International Transactions on Artificial Intelligence

Blockchain Technology Integration for Enhancing Security and Reliability in Modern Information Systems

2025-10-14T09:46:29+00:00

Blockchain has become a critical digital infrastructure for strengthening data integrity, transparency, and trust within intelligent information systems, particularly in environments that depend on continuous AI–IoT data exchange. Despite its potential, empirical evidence quantifying blockchain’s actual security benefits remains limited. This study employs a hybrid analytical design combining Smart Partial Least Squares (SmartPLS) modeling with expert-based qualitative triangulation. Five core constructs Resistance to Attack, Data Integrity, Transparency, System Security, and User Satisfaction and Trust were evaluated to capture both the technical and perceptual dimensions of blockchain-enabled security. The research aims to empirically determine how blockchain architecture enhances intelligent information security and to identify the structural relationships among its socio technical components. Quantitative findings reveal that blockchain improves data integrity by 23%, increases transaction transparency by 19%, and enhances user trust by 17% compared with centralized systems. The model demonstrates strong reliability (ρc > 0.85) and high explanatory
power (R2 > 0.70), confirming the robustness of the proposed framework. The study advances theoretical understanding by validating blockchain as a socio technical enabler of secure and trustworthy intelligent ecosystems. Practically, the findings highlight how decentralization promotes ethical, resilient, and transparent digital infrastructures capable of supporting next generation intelligent
systems.

AI-Driven Optimization of Pulsed DC Sputtering for Enhanced Indium Tin Oxide Films

2025-10-20T08:34:34+00:00

The performance of heterojunction silicon solar cells strongly depends on the quality of the Transparent Conductive Oxide (TCO) layer, particularly Indium Tin Oxide (ITO), which governs both lateral charge transport and optical coupling. Despite its industrial relevance, achieving low-resistivity and high transmittance ITO at low thermal budgets remains a manufacturing challenge. This study aims to identify and optimize the key pulsed DC magnetron sputtering parameters that govern the structural, electrical, and optical properties of ultra-thin ITO films suitable for heterojunction applications. A systematic experimental approach was implemented by varying discharge power, oxygen partial pressure, deposition temperature, and post-deposition annealing conditions using an inline industrial sputtering system. The results show that moderate discharge power, controlled oxygen incorporation, and substrate temperatures around 180 ◦C significantly enhance film densification and electron transport. Under the optimized parameter set, the ITO films achieved low resistivity in the range of (4.6–5)×10−4 Ω·cm and visible-light transmittance above 90%, while annealing at 160 ◦C further reduced defect density and stabilized electrical per- formance. These findings demonstrate that high-quality ITO can be produced within the thermal constraints of heterojunction silicon technologies and provide a robust foundation for integration into automated or AI-assisted sputtering control frameworks. Overall, this work supports the development of scalable, energy-efficient, and industrially viable fabrication routes for next-generation photovoltaic devices.

Assessing User Satisfaction in Hadirku Through an Extended TAM Framework

2025-10-27T09:28:36+00:00

The rapid advancement of Information and Communication Technology (ICT) has accelerated the transition from manual, paper based attendance systems toward digital platforms that promote efficiency and environmental sustainability through reduced paper usage. In this context, the Hadirku online attendance platform has been increasingly adopted across educational, organizational, and event
management settings. This study employs the Technology Acceptance Model (TAM), extended with Service Quality, Organizational Support, and Information Security, to examine determinants of User Satisfaction and Continued Usage. A quantitative design was implemented with 200 valid respondents, and SmartPLS was used to assess construct validity and structural relationships. Reliability was strong (Cronbach’s α = 0.77–0.92), and model fit met recommended thresholds (SRMR = 0.057; NFI = 0.91). The study aims to analyze how perceived usefulness, ease of use, service quality, information security, and organizational support influence user engagement with Hadirku. Findings reveal that information security and perceived usefulness significantly predict continued usage intention, while perceived ease of use and organizational support enhance user satisfaction. Users overall reported positive experiences and strong behavioral intention to continue using the platform. This study contributes to digital transformation and Green ICT literature by providing an extended TAM framework that explains sustained engagement with online attendance systems. The results offer practical insights for platform developers and institutions seeking to optimize user trust, system reliability, and sustainable administrative practices.

Integrating Artificial Intelligence for Academically Challenged Students Education and Health

2025-10-29T14:32:02+00:00

Students with Intellectual and Developmental Disabilities (ID/DD) often experience overlapping medical and cognitive challenges that affect their academic participation and social interaction. Frequent absences, delayed progress, and limited communication skills highlight the urgent need for an integrated support system. Despite advancements in educational technology, most digital learning tools remain limited in addressing the dual educational and healthcare needs of ID/DD students. This study aims to identify existing gaps and propose a systematic framework for integrating Artificial Intelligence (AI) into education and health systems to enhance personalized learning and well-being for students with ID/DD. The study emphasizes the importance of combining health data with instructional design to achieve inclusive and adaptive learning experiences. A systematic literature review was conducted across multiple databases, including IEEE Xplore, ERIC, ACM Digital Library, and NFER, covering studies published between 2020 and 2025. The review process followed the PRISMA guideline and applied strict inclusion and exclusion criteria to ensure the validity of selected studies. The findings reveal that AI has been used to support ID/DD learners in various contexts, but most implementations remain fragmented, lacking integration between educational and medical data. The proposed AI-based framework connects these domains through data-driven decision-making, adaptive feedback, and intelligent reasoning mechanisms. This study contributes to the development of a holistic AI-driven model that supports individualized learning and health monitoring in line with SDG 3 (Good Health and Well-Being) and SDG 4 (Quality Education). Strengthening collaboration among educators, caregivers, and healthcare professionals can create more inclusive and effective educational ecosystems for ID/DD students.

AIoT Driven Smart Solar System for Real Time Predictive Sustainable Energy Management

2025-11-04T04:50:22+00:00

The rapid expansion of solar photovoltaic (PV) technologies has increased the demand for intelligent, adaptive, and data-driven energy management systems. However, conventional and IoT only solar infrastructures still face limitations, including inefficient energy distribution, delayed fault detection, and an inability to respond dynamically to fluctuating environmental conditions. This study proposes an AIoT-based Smart Solar System that integrates IoT-enabled sensing modules with artificial intelligence for real-time monitoring, predictive analytics, and autonomous control. The system employs a distributed architecture consisting of edge devices, cloud analytics, and machine learning models particularly Long Short-Term Memory (LSTM) networks and regression-based predictors to enhance forecasting accuracy and operational responsiveness. The objective of this research is to improve power utilization, predictive reliability, and maintenance efficiency within solar energy systems. Experimental results demonstrate a 22.8% increase in power utilization, a 17% reduction in maintenance downtime, and a forecasting accuracy of 95.2% (R2 = 0.952). These findings indicate that AIoT integration significantly enhances energy intelligence, system reliability, and sustainability. Overall, the proposed architecture establishes a scalable foundation for next generation renewable energy systems capable of self learning, adaptive optimization, and real-time decision making.

SWOT Analysis of AI-Based Learning Recommendation Systems for Student Engagement

2025-08-19T11:48:47+00:00

This study presents a SWOT analysis (Strengths, Weaknesses, Opportunities, Threats) of AI-based learning recommendation systems for students. These innovative systems hold significant potential in supporting Sustainable Development Goal (SDG) 4 Quality Education by personalizing learning pathways, enhancing access to resources, and boosting student engagement. Their primary strengths include increased learning efficiency, adaptive content delivery, and instant feedback mechanisms. Nevertheless, weaknesses such as potential algorithmic bias, data privacy concerns, and over reliance on technology warrant careful consideration. Emerging opportunities encompass expanding educational access for underserved populations, facilitating lifelong learning, and integrating diverse educational platforms. However, threats like the digital divide and the need for robust ethical guidelines must be addressed to ensure equitable access. This analysis underscores the necessity of a balanced approach in developing and deploying these AI systems, maximizing their educational benefits while mitigating risks to achieve more inclusive and equitable quality education for all. Quantitatively, the synthesis of reviewed studies reveals that adaptive AI-based recommendation systems improve student engagement by up to 18% and content relevancy by approximately 22% compared to conventional systems. Moreover, the SWOT analysis indicates that the strength to threat ratio (S/T) exceeds 2.1, implying that institutional readiness and technological innovation significantly outweigh identified implementation risks. These findings confirm the robust potential of AI-LRS in higher education.

Reliability Assessment of Attendance Systems Based on Face Recognition Under Varying Lighting Conditions

2025-10-16T09:17:08+00:00

The rapid adoption of face recognition technology for attendance systems has raised concerns about its reliability under varying lighting conditions, which often affect real world deployment. This study aims to analyze the reliability of a face recognition based attendance system under diverse lighting scenarios, addressing challenges in accuracy and robustness. The research employs a deep learning approach, utilizing a Convolutional Neural Network (CNN) trained on a dataset of facial images captured under controlled and uncontrolled lighting conditions, ranging from low to high illumination levels. The methodology includes preprocessing techniques for illumination normalization and feature extraction, followed by performance evaluation using metrics such as accuracy, precision, and false acceptance rate. Experimental results demonstrate that the proposed system achieves an accuracy of 92% in optimal lighting but drops to 78% under low light conditions, highlighting the impact of illumination on recognition performance. The integration of adaptive preprocessing techniques improves reliability by 12% in challenging scenarios. This study concludes that while face recognition based attendance systems are highly effective, their reliability in diverse lighting conditions can be significantly enhanced through advanced preprocessing and robust algorithm design, offering practical implications for real time biometric applications in dynamic educational and workplace settings.

Assessing the Environmental and Economic Effects of Smart Grid Integration Using SEM

2025-10-23T09:19:45+00:00

The global shift toward renewable energy has intensified the need for intelligent energy management systems capable of addressing variability in power supply and optimizing system-wide performance. Smart grid technologies have emerged as a key enabler in achieving sustainable, efficient, and data-drivenvenergy distribution. This study employs a quantitative approach using Structural Equation Modeling (SEM) via SmartPLS to analyze data collected from stakeholders involved in renewable energy deployment, utility operations, and smart grid implementation. The model evaluates the relationships between smart grid integration, environmental performance, and economic outcomes. The primary aim of this research is to assess how smart grid adoption influences carbon emission reduction, energy efficiency enhancement, and cost optimization within renewable energy ecosystems. The SEM analysis indicates a statistically significant positive effect of smart grid integration on both environmental and economic indicators. Smart grid implementation improves energy efficiency by more than 30%, while operational cost savings reach up to 25% over extended periods. Carbon emission reduction is identified as a key mediating factor within the model, reinforcing the ecological benefits of smart grid adoption. The findings demonstrate that smart grid technologies contribute substantially to both sustainability and economic resilience in renewable energy management. The study provides actionable insights for energy policymakers, grid operators, and industry practitioners, highlighting the vital role of intelligent, data-driven infrastructures in advancing future global energy systems.

Life Cycle Assessment of Silicon Photovoltaics and Their Environmental Impacts

2025-10-29T08:08:56+00:00

The rapid expansion of silicon based Photovoltaic (PV) technologies continues to drive the global shift toward sustainable energy systems. However, the environmental implications across the full life cycle of PV modules particularly those associated with upstream silicon purification routes remain insufficiently examined. This study provides a comprehensive assessment of the environmental and process level impacts of Metallurgical Grade Silicon (MGS) and Upgraded Metallurgical Grade Silicon (UMGS), covering extraction, manufacturing, operation, and end of life stages. A process oriented Life Cycle Assessment (LCA) is conducted to analyze variations in carbon intensity, hazardous material use, and energy demand, complemented by comparative evaluations of monocrystalline and polycrystalline module production pathways. To enhance analytical precision, this study incorporates an AI-assisted predictive modeling framework using supervised machine learning to estimate Global Warming Potential (GWP) and identify key factors influencing emission variability. The AI-enhanced model reveals that electricity mix and purification route exert the strongest influence on GWP, and scenario simulations demonstrate that UMGS based processes can reduce upstream emissions by up to 89% under favorable energy conditions. Additionally, the study highlights future challenges related to increasing PV waste volumes between 2025 and 2030 and the need for improved recycling infrastructures. Overall, the integration of AI-based prediction with conventional LCA offers a more dynamic and adaptive evaluation of PV sustainability performance. The findings underscore the importance of renewable powered manufacturing, early adoption of low-energy purification technologies, and policy support to achieve long-term environmental and socio-economic benefits.

Integrating MidJourney Scripts into Architectural Design for Aesthetic Innovation

2025-10-30T17:22:21+00:00

The use of Artificial Intelligence (AI) in creative disciplines, particularly architecture, has introduced a paradigm shift in how design concepts are developed and visualized. This research explores the integration of MidJourney generative scripts within the architectural design process. Using a hybrid methodology of qualitative observation and computational experimentation, this study evaluates how AI-driven image generation influences form exploration, material perception, and aesthetic decision-making. The main objective is to identify how AI-based generative systems, specifically MidJourney, can enhance conceptual creativity and accelerate the design iteration cycle in architectural practice. Unlike previous procedural models limited to parametric control, this study introduces an adaptive AI human feedback mechanism enabling continuous co-evolution between designer intent and machine generation. Our findings indicate that AI-assisted workflows enhance the production of innovative architectural compositions, offering greater visual diversity, while simultaneously enhancing creative efficiency and reducing design fatigue. Quantitatively, AI integration improved design iteration speed by 65% and increased aesthetic consistency scores from 78% to 91%, compared to traditional workflows. Integrating MidJourney generative scripting into architectural workflows creates a dynamic feedback loop between human intuition and machine creativity, leading to a new model of aesthetic co-creation that expands the boundaries of contemporary architectural design.