• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.

• Progress in Medical Physics
• /
• v.23 no.2
• /
• pp.91-98
• /
• 2012

Verification of internal organ motion during treatment and its feedback is essential to accurate dose delivery to the moving target. We developed an offline based internal organ motion verification system (IMVS) using cine EPID images and evaluated its accuracy and availability through phantom study. For verification of organ motion using live cine EPID images, a pattern matching algorithm using an internal surrogate, which is very distinguishable and represents organ motion in the treatment field, like diaphragm, was employed in the self-developed analysis software. For the system performance test, we developed a linear motion phantom, which consists of a human body shaped phantom with a fake tumor in the lung, linear motion cart, and control software. The phantom was operated with a motion of 2 cm at 4 sec per cycle and cine EPID images were obtained at a rate of 3.3 and 6.6 frames per sec (2 MU/frame) with $1,024{\times}768$ pixel counts in a linear accelerator (10 MVX). Organ motion of the target was tracked using self-developed analysis software. Results were compared with planned data of the motion phantom and data from the video image based tracking system (RPM, Varian, USA) using an external surrogate in order to evaluate its accuracy. For quantitative analysis, we analyzed correlation between two data sets in terms of average cycle (peak to peak), amplitude, and pattern (RMS, root mean square) of motion. Averages for the cycle of motion from IMVS and RPM system were $3.98{\pm}0.11$ (IMVS 3.3 fps), $4.005{\pm}0.001$ (IMVS 6.6 fps), and $3.95{\pm}0.02$ (RPM), respectively, and showed good agreement on real value (4 sec/cycle). Average of the amplitude of motion tracked by our system showed $1.85{\pm}0.02$ cm (3.3 fps) and $1.94{\pm}0.02$ cm (6.6 fps) as showed a slightly different value, 0.15 (7.5% error) and 0.06 (3% error) cm, respectively, compared with the actual value (2 cm), due to time resolution for image acquisition. In analysis of pattern of motion, the value of the RMS from the cine EPID image in 3.3 fps (0.1044) grew slightly compared with data from 6.6 fps (0.0480). The organ motion verification system using sequential cine EPID images with an internal surrogate showed good representation of its motion within 3% error in a preliminary phantom study. The system can be implemented for clinical purposes, which include organ motion verification during treatment, compared with 4D treatment planning data, and its feedback for accurate dose delivery to the moving target.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.30 no.1
• /
• pp.46-56
• /
• 2012

The research results of tracing the Landscape Philosophy of Hageowon garden(何去園) in Musu-dong, Daejon of Youhwadang, Kwon, Iijin(權以鎭, 1668-1734) is as below. The ideological background of the protagonist reflected in Hageowon is the Hyoje Ideology(filial piety and brotherly love, 孝弟) of Sinjongchuwon(painstakingly caring for one's ancestors), Musil ideology(pursuing ethical diligence and truthful mind, 務實) based on sadistic tradition and ethical rationalism, Confucionist Eunil Ideology(ideology on seclusion, 隱逸) of Cheonghanjiyeon(quiet relaxation, 淸閒之燕), and the Pungryu ideology(appreciation for the arts, 風流) of Taoism in the Taoist style. Thus, by substituting these ideological values into a space called Hageowon, the Byulup gardens(別業) such as the Symbolic garden(象徵園), meaning gaeden(意園), and miniascape garden(縮景園) were able to be constructed. 2) The space organization system of Hageowon is generally classified into three phases considering the hierarchy. The first territory is the transitional space having residential features, which is an area to reach peach tree - road(Taoist world 桃經) from Youhwadang(有懷堂). The second territory is a monumental memorial space where the Yocheondae(繞千臺), Jangwoodam(丈藕潭), Hwagae(花階), and the ancestral graves take place, centering on the yards of Sumanheon(收漫軒), and the third territory is the secluded space in the eastern outer garden where the mountain stream flows from the north to south and which is the vein of the left-hand blue dragon(靑龍) of the guardian mountain of Hageowon. 3) Symbolically, the first phase has symbolized the space as a meaningful scenery by overlapping the Confucionist place of Youhwadang - Gosudae(孤秀臺) - Odeokdae(五德臺), and the mystic world of Jukcheondang(竹遷堂) - peach tree - road(桃徑). The second phase, which is the space of Sumanheon(收漫軒), Yocheondae, and Jangwoodam, the symbolical value of Sinjongchuwon(愼終追遠) and the remembrance and longing for one's parents are reflected. The third phase, which is the eastern outer garden of Hageowon and where the mountain stream flows from the north to south, is composed of the east valley(東溪) - Hwalsudam(活水潭) - Sumi Waterfall(修眉瀑布). More specifically, (1) Mongjeong symbolizes the life of gaining knowledge through studying to realize one's foolishness, (2) Hwalsudam symbolizes a transcending attitude in life refusing to pursue wealth and fame, and (3) Jangwoodam symbolizes the gateway to the fairyland to enter the world of mystic gods. 4) The rationale behind Hageowon is that the two algorithms of Confucionism and Taoist Theory appear repeatedly and in an overlapping way. The Napoji(納汚池) and Hwalsudam, which pertains to the prelude of space development, has symbolized Susimyangseong(修心養成, meditating one's mind and improving one's nature), which is based on ethical rationalism. Moreover, if the Monjeong sphere pertaining to the eastern outer garden of Hageowon takes the Confucionist value system as its theme, including moral training, studying, and researching, Jangwudam, Sumi Waterfalls, and Unwa can be understood as a taste of Cheokbyeon(滌煩, eliminating troubles) for the arts where the mystic world is substituted as a meaningful scenery. 5) The miniascape technique called artificial mountain was substituted to Hageowon to construct a mystic world like the 12 peaks of Mt. Mu(巫山). By borrowing the symbolic meaning expressed in old poems, it has been named 'Habang(1/何放), Hwabong(2, 3/和峯), Chulgun(4, 5, 6/出群), Sinwan(7/神浣), Chwhigyu(8, 9, 10/聚糾), Cheomyo(11/處杳), Giyung(12/氣融).' The representative poet reciting artificial mountain were Wangeui(汪醫), Nosamgang(魯三江), Dubo(杜甫), Hanyou(韓愈), Jeonheaseong(錢希聖), and Beomseokho(范石湖). They related themselves with literature by transcending time and space and attempted to sing about the richness of the mental world by putting the mystic world and culture of appreciating the arts they pursued in the vacation home called Hageowon.

• Progress in Medical Physics
• /
• v.25 no.3
• /
• pp.167-175
• /
• 2014

The purpose of this study is to evaluate the variation of the dose which is delivered to the patients with glottis cancer under IMRT (intensity modulated radiation therapy) by using the 3D registration with CBCT (cone beam CT) images and the DIR (deformable image registration) techniques. The CBCT images which were obtained at a one-week interval were reconstructed by using B-spline algorithm in DIR system, and doses were recalculated based on the newly obtained CBCT images. The dose distributions to the tumor and the critical organs were compared with reference. For the change of volume depending on weight at 3 to 5 weeks, there was increased of 1.38~2.04 kg on average. For the body surface depending on weight, there was decreased of 2.1 mm. The dose with transmitted to the carotid since three weeks was increased compared be more than 8.76% planned, and the thyroid gland was decreased to 26.4%. For the physical evaluation factors of the tumor, PITV, TCI, rDHI, mDHI, and CN were decreased to 4.32%, 5.78%, 44.54%, 12.32%, and 7.11%, respectively. Moreover, $D_{max}$, $D_{mean}$, $V_{67.50}$, and $D_{95}$ for PTV were increased or decreased to 2.99%, 1.52%, 5.78%, and 11.94%, respectively. Although there was no change of volume depending on weight, the change of body types occurred, and IMRT with the narrow composure margin sensitively responded to such a changing. For the glottis IMRT, the patient's weight changes should be observed and recorded to evaluate the actual dose distribution by using the DIR techniques, and more the adaptive treatment planning during the treatment course is needed to deliver the accurate dose to the patients.

• Progress in Medical Physics
• /
• v.20 no.4
• /
• pp.308-316
• /
• 2009

To achieve the accurate evaluation of given absorbed dose from output dose of linear accelerator photon beam through investigate the characteristics of LiF:Mg,Cu,P TLD powder. This experimental TL phosphor is performed with a commercial LiF:Mg,Cu,P powder (Supplied by PTW) and TL reader (LTM, France). The TLD was exposed to 6 MV X rays of linear accelerator photon beam with range 15 to 800 cGy in blind dose at two hospitals. The dose evaluation of TLD was through the experimental algorithms which were dose dependency, dose rate dependency, fading and powder weight dependency. The glow curve has shown the three peaks which are 110, 183 and 232 degrees of heating temperature and the main dosimetric peak showed highest TL response at 232 high temperature. In this experiments, the LiF:Mg,Cu,P phosphor has shown the 2.5 eV of electron trap energy with a second order. This experiments guided the dose evaluation accuracy is within 1% +2.58% of discrepancy. The TLD powder of LiF:Mg,Cu,P was analyzed to dosimetric characterists of electron captured energy and order by glow shape, and dose-TL response curve guided the accuracy within 1.0+2.58% of output dose discrepancy.

• Journal of Gifted/Talented Education
• /
• v.25 no.2
• /
• pp.339-358
• /
• 2015

This study was to examine perceptions of information technology(IT) competencies among gifted and non-gifted students(i.e., information science high school students and technical high school students). Of the 370 high school students surveyed from 3 high schools(i.e., gifted academy, information science high school, and technical high school) in three metropolitan cities, Korea, 351 students completed and returned the questionnaires yielding a total response rate of 94.86%. High school students recognized the IT professional competence as being most important when recruiting IT employees. And they considered that practice-oriented education was the most importantly needed to improve their IT skills. In addition, the most important sub-factors of IT core competencies among gifted academy students and information science high school students were basic software skills. Also Technical high school students responded that the main network and security capabilities were the most importantly needed to do so. Finally, the most appropriate training courses for enhancing IT competencies were recognized differently among gifted and non-gifted students. Gifted academy students responded that the 'algorithm' was the mostly needed for enhancing IT competencies, whereas information science high school students responded that 'data structures' and 'computer architecture' were mostly needed to do. For technical high school students, they responded that a 'programming language' course was the most needed to do so. Results are discussed in relations to IT corporate and school settings.

• The Journal of Korean Society for Radiation Therapy
• /
• v.20 no.1
• /
• pp.1-9
• /
• 2008

Purpose: For head and neck cancer patients treated with radiation therapy, proper immobilization of intra-oral structures is crucial in reproducing treatment positions and optimizing dose distribution. We produced a man-made tongue immobilization device for each patient subjected to this study. Reproducibility of treatment positions and dose distributions at air-and-tissue interface were compared using man-made tongue immobilization devices and conventional tongue-bites. Materials and Methods: Dental alginate and putty were used in producing man-made tongue immobilization devices. In order to evaluate reproducibility of treatment positions, all patients were CT-simulated, and linac-gram was repeated 5 times with each patient in the treatment position. An acrylic phantom was devised in order to evaluate safety of man-made tongue immobilization devices. Air, water, alginate and putty were placed in the phantom and dose distributions at air-and-tissue interface were calculated using Pinnacle (version 7.6c, Phillips, USA) and measured with EBT film. Two different field sizes (3$\times$3 cm and 5$\times$5 cm) were used for comparison. Results: Evaluation of linac grams showed reproducibility of a treatment position was 4 times more accurate with man-made tongue immobilization devices compared with conventional tongue bites. Patients felt more comfortable using customized tongue immobilization devices during radiation treatment. Air-and-tissue interface dose distributions calculated using Pinnacle were 7.78% and 0.56% for 3$\times$3 cm field and 5$\times$5 cm field respectively. Dose distributions measured with EBT (international specialty products, USA) film were 36.5% and 11.8% for 3$\times$3 cm field and 5$\times$5 cm field respectively. Values from EBT film were higher. Conclusion: Using man-made tongue immobilization devices made of dental alginate and putty in treatment of head and neck cancer patients showed higher reproducibility of treatment position compared with using conventional mouth pieces. Man-made immobilization devices can help optimizing air-and-tissue interface dose distributions and compensating limited accuracy of radiotherapy planning systems in calculating air-tissue interface dose distributions.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.