• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.221-232
• /
• 2021

The purpose of this study is to explore the design direction of artificial intelligence convergence liberal arts subjects based on flip learning and maker education through analysis of learner needs in a non-face-to-face classroom environment caused by COVID-19. To this end, we analyzed the priorities of subject content elements by using the Borich needs assessment and The Locus for Focus model along with students' perceptions of flip learning for students who took and did not take maker education-based liberal arts courses. Based on this, it was used as basic data for designing the curriculum. The study results are as follows. First, the content elements of the artificial intelligence liberal arts curriculum based on maker education consisted of a total of 9 areas and were designed as a class using flip learning. Second, the areas with the highest demand for education are 'Artificial Intelligence Theory', 'Artificial Intelligence Programming Practice', 'Physical Computing Theory', 'Physical Computing Practice', followed by 'Convergence Project', '3D Printing Theory', '3D Printing practice' was decided. Third, most of the questionnaires regarding the application of flip learning in maker education-based artificial intelligence liberal arts subjects showed positive responses regardless of whether they took the course, and the satisfaction of the students was very high. Based on this, an artificial intelligence-based convergence liberal arts curriculum using flip learning and maker education was designed. This is meaningful in that it provides an opportunity to cultivate artificial intelligence literacy for college students by preparing the foundation for artificial intelligence convergence education in liberal arts education by reflecting the needs of students.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2334-2347
• /
• 2023

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

• The Journal of the Korea Contents Association
• /
• v.21 no.2
• /
• pp.587-593
• /
• 2021

In this thesis, we will break away from the classic DDoS response system for large-scale denial-of-service attacks that develop day by day, and effectively endure intelligent denial-of-service attacks by utilizing artificial intelligence-based technology, one of the core technologies of the 4th revolution. A possible service model development plan was proposed. That is, a method to detect denial of service attacks and minimize damage through machine learning artificial intelligence learning targeting a large amount of data collected from multiple security devices and web servers was proposed. In particular, the development of a model for using artificial intelligence technology is to detect a Western service attack by focusing on the fact that when a service denial attack occurs while repeating a certain traffic change and transmitting data in a stable flow, a different pattern of data flow is shown. Artificial intelligence technology was used. When a denial of service attack occurs, a deviation between the probability-based actual traffic and the predicted value occurs, so it is possible to respond by judging as aggressiveness data. In this paper, a service denial attack detection model was explained by analyzing data based on logs generated from security equipment or servers.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.29 no.3
• /
• pp.234-246
• /
• 2023

Purpose: This study aimed to develop a case-based nursing education program using generative artificial intelligence and to assess its usability and applicability in nursing curriculums. Methods: The program was developed by following the five steps of the ADDIE model: analysis, design, development, implementation, and evaluation. A panel of five nursing professors served as experts to implement and evaluate the program. Results: Utilizing ChatGPT, six program modules were designed and developed based on experiential learning theory. The experts' evaluations confirmed that the program was suitable for case-based learning, highly usable, and applicable to nursing education. Conclusion: Generative artificial intelligence was identified as a valuable tool for enhancing the effectiveness of case-based learning. This study provides insights and future directions for integrating generative artificial intelligence into nursing education. Further research should be attempted to implement and evaluate this program with nursing students.

• ETRI Journal
• /
• v.46 no.5
• /
• pp.851-864
• /
• 2024

Deep learning (DL) has significantly advanced artificial intelligence (AI); however, frameworks such as PyTorch, ONNX, and TensorFlow are optimized for general-purpose GPUs, leading to inefficiencies on specialized accelerators such as neural processing units (NPUs) and processing-in-memory (PIM) devices. These accelerators are designed to optimize both throughput and energy efficiency but they require more tailored optimizations. To address these limitations, we propose the NEST compiler (NEST-C), a novel DL framework that improves the deployment and performance of models across various AI accelerators. NEST-C leverages profiling-based quantization, dynamic graph partitioning, and multi-level intermediate representation (IR) integration for efficient execution on diverse hardware platforms. Our results show that NEST-C significantly enhances computational efficiency and adaptability across various AI accelerators, achieving higher throughput, lower latency, improved resource utilization, and greater model portability. These benefits contribute to more efficient DL model deployment in modern AI applications.

• Journal of The Korean Association of Information Education
• /
• v.23 no.2
• /
• pp.189-196
• /
• 2019

Artificial intelligence has begun to be used in various parts of our lives, and recently its sphere has been expanding. However, students tend to find it difficult to recognize artificial intelligence technology because education on artificial intelligence is not being conducted on elementary school students. This paper examined the teaching programming language and artificial intelligence teaching methods, and looked at the changes in students' attitudes toward artificial intelligence technology by conducting education on artificial intelligence. To this end, education on block-type programming language-based artificial intelligence technology was provided to students' level. And we looked at students' attitudes toward artificial intelligence technology through a single group pre-postmortem. As a result, it brought about significant improvements in interest in artificial intelligence, possible access to artificial intelligence technology and the need for education on artificial intelligence technology in schools.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.837-846
• /
• 2019

Purpose: The purpose of this study is to define various concepts, features, and scopes by examining various previous studies on AI services that are completely different from existing services. It also examines the limitations of existing service quality evaluation methods and studies the characteristics by combining them with various cases of new AI services. And this is to derive and propose quality evaluation attributes of AI service. Methods: The concept and characteristics of artificial intelligence were derived through research and analysis of various previous studies related to artificial intelligence. The key characteristics and quality evaluation items were derived through the KJ method and matching based on the keywords and characteristics derived from previous studies and various cases. Results: Based on the review of various previous studies on the quality of artificial intelligence services, this study presents the main characteristics and quality evaluation items of new artificial intelligence services, which are completely different from existing service quality evaluations. Conclusion: The quality measurement model of AI service is very useful when planning and developing AI-based new products or services because it can accurately evaluate the requirements of consumers using the services of the new AI era. In addition, consumers can be recommended a customized service according to the situation or taste, and can be provided with a customized service based on this.

• Informatization Policy
• /
• v.29 no.1
• /
• pp.60-83
• /
• 2022

The purpose of this study is to empirically analyze the effect of individual perception of artificial intelligence and the level of digital literacy on the acceptance of artificial intelligence-based public services. For empirical analysis, a research model was set up based on the technology acceptance model and planned behavior theory using survey data of 2017 and analyzed through structural equations. To summarize the results of the analysis, firstly, the positive perception of individuals about artificial intelligence technology plays a role in reinforcing attitudes toward benefits and reducing concerns about public service in which artificial intelligence technology has been introduced. Secondly, the level of digital literacy reinforces both benefits and concerns about artificial intelligence technology, but it was found that the intention to use public services was reinforced through the benefits of artificial intelligence technology perceived by individuals, rather than privacy concerns about artificial intelligence technology. Thirdly, it was confirmed that the perceived benefits of individuals on artificial intelligence technology reinforced the intention to use public civil services, and privacy concerns negatively influenced the intention to use. It was confirmed that the influence of a perceived ease of use and usefulness, as opposed to privacy concerns, further reinforces the intention to use. Both citizens' positive perceptions regarding the accuracy and reliability of information provided through artificial intelligence technology and institutional complementation of responsibility for errors caused by artificial intelligence technology are strengthened, and technical problems related to privacy protection are solved.

• Journal of Information Technology Services
• /
• v.20 no.3
• /
• pp.41-56
• /
• 2021

New drug discovery and development research enable clinical treatment that saves human life and improves the quality of life, but the possibility of success with new drugs is significantly low despite a long time of 14 to 16 years and a large investment of 2 to 3 trillion won in traditional methods. As artificial intelligence is expected to radically change the new drug development paradigm, artificial intelligence new drug discovery and development projects are underway in various forms of collaboration, such as joint research between global pharmaceutical companies and IT companies, and government-private consortiums. This study uses the TOE framework and the Value-based Adoption Model, and the technical, organizational, and environmental factors that should be considered for the acceptance of AI technology at the level of the new drug research organization are the value of artificial intelligence technology. By analyzing the explanatory power of the relationship between perception and intention to use, it is intended to derive practical implications. Therefore, in this work, we present a research model in which technical, organizational, and environmental factors affecting the introduction of artificial intelligence technologies are mediated by strategic value recognition that takes into account all factors of benefit and sacrifice. Empirical analysis shows that usefulness, technicality, and innovativeness have significantly affected the perceived value of AI drug development systems, and that social influence and technology support infrastructure have significant impact on AI Drug Discovery and Development systems.