• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1290-1304
• /
• 2020

Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmentation has been found to be a solution. In this review, we introduce data augmentation techniques, including image processing, such as rotation, shift, and intensity variation methods, generative adversarial network-based method, and image property mixing methods. Subsequently, we examine various deep learning studies based on data augmentation techniques. Finally, we discuss the necessity and future directions of data augmentation.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.2
• /
• pp.153-169
• /
• 2020

A new way of shopping based on virtual assistant, so called voice shopping, is drawing attention. The voice shopping market is growing around the world, and Korea is on the verge of full-scale commercialization of this new shopping. For the development of voice shopping-related industries, it is necessary to research on specific issues related to this new shopping methods, such as the quality of services, efficient processes tailored to new ways, and ways to build customer relationships. As part of such an attempt, the study seeks to determine the factors that affect consumers' perception and attitudes toward voice shopping. The study conducted the analysis based on survey response data of 171 online shopping users. In addition to the typical factors of the technology acceptability model(TAM) such as perceived usefulness and ease of use, the impact of perceived playfulness was included for analyzing the intention on the acceptance of voice shopping. In particular, this study focuses on the impact of user attributes. For the spread of voice shopping, it is necessary to set up a valid target customer and understand users for establishing an effective customer relationship. Therefore, this study tries to analyze how the perceptions on the voice shopping(perceived usefulness, ease of use, and perceived playfulness) are affected by users' attributes, such as user innovativeness and user knowledge level. The result of analysis shows that user innovativeness have a positive relationship with all of perceived usefulness, ease of use, and perceived playfulness. The user knowledge base, however, was not significant to all these three variables. The user knowledge base is shown to have a positive effect on user innovativeness which is the source of positively significant factor for the variable of the perceptions on the voice shopping. Meanwhile, among the variables of extended technology acceptance model, perceived usefulness and perceived playfulness have positive effects on the acceptance of voice shopping, while ease of use has no significant impact on the voice shopping acceptance. Ease of use has a positive relationship with perceived usefulness and playfulness. This study is meaningful in providing implications on the development of voice shopping platforms and related services, and establishment of customer relationship.

• International Journal of Highway Engineering
• /
• v.8 no.3 s.29
• /
• pp.129-141
• /
• 2006

The vertical soil pressure developed in the granular layer of asphalt pavement system is influenced by various factors, including the wheel load magnitude, the loading speed, and asphalt pavement temperature. This research observed the distribution of vertical soil pressure in pavement supporting layer by investigating measured data from soil pressure gage in the KHC Test Road. The existing specification of subbase and subgrade compaction was also evaluated with measured vertical pressure. The finite element analysis was conducted to verify the accuracy of results with measured data because it can maximize research capacity without significant field test. The test data was collected from A5, A7, A14, and A15 test sections at August, September, and November 2004 and August 2005. Those test sections and test data were selected because they had best quality. The size of influence area was evaluated and the vertical pressure variation was investigated with respect to load level, load speed, and pavement temperature. The lower speed, higher load level, and higher pavement temperature increased the vertical pressure and reduced the area of influence. The finite element result showed the similar trend of vertical pressure variation in comparison with measured data. The specification of compaction quality for subbase and subgrade is higher than the level of vertical pressure measured with truck load so that it should be lurker investigated.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.3
• /
• pp.104-115
• /
• 2014

A levee is defined as an man-made structure protecting the areas from temporary flooding. This paper suggests a methodology for establishing the levee GIS database using the airborne topographic LiDAR(Light Detection and Ranging) data taken in the Nakdong river basins and the WAMIS(WAter Management Information System) information. First, the National Levee Database(NLD) established by the USACE(United States Army Corps Engineers) and the levee information tables established by the WAMIS are compared and analyzed. For extracting the levee information from the LiDAR data, the DSM(Digital Surface Model) is generated from the LiDAR point clouds by using the interpolation method. Then, the slope map is generated by calculating the maximum rates of elevation difference between each pixel of the DSM and its neighboring pixels. The slope classification method is employed to extract the levee component polygons such as the levee crown polygons and the levee slope polygons from the slope map. Then, the levee information database is established by integrating the attributes extracted from the identified levee crown and slope polygons with the information provided by the WAMIS. Finally, this paper discusses the advantages and limitations of the levee GIS database established by only using the LiDAR data and suggests a future work for improving the quality of the database.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.612-628
• /
• 2001

This paper presents a methodology to extract classes and inheritance relations from procedural software. The methodology is based on the idea of generating all groups of class candidates, based on the combinatorial groups of object candidates, and their inheritance with all possible combinations and selecting a group of object candidates, and their inheritance with all possible combinations and selecting a group with the best or optimal combination of candidates with respect to the degree of relativity and similarity between class candidates in the group and classes in a domain model. The methodology has innovative features in class candidates in the group and classes in a domain model. The methodology has innovative features in class and inheritance extraction: a clustering method based on both static (attribute) and dynamic (method) clustering, the combinatorial cases of grouping class candidate cases based on abstraction, a signature similarity measurement for inheritance relations among n class candidates or m classes, two-dimensional similarity measurement for inheritance relations among n class candidates or m classes, two-dimensional similarity measurement, that is, the horizontal measurement for overall group similarity between n class candidates and m classes, and the vertical measurement for specific similarity between a set of classes in a group of class candidates and a set of classes with the same class hierarchy in a domain model, etc. This methodology provides reengineering experts with a comprehensive and integrated environment to select the best or optimal group of class candidates.

• Journal of Korea Technology Innovation Society
• /
• v.20 no.3
• /
• pp.732-753
• /
• 2017

Recently, when evaluating the technology values in the fields of biotechnology, pharmaceuticals and medicine, we have needed more to estimate those values in consideration of the period and cost for the commercialization to be put into in future. The existing discounted cash flow (DCF) method has limitations in that it can not consider consecutive investment or does not reflect the probabilistic property of commercialized input cost of technology-applied products. However, since the value of technology and investment should be considered as opportunity value and the information of decision-making for resource allocation should be taken into account, it is regarded desirable to apply the concept of real options, and in order to reflect the characteristics of business model for the target technology into the concept of volatility in terms of stock price which we usually apply to in evaluation of a firm's value, we need to consider 'the continuity of stock price (relatively minor change)' and 'positive condition'. Thus, as discussed in a lot of literature, it is necessary to investigate the relationship among volatility, underlying asset values, and cost of commercialization in the Black-Scholes model for estimating the technology value based on real options. This study is expected to provide more elaborated real options model, by mathematically deriving whether the ratio of the present value of the underlying asset to the present value of the commercialization cost, which reflects the uncertainty in the option pricing model (OPM), is divided into the "no action taken" (NAT) area under certain threshold conditions or not, and also presenting the estimation logic for option values according to the observation variables (or input values).

• Journal of Navigation and Port Research
• /
• v.30 no.6 s.112
• /
• pp.439-446
• /
• 2006

In ship structures many of the structural plates have cutouts, for example, at inner bottom structure, girder, upper deck hatch, floor and dia-frame etc. In the case where a plate has a cutout it experiences reduced buckling and ultimate strength and at the same time the in-plane stress under compressive load produced by hull girder bending will be redistributed In general, actual ship structure adopted reinforcement of stiffener around the cutout in order to preventing from buckling so it need to examine a buckling and ultimate strength behaviour considering a cutout because In many ship yards used class rule for calculating buckling strength but it is difficult to evaluate perforate stiffened plate with random size. In the present paper, we investigated several kinds of perforated stiffened model from actual ship and then was performed finite element series analysis varying the cutout ratio, web height, thickness and type of cross-section using commercial FEA program(ANSYS) under compressive load.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.1
• /
• pp.82-90
• /
• 2013

In the construction industry, there are so many qualitative factors affecting the performance of a project. So it is crucial to measure the factors in an effective way in order to analyze the interrelationship among the various factors. To improve the performance level of a project, it is also important to identify the most appropriate management practices which are inter-linked with the subject project. The purpose of this study is to develop a project performance management system (PPMS) to quantitatively analyze the variety of project performance data and identify the best management practice to increase the potential level of a particular performance area. Using a comparative statistical method, this study developed a quantification method and web-based computerized system to enhance the usage of the system. The system, however, is still under the validation stage because of the shortage of data set. In the future, when more and more completed project data are stored in the system, the system would play a crucial role in predicting the performance level and matching the best management practice for a subject project. In addition, the system can also be modified as a tool for a business- or industry-level system by incorporating the existing enterprise resource programs.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.89-92
• /
• 2015

In this paper, we propose a method to reduce the fire suppression time. Our suggestions can secure a safe area according to the diffusion path and speed of the fire, forest fire prediction minimize casualties and property damage forests. The existing path prediction method wildfire spread predict the wildfire spread model and speed through topography, weather, fuel factor and the image information. In this case, however, occur to control a large mountain huge costs. Also Focus on the diffusion model predictions and the path identified by the problem arises that insufficient efforts to ensure the safe area. In this paper, we estimate the moving direction and speed of fire at a lower cost, and proposes an algorithm to ensure the safety zone for fire suppression. The proposed algorithm is a technique to analyze the attribute information that temperature, wind, smoke measured over time. According to our algorithm forecast wildfire moving direction and ensure the safety zone. By analyzing the moving speed and the moving direction of the simulated fire in a given environment is expected to be able to quickly reduce the damage to the forest fire fighters.