cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Chandra Lukita
Contact Email
chandralukita@pandawan.id
Phone
+6285778834017
Journal Mail Official
italic@pandawan.id
Editorial Address
Premier Park 2 Ruko Blok B-11 Kota Tangerang – Banten 15117
Location
Kota tangerang,
Banten
INDONESIA
International Transactions on Artificial Intelligence (ITALIC)
Published by Pandawan Sejahtera Indonesia
ISSN : 29636086     EISSN : 29631939     DOI : https://doi.org/10.33050/italic
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Library & Information Science
International Transactions on Artificial Intelligence (ITALIC) is an international, open-access journal established to publish groundbreaking research in the field of Artificial Intelligence (AI). ITALIC focuses on both theoretical and experimental AI research and explores its applications across various interdisciplinary fields. The journal places a strong emphasis on emerging technologies that contribute to sustainable development, in line with the United Nations Sustainable Development Goals (SDGs). ITALIC welcomes contributions that cover a wide range of AI applications, including machine learning, neural networks, natural language processing, AI in energy management, sustainability, and urban infrastructure. In addition to original research, the journal publishes reviews, mini-reviews, case studies, and commentaries, fostering dynamic discussions on the evolving role of AI in addressing global challenges. All submissions are rigorously reviewed through a double-blind peer-review process, ensuring high academic standards. As an open-access journal, ITALIC makes its content freely available to a global audience, enhancing the dissemination of critical insights. Each article is assigned a Digital Object Identifier (DOI), ensuring permanent access and easy referencing.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 80 Documents
 4   5   6   7   8 
Evaluating Smart Mobile Public Services for Bridging Digital Divide in Rural Governance Systems Muhtarom Muhtarom; Dewi Immaniar Desrianti; Nengah Sukendri; Thomas Green; Muhammad Farhan Kamil
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1065

Abstract

The persistent digital divide remains a critical challenge for rural governance, particularly in developing regions where disparities in infrastructure, digital literacy, and institutional capacity hinder equitable access to public services. This study aims to evaluate the impact of mobile-based public services on improving governance outcomes, specifically in terms of accessibility, efficiency, transparency, citizen participation, and public trust within rural contexts. A quantitative research design is employed using Structural Equation Modeling (SEM), based on survey data collected from 250 rural respondents and supported by national digital access indicators to ensure empirical robustness. The results reveal that mobile-based public services significantly enhance governance performance, with strong positive effects on accessibility (β= 0.72), efficiency (β = 0.68), and transparency (β = 0.70). These improvements subsequently foster higher levels of citizen participation (β = 0.75), which plays a critical mediating role in strengthening public trust (β = 0.80). Additionally, the measurement and structural models demonstrate strong reliability, convergent validity, discriminant validity, and overall model fit, confirming the robustness of the proposed framework. This study contributes to the digital governance literature by offering an integrated socio-technical and empirical SEM-based framework that explains how mobile-based services can effectively bridge the digital divide and enhance rural governance outcomes. Furthermore, it provides practical and policy-relevant insights aligned with Sustainable Development Goals (SDG 9, SDG 10, and SDG 16), supporting inclusive and sustainable digital transformation strategies.
Adaptive Fuzzy Hybrid AI for Urban Energy Traffic Decision Support Qurotul Aini; Andriyansah Andriyansah; Mekani Vestari; Po Abas Sunarya; Carlos Perez
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1049

Abstract

Urban energy and traffic systems are two highly interdependent components of smart city infrastructures, both of which operate under significant uncertainty caused by fluctuating demand, human mobility patterns, weather variability, and policy constraints. While Artificial Intelligence (AI) techniques particularly machine learning and deep learning have demonstrated strong predictive capabilities in these domains, their black box nature limits interpretability, trust, and adoption in real world urban governance. Methods: This study proposes an adaptive fuzzy hybrid artificial intelligence framework that integrates fuzzy inference systems with ensemble machine learning models to support uncertainty aware and explainable decision making in urban energy and traffic management. The proposed framework is validated using real world secondary data obtained from open government and smart city data portals, including urban energy demand, traffic flow, and environmental indicators. The primary objective of this research is to develop a robust and interpretable decision-support model capable of dynamically adapting to uncertain urban conditions while maintaining high predictive performance. Experimental evaluations demonstrate that the proposed fuzzy hybrid AI framework consistently outperforms standalone machine learning approaches in terms of decision stability, robustness under uncertainty, and interpretability across multiple urban scenarios. Conclusion: The findings indicate that adaptive fuzzy hybrid AI offers a practical, scalable, and policy aligned solution for urban energy traffic decision support, contributing to sustainable smart city governance and supporting evidence-based decision making in line with global sustainability agendas.
Interpretable Deep Vision Model Enhancing Robustness and Transparency in Robotic Perception Shahzada Muhammad Ali; Mohamad Rakhmansyah; Aulia Rahma Dina; Zeze Nanle
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1062

Abstract

The increasing deployment of artificial intelligence in robotic perception systems necessitates models that are both accurate and interpretable to ensure reliable decision-making in dynamic environments. This study proposes an intrinsically interpretable deep vision framework designed to enhance robustness and transparency in robotic perception tasks. The framework integrates convolutional feature extraction with embedded attention mechanisms, producing predictive outputs alongside spatially interpretable explanations. Experiments were conducted on publicly available benchmark datasets, including RGB-D Object Dataset, KITTI Vision Benchmark Suite, and adapted COCO subsets, covering scenarios with varying illumination, occlusion, and background complexity. Performance was evaluated through classification accuracy, precision, recall, localization consistency, and stability across repeated executions, with statistical validation using paired two-tailed t-tests and confidence interval analysis. Results indicate that the proposed framework maintains competitive accuracy while providing superior localization consistency, reduced variance, and stable attention behavior compared with conventional CNN baselines and post-hoc explanation methods. These findings demonstrate that embedding interpretability within the model architecture improves both predictive reliability and operational transparency. The proposed approach addresses key challenges in real-world robotic applications, facilitating safer automation, enhanced user trust, and alignment with regulatory expectations for explainable AI. By combining accuracy, robustness, and interpretability, this framework provides a scalable solution for intelligent robotic perception systems, supporting sustainable and responsible deployment in complex environments. The study highlights the critical role of intrinsic interpretability as a design principle for AI-driven robotics, offering practical insights for researchers, system developers, and policymakers seeking to advance trustworthy autonomous systems.
Trustworthy Machine Learning Evaluation Framework for Robust and Interpretable Intelligent Systems Ninda Lutfiani; Sutarto Wijono; Rifqa Nabila Muti; Yasir Mustafa Kareem
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1067

Abstract

Artificial intelligence (AI) deployment in critical domains requires machine learning systems that are not only accurate but also robust, interpretable, fair, and aligned with responsible governance principles. However, conventional machine learning evaluation approaches often prioritize predictive performance and computational efficiency while giving limited attention to ethical accountability, transparency, regulatory compliance, and sustainability. This study aims to develop a trustworthy machine learning evaluation framework for robust and interpretable AI systems. The focus of the study is the evaluation of intelligent systems across healthcare, finance, and transportation, where reliability and accountability are essential for real-world deployment. A qualitative case study approach was employed through expert interviews, literature analysis, document review, and cross-domain case comparisons to identify key evaluation dimensions. The findings show that trustworthy evaluation should integrate technical indicators, including accuracy, robustness, and interpretability, with broader dimensions such as fairness, accountability, governance compliance, and social responsibility. The proposed framework provides a structured model for assessing intelligent systems beyond conventional performance metrics. It also supports better consistency in interpretability assessment, stronger fairness evaluation, and improved alignment with international AI governance expectations. This study contributes to the development of responsible AI by offering a practi- cal evaluation framework that can guide researchers, developers, and institutions in designing machine learning systems that are reliable, transparent, and socially accountable. The framework has implications for sustainable and compliant AI implementation in high-impact sectors.
Decision Reliability Evaluation of AI Expert Systems in High Impact Domains Zubair Ahmad; Adam Faturahman; Meriyana Sunengsih; Noah Rangi
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1074

Abstract

AI expert decision support systems are increasingly used in public administration, healthcare, and financial risk management, yet conventional accuracy centered evaluations often fail to capture whether systems produce stable decisions across repeated executions. This study aims to develop a reliability oriented evaluation framework for assessing AI expert decision support systems beyond single-run predictive performance. The focus of the study is decision reliability in high-impact AI applications where inconsistent outputs may reduce accountability, weaken institutional trust, and create governance risks. A repeated experimental evaluation approach was applied using recent datasets from 2022 to 2024 representing heterogeneous and imbalanced decision conditions. The proposed framework integrates decision stability measurement, interpretability consistency assessment, confidence interval analysis, and statistical significance testing to examine system behavior under realistic operational scenarios. The results show that models with comparable predictive accuracy can demonstrate statistically significant differences in decision reliability. Confidence interval analysis indicates meaningful variability in output consistency, while interpretability evaluation reveals uneven explanatory stability across model executions. These findings confirm that reliability-oriented evaluation provides a more comprehensive and policy-relevant assessment of AI expert systems than accuracy-based evaluation alone. The study contributes to responsible AI deployment by offering an evaluation perspective that strengthens technical assessment, governance accountability, and trustworthiness in high-impact decision environments.
Reliable Machine Learning Models for Energy Optimization in Smart Green Cities Ignatius Agus Supriyono; Mochamad Heru Riza Chakim; Henry Zainarthur; Dimas Aditya Prabowo
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1092

Abstract

Rapid urbanization and increasing energy consumption have intensified the need for intelligent approaches that support sustainable and efficient energy management in smart green cities. This study investigates the effectiveness of machine learning models in improving energy demand forecasting and energy optimization through a reliability-oriented evaluation framework. The research utilizes a real-world smart city energy consumption dataset comprising 17,520 hourly observations collected between January 2022 and December 2023. Three machine learning models, namely Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM), were developed and evaluated using 30 independent execution runs. Model performance was assessed through Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coefficient of determination (R2), reliability analysis, and interpretability consistency measurements. The results demonstrate that LSTM achieved the best predictive performance with an MAE of 0.31, RMSE of 0.45, and R2 of 0.93, outperforming Random Forest and SVM across all evaluation metrics. Furthermore, LSTM exhibited the highest reliability score of 0.912 and superior explanation stability, indicating robust and consistent performance under repeated executions. The forecasting outputs were integrated into an energy optimization framework, resulting in reductions in peak energy loads and overall electricity consumption. These findings confirm that reliable and explainable machine learning models can support adaptive, data-driven energy management strategies capable of enhancing operational efficiency and sustainability in urban environments. The proposed framework contributes to the development of trustworthy intelligent systems for smart green cities and supports the achievement of sustainable development objectives related to clean energy, sustainable communities, and climate action.
SEO Dimensions and AI-Assisted Predictive Scoring for Digital Business Sales Performance in Indonesia Muchtadin Muchtadin; Michael Surya Gunawan; Dwi Safarina; Kamal Arif Al-Farouqi
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1093

Abstract

The intensification of digital commerce competition has elevated Search Engine Optimization (SEO) into a strategically important yet empirically underexplored determinant of sales performance, particularly within Indonesia’s rapidly expanding e-commerce ecosystem, where organic search drives over 64% of commercial platform traffic. This study examines the influence of three core SEO dimensions on page optimization, off-page optimization, and technical SEO on digital business sales performance, measured through website traffic growth, customer conversion rates, and revenue improvement. A quantitative explanatory design was applied using primary data from structured question naires administered to 120 digital business owners and e-commerce managers in Indonesia, cross-validated with secondary Google Analytics records over a twelve-month observation window. Multiple linear regression was conducted after validity, reliability, normality, multicollinearity, and heteroscedasticity tests. An AI-assisted Predictive SEO Performance Scoring (PSPS) model was also developed as a weighted composite function based on standardized regression coefficients to simulate performance trajectories across three SEO deployment scenarios. All three SEO dimensions showed statistically significant positive effects on sales performance (p < 0.05), with on-page SEO recording the strongest coefficient (β = 0.342), followed by technical SEO (β = 0.318) and off-page SEO (β = 0.291). The model explained 68% of performance variance (R2 = 0.68). PSPS scenario analysis showed that comprehensive SEO adoption produced an 83.5% relative performance improvement over minimal deployment. These findings position SEO as a core strategic investment aligned with Indonesia’s Making Indonesia 4.0 agenda and SDGs 8, 9, and 10.
Hybrid Fuzzy Logic Models for Performance Evaluation in Complex Decision-Making Systems Cicilia Sriliasta Bangun; Padeli Padeli; Muhamad Yusup; Adele Valerry
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1095

Abstract

Complex decision-making systems increasingly face uncertainty, nonlinearity, incomplete information, and dynamic data streams, making conventional rule-based and statistical approaches less reliable for adaptive and consistent decision support. Fuzzy logic offers interpretability for imprecise reasoning, whereas machine learning contributes predictive strength and optimization capability. This study develops and evaluates fuzzy logic-based hybrid models that integrate fuzzy inference systems with neural learning and evolutionary optimization. Benchmark datasets and simulation-based case studies were used to test model performance under uncertain and nonlinear conditions. The models were assessed using prediction accuracy, decision consistency, computational efficiency, error reduction, scalability, and adaptability, followed by comparison with conventional fuzzy, statistical, and standalone machine learning models. The main objective is to evaluate the effectiveness, reliability, scalability, and adaptability of hybrid fuzzy models for complex decision-making systems. The findings show that the proposed hybrid fuzzy models outperform conventional single model approaches across different scenarios. The models improve prediction precision, stabilize decision outputs under uncertainty, reduce error rates, and enhance adaptability to nonlinear data patterns. Neural learning strengthens predictive capability, while evolutionary optimization improves rule refinement, parameter tuning, and adaptive decision processing. This study concludes that fuzzy logic-based hybrid models provide a robust, interpretable, and scalable framework for intelligent decision support in uncertain and dynamic environments. The findings support the development of adaptive hybrid artificial intelligence systems for healthcare, energy management, smart cities, finance, and industrial automation. This structure also promotes transparent reasoning, reproducible evaluation, and practical deployment in high-stakes environments requiring explainability and resilience simultaneously.
Artificial Intelligence for Optimizing Renewable Energy Systems in Sustainable Power Generation Ageng Setiani Rafika; Dendy Jonas; Muchlisina Madani; Oliver Sauntos
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1098

Abstract

The rapid expansion of renewable energy adoption has increased the need for intelligent energy management, as conventional rule based dispatch systems of ten struggle with the dynamic, nonlinear, and uncertain operating conditions of high-penetration renewable grids. Traditional controllers show limited energy utilization efficiency and frequent frequency-standard violations under variable wind and solar conditions. This study proposes and evaluates an integrated Artificial Intelligence (AI) framework combining a Long Short-Term Memory (LSTM) neural network for 24-hour energy demand and generation forecasting with Particle Swarm Optimization (PSO) for real-time dispatch optimization. The framework is tested against a conventional rule-based baseline using three benchmark datasets from the UCI Machine Learning Repository, the National Renewable Energy Laboratory (NREL), and Open Power System Data, covering 36 months of hourly solar and wind observations. The objective is to design and experimentally validate an AI-based optimization framework that improves energy efficiency, reduces operational losses, and enhances grid stability in renewable energy systems. The proposed LSTM-PSO framework reduces Mean Absolute Error (MAE) by 50.7% and Root Mean Square Error (RMSE) by 44.3%. Energy efficiency increases from 76.2% to 91.4%, while energy losses decrease from 20.7% to 9.6%, equivalent to approximately 5,800 tonnes of CO2 equivalent avoided annually at a 100 MW grid scale. The integrated LSTM PSO architecture provides a reliable and scalable basis for AI-driven renewable energy optimization, supporting SDG 7, SDG 9, SDG 11, and SDG 13.
Vision-Based Pattern Recognition Models for Intelligent Human Robot Interaction in Smart Spaces Muhamad Faizal Fazri; Konita Lutfiyah; Lukita Pasha; Lily Maria
International Transactions on Artificial Intelligence Vol. 4 No. 2 (2026): May
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/italic.v4i2.1101

Abstract

The rapid expansion of smart spaces has increased the need for robotic systems capable of interpreting visual cues, recognizing human behavior, and responding safely in real time. However, existing vision-based models often struggle with occlusion, lighting variation, latency constraints, and limited contextual understanding in dynamic human-centered environments. This study develops a hybrid vision-based pattern recognition framework that integrates Convolutional Neural Networks (CNNs), Transformer-based attention mechanisms, multi-scale feature fusion, supervised learning, and reinforcement learning. The model is trained and validated using publicly available human–robot interaction datasets and simulated smart space scenarios involving gesture recognition, object detection, activity recognition, and intention prediction. The objective is to enhance intelligent human–robot interaction by improving visual perception accuracy, contextual interpretation, adaptive decision-making, and real-time responsiveness in smart environments. The proposed framework achieves stronger performance than baseline CNN-only and Vision Transformer models, with improved accuracy in gesture recognition, object detection, activity recognition, and intention prediction while maintaining low-latency inference suitable for real-time robotic interaction. The model also demonstrates better adaptability under dynamic lighting, occlusion, and multi-person interaction scenarios. This study concludes that combining CNN-based local feature extraction, Transformer-based global attention, and reinforcement learning-based policy optimization provides a reliable, adaptive, and context-aware framework for intelligent robotic systems. The findings support safer and more efficient human–robot collaboration in healthcare, smart homes, collaborative workplaces, and smart city environments.

Page 8 of 8 | Total Record : 80

 4   5   6   7   8 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 2 (2026): May Vol. 4 No. 1 (2025): November Vol. 3 No. 2 (2025): May Vol. 3 No. 1 (2024): International Transactions on Artificial Intelligence Vol. 2 No. 2 (2024): International Transactions on Artificial Intelligence Vol. 2 No. 1 (2023): International Transactions on Artificial Intelligence Vol. 1 No. 2 (2023): International Transactions on Artificial Intelligence Vol. 1 No. 1 (2022): International Transactions on Artificial Intelligence