cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Saluky
Contact Email
luke4line@gmail.com
Phone
+6285173250534
Journal Mail Official
info@etunas.com
Editorial Address
Etunas Sukses Sistem Kantor Sekretariat Jl. Flamboyan 1 F2.34 Griya Caraka Kedawung, Kab Cirebon, Jawa Barat, Indonesia, 45153 Email: info[@]etunas.com
Location
Kab. cirebon,
Jawa barat
INDONESIA
International Journal of Smart Systems
Published by Etunas Sukses Sistem
ISSN : -     EISSN : 29865263     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Industrial & Manufacturing Engineering
International Journal of Smart Systems with eISSN: 2986-5263 is a peer-reviewed journal as a media for publishing research results that support the development of cities, villages, sectors, and other systems. The International Journal of Smart Systems is published by Etunas Suskes Sistem and is published every three months (February, May, August, and November). This journal is expected to be a forum for the publication of research results from practitioners, academics, and related interested parties. The scope of the system discussed is attached but not limited; Smart System System engineering Artificial Intelligence (AI) Technology Machine Learning & Deep Learning Internet of Things Big data Computer Vision Natural Language Processing Smart city security Smart infrastructure Smart Health Smart Education Robots process automation (RPA) etc.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 18 Documents
 1   2 
Bacterial Population Growth Model with Runge-Kutta Method: Bacterial Population Growth Model with Runge-Kutta Method Ditha Pertiwi, Ratu Hindi; della Puspa, Rani
International Journal of Smart Systems Vol. 1 No. 3 (2023): August
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i3.23

Abstract

The bacterial population growth model is one way to understand the dynamics of microorganisms under various environmental conditions. This study aims to model the growth of bacterial populations using the Runge-Kutta method as a numerical approach to solve differential equations describing growth rates. This method was chosen because of its high accuracy in predicting the solution value at a given time interval compared to other numerical methods. In this study, a logistics model was applied that considered factors such as environmental capacity and the intrinsic growth rate of bacteria. The initial population data and model parameters were processed using the fourth-order Runge-Kutta method, which was then validated with analytical solutions or simulations based on experimental data. The results of the analysis show that this method is able to predict bacterial growth patterns with minimal error rates. In addition, this method is also flexible to be applied to scenarios with variable parameters, such as environmental changes or the influence of antibiotics. The conclusions of this study show that the Runge-Kutta method is an effective tool for modeling the dynamics of bacterial growth, providing a more accurate picture of population changes over time. These findings have the potential to support the development of strategies in various fields, such as biotechnology, waste treatment, and microorganism infection control. Further research is recommended to integrate other external factors to improve the accuracy of the model.
Modeling the Movement of Autonomous Vehicles with the Euler Method Fadila Akmalia Wardani; Rifka Khairunisa; Dede Setiawan, Dede Setiawan
International Journal of Smart Systems Vol. 1 No. 3 (2023): August
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i3.31

Abstract

The development of autonomous vehicle technology has brought about a revolution in transportation systems, presenting solutions for efficiency, safety, and comfort. One of the main challenges in the development of autonomous vehicles is accurate motion modeling to understand and predict vehicle dynamics in various conditions. This article discusses the application of the Euler Method, a simple but effective numerical method, to model the movement of autonomous vehicles. This method is used to solve differential equations that describe the dynamics of the vehicle, including acceleration, speed, and position based on the input of the control system. Modeling is done through a discrete approach, where changes in variable values are calculated at small time intervals. This study evaluates the performance of the method in various scenarios, such as straight trajectories, sharp turns, and sudden stop situations, which are often encountered by autonomous vehicles in the real world. The simulation was carried out using MATLAB software to visualize the dynamics of movement and analyze the accuracy of the prediction results. The results show that the Euler Method is able to produce fairly accurate modeling on simple scenarios, although there are limitations in dealing with more complex dynamics due to the linear nature of this method. Therefore, further development with more sophisticated numerical methods, such as the Runge-Kutta Method or adaptive algorithms, is needed to improve accuracy on more complex scenarios. This article makes a significant contribution in providing technical and practical references for researchers and developers in optimizing more reliable and efficient autonomous vehicle systems.
Investment Optimization with Nonlinear Equation Solving Camilla, Aida Dwi; Febiyanti, Shintya Sukma; Rika Aprilia
International Journal of Smart Systems Vol. 1 No. 4 (2023): November
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i4.61

Abstract

Investment optimization is one of the important topics in the world of finance that aims to maximize profits with minimal risk. Mathematical approaches, particularly through the solution of nonlinear equations, have become an effective method of aiding investment decision-making. This article discusses the development of an investment optimization model that uses nonlinear equation solving techniques to determine optimal asset allocation. In this study, a nonlinear equation is used to describe the relationship between various investment variables, such as profit level, risk, and asset allocation. Using this approach, investors can find optimal solutions that meet their investment goals, whether in conservative, moderate, or aggressive scenarios. The methodology used involves historical data analysis, mathematical model formulation, and the application of numerical algorithms to solve the nonlinear equations. The results show that the solution of nonlinear equations is able to provide a more precise solution than traditional methods, such as linear programming or simple heuristic. This approach not only improves accuracy in determining the optimal portfolio, but also provides flexibility in dealing with dynamic market conditions. The proposed model allows sensitivity analysis to variable changes, allowing investors to make more informative and adaptive decisions. Investment optimization with the solution of nonlinear equations is a significant innovation in the field of finance, which not only supports investment efficiency but also opens up opportunities for the development of more complex investment models. This article is expected to be a reference for academics and practitioners in applying a mathematical approach for optimal portfolio management.
Security Analysis of the VoIP (Voice Over Internet Protocol) System wulan, alya; Rahman, Rakhmadi; Desvi
International Journal of Smart Systems Vol. 1 No. 3 (2023): August
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i3.69

Abstract

Voice over Internet Protocol (VoIP) is a communication technology that enables voice transmission over IP-based networks, offering advantages such as cost efficiency, flexibility, and service integration. Despite its benefits, VoIP faces significant security vulnerabilities due to its open architecture and dependence on public internet infrastructure. This study presents a literature-based analysis of the primary security threats targeting VoIP systems, including eavesdropping, Denial of Service (DoS) attacks, spoofing, session hijacking, and Network Address Translation (NAT) traversal problems. The research also discusses a range of countermeasures, including Secure Real-time Transport Protocol (SRTP), Transport Layer Security (TLS), Intrusion Detection and Prevention Systems (IDS/IPS), adaptive firewalls, and robust authentication protocols such as STIR/SHAKEN. While these technical solutions are effective, their success depends on proper implementation and continuous system monitoring. Although there may be minor trade-offs in performance, particularly in latency, such compromises are acceptable under global standards to ensure secure communication. The findings underscore the importance of a layered security strategy that maintains both protection and Quality of Service (QoS), making VoIP a dependable solution for critical sectors such as government, finance, and business.
A Comparative Study of Explainable AI Models in High-Stakes Decision-Making Systems Gupta, Aarav Sharma; Desai, Meera
International Journal of Smart Systems Vol. 1 No. 2 (2023): May
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i2.72

Abstract

High-stakes decision-making systems such as those used in healthcare, finance, and criminal justicedemand not only high predictive accuracy but also transparency to ensure trust, accountability, and ethical compliance. Explainable Artificial Intelligence (XAI) has emerged as a pivotal approach to address the black-box nature of complex machine learning models, offering interpretable insights into model predictions. This study presents a comparative analysis of leading XAI techniques, including SHAP, LIME, Counterfactual Explanations, and Rule-based Surrogates, across three real-world high-stakes domains. Using standardized evaluation metrics—fidelity, stability, usability, and computational efficiency—we examine the trade-offs between explanation quality and system performance. The results reveal that while SHAP consistently provides the highest fidelity explanations, it suffers from higher computational costs, whereas LIME offers faster, though sometimes less stable, explanations. Counterfactual methods excel in user interpretability but face challenges in generating plausible scenarios for complex datasets. Our findings highlight that no single XAI method is universally optimal; rather, the selection should align with domain-specific requirements and the criticality of the decisions involved. This comparative study contributes to the discourse on responsible AI deployment by providing actionable insights for practitioners, policymakers, and researchers seeking to integrate XAI into high-stakes environments.
Adaptive Federated Learning for Privacy-Preserving Smart Applications Dominguez, Beatrice Lorraine; Emmanuel, Richard; Montemayor, Angelica Faye
International Journal of Smart Systems Vol. 1 No. 2 (2023): May
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i2.73

Abstract

The rapid growth of smart applications across domains—ranging from healthcare and finance to personalized education—has intensified concerns about data privacy and model scalability. Federated Learning (FL) offers a promising framework by enabling distributed model training without sharing raw data, yet conventional FL approaches struggle with challenges such as heterogeneous data distributions, limited device resources, and dynamic network conditions. This paper introduces an Adaptive Federated Learning (AFL) framework designed to address these limitations while preserving user privacy. The proposed AFL dynamically adjusts aggregation strategies, learning rates, and participation levels based on client performance metrics and resource availability. We integrate differential privacy mechanisms and secure aggregation to ensure robust privacy guarantees without compromising model accuracy. Experimental evaluations on benchmark smart application datasets—including IoT sensor data and mobile user behavior logs—demonstrate that AFL achieves up to 15–20% improvement in convergence speed and notable reductions in communication overhead compared to standard FL methods. Our findings highlight AFL’s potential as a scalable and privacy-preserving solution for next-generation smart applications, paving the way for more secure and adaptive AI ecosystems.
Interpretable Deep Learning for Industrial Fault Detection Syarif, Ahmet Yılmaz; Demir, Elif; Kaya, Mehmet
International Journal of Smart Systems Vol. 1 No. 2 (2023): May
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i2.74

Abstract

The integration of deep learning into industrial fault detection systems has significantly enhanced predictive accuracy and operational efficiency. However, the lack of model interpretability poses a critical barrier to its widespread adoption in safety-critical environments. This study proposes an interpretable deep learning framework that combines Convolutional Neural Networks (CNNs) with attention mechanisms and Layer-wise Relevance Propagation (LRP) to enable transparent fault diagnosis in complex machinery. Using a benchmark dataset from a rotating machinery system, the model achieves high classification performance while providing intuitive visual and quantitative explanations for its predictions. The attention module highlights critical temporal and spatial features, while LRP decomposes prediction scores to reveal feature-level contributions. Experimental results demonstrate that the proposed model not only maintains high accuracy (above 95%) but also delivers interpretable outputs that align with domain expert reasoning. Additionally, the model supports root cause analysis and facilitates trust in automated systems, which is essential for industrial stakeholders. This research bridges the gap between black-box deep learning models and real-world industrial applications by promoting transparency, accountability, and actionable insights. The proposed framework serves as a practical step toward deploying explainable AI in industrial settings, supporting both real-time monitoring and decision-making processes.
The Role of AI-Powered Analytics in Building a Human-Centered Smart Campus Delgado, Samantha Joyce; Panganiban, Nathaniel Joseph; Robles, Kimberly Anne
International Journal of Smart Systems Vol. 1 No. 3 (2023): August
Publisher : Etunas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63876/ijss.v1i3.81

Abstract

The rapid digital transformation of higher education has accelerated the adoption of smart campus technologies integrating artificial intelligence (AI), Internet of Things (IoT), and cloud computing. While existing initiatives often emphasize operational efficiency and infrastructure optimization, limited attention has been given to building human-centered smart campuses that prioritize student engagement, well-being, and academic success. This study investigates the role of AI-powered analytics in shaping adaptive, inclusive, and student-focused campus ecosystems, with an observational study conducted at De La Salle University (DLSU), Manila, Philippines. AI-driven analytics were deployed to process multi-source datasets, including IoT-enabled classroom sensors, learning management system (LMS) activity logs, and student survey feedback. The system generated predictive insights to identify at-risk learners, support personalized learning pathways, and recommend interventions for improved academic outcomes. Preliminary findings from the DLSU pilot revealed a 19% increase in course participation and a 12% reduction in dropout risk among vulnerable student groups. Additionally, real-time analytics enhanced campus services by optimizing space utilization, energy efficiency, and scheduling flexibility, indirectly improving student comfort and productivity. The results suggest that AI-powered analytics extend the smart campus paradigm beyond efficiency, enabling higher education institutions to foster human-centered learning environments that integrate inclusivity, well-being, and sustainability. By demonstrating how data-driven systems can support both academic and non-academic aspects of student life, this research positions AI as not only a technological enabler but also a catalyst for equitable and student-centered digital transformation in higher education.

Page 2 of 2 | Total Record : 18

 1   2 

Filter by Year

2023 2023


Reset
Filter By Issues
All Issue Vol. 1 No. 4 (2023): November Vol. 1 No. 3 (2023): August Vol. 1 No. 2 (2023): May Vol. 1 No. 1 (2023): February