Rapid advancements in satellite technology have led to a significant increase in high-resolution remote sensing (RS) images, necessitating the use of advanced processing methods. Additionally, patent analysis revealed a substantial increase in deep learning and machine learning applications in remote sensing, highlighting the growing importance of these technologies. Therefore, this paper introduces the Kolmogorov-Arnold Network (KAN) model to remote sensing to enhance efficiency and performance in RS applications. We conducted several experiments to validate KAN’s applicability, starting with the EuroSAT dataset, where we combined the KAN layer with multiple pre-trained CNN models. Optimal performance was achieved using ConvNeXt, leading to the development of the KonvNeXt model. KonvNeXt was evaluated on the Optimal-31, AID, and Merced datasets for validation and achieved accuracies of 90.59%, 94.1%, and 98.1%, respectively. The model also showed fast processing speed, with the Optimal-31 and Merced datasets completed in 107.63 s each, while the bigger and more complicated AID dataset took 545.91 s. This result is meaningful since it achieved faster speeds and comparable accuracy compared to the existing study, which utilized VIT and proved KonvNeXt’s applicability for remote sensing classification tasks. Furthermore, we investigated the model’s interpretability by utilizing Occlusion Sensitivity, and by displaying the influential regions, we validated its potential use in a variety of domains, including medical imaging and weather forecasting. This paper is meaningful in that it is the first to use KAN in remote sensing classification, proving its adaptability and efficiency.

In an industry, society gets more interest in software. In accordance with this trend, in the process of composing the university's curriculum, it is increasingly emphasized that problem-based learning through computational thinking and programming ability based on logical thinking is weighted. This study conducted a study on how to identify students' educational characteristics and study intention. In particular, a methodology to explore the study intention for Python programming from the characteristics of each student was reviewed. For this analysis, the relationship between new technology from their point of view and factors is analyzed, factors are identified for methodologies, and statistical methodologies are used to verify them. The purpose of this study is to find improvements for software education operation and to provide help in educational policy decision-making of university members who conduct computer software education.

This paper proposes a method to quantitatively identify the changes of technological paradigm over time. Specifically, the method identifies previous paradigms and predicts future paradigms by analyzing a patent citation-based knowledge network. The technological paradigm can be considered as dominantly important knowledge in a specific period. Therefore, we adopted the knowledge persistence which can quantify technological impact of an invention to recent technologies in a knowledge network. High knowledge persistence patents are dominant or paradigmatic inventions in a specific period and so changes of top knowledge persistence patents over time can show paradigm shifts. Moreover, since knowledge persistence of paradigmatic inventions are increasing dramatically faster than other ordinary inventions, recent patents having similar increasing trends in knowledge persistence with previous paradigms are identified as future paradigm inventions. We conducted an empirical case study using patents related to the genome sequencing technology. The results show that the identified previous paradigms are widely recognized as critical inventions in the domain by other studies and the identified future paradigms are also qualitatively significant inventions as promising technologies.