Journal of Computing and Smart Ecosystems

Integrating Shortest Job First (SJF) Scheduling with Neural Networks for Enhanced Predictive Process Scheduling

2025-07-18T05:55:25+00:00

Process scheduling is a critical component of operating systems, directly influencing CPU utilization and overall system efficiency. The Shortest Job First (SJF) algorithm is theoretically optimal in minimizing average waiting time but is limited by its dependence on accurate burst time estimation. This study proposes a hybrid scheduling approach that integrates neural networks (NN) with SJF to dynamically predict process execution times. The neural model was trained on process-level features, including CPU usage, memory usage, priority, and arrival time, and its predictions were embedded into the SJF mechanism. Simulation results demonstrate that the NN-enhanced SJF achieves notable reductions in average waiting time and turnaround time while improving CPU utilization compared to traditional SJF and Round Robin algorithms. These findings highlight the practical viability of lightweight predictive models for enhancing classical scheduling techniques and extend their applicability to dynamic and heterogeneous computing environments.

From Text to Action: AI-Driven Classification of Public Service Complaints in Karanganyar, Indonesia

2025-07-21T02:16:31+00:00

Efficiently classifying public complaints is crucial for fostering transparent and responsive governance in the digital age. However, the sheer volume and textual nature of complaint data pose significant challenges for manual categorization, particularly within local government systems. This study seeks to develop an automatic classification model for public complaints by employing Logistic Regression and TF-IDF vectorization. The dataset, comprising complaints submitted to the Karanganyar Regency Government from January to June 2025, underwent preprocessing through standard natural language techniques and was converted into numerical features using TF-IDF. Logistic Regression was chosen for its simplicity, interpretability, and effectiveness with sparse text data. To address class imbalance, class weighting and stratified sampling were utilized. The model achieved an overall accuracy of 61%, surpassing the Naive Bayes baseline. Confusion matrix analysis demonstrated strong performance in dominant categories, although minority classes continued to present challenges. The results suggest that Logistic Regression offers a practical and explainable solution for early-stage complaint classification systems, especially in public sector contexts. This study lays the foundation for the future development of intelligent e-government platforms capable of real-time complaint handling.

Evaluating Usability And Customer Satisfaction in E-Marketplaces Using System Usability Scale and Customer Satisfaction Score

2025-07-22T15:09:19+00:00

In the digital era, user experience (UX) plays a critical role in determining the success of online platforms, particularly in the highly competitive e-commerce industry. This study presents a comparative evaluation of three major e-commerce applications in Indonesia namely Shopee, Tokopedia, and Lazada using two standardized instruments: the System Usability Scale (SUS) and the Customer Satisfaction Score (CSAT). A total of 100 respondents participated in the survey, which included 10 questions mapped to SUS and 10 questions mapped to CSAT. The results revealed that all three platforms scored poorly in usability and customer satisfaction metrics. Shopee achieved the highest SUS score 51, categorized as marginal, while Tokopedia 50 and Lazada 49.55. CSAT scores followed a similar pattern, with Shopee 52%, Tokopedia 55%, and Lazada 50% falling into low or very low satisfaction categories. These findings highlight the need for substantial improvements in both usability and service quality to enhance overall user experience and engagement. This study emphasizes the importance of integrating both SUS and CSAT methods to obtain a holistic understanding of user perceptions

Enhancing Conceptual Understanding of the Solar System Through 3D Augmented Reality in Primary Education

2025-07-31T10:06:50+00:00

The advancement of digital technologies has introduced new methods in science education, including the use of Augmented Reality (AR). Traditional astronomy instruction often relies on two-dimensional media, which limits students’ ability to visualize and interact with celestial phenomena. This paper presents EduPlanet, a 3D AR-based educational application designed to enhance students’ understanding of the solar system. The application allows users to explore planets interactively, visualize orbital movements, and access informative content in real time. Developed using Unity and Vuforia SDK, EduPlanet consists of three main modules: learning content, marker-based AR visualization, and a quiz system with instant feedback. Functional testing using the Black Box method confirmed that all features performed as intended. Informal usability testing with elementary school students showed high levels of engagement, particularly in the AR and quiz components. The findings suggest that EduPlanet offers an effective and accessible tool to support astronomy learning in primary education, with potential for broader application in digital science pedagogy.

Development Potential of AR Anatomy as an Interactive Learning Medium for Elementary Science Education

2025-07-31T16:59:09+00:00

In the era of the Industrial Revolution 4.0 and Society 5.0, education is expected to deliver adaptive, interactive, and contextual learning experiences. One of the main challenges in elementary science education lies in teaching abstract concepts such as human anatomy, where traditional textbooks and two-dimensional images often fail to support deep understanding. Augmented Reality (AR) offers a promising alternative by enabling the real-time visualization of three-dimensional (3D) models through mobile devices. This study explores the development and potential of “AR Anatomy,” a camera-based AR application designed to provide interactive visualizations of human organs for elementary students. Using a qualitative literature review of recent studies published after 2022, the analysis indicates that AR Anatomy can enhance student motivation, active engagement, and spatial understanding, while offering a cost-effective alternative to physical anatomical models. Nevertheless, limitations remain, including restricted organ coverage, lack of integrated evaluation features, and limited alignment with the national curriculum. In conclusion, AR Anatomy represents a promising step toward technology-enhanced science education at the elementary level, with further refinement needed to improve content coverage and classroom implementation.