cover
Contact Name
Adam Mudinillah
Contact Email
adammudinillah@staialhikmahpariangan.ac.id
Phone
+6285379388533
Journal Mail Official
adammudinillah@staialhikmahpariangan.ac.id
Editorial Address
Jorong Kubang Kaciak Dusun Kubang Kaciak, Kelurahan Balai Tangah, Kecamatan Lintau Buo Utara, Kabupaten Tanah Datar, Provinsi Sumatera Barat, Kodepos 27293.
Location
Kab. tanah datar,
Sumatera barat
INDONESIA
Journal of Computer Science Advancements
ISSN : 30263379     EISSN : 3024899X     DOI : https://doi.org/10.70177/jsca
Core Subject : Science,
Journal of Computer Science Advancements is an international peer-reviewed journal dedicated to interchange for the results of high quality research in all aspect of science, engineering and information technology. The journal publishes state-of-art papers in fundamental theory, experiments and simulation, as well as applications, with a systematic proposed method, sufficient review on previous works, expanded discussion and concise conclusion. As our commitment to the advancement of science and technology, the Journal of Computer Science Advancements follows the open access policy that allows the published articles freely available online without any subscription.
Articles 86 Documents
Implementation of an Agent System to Increase Manufacturing Process Efficiency in a Smart Factory Nugroho, Budi; Pasaribu, Hiras; Oscar, Schersclight
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1532

Abstract

The rapid advancement of Industry 4.0 technologies has transformed traditional manufacturing into highly interconnected smart factory systems. However, achieving optimal efficiency in such environments remains challenging due to complex production flows and the need for real-time decision-making. This study explores the implementation of an agent-based system to improve efficiency within a smart factory setting, focusing on how autonomous agents can manage, coordinate, and optimize manufacturing processes. The research aims to analyze the effectiveness of agent systems in reducing production delays, enhancing resource allocation, and improving overall productivity. A combination of simulation and experimental analysis was employed to assess the impact of agent-based solutions on production efficiency. The agent system was integrated into the smart factory model, where agents performed tasks such as process monitoring, predictive maintenance scheduling, and dynamic resource management. Results indicate that the agent system contributed to a 15% reduction in idle time, a 20% improvement in machine utilization, and an overall increase in production throughput. These improvements highlight the potential of agent systems to address inefficiencies in manufacturing by enabling adaptive and autonomous decision-making processes. The findings suggest that agent-based systems are viable solutions for enhancing operational efficiency in smart factories, paving the way for further innovations in automated manufacturing environments. Implementing such systems could lead to more resilient, responsive, and efficient manufacturing processes, ultimately supporting the broader adoption of smart factory practices in the industry.
Implementation of Deep Learning in a Voice Recognition System for Virtual Assistants Apriyanto, Apriyanto; Sahirin, Rohmat; Bradford, Snyder
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1533

Abstract

Voice recognition technology has become a vital component in virtual assistants, enabling more natural and efficient user interactions. However, traditional voice recognition systems face challenges in accurately interpreting diverse accents, dialects, and background noise, which can limit their usability. This study investigates the implementation of deep learning techniques to improve the accuracy and adaptability of voice recognition systems within virtual assistant applications. The research aims to enhance voice recognition performance by leveraging deep learning models that can process complex speech patterns and adapt to varied linguistic nuances. A convolutional neural network (CNN) architecture combined with recurrent neural networks (RNN) was used to train the voice recognition model on a large, diverse dataset of audio samples. The dataset included multiple languages, accents, and noisy environments to test the robustness of the model. Results indicate a 25% improvement in word error rate (WER) and a significant increase in recognition accuracy across diverse voice inputs compared to traditional voice recognition systems. The model demonstrated high adaptability, accurately interpreting speech in varying acoustic conditions, thus improving user experience with virtual assistants. These findings suggest that deep learning can significantly enhance voice recognition systems, offering more reliable performance in real-world applications. Implementing deep learning models in voice recognition systems can bridge the gap between human and machine communication, making virtual assistants more accessible and user-friendly.
Utilization of Multi-Agent Systems in Managing Smart Transportation Systems in Urban Areas Hayati, Amelia; Prasetio, Rachmat; Puspitasari, Mariana Diah; Jiao, Deng
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1534

Abstract

Urban areas face increasing challenges in managing transportation systems due to rising population densities and traffic congestion. Traditional traffic management methods often lack the flexibility and responsiveness needed to address dynamic conditions in real time. This study explores the utilization of multi-agent systems (MAS) as a solution for optimizing smart transportation systems within urban environments. The research aims to evaluate the effectiveness of MAS in improving traffic flow, reducing congestion, and enhancing system responsiveness through autonomous decision-making and coordination among multiple agents. A simulation-based methodology was employed to analyze MAS performance in managing various transportation variables, including traffic density, signal timing, and incident response. Each agent was programmed to perform specific tasks, such as monitoring traffic, optimizing traffic signals, and re-routing vehicles, with collaborative decision-making to address congestion in real time. Results indicate that MAS implementation led to a 30% improvement in traffic flow efficiency and a 25% reduction in congestion levels. The system also demonstrated adaptive capabilities, allowing for real-time adjustments to unexpected conditions, such as accidents or road closures. The findings suggest that multi-agent systems provide a viable, scalable solution for smart transportation management in complex urban settings. Implementing MAS can significantly enhance the efficiency and adaptability of urban transportation systems, contributing to more sustainable and efficient mobility solutions in rapidly growing cities.
Big Data Analysis to Predict Consumption Patterns in Smart Cities Susilo, Anto; Prasetiyo, Rachmat; Aslam, Bilal; Farah, Rina
Journal of Computer Science Advancements Vol. 3 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i1.1535

Abstract

The rapid development of smart cities has increased the demand for efficient resource management and personalized services, where understanding consumption patterns is crucial. Big data analysis offers a powerful tool for predicting these patterns, enabling city planners and service providers to make data-driven decisions to enhance urban living quality. This study aims to utilize big data analytics to predict consumption patterns across various sectors in smart cities, including energy, water, and transportation. By leveraging large datasets, this research seeks to provide actionable insights for optimizing resource allocation and anticipating future consumption demands. The methodology involves collecting and analyzing data from multiple sources, such as IoT sensors, public utility records, and social media, to identify consumption trends. Machine learning algorithms, including time series analysis and clustering, were applied to detect patterns and forecast demand. Results indicate that big data analytics can accurately predict consumption fluctuations, with an 85% accuracy in energy demand forecasting and a 78% accuracy in water usage prediction. The findings highlight correlations between demographic factors and consumption, providing a comprehensive understanding of urban needs. The study concludes that big data analysis is a valuable approach to managing resources effectively in smart cities. By predicting consumption patterns, city planners can proactively address demand surges, reduce waste, and improve resource distribution, ultimately supporting sustainable urban growth. Implementing these insights could significantly enhance smart city efficiency and resilience.
Sentiment Analysis on Social Media Using Data Mining for Mapping Community Satisfaction Usup, Usup; Sahirin, Rohmat; Lucas, Laura; Qingjun, Chu
Journal of Computer Science Advancements Vol. 3 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i1.1536

Abstract

Social media has become a significant platform for individuals to express opinions, including satisfaction and dissatisfaction with services and policies, making it a valuable source of community sentiment data. Understanding public sentiment can assist policymakers and organizations in responding to community needs effectively. This study aims to conduct sentiment analysis on social media using data mining techniques to map community satisfaction levels. By analyzing sentiment patterns, this research seeks to provide actionable insights for improving public services and enhancing community engagement. The research applies data mining methodologies, including text mining and machine learning algorithms, to analyze posts and comments collected from various social media platforms. Sentiment classification was performed using natural language processing (NLP) and a supervised machine learning approach to categorize sentiments as positive, neutral, or negative. The model was trained on a large dataset and validated to ensure accuracy in sentiment detection. Results indicate that social media sentiment analysis can reliably reflect community satisfaction trends, with findings showing 70% positive, 15% neutral, and 15% negative sentiments regarding local services. The study concludes that data mining for sentiment analysis provides a robust method for assessing community satisfaction on social media, offering a real-time understanding of public opinion. By implementing this approach, organizations and policymakers can identify areas of improvement and proactively address community concerns, ultimately fostering a responsive and community-centered approach to public service.  
Implementation of Grid Computing in Genomic Data Processing in Biomedical Informatics Rahmawati, Rahmawati; Al-Momani, Ammar; Williams, Sarah
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1618

Abstract

The exponential growth of genomic data in biomedical informatics has necessitated efficient computational methods to process and analyze vast datasets. Traditional computational systems often fall short in handling the scale and complexity of genomic data. This study investigates the implementation of grid computing as a scalable and cost-effective solution for genomic data processing in biomedical informatics. The research aims to evaluate the feasibility and performance of grid computing in enhancing data throughput, reducing computational latency, and improving resource utilization in genomic data workflows. The study adopts a methodological approach that integrates grid computing frameworks, such as Globus Toolkit and Apache Hadoop, into genomic data processing pipelines. Simulated genomic datasets and real-world case studies were employed to benchmark the grid computing system against conventional computational environments. The results demonstrate significant improvements in processing speed, with an average reduction of 40% in computational time, and a 25% increase in resource efficiency. Additionally, the system showcased robust scalability, handling up to 10 times larger datasets without compromising accuracy or reliability. In conclusion, the findings underscore the potential of grid computing to revolutionize genomic data processing, making it a pivotal technology in biomedical informatics. This study highlights the importance of adopting distributed computing paradigms to address the challenges posed by modern bioinformatics demands.
Optimization of Grid Computing for Big Data Processing in Biomedical Research Sope, Devi Rahmah; Cale, Wolnough; Aini, M. Anwar; Yusuf, Nur Fajrin Maulana; Zoraida, Masli Nurcahya
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1619

Abstract

The rapid growth of biomedical research has generated massive volumes of data, creating significant computational challenges. Traditional high-performance computing systems struggle to efficiently process, analyze, and manage such large-scale datasets. Grid computing, with its distributed architecture, offers a promising solution by enabling scalable and cost-effective data processing. This study explores the optimization of grid computing frameworks for big data processing in biomedical research, focusing on enhancing computational efficiency, scalability, and fault tolerance. The research aimed to evaluate the performance of optimized grid computing systems in processing diverse biomedical datasets, including genomic, proteomic, and imaging data. A combination of experimental and comparative approaches was employed, integrating grid computing frameworks such as Apache Hadoop and Globus Toolkit with biomedical data pipelines. Key metrics, including processing time, resource utilization, and error rates, were analyzed to assess the system’s performance. The findings demonstrated that optimized grid computing systems reduced processing time by an average of 35% compared to traditional methods while maintaining high accuracy. Scalability tests confirmed the framework’s ability to handle datasets up to 15 times larger without significant performance degradation. Fault tolerance improved through adaptive resource allocation, minimizing workflow interruptions. The study concludes that optimized grid computing is a transformative approach for big data processing in biomedical research. Its ability to enhance computational efficiency and scalability positions it as a crucial tool for addressing the growing data demands of modern biomedical science.
Use of Artificial Intelligence in Predicting Electricity Needs in Smart Cities Fawait, Aldi Bastiatul; Li, Zhang; Hussain, Sara
Journal of Computer Science Advancements Vol. 3 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i1.1620

Abstract

The rapid urbanization and adoption of smart city technologies have led to increasing complexities in managing electricity demand. Traditional methods of forecasting electricity needs often fail to accommodate the dynamic and real-time nature of energy consumption in smart cities. Artificial Intelligence (AI) offers a promising approach by leveraging machine learning algorithms and predictive analytics to address these challenges. This study explores the use of AI in predicting electricity needs, focusing on its applicability in optimizing energy distribution and reducing inefficiencies in smart city infrastructures. The research aims to develop an AI-based predictive model to forecast electricity demand using historical and real-time data. The methodology involves data collection from smart meters, weather forecasts, and demographic records, followed by training machine learning algorithms such as Random Forest, Support Vector Machines, and Neural Networks. Performance metrics, including prediction accuracy, computational efficiency, and scalability, were analyzed to evaluate the model's effectiveness. Results indicate that AI-based models outperform traditional forecasting methods, achieving an average prediction accuracy of 92%. Neural Networks demonstrated the highest performance, particularly in handling complex and nonlinear data patterns. The AI model also showcased scalability by adapting to increasing datasets without significant degradation in performance. The study concludes that AI is a transformative tool for predicting electricity needs in smart cities. By enhancing forecast accuracy and enabling efficient energy distribution, AI contributes to sustainable urban development and smarter energy management systems.
Analysis of the Application of Blockchain in E-Business to Increase Consumer Trust Harjoni, Harjoni; Xavier, Embrechts; Haruka, Hide
Journal of Computer Science Advancements Vol. 2 No. 6 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v2i6.1621

Abstract

The rapid growth of e-business has led to increasing concerns about consumer trust due to issues such as data breaches, fraudulent activities, and lack of transparency. Blockchain technology, with its inherent characteristics of decentralization, immutability, and transparency, has emerged as a potential solution to address these challenges. This research aims to analyze the application of blockchain in e-business to enhance consumer trust, providing insights into its effectiveness and adoption barriers. The study employs a qualitative approach, combining a systematic literature review and expert interviews to gather comprehensive data. The research evaluates blockchain’s impact on key trust factors, such as data security, transaction transparency, and accountability within the e-business ecosystem. The findings reveal that blockchain significantly enhances consumer trust by ensuring data integrity, enabling secure and transparent transactions, and reducing intermediary dependency. However, challenges such as high implementation costs, technical complexity, and regulatory uncertainty hinder widespread adoption. The study concludes that blockchain technology has the potential to revolutionize trust mechanisms in e-business. To maximize its benefits, businesses must address implementation barriers and foster collaborations with regulatory authorities. Future research should explore blockchain’s integration with emerging technologies such as artificial intelligence and the Internet of Things to create a more robust e-business ecosystem.
Application of Augmented Reality in E-Commerce to Increase Product Sales Susanto, Ruhiat; Rizalfi, Vinto; Sok, Vanna; Khan, Omar
Journal of Computer Science Advancements Vol. 3 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i1.1622

Abstract

The rapid development of e-commerce has led businesses to adopt innovative technologies to enhance customer engagement and increase product sales. Augmented reality (AR) has emerged as a transformative tool that allows consumers to visualize products in real-world settings, bridging the gap between physical and digital shopping experiences. This research explores the application of AR in e-commerce and its effectiveness in driving product sales by enhancing customer interaction and confidence in purchasing decisions. The study employs a mixed-method approach, combining quantitative surveys of 300 e-commerce users with qualitative interviews of 10 industry experts. The survey measured user engagement, purchasing intent, and satisfaction with AR-enhanced shopping experiences. Expert interviews provided insights into AR implementation strategies and its impact on sales performance. The findings indicate that AR significantly improves product visualization, leading to a 25% increase in customer engagement and a 30% boost in sales conversions. Consumers reported higher confidence in their purchases when using AR features, citing improved understanding of product dimensions, colors, and functionality. However, challenges such as high implementation costs and technical complexity were identified as barriers to widespread adoption. The study concludes that AR is a valuable tool for e-commerce businesses aiming to increase sales by enhancing the customer experience. Addressing challenges such as cost and accessibility will be critical for maximizing AR’s potential. Future research should explore the integration of AR with other emerging technologies to further optimize its impact on e-commerce performance.