, with CNN achieving an accuracy of 69% and a loss of 0.63, while RNN achieved 67% accuracy with a loss of 0.72. These findings highlight CNN's superior effectiveness in sentiment analysis across diverse user review categories.
Analisis Pemilihan Payment Gateway Menggunakan Metode Simple Additive Weighting (SAW) S, Muhammad Ikhsan; Susanto, Erliyan Redy; Puspaningrum, Ajeng Savitri; Neneng, Neneng
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6099

Abstract

This research discusses the analysis of payment gateway selection using the Simple Additive Weighting (SAW) method. The criteria considered in this study include transaction costs, transaction speed, transaction security, and service availability. The objective of this research is to assist business owners and individuals in choosing the appropriate payment gateway based on their needs. The use of the SAW method enables a relative assessment of predefined criteria for each considered payment gateway. The results show that Finpay is the top choice of payment gateway, followed by Winpay and IPaymu. This study aims to serve as a practical guide for online businesses in improving performance and customer satisfaction through the optimal use of a payment gateway.
Deteksi Dini Kanker Payudara Menggunakan Citra Ultrasonografi Berbasis Convolutional Neural Networks dan Particle Swarm Optimization Azahra, Serina; Kusumaningtyas, Pramesti; Rofi'i, Mohammad
Journal of Computer System and Informatics (JoSYC) Vol 6 No 2 (2025): February 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i2.6637

Abstract

The increasing prevalence of breast cancer, one of the cancers with the highest incidence rate in the world, demands the development of effective early detection methods to increase patients' chances of recovery and reduce treatment costs. The main challenge in early detection of breast cancer is the identification of early symptoms that are often not felt, so many cases are only detected at an advanced stage. This study aims to develop a breast cancer early detection model using ultrasound images based on the convolutional neural networks (CNN) artificial neural network method optimized with the particle swarm optimization (PSO) algorithm. CNN is used to extract complex features from medical images, while PSO optimizes model parameters to improve accuracy. The dataset consists of 1,607 images classified into normal, benign, and malignant categories, through the process of model training and validation. The results showed that the integration of particle swarm optimization and convolutional neural networks resulted in an accuracy of 90.67%, higher than the convolutional neural networks method alone at 87.33%. In addition, the CNN-PSO model also excels in precision, sensitivity, and F1-score value. This research provides an effective diagnostic technology solution for primary healthcare facilities, with implications for improved early detection and reduced delayed diagnosis. This technology can be applied more widely through training of health workers and equitable distribution of diagnostic devices to improve service accessibility.
IndoBERT-Based Sentiment Analysis for Understanding Hotel Guests’ Preferences Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 6 No 2 (2025): February 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i2.6864

Abstract

The rapid growth of the hospitality industry and the increasing reliance on online reviews emphasize the need for advanced sentiment analysis tools to understand customer preferences effectively. This study explores the application of IndoBERT, a pre-trained language model tailored for the Indonesian language, in classifying sentiments from hotel guest reviews. Utilizing a dataset of 715 reviews, the study employed the Knowledge Discovery in Databases (KDD) framework for systematic data preprocessing, feature extraction, and machine learning analysis. IndoBERT demonstrated exceptional performance, achieving perfect precision, recall, and F1-scores of 1.00 for both positive (657 reviews) and negative (53 reviews) sentiment classes. The ROC curve analysis also yielded a mean AUC score of 0.86, validating the model's robustness and reliability. The results highlight IndoBERT's capability to accurately capture linguistic nuances and contextual meaning, offering actionable insights into factors influencing guest satisfaction, such as cleanliness, staff behavior, and service quality. This research contributes to advancing natural language processing applications in regional contexts and provides practical implications for enhancing service strategies in the hospitality sector. Future research should expand the model's application to other industries and explore multimodal approaches for a more comprehensive understanding of customer behavior.
Improved Sentiment Classification Using Multilingual BERT with Enhanced Performance Evaluation for Hotel Guest Review Analysis Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 6 No 2 (2025): February 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i2.6870

Abstract

Sentiment analysis in hotel guest reviews has become essential for evaluating customer satisfaction and service quality. This study improves sentiment classification accuracy by utilizing the Multilingual BERT model with an improved performance evaluation framework. Using the Knowledge Discovery in Databases (KDD) methodology, this research involves data selection, preprocessing, transformation, sentiment classification, and performance evaluation. A dataset of 715 hotel reviews from Qubika Boutique Hotel, sourced from Agoda, was used to assess the model's effectiveness. The classification results showed high accuracy in identifying positive sentiment, with 98% precision, 97% memory, and 98% F1 score, as observed in 432 correctly classified reviews. However, challenges were identified in the classification of neutral sentiment, which achieved a precision of 87% with 127 correctly classified cases, and negative sentiment, where the accuracy was 92%, with 104 correctly identified reviews. The overlap in confidence scores, especially in the range of 0.4-0.6 between neutral and negative sentiment, highlights the need for improved contextual embedding and hybrid modeling techniques. The sentiment distribution analysis revealed that 60-70% of reviews were positive, 20-30% neutral, and 10-15% indicated dissatisfaction, underscoring the need for targeted service improvement. These findings provide valuable insights for data-driven decision-making in hospitality management, enabling businesses to strengthen service power and address critical areas of concern. Future research should focus on refining model interpretability, expanding multilingual datasets, and integrating real-time sentiment analysis to improve classification performance. Strengthening these aspects will contribute to a more robust and scalable sentiment analysis framework, ensuring greater precision in capturing the guest experience and optimizing service strategies in the hospitality industry.
Optimasi Penjadwalan Pengangkutan Sampah Secara Adaftif Menggunakan Algoritma Tabu Search Ahmad, Suprian; Ikhsan, Muhammad
Journal of Computer System and Informatics (JoSYC) Vol 6 No 2 (2025): February 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i2.6935

Abstract

This research aims to optimize waste transportation scheduling adaptively using the Tabu Search algorithm. Inefficient waste management can lead to increased operational costs and accumulation of waste, so an adaptive optimization approach is needed. Data collection techniques in this research include direct observation, interviews with related parties, and literature study to obtain relevant data. The data collected includes the initial schedule for transporting waste, a list of villages in the three sub-districts, and the distance traveled by the waste transport fleet. The implementation of the Tabu Search algorithm was carried out with the parameters tabu_tenure = 5 and max_iterations = 100. The research results showed that this algorithm was successful in optimizing the waste transportation route, with a total optimal cost of 35.1 in Natal District, 17.5 in Panyabungan Kota District, and 11.5 in Kotanopan District. This optimization process increases the operational efficiency of waste transportation by reducing costs and travel time. In addition, the Tabu Search algorithm is able to overcome complex route problems by finding better solutions than conventional methods. Thus, this research proves that the Tabu Search algorithm can be an adaptive solution for more effective and efficient waste management in Mandailing Natal, and has the potential to be applied in other areas with similar conditions.

Page 43 of 45 | Total Record : 443

 41   42   43   44   45 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 6 No 4 (2025): August 2025 Vol 6 No 3 (2025): May 2025 Vol 6 No 2 (2025): February 2025 Vol 6 No 1 (2024): November 2024 Vol 5 No 4 (2024): August 2024 Vol 5 No 3 (2024): May 2024 Vol 5 No 2 (2024): February 2024 Vol 5 No 1 (2023): November 2023 Vol 4 No 4 (2023): August 2023 Vol 4 No 3 (2023): May 2023 Vol 4 No 2 (2023): Februari 2023 Vol 4 No 1 (2022): November 2022 Vol 3 No 4 (2022): August 2022 Vol 3 No 3 (2022): May 2022 Vol 3 No 2 (2022): Februari 2022 Vol 3 No 1 (2021): November 2021 Vol 2 No 4 (2021): Agustus 2021 Vol 2 No 3 (2021): Mei 2021 Vol 2 No 2 (2021): February 2021 Vol 2 No 1 (2020): November 2020 Vol 1 No 4 (2020): August 2020 Vol 1 No 3 (2020): Journal of Computer System and Informatics (JoSYC) - May 2020 Vol 1 No 2 (2020): Journal of Computer System and Informatics (JoSYC) - Februari 2020 Vol 1 No 1 (2019): Journal of Computer System and Informatics (JoSYC) - November 2019 More Issue