• Smart Media Journal
• /
• v.9 no.3
• /
• pp.59-70
• /
• 2020

This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.39-52
• /
• 2022

In the context of the evolution of automation and intelligence, deep learning and machine learning algorithms have been widely applied in aquaculture in recent years, providing new opportunities for the digital realization of aquaculture. Especially, water quality management deserves attention thanks to its importance to food organisms. In this study, we proposed an end-to-end deep learning-based TabNet model for water quality prediction. From major indexes of water quality assessment, we applied novel deep learning techniques and machine learning algorithms in innovative fish aquaculture to predict the number of water cells counting. Furthermore, the application of deep learning in aquaculture is outlined, and the obtained results are analyzed. The experiment on in-house data showed an optimistic impact on the application of artificial intelligence in aquaculture, helping to reduce costs and time and increase efficiency in the farming process.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.67-73
• /
• 2020

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left, shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 × 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.55-62
• /
• 2021

We applied machine learning of semi-supervised learning, transfer learning, and federated learning as examples of AI use cases that can be applied to the three major industries(Automobile industry, Energy industry, and AI/Healthcare industry) of Gwangju Metro-city, and established an ML strategy for AI services for the major industries. Based on the ML strategy of AI service, practical approaches are suggested, the semi-supervised learning approach is used for automobile image recognition technology, and the transfer learning approach is used for diabetic retinopathy detection in the healthcare field. Finally, the case of the federated learning approach is to be used to predict electricity demand. These approaches were tested based on hardware such as single board computer Raspberry Pi, Jaetson Nano, and Intel i-7, and the validity of practical approaches was verified.

• Journal of Korea Game Society
• /
• v.8 no.1
• /
• pp.91-101
• /
• 2008

Most designers use professional 3D animation tools such as 3DS MAX to manually create animation. This manual method requires a great deal of time and efforts, and does not allow animation characters to interact with one another. In this paper, we design an AI middleware of form as 3DS MAX plug-in to solve these issues. We present an AI expression structure and internal processing method for this middleware, and the method for creating AI character's structure. It creates AI character's structure by drawing figures and lines for representing AI elements. For experiment, we have produced same animations with the traditional method and our method, and measured the task volume in both methods. This result verifies that the task volume is similar or higher than the traditional method in small-scale tasks, but up to 43% of the task volume is reduced in large-scale tasks. Using the method proposed in this paper, we see that characters in an animation interact each other, and task volume in large-scale tasks are reduced.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.175-185
• /
• 2023

As the era of ChatGPT and generative AI technologies unfolds, the marketing industry stands on the precipice of a paradigm shift. Innovations such as GPT-4, DALL-E 2, and Mid-journey Stable Diffusion possess the capacity to dramatically transform the methods by which advertisers reach and engage with customers. The potential applications of these advanced tools herald a new age for the marketing and advertising sectors, offering unprecedented opportunities for growth and optimization. Nevertheless, the rapid adoption of generative AI within these industries presents a unique set of challenges, particularly for organizations that lack the necessary technological infrastructure and human capital to effectively leverage these innovations. As a result, a competitive crisis may emerge, exacerbating existing disparities between well-equipped enterprises and their less technologically adept counterparts. In this article, we undertake a comprehensive exploration of the implications of generative AI for the future of marketing, examining both its potential benefits and drawbacks. We consider the possible impact of these developments on the advertising and marketing industries at large, as well as the ways in which professionals operating within these fields may need to adapt to remain competitive in an increasingly AI-driven landscape. By providing a holistic overview of the challenges and opportunities associated with generative AI, this study aims to elucidate the complex dynamics at play in the ongoing evolution of the marketing and advertising sectors.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.197-202
• /
• 2019

Society advances through technology, and technology has changed many lifestyles. The need for food is varying, but the availability of food is constantly changing as trends in production change. Combining the food industry and technology, a robot that delivers food and also cooks it has been developed. The time has come for a combination of food content and technology to advance the restaurant industry. This study discusses the application of a recommended food content media providing system using a curation engine that recommends contents according to individual tastes and preferences for the convenience of those who use food contents, using artificial intelligence speakers. We discuss the technologies required to develop video contents optimized for AI speakers with screens and shapes, combined with inset top boxes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.615-617
• /
• 2022

본 논문에서는 얼굴사진 기반 감정인식 심층망, 음성사운드를 기반한 감정인식 심층망을 결합한 앙상블 네트워크 구축을 위한 사전연구로서 얼굴사진 기반 감정을 인식하는 기존 딥뉴럴 네트워크 모델들을 입력 데이터 처리 방법에 따라 분류하고, 각 방법의 특성을 분석한다. 또한, 얼굴사진 외관 특성을 기반한 감정인식 네트워크를 여러 구조로 구성하고, 구성된 방법의 성능을 비교하여, 우수 성능을 보이는 네트워크를 선정하여 추후 앙상블 네트워크의 구성 네트워크로 사용하고자 한다.

• Journal of agricultural medicine and community health
• /
• v.34 no.1
• /
• pp.58-66
• /
• 2009

Objectives: Active participation of poultry breeder in surveillance system of Avian Influenza (AI) is very important. Therefore this study was conducted to present basis data for active report of AI that is affected by media's coverage in poultry breeder. Methods: Subjects were 88 persons, 28 who were poultry breeder at epidemic area of AI and 60 who were general person at non-epidemic area. Data were collected by the trained investigator from Jul. 1 to Aug. 31, 2008. Respondents were interviewed by means of a structured questionnaire. Results: The third-person effect among perceptions of influence in media's report on the AI was higher in breeder (32.1%) than in non-breeder (10.0%). However, Confidence to media report on the AI was lower in breeder than in non-breeder. Intention to report of the AI was 71.4% in breeder respectively, was 90.0% in non-breeder. There was statistically significant lower in breeder than non-breeder. The cause of avoidance of report was 'economic damage' for 87.5%, which acocounted for the majority of cases. Confidence to media report on the AI were positively correlated with concern on the AI and perception on seriousness of the AI, but negatively correlated with the third-person effect. Conclusions: These results showed that intention to report of the AI of breeder was susceptible to influenced by the third person effect and confidence in media's report on the AI. Therefore we should give a special attention to increase active report of poultry breeder during epidemic period of AI which is consideration of reasonable strategy of media's coverage, including mind and emotion state of poultry breeder.

• Smart Media Journal
• /
• v.12 no.8
• /
• pp.60-68
• /
• 2023

After COVID-19, hotel industry is rapidly experiencing changes in the business environment, and under the influence of the Fourth Industrial Revolution, hotel industry is striving to secure competitive advantages through differentiation, including the use of big data and the IoT in service provision, as well as the introduction of artificial intelligence(AI) robot services. This study analyzed the perceived value of AI robot services and their impact on usage attitudes and behavioral intentions of customers who have used hotels that have introduced AI robot services. The results of the study showed that the value of robot services perceived by customers who have used robot services in hotels is categorized into three dimensions: social, experiential, and functional, and all of them have a positive effect on usage attitudes, with social, functional, and experiential values having a positive effect on usage attitudes in that order. Attitude toward use was also analyzed to have a positive effect on behavioral intention, which is consistent with the value-attitude-behavior model. Therefore, it is necessary for hotels to improve the satisfaction of hotel guests through diversified services of AI robot service.