• ETRI Journal
• /
• v.39 no.5
• /
• pp.643-651
• /
• 2017

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1801-1806
• /
• 2004

Stochastic nature of subgrid-scale stress causes the predictability problem in large eddy simulation (LES) by which the LES solution field decorrelates with field from filtered directnumerical simulation (DNS). In order to evaluate the predictability limit in a priori sense, the information on the interplay between resolved scale and subgrid-scale (SGS) is required. In this study, the analysis on the inter-scale interaction is performed by applying tophat and cutoff filters to DNS database of flow over a circular cylinder at Reynolds number of 3900. The effect of filter shape is investigated on the interpretation of correlation between scales. A critique is given on the use of tophat filter for SGS analysis using DNS database. It is shown that correlations between Karman vortex and SGS kinetic energy drastically decrease when the cutoff filter is used, which implies that the small scale universality holds even in the presence of the large scale coherent structure.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.245-248
• /
• 2005

This paper presents a novel user interface system which aims at easy controlling of mobile devices. The fundamental concept of the proposed interface is to launch an appropriate function of the device by sensing and recognizing the grip-pattern when the user tries to use the mobile device. To this end, we develop a prototype system which employs capacitive touch sensors covering the housing of the system and a recognition algorithm for offering the appropriate function which suitable for the sensed grip-pattern. The effectiveness and feasibility of the proposed method is evaluated through the test of recognition rate with the collected grip-pattern database.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.851-860
• /
• 2009

Recently, among the computational methods of protein-protein interaction prediction, vast amounts of domain based methods originated from domain-domain relation consideration have been developed. However, it is true that multi domains collaboration is avowedly ignored because of computational complexity. In this paper, we implemented a protein interaction prediction system based the Interaction Significance matrix, which quantified an influence of domain combination pair on a protein interaction. Unlike conventional domain combination methods, IS matrix contains weighted domain combinations and domain combination pair power, which mean possibilities of domain collaboration and being the main body on a protein interaction. About 63% of sensitivity and 94% of specificity were measured when we use interaction data from DIP, IntAct and Pfam-A as a domain database. In addition, prediction accuracy gradually increased by growth of learning set size, The prediction software and learning data are currently available on the web site.

• Korean Journal of Clinical Pharmacy
• /
• v.25 no.3
• /
• pp.138-144
• /
• 2015

Objective: It is to evaluate the drug interaction monitoring program as a pilot project to develop a pharmaceutical care model in a medical intensive care unit and to analyze the influencing factors of drug interactions. Method: Electronic medical records were retrospectively investigated for 116 patients who had been hospitalized in a medical intensive care unit from October to December in 2014. The prevalence of adverse reaction with risk rating higher than 'D' was investigated by Lexi-$Comp^{(R)}$ Online database. The factors related with potential drug interaction and with treatment outcomes were analyzed. Results: The number of patients with a potential interaction of drug combination was 92 (79.3%). Average ages, the length of stay in the intensive care unit and the numbers of prescription drugs showed significant differences between drug interaction group and non-drug interaction group. Opioids (14.4%), antibiotics (7.2%), and diuretics (7.2%) were most responsible drug classes for drug interactions and the individual medications included furosemide (6.4%), tramadol (4.9%), and remifentanil (4.5%). There were 950 cases with a risk rating of 'C' (84.6%), 142 cases with a risk rating of 'D' (12.6%), and 31 cases with a risk rating of 'X' (avoid combination) (2.8%). The factors affecting drug interactions were the number of drugs prescribed (p < 0.0001) and the length of stay at intensive care unit (p < 0.01). The patients in intensive care unit showed a high incidence of adverse reactions related to potential drug interaction. Therefore, drug interaction monitoring program as a one of pharmaceutical care services was successfully piloted and it showed to prevent adverse reaction and to improve therapeutic outcomes. Conclusion: Active participation of a pharmacist in the drug management at the intensive care unit should be considered.

• Journal of Distribution Science
• /
• v.14 no.7
• /
• pp.71-81
• /
• 2016

Purpose - Because creativity, which is an intangible resource embedded within the company, can offer a competitive advantage, most companies have an interest in promoting creativity among their employees and division(e.g., marketing organization). Creativity renders a sustainable competitive advantage to a firm because it is a strategic resource that is valuable, flexible, rare, and imperfectly imitable or substitutable. Although most companies broadly recognize the importance of creativity, the methods for developing creativity remain elusive. Therefore, the present study investigates how to structure incentives to motivate employees to be more creative and how to develop tools to facilitate creativity. In detail, the present study aimed to examine the relationship between the regulatory focus of marketing organizations(e.g., promotion focus vs prevention focus) and creativity of marketing organizations. In addition, the present study set out to examine the moderating role of interaction of financial reward and creative training in addition to investigating the direct relationship between creativity and regulatory focus in New Product Development(NPD) context. Research design, data, and methodology - The data used to test the hypotheses are drawn from a survey of full time NPD project members(including project manager, designer, engineer, and marketer). The present study utilized data obtained mainly from a database compiled by the Korea Investors Service-Financial Analysis System which provides comprehensive corporate and financial information on firms listed on the Korea Stock Exchange. A study population comprising 1,000 South Korean firms was obtained from this database. We selected 864 firms from the database, and the firms have experiences of new product development project. We collected a total of 162 responses, for a 18.8% response rate. After we excluded 14 questionnaire because of incomplete responses, a total of 148 questionnaire remained(final response rate: 17.1%). Working with a sample of 148 responses in South Korea, hierarchical moderated regression is employed to test research hypotheses(

The relationship between promotion focus and creativity of marketing organization,

The relationship between prevention focus and creativity of marketing organization,

The moderating effect of joint influences(interaction between financial rewards and creativity training) on the relationship between promotion focus creativity of marketing organization,

The moderating effect of joint influences(interaction between financial rewards and creativity training) on the relationship between prevention focus creativity of marketing organization). SPSS 18.0 and AMOS software were used in the data analysis. Results - The empirical study confirmed that promotion focus of marketing organization is positively related to creativity of marketing organization. Also, prevention focus of marketing organization is positively affected to creativity of marketing organization. In addition, the interaction between financial rewards and creativity training moderated the relationship between regularity focus(e.g.), promotion focus vs prevention focus) and creativity of marketing organization. These results suggest that managers can improve the performances of their creative efforts by providing the use of financial rewards and creativity training in combination. Conclusion - Based on results of this study that examine the effects of regulatory focused creative efforts on creativity of marketing organization, promotion focus is helpful with marketing organizations to enhance their service innovation and performance. Prevention focused organization should allow monetary rewards and creativity training to increase their creativity for innovation of new products.

• The Journal of Information Technology and Database
• /
• v.6 no.1
• /
• pp.1-13
• /
• 1999

The modeling components in the object-oriented paradigm are based on the object, not the structured function or procedure. That is, in the past, when one wanted to solve problems, he would describe the solution procedure. However, the object-oriented paradigm includes the concepts that solve problems through interaction between objects. The object-oriented model is constructed by describing the relationship between object to represent the real world. As in object-oriented model the relationships between objects increase, the control of objects caused by their insertions, deletions, and modifications comes to be very complex and difficult. Because the loss of the referential integrity happens and the object reusability is reduced. For these reasons, the necessity of the control of objects and the visualization of the relationships between them is required. In order that we design a database necessary to implement Object Browser that has functionalities to visualize Java objects and to perform the query processing in Java object modeling, in this paper we show the processes for EER modeling on Java object and its transformation into relational database schema. In addition we implement Java Object Parser that parses Java object and inserts the parsed results into the implemented database.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.623-626
• /
• 2006

Group of genes controls the functioning of a cell by complex interactions. These interacting gene groups are called Gene Regulatory Networks (GRNs). Two previous data mining approaches, clustering and classification have been used to analyze gene expression data. While these mining tools are useful for determining membership of genes by homology, they don't identify the regulatory relationships among genes found in the same class of molecular actions. Furthermore, we need to understand the mechanism of how genes relate and how they regulate one another. In order to detect regulatory relationships among genes from time-series Microarray data, we propose a novel approach using frequent pattern mining and chain rule. In this approach, we propose a method for transforming gene expression data to make suitable for frequent pattern mining, and detect gene expression patterns applying FP-growth algorithm. And then, we construct gene regulatory network from frequent gene patterns using chain rule. Finally, we validated our proposed method by showing that our experimental results are consistent with published results.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.1-8
• /
• 2019

Coronaviruses are known respiratory pathogens. In the past, most human coronaviruses were thought to cause mild symptoms such as cold. However recently, as seen in the Severe Acute Respiratory Syndrome (SARS) and the Middle East Respiratory Syndrome (MERS), infectious diseases with severe pulmonary disease and respiratory symptoms are caused by coronaviruses, making research on coronaviruses become important. Considering previous studies, we constructed 'HCoV-IMDB (Human Corona Virus Immune Database)' to systematically provide genetic information on human coronavirus and host immune information, which can be used to analyze the interaction between human coronavirus and host immune proteins. The 'HCoV-IMDB' constructed in the study can be used to search for genetic information on human coronavirus and host immune protein and to download data. A BLAST search specific to the human coronavirus, one of the database functions, can be used to infer genetic information and evolutionary relationship about the query sequence.

• Genomics & Informatics
• /
• v.15 no.1
• /
• pp.19-27
• /
• 2017

Understanding complex relationships among heterogeneous biological data is one of the fundamental goals in biology. In most cases, diverse biological data are stored in relational databases, such as MySQL and Oracle, which store data in multiple tables and then infer relationships by multiple-join statements. Recently, a new type of database, called the graph-based database, was developed to natively represent various kinds of complex relationships, and it is widely used among computer science communities and IT industries. Here, we demonstrate the feasibility of using a graph-based database for complex biological relationships by comparing the performance between MySQL and Neo4j, one of the most widely used graph databases. We collected various biological data (protein-protein interaction, drug-target, gene-disease, etc.) from several existing sources, removed duplicate and redundant data, and finally constructed a graph database containing 114,550 nodes and 82,674,321 relationships. When we tested the query execution performance of MySQL versus Neo4j, we found that Neo4j outperformed MySQL in all cases. While Neo4j exhibited a very fast response for various queries, MySQL exhibited latent or unfinished responses for complex queries with multiple-join statements. These results show that using graph-based databases, such as Neo4j, is an efficient way to store complex biological relationships. Moreover, querying a graph database in diverse ways has the potential to reveal novel relationships among heterogeneous biological data.