All articles published in this issue have undergone a thorough peer review process, and stringent checks for repetition rates have been implemented to ensure the integrity of the content.
Total number of articles in this issue: 5 Total number of pages in this issue: 38
For inquiries regarding the content of specific articles, please feel free to contact the respective authors via their provided email addresses. For questions related to the journal itself, please reach out directly to SUAS Press.
Year
2024
Volume
1
Number
6
Status
Archived
Published
2024 December 16
Articles
Open Access Research ArticlePublished 16 December 2024
This study explores the potential of real-time personalization to enhance user engagement in web applications through adaptive interfaces. Although traditional static interfaces are reliable, they often fail to meet the dynamic and diverse needs of users, leading to a decline in user interaction over time. This article proposes a comprehensive model that utilizes machine learning algorithms to adjust network content based on user behavior, preferences, and contextual factors, providing a more personalized experience. Empirical data from experiments shows that adaptive interfaces significantly improve key engagement metrics such as time spent on the platform, click through rates, and user satisfaction. The research findings emphasize the importance of adaptive design principles in enhancing user experience, cultivating user retention, and maintaining competitiveness in the digital environment.
Artificial Intelligence (AI)-driven voice assistants, such as Amazon's Alexa and Google Assistant, have become essential components in modern smart home ecosystems, revolutionizing the way users interact with their environments. These voice assistants enable hands-free control over various home automation systems, offering unprecedented levels of convenience and enhancing daily productivity. By integrating with a wide range of smart devices—from lighting and temperature control to security systems and entertainment—AI-driven voice assistants simplify the management of daily routines, allowing users to perform tasks more efficiently with minimal effort.
This study aims to explore the influence of AI-driven voice assistants on user productivity and overall satisfaction within smart homes. Employing both quantitative data collection methods, such as usage statistics and automation completion rates, alongside qualitative insights gathered from user feedback, we conduct a comprehensive analysis of how voice-controlled smart home interactions affect daily activities. The research examines aspects such as task completion speed, automation accuracy, and the seamlessness of multi-device integrations, in addition to the subjective user experience, including perceived ease of use, convenience, and general satisfaction with the system.
Our findings suggest that AI-driven voice assistants offer considerable improvements in user productivity, reducing the time and effort required to complete tasks by streamlining processes and enabling multi-tasking. Additionally, users reported higher satisfaction levels due to the simplicity and efficiency introduced by these technologies. However, the study also highlights ongoing challenges, particularly regarding the assistants' limited ability to understand complex contextual information and the growing concerns over privacy and data security. Despite these issues, the positive impact of AI-driven voice assistants on smart home ecosystems is clear, with potential for further enhancements as the technology evolves.
Disciplines:Business and ManagementSubjects:Smart Home MarketReferences:44
Educational resource imbalances pose considerable barriers to accomplishing equitable opportunities to learn worldwide. Traditional approaches to resource allocation frequently fail to adapt to the ever-changing and intricate needs of educational systems, exacerbating disparities. This paper explores applying reinforcement learning (RL) in optimizing how resources in education are distributed and used, offering a promising solution to these hurdles. The analysis delves into fundamental RL concepts and algorithms, like deep reinforcement learning and multi-agent reinforcement learning, and investigates their applications in customized learning, scheduling resources, and promoting fairness. It highlights major difficulties such as information quality, scalability, fairness, and transparency, along with possibilities for innovation through blended methodologies and instant decision making. By combining existing research and distinguishing critical gaps, this study provides practical insights for advancing RL applications in education, paving the way for more inclusive and effective systems for managing resources.
Disciplines:Artificial Intelligence and IntelligenceSubjects:Machine LearningReferences:20
This paper explores the application of the Contrastive Unsupervised Graph Neural Network (CuGNN) framework in financial domains, leveraging its heterophily-based adaptive convolution to address critical tasks like fraud detection, risk propagation, and portfolio optimization. CuGNN's ability to identify and utilize heterophilic patterns in financial transaction graphs enables robust representation learning even in unsupervised settings, where labeled data is scarce. Specifically, we adapt CuGNN to model risk spread across trading and investment networks by dynamically capturing high-frequency and low-frequency signals through its adaptive convolution mechanism. This approach allows us to differentiate between correlated and inverse-correlated asset behaviors, providing deeper insights into systemic risks and diversification strategies. Furthermore, CuGNN’s feature-distribution embedding and latent-space contrastive learning strategies are utilized to detect anomalous interactions in high-frequency trading networks and to identify heterophilic relationships in credit scoring and supply chain finance. By applying the CuGNN framework across diverse financial datasets, this study demonstrates its potential to uncover hidden structures and optimize decision-making in critical financial applications, addressing the growing need for explainable and adaptive graph-based methods in the sector.
In recent years, we have a higher demand for machine learning models in the field of economics and business managment. We have a higher demand for quality of the features used for training. In this process, feature selection plays a key role in identifying the most meaningful features from a dataset while we perfrom various business tasks. Feature selection is not just a technical exercise; it also has profound implications for the transparency and explainability of machine learning models. This study aims to be a valuable resource for both academic and industry experts, offering insights that connect theoretical knowledge with practical implementation. And this paper also highlights the potential applications and significance of feature selection across industries like business, finance, and other real-world scenarios. And it aims to explore deep in the feature selection, showing that its impact on model performance and its role in various domains.
