• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2016

In this paper, we propose an object recognition system that can effectively find out its category, its instance name, and several attributes from the color and depth images of an object with hierarchical feature learning. In the preprocessing stage, our system transforms the depth images of the object into the surface normal vectors, which can represent the shape information of the object more precisely. In the feature learning stage, it extracts a set of patch features and image features from a pair of the color image and the surface normal vector through two-layered learning. And then the system trains a set of independent classification models with a set of labeled feature vectors and the SVM learning algorithm. Through experiments with UW RGB-D Object Dataset, we verify the performance of the proposed object recognition system.

• Journal of Radiation Protection and Research
• /
• v.28 no.2
• /
• pp.145-154
• /
• 2003

By optimizing the radiation protection the collective dose and individual dose could be reduced during YGN #4 $5^{th}$ outage in 2001. The collective doses for the two high radiation jobs decreased to 85% and 65% of expected doses. The proportion of workers with low dose (below 1mSv) exposure increased 4% while the proportion of workers with over 3mSv and 5mSv exposure are decreased to 2%, 1% respectively. But none is exposed over 8mSv for the annual dose. To aid decision of utilizing the robot, cost- benefit analysis was performed and reasonable point was proposed to use the robot. For the first time job, repeated ALARA meeting and mock up training were implemented to set up working procedure by identifying the trouble. To easily set up standard procedure, mockup process was videotaped and reviewed during ALARA meeting. Monitoring is a good approach to chase radiological working condition such as working time, dose rate. behavior of workers, especially for high radiation work. Those data were estimated and adjusted from the stage of work planning to mock up. At the stage of actual work the monitoring data were compared to the estimation and recorded to database. This database will not only be used as a powerful tool for dose optimization at the following outage but also as a guideline to dose constraint set up for optimization for each specific situation.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.1-16
• /
• 2012

In order to improve the workflow of 3D video production, this paper analyzes the visual fatigue caused from distortions in 3D video production stage through a set of subjective visual assessment tests. To establish a set of objective indicators for subjective visual tests, various distortions in production stage are investigated to be categorized into 7 representative visual-fatigue-producing factors, and to conduct visual assessment tests for each selected category, 4 test video clips are produced by combining the extent of camera movement as well as the object(s) movement in the scene. Each produced test video is distorted to reflect each of the selected 7 visual-fatigue-producing factors, and we set 7 levels of distortion for each factor, resulting in 196 5-second-long video clips for testing. Based on these test materials and the recommendation of ITU-R BT.1438, subjective visual assessment tests are conducted by 101 applicants. The test results provide a relative importance and the tolerance limit of each visual-fatigue-producing factor, which corresponds to various distortions in 3D video production field.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.3
• /
• pp.60-67
• /
• 2002

Existing as a reverse function in the information age, the security threats against the information system is increasing day by day and a systematic security management to this is being considered more and more important. The most important thing on security management is a risk analysis to understand the cause of the threat and to set up a countermeasure. Therefore, to increase security the proposed model will advise on the set up of the security policy and for a set up of an economic security countermeasure we have increased the reliability on the risk calculation stage. Especially, on the countermeasure stage we have requested a security level on the asset in order to examine the mutual reliance between assets, and differing from the standard model, we have improved the proposed model so that the materializing of the proposed countermeasure has been made to identify the restricted items for each asset and in order to not materialize superficial countermeasures and to make sure to materialize an economic countermeasure.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.1
• /
• pp.10-22
• /
• 2021

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.7
• /
• pp.3159-3163
• /
• 2012

Background: For cervical cancer the epidemiological profile is poorly known in Morocco and no data is available concerning the direct medical costs. The purpose of this work is to estimate the direct cost of medical management of invasive cervical cancer during the first year after diagnosis in Morocco. Methods: The estimation of direct costs of medical management of invasive cervical cancer during the first year after diagnosis in Morocco is based on the estimation of individual cost in each stage which covers diagnosis, treatment and follow-up during first year. The cost was estimated per patient and whole cycle-set using the costs for each drug and procedure as indicated by the Moroccan National Agency for Health Insurance. Extrapolation of the results to the whole country was used to calculate the total annual cost of cervical cancer treatments in Morocco. Results: Overall approximately 1,978 new cases of cervical cancer occur each year in Morocco. The majority (82.96%) of these cases were diagnosed at a late stage (stageII or more). The cost of one case of cervical cancer depends on stage of diagnosis, the lowest cost is $382 for stageCis followed by the cost of stageIA1 for young women (< 40 years) which is $2,952. The highest cost is for stageIV, which is $7,827. The total cost of cervical cancer care for one year after diagnosis is estimated at $13,589,360. The share allocated to treatment is the most important part of the global care budget with an annual sum of $13,027,609 whereas other cost components are represented as follows: $435,694 for annual follow-up activity and $126,057 for diagnosis and preclinical staging. Conclusion: This study provides health decision-makers with a first estimate of costs and the opportunity to achieve the optimal use of available data to estimate the needs of health facilities in Morocco.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.638-645
• /
• 2018

'42nd Broadway' is one of the most authentic, genuine and renowned musical pieces among the numerous musicals. By approaching every element in the Backstage from the perspective of an actor who is apart of the show, not a professional photographer, rather than an the usual objects on the Front Stage which is imprinted in the minds of the ordinary people through the media or the numerous flyers sent from the theaters, intented to describe the life as it is in the Back Stage by examining various elements such as the sets or make-up rooms, rather than the momentary, technically staged imageries. In the industrial aspect as well, the implication of this documentary would be that a more realistic set of photography was provided instead of the existing ones that usually focused on the'staged,' or 'guarded' images of the musical as shown in the promotional materials or the Front Stage still cuts.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.53 no.1
• /
• pp.27-35
• /
• 2020

Filefish Thamnaconus modestus has seen a sharp decline in their catch, we must strive for continuous resource management. We investigated the maturation and spawning of T. modestus by trawl net and set net from January 2018 to November 2019, off Jeju Is. and in coastal waters of North Gyeongsang Province's Korea. We analyzed monthly change total length (cm), gonadosomatic index (GSI) and maturity stages, egg diameter (mm), the relations fecundity and total length. GSI for Jeju Is. was the highest in April (3.17, 2.43), and decreased from July to 1.73 in August and GyeongBuk's GSI was the highest in Apri l (1.86, 2.58), followed by the high in May and the sharp decline in September, which is 0.23. Using a histological method, the annual reproductive cycle of T. modestus can be divided into 5stage in females; the early growing stage (Jan.-Mar.), late growing stage (Apr.-May), Mature stage, spent stage (Oct.), Recover and resting stage (Nov.-Jan.).We estimate the TL at 50% maturity as 24.1cm for female, fecundity ranged from 560,044 eggs at 23.4cm total length to 1,580,387 eggs at 36.6.cm TL.

• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.123-128
• /
• 2012

In this paper, we propose a landmark-detection system of object for more accurate object recognition. The landmark-detection system of object becomes divided into a learning stage and a detection stage. A learning stage is created an interest-region model to set up a search region of each landmark as pre-information necessary for a detection stage and is created a detector by each landmark to detect a landmark in a search region. A detection stage sets up a search region of each landmark in an input image with an interest-region model created in the learning stage. The proposed system uses Fast Fourier Transform to detect landmark, because the landmark-detection is fast. In addition, the system fails to track objects less likely. After we developed the proposed method was applied to environment video. As a result, the system that you want to track objects moving at an irregular rate, even if it was found that stable tracking. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.849-860
• /
• 2021

Recently, it is easy to find cases of 3D printing product, equipment, and materials in the architecture field. However, there is a lack of distribution environment where 3D printing products can be traded on an online platform or to access on-demand services in the architecture field. Therefore, in this study, a distribution platform development plan was proposed in consideration of the maturity level of the 3D printing distribution market in the domestic architecture field. For this purpose, the research was carried out as follows. First, by analyzing the case of the 3D printing distribution platform, the development stage of the distribution platform was set as three stages from the perspective of market maturity, platform development level, and sales/purchase experience level of suppliers and consumers. Second, the market maturity of the current domestic architecture field was evaluated as the first stage, and a distribution platform that could be implemented in the first stage was presented as a pilot. Third, we presented the first stage pilot, collected practical opinions on future construction plans through in-depth interviews, and presented detailed implementation plans for each stage necessary to achieve the second and third stage market maturity goals. Based on the roadmap derived from this study, it is expected that the domestic distribution platform market will grow step by step in the future and be utilized for business model development.