• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• Asia pacific journal of information systems
• /
• v.28 no.2
• /
• pp.75-92
• /
• 2018

Conceptual modeling is well suited as a subject that constitutes the "core" of the Information Systems (IS) discipline and has grown in response to IS development. Several modeling grammars and methods have been studied extensively in the IS discipline. Previous studies, however, present deficiencies in research methods and even put forward contradictory results about the ternary relationship in conceptual modeling. For instance, some studies contend that the semantics of a binary relationship are better for novices, but others argue that a ternary relationship is better than three binary relationships when the association among three entity types clearly exists. The objective of this research is to acquire complete and accurate understanding of the ternary relationship, specifically to understand practitioners' modeling performance when utilizing either a ternary or binary relationship. To the best of our knowledge, no previous work clearly compares real-world modeler performance differences between binary and ternary representations. By investigating practitioners' understanding of ternary relationship and identifying practitioners' cognition, this research can broaden the perspective on conceptual modeling.

• Tuberculosis and Respiratory Diseases
• /
• v.73 no.3
• /
• pp.137-142
• /
• 2012

In the last several years, we have made slow but steady progress in understanding molecular biology of lung cancer. This review is focused on advances in understanding the biology of lung cancer that have led to proof of concept studies on new therapeutic approaches. The three selected topics include genetics, epigenetics and non-coding RNA. This new information represents progress in the integration of molecular mechanisms that to identify more effective ways to target lung cancer.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.6
• /
• pp.961-968
• /
• 1987

This paper describes an intelligent image compression system called AIIC which is capable of adjusting image compression ratios ranging from 1:1 to 12,000:1 depending on available bandwidth. This system utilizes not only conventional image compression algorithms but also intelligent techniques through understanding image contents to achieve ultra-high compression ratios. This system was simulated on a micro-computer network.

• Ocean Science Journal
• /
• v.41 no.2
• /
• pp.121-124
• /
• 2006

Argo drifters provide information of the vertical structure in the water column and have a potential for the improvement of understanding phytoplankton primary production and biogeochemical cycles in combination with ocean color satellite data, which can obtain the horizontal distribution of phytoplankton biomass in the surface layer. Our examples show that using Argo drifters with satellite-measured horizontal distribution of phytoplankton biomass at the sea surface allow an improved understanding of the development of the spring bloom. The other possible uses of Argo drifter are discussed.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.235-241
• /
• 2020

Artificial intelligence and machine learning are used in many parts of our daily lives, but the basic processes and concepts are barely exposed to most people. Understanding these basic concepts is becoming increasingly important as kids don't have the opportunity to explore AI processes and improve their understanding of basic machine learning concepts and their essential components. Machine learning educational tools can help children easily understand artificial intelligence and machine learning. In this paper, we examine machine learning education tools and compare their features.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.333-335
• /
• 2015

A computer vision-based scene recognition algorithm is proposed for monitoring construction sites. The system analyzes images acquired from a surveillance camera to separate regions and classify them as building, ground, and hole. Mean shift image segmentation algorithm is tested for separating meaningful regions of construction site images. The system would benefit current monitoring practices in that information extracted from images could embrace an environmental context.

• Journal of The Korean Association of Information Education
• /
• v.20 no.6
• /
• pp.645-654
• /
• 2016

As the 4th industrial revolution has progressed in recent years, the importance of robot education in elementary school education is increasing. In this paper, I suggested robot education framework to consider conceptual understanding and learning activities based on the 2014, 2015 KAIE software education standard curriculum for elementary school. The framework is reconstructed the 7 stages, In order to generalize the standardized model of the software curriculum, the achievement criteria should be prepared according to the content system of the curriculum considering the conceptual understanding and learning activities proposed in this paper, and if the educational contents are developed and utilized, it is expected to contribute to the activation of robot education in addition to elementary school software education.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.502-513
• /
• 2017

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

• Asia pacific journal of information systems
• /
• v.26 no.2
• /
• pp.211-230
• /
• 2016

Social commerce is a new type of e-commence that is based on social networking technologies and aggressive marketing strategies, such as one-deal-a-day. However, although social commerce has become very popular, little is known of customers' substantive purchasing behaviors when using social commerce sites. These behaviors, namely visiting and purchasing behaviors, are the focus of this study. Hence, this study aims to provide comprehensive understanding of the visiting and purchasing behaviors of customers in relation to social commerce sites. A research model based on the utilitarian and hedonic values of shopping, social influence, and convenience, which represent social commerce features, was developed and empirically analyzed using data from social commerce site users. The results revealed that purchasing behaviors of consumers when they use social commerce sites are affected directly by the utilitarian value (perceived usefulness) of the site as well as their purchase intention. Purchase intention is affected by perceived usefulness, subjective norm, and visiting behaviors. The visiting behaviors of consumers in relation to social commerce sites are also affected directly by the hedonic value (playfulness) of the site as well as their intention to visit the site. The findings of this study have implications for practitioners with regard to understanding and promoting the use of social commerce sites.