• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.553-563
• /
• 2019

As the number of videos uploaded on live streaming platforms rapidly increases, the demand for providing highlight videos is increasing to promote viewer experiences. In this paper, we present novel methods for predicting highlights using chat logs and audio data in videos. The proposed models employ bi-directional LSTMs to understand the contextual flow of a video. We also propose to use the features over various time-intervals to understand the mid-to-long term flows. The proposed Our methods are demonstrated on e-Sports and baseball videos collected from personal broadcasting platforms such as Twitch and Kakao TV. The results show that the information from multiple time-intervals is useful in predicting video highlights.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.567-570
• /
• 2014

The basic of a reliable service using a system and network is duplex configuration. There are a various duplex configuration for a system and network and we must have a performance indicator about how to use some redundancy. Then, we need analysis tool and method which analyze efficiently the performance about various duplex models. The tool that analyzing the performance and stability of the system and the network are a mathematical analysis method and simulation method. The mathematical analysis is a commonly used method, but high complexity system is not suitable for analysis methods and the simulation method has the problems which take a long time to understand in itself. Then, to overcome this problems, we propose the more simple method than used method for network analysis and we prove the efficiency by using the simple redundancy models.

• Journal of The Korean Association For Science Education
• /
• v.39 no.2
• /
• pp.207-220
• /
• 2019

Although the 2015 revised science curriculum has newly introduced core science competencies, there are a lot of confusions and difficulties at the school sites because the concept of competence is not clear. In this study, we conducted literature analysis to understand what constitutes the components of science competence and how the components are related. Based on this analysis, a model of science competency, composed of six factors (non-cognitive characteristics, knowledge, skill, context, performance, level) was suggested. In addition, we have explored ways to utilize this science competency model to re-write the achievement criteria of current science curriculum as science learning objectives expressed in the form of science competency. Finally, advantages and limits of the model are discussed and related further researches are suggested.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.543-548
• /
• 2021

The higher the resolution of the image, the higher the satisfaction of the viewers of the image, and the super-resolution imaging has a considerable increase in research value among the fields of computer vision and image processing. In this study, the main features of low-resolution image LR are extracted mainly using deep learning super-resolution models. It learns and reconstructs the extracted features, and focuses on reconstruction-based algorithms that generate high-resolution image HR. In this paper, we investigate SRCNN and VDSR in a super-resolution algorithm model based on reconstruction. The structure and algorithm process of the SRCNN and VDSR model are briefly introduced, and the multi-channel and special form are also examined in the improved performance evaluation function, and understand the performance of each algorithm through experiments. In the experiment, an experiment was performed to compare the results of the SRCNN and VDSR models with the peak signal-to-noise ratio and image structure similarity, so that the results can be easily judged.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.19-26
• /
• 2023

IoT edge services utilizing neuromorphic hardware architectures are suitable for autonomous IoT applications as they perform intelligent processing on the device itself. However, spiking neural networks applied to neuromorphic hardware are difficult for IoT developers to comprehend due to their complex structures and various hyper-parameters. In this paper, we propose a method for generating spiking neural network (SNN) models that satisfy user performance requirements while considering the constraints of neuromorphic hardware. Our proposed method utilizes previously trained models from pre-processed data to find optimal SNN model parameters from profiling data. Comparing our method to a naive search method, both methods satisfy user requirements, but our proposed method shows better performance in terms of runtime. Additionally, even if the constraints of new hardware are not clearly known, the proposed method can provide high scalability by utilizing the profiled data of the hardware.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.51-57
• /
• 2021

Quite a few elementary school teachers began to utilize AI technology in order to provide students with customized, intelligent information services in recent years. However, learning principles of AI may be as important as utilizing AI in everyday life because understanding principles of AI can empower them to buildup adaptability to changes in highly technological world. In the paper, 'Linear Regression Algorithm' is selected for teaching AI-based prediction system to solve real world problems suitable for elementary students. A simulation program written in Scratch was developed so that students can find a solution of linear regression model using the program. The paper shows that students have learned analyzing data as well as comparing the accuracy of the prediction model. Also, they have shown the ability to solve real world problems by finding suitable prediction models.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Informatization Policy
• /
• v.30 no.3
• /
• pp.92-121
• /
• 2023

As music streaming services (MSS) involve various interactions with users during the music consumption process, it is important to understand the user experience and manage the service accordingly. This study developed a user experience model for MSS by theoretically linking the quality characteristics considered important by music service users with the structure of user experience. PLS analysis was then performed using survey data to test the model. As a result, functionality (search, browsing, and personalized recommendation), UI usability, content quality (currentness, sufficiency, relevance), and monetary cost were found to be key experience factors that determine the experience consequence, i.e., user satisfaction. In addition, in a supplementary analysis comparing domestic and global services, differences in user experience were found between the two groups in terms of functionality and content quality. The user experience model of MSS proposed in this study serves as a new foundation for theory-based research in this field and provides meaningful implications for the competitive landscape among music streaming service platforms and for their competitive strategies.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.6
• /
• pp.175-193
• /
• 2022

Although there is paradigm shift in art industry and interdisciplinary convergence between art and entrepreneurship, little has been done in "art entrepreneurship." First, this study organized the concepts of art entrepreneurship and conducted literature reviews on the trends of international and domestic research. Second, this paper aimed to understand the concept of art platform business. To do so, authors reviewed the general concept of business model and special features of platform business. Third, this paper categorized and introduced 11 art platform businesses from the based on the purposes of companies (① rental & selling, ②commercialize & selling, ③crowdfunding, ④information sharing & digital exhibition). Forth, this study provided two frameworks (①business model components, ②platform controllability and customers' information asymmetry) and applied them into 11 cases. By systematically reviewing the previous studies, this paper expects to increase scholarly understanding of the field of art entrepreneurship where two different areas (art and entrepreneurship) have studied separately. In addition, introduction and analyses of 11 online art platform have practical implications.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.44-53
• /
• 2024

Companies in modern society are increasingly recognizing sentiment classification as a crucial task, emphasizing the importance of accurately understanding consumer opinions opinions across various platforms such as social media, product reviews, and customer feedback for competitive success. Extensive research is being conducted on sentiment classification as it helps improve products or services by identifying the diverse opinions and emotions of consumers. In sentiment classification, fine-tuning with large-scale datasets and pre-trained language models is essential for enhancing performance. Recent advancements in artificial intelligence have led to high-performing sentiment classification models, with the ELECTRA model standing out due to its efficient learning methods and minimal computing resource requirements. Therefore, this paper proposes a method to enhance sentiment classification performance through efficient fine-tuning of various datasets using the KoELECTRA model, specifically trained for Korean.