• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• The Korean Journal of Nuclear Medicine
• /
• v.34 no.1
• /
• pp.62-73
• /
• 2000

Purpose: Esophageal cancer patients have a difficulty in the intake of meals through the blocked esophageal lumen, which is caused by an ingrowth of cancer cells and largely influences on the prognosis. It is reported that esophageal cancer has a very low survival rate due to the lack of nourishment and immunity as the result of this. In this study a new radioactive stent, which prevents tumor ingrowth and restenosis by additional radiation treatment, has been developed. Materials and Methods: Using ${\ulcorner}HANARO{\lrcorner}$ research reactor, the radioactive stent assembly ($^{166}Ho$-SA) was prepared by covering the metallic stent with a radioactive sleeve by means of a post-irradiation and pre-irradiation methods. Results: Scanning electron microscopy and autoradiography exhibited that the distribution of $^{165/166}Ho\;(NO_3)$ compounds in polyurethane matrix was homogeneous. A geometrical model of the esophagus considering its structural properties, was developed for the computer simulation of energy deposition to the esophageal wall. The dose distributions of $^{166}Ho$-stent were calculated by means of the EGS4 code system. The sources are considered to be distributed uniformly on the surface in the form of a cylinder with a diameter of 20 mm and length of 40 mm. As an animal experiment, when radioactive stent developed in this study was inserted into the esophagus of a Mongrel dog, tissue destruction and widening of the esophageal lumen were observed. Conclusion: We have developed a new radioactive stent comprising of a radioactive tubular sleeve covering the metallic stent, which emits homogeneous radiation. If it is inserted into the blocked or narrowed lumen, it can lead to local destruction of the tumor due to irradiation effect with dilatation resulting from self-expansion of the metallic property. Accordingly, it is expected that restenosis esophageal lumen by the continuous ingrowth and infiltration of cancer after insertion of our radioactive stent will be decreased remarkably.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.17-31
• /
• 2006

In this paper, passport recognition and face verification methods which can automatically recognize passport codes and discriminate forgery passports to improve efficiency and systematic control of immigration management are proposed. Adjusting the slant is very important for recognition of characters and face verification since slanted passport images can bring various unwanted effects to the recognition of individual codes and faces. Therefore, after smearing the passport image, the longest extracted string of characters is selected. The angle adjustment can be conducted by using the slant of the straight and horizontal line that connects the center of thickness between left and right parts of the string. Extracting passport codes is done by Sobel operator, horizontal smearing, and 8-neighborhood contour tracking algorithm. The string of codes can be transformed into binary format by applying repeating binary method to the area of the extracted passport code strings. The string codes are restored by applying CDM mask to the binary string area and individual codes are extracted by 8-neighborhood contour tracking algerian. The proposed RBF network is applied to the middle layer of RBF network by using the fuzzy logic connection operator and proposing the enhanced fuzzy ART algorithm that dynamically controls the vigilance parameter. The face is authenticated by measuring the similarity between the feature vector of the facial image from the passport and feature vector of the facial image from the database that is constructed with PCA algorithm. After several tests using a forged passport and the passport with slanted images, the proposed method was proven to be effective in recognizing passport codes and verifying facial images.

• Journal of the Korean Society of Costume
• /
• v.26
• /
• pp.175-206
• /
• 1995

The costume culture of China is as old and varied as her long history. As China is a multiracial nation and consists of fifty-six min-ority races including Han race, there are not only fifty-six different costumes in China but each races' costume habit is very different. Therefore, Chinese penninsula can be considered an enor-mous exhibition center of the costumes. This study undertook on the assumption that the costumes' mainstream of Korea and east-northern Asia as well as that of China could be examined by investigating the minority races' costumes in the east-and west-northern areas of China. The process of evolution of the costume of a particular people, country or area is subject not only to constraints related to geography such as climate, topography or local products but is also affected by numorous environmental influences including cultural, economic, social and even pol-itical ones in terms of the selection of material, styling, color and standard of tailoring. In other words, things like philosophy of life, religious be-lief, aesthetic outlook, moral code, class system, degree of affluence, and cultural exchange will all be reflected directly or indirectly by features of a people's or country's style costume. Of course, there are several factors affecting to the style of costume of the minority people in China. However, the only three factors-geo-graphical and environmental, production method, and religious belef-will be touched in this study. First of all, the geograghical and eenviron-mental factor would be the decisive one because the costume should be designed to overcome the constraints of climate and geographical environ-ments. Accordingly, each race has an unique style of costume. The costume of the minority races in the northern parts are loose and wide, and made of warm furs. For instance, Mongolian robe has the quality of anti-wind, anti-cold and warmness, and the width of a sleeve is narrow and long. Secondly, the costume style can be said to be limited by the production pattern, when the geo-graphical environment was affected to decide the costume style, the production pattern was together affected to it . In case of Mongolian robe, they should satisfy the dual condition as the practical function. One is the condition that they should be fitted to the climate, and the other is the condition that they should be suit-able to the nomadic life. Mongolian robes are suitable to the nomadic peoples because they are designed for not only overcoming the cold wind and weather but being used as the bedquit at night. The costumes of Hoche people was made of the skin of the fish and wild animals because of their main means of living being fishing and hunting. Accordingly, their costumes are dur-able, warm and water-proof. Finally, the style of the costume is affected by the religious belief. In other words, the pattern in fashion is closely related with the religious be-lief or ancestor worship and nature worship. Ac-cordingly, the symbols of these worship are often emerged in the decoration of the costume. The design of costume of the people in the northern areas of China is very simple. It is related with their monotheism. On the other hand, the costumes of twen쇼 minority races in the east-northern parts of China can be devided into three racial groups such as the long robes of Man people and Mongols, Tunics of the peoples in the west-northern areas, and the pants and jackets of Hoche people. The minorority races all has not only the unique costume habit but their costumes are also related with their living style and production means.

• Journal of Astronomy and Space Sciences
• /
• v.12 no.2
• /
• pp.216-233
• /
• 1995

The distributions of the ionospheric conductivities, electric potential, ionospheric currents, field-aligned currents, Joule heating rate, and particle energy input rate by auroral electrons along with the characteristics of auroral particle spectrum are examined during moderately disturbed period by using the computer code developed by Kamide et al. (1981) and the ionospheric conductivity model developed by Ahn et al. (1995). Since the ground magnetic disturbance data are obtained from a single meridian chain of magnetometers (Alaska meridian chain) for an extended period of time (March 9 - April 27, 1978), they are expected to present the average picture of the electrodynamics over the entire polar ionosphere. A number of global features noted in this study are as follows: (1) The electric potential distribution is characterized by the so-called two cell convection pattern with the positive potential cell in the morning sector extending into the evening sector. (2) The auroral electrojet system is well developed during this time period with the signatures of DP-1 and DP-2 current systems being clearly discernable. It is also noted that the electric field seems to play a more important role than the ionospheric conductivity the conductivity over the poleward half of the westward electrojet in the morning sector while the conductivity enhancement seems to be more important over its equatorward half. (3) The global field-aligned current distribution pattern is quite comparable with the statistical result obtained by Iijima and Potemra (1976). However, the current density of Region 1 is much higher than that of Region 2 current at pointed out by pervious studies (e.g.; Kamide 1988). (4) The Joule heating occurs over a couple of island-like areas, one along the poleward side of the westward electrojet region in the afternoon sector. (5) The maximum average energy of precipitating electrons is found to be in the morning sector (07∼08 MLT) while the maximum energy flux is registered in the postmidnight sector (02 MLT). Thus auroral brightening and enhancement of ionospheric conductivity during disturbed period seem to be more closely associated with enhancement of particle flux rather than hardening of particle energy.

• Journal of Navigation and Port Research
• /
• v.28 no.10 s.96
• /
• pp.899-908
• /
• 2004

The rise of income and introduction of 5 day a week working system give korean people opportunities to enjoy their leisure time. And many korean people have much interest in oceanic sports such as yachting and also oceanic leisure equipments. With the popularization and development of the equipments, the scope of oceanic activities has been expanding in Korea just as in the advanced oceanic countries. However, The current conditions for the sports in Korea are not advanced and even worse than underdeveloped countries. In order to develop the underdeveloped resources of Korean marina, we need to customize the marina models of advanced nations to serve the specific needs and circumstances of Korea As such we have carried out a comparative analysis of how Austrailia, Newzealand, Singapore, japan and Malaysia operate their marina, reaching the following conclusions. Firstly, in marina operations, in order to protect personal property rights and to preserve the environment, we must operate membership and non-membership, profit and non-profit schemes separately, yet without regulating the dress code entering or leaving the club house. Secondly, in order to accumulate greater value added, new sporting events should be hosted each year. There is also the need for an active use of volunteers, the generation of greater interest in yacht tourism, and the simplification of CIQ procedures for foreign yachts as well as the provision of language services. Thirdly, a permanent yacht school should be established, and classes should be taught by qualified instructors. Beginners, intermediary, and advanced learner classes should be managed separately with special emphasis on the dinghy yacht program for children. Fourthly, arrival and departure at the moorings must be regulated autonomically, and there must be systematic measures for the marina to be able, in part, to compensate for loss and damages to equipment, security and surveillance after usage fees have been paid for. Fifthly, marine safety personnel must be formed in accordance with Korea's current circumstances from civilian organizations in order to be used actively in benchmarking, rescue operations, and oceanic searches at times of disaster at sea.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.116-130
• /
• 2019

In South Korea, forest fire occurrences are increasing in size and duration due to various factors such as the increase in fuel materials and frequent drying conditions in forests. Therefore, it is necessary to minimize the damage caused by forest fires by appropriately providing the probability of forest fire risk. The purpose of this study is to improve the Daily Weather Index(DWI) provided by the current forest fire forecasting system in South Korea. A new Fire Risk Index(FRI) is proposed in this study, which is provided in a 5km grid through the synergistic use of numerical weather forecast data, satellite-based drought indices, and forest fire-prone areas. The FRI is calculated based on the product of the Fine Fuel Moisture Code(FFMC) optimized for Korea, an integrated drought index, and spatio-temporal weighting approaches. In order to improve the temporal accuracy of forest fire risk, monthly weights were applied based on the forest fire occurrences by month. Similarly, spatial weights were applied using the forest fire density information to improve the spatial accuracy of forest fire risk. In the time series analysis of the number of monthly forest fires and the FRI, the relationship between the two were well simulated. In addition, it was possible to provide more spatially detailed information on forest fire risk when using FRI in the 5km grid than DWI based on administrative units. The research findings from this study can help make appropriate decisions before and after forest fire occurrences.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.17 no.1
• /
• pp.30-35
• /
• 2013

Purpose: One of the current services, providing information to the patients and their guardians by using promotion materials induces positive responses and contributes to the improvement of the hospital reliability. Therefore, the objective of this study is to evaluate the effectiveness of audio visual materials, one of the means of promotion, as a way to give accurate medical information to resolve patient's curiosity about purpose and procedure of their examination and deplete complains about waiting which attributes negative effect to service quality assessment. Materials and Methods: 60 patients(mean age $53.97{\pm}12.24$, male : female = 26 : 34) who had $^{18}F-FDG PET/CT$ scan from July 2012 to August 2012 in Seoul Asan Medical Center were referred to the study. All of the patients having PET/CT scan were asked to watch an informative video material before the injection of radiopharmaceutical ($^{18}F-FDG$) and to fill in a questionnaire. Results: As a result of analyzing the contents of questionnaire, 52% of 60 patients had PET/CT scan for the first time and 72.4% of the patients read the PET/CT guidebook offered from their outpatient department or inpatient wards before their scan. After we searched the level of previous knowledge of the purpose and method of PET/CT scan, the patients answered 25.1% "know well", 34% "not sure", 40.9% "don't know" respectively. And 84.7% of the patients answered that watching the PET/CT guide video before the injection helps understanding what exam they were having and 15.3% of the patients did not. For the question asking ever the patients have experienced using our homepage or smart phone QR code to see the guide video before they visit out PET center, only 3.3% of them answered "yes". Lastly, the patients answered 60.1% "yes", 31.4% "so so" and 8.5% "no" respectively for the question asking whether watching the video makes the patients to fill the waiting time short. Conclusion: It is found that understanding of objective and method of the PET/CT scan and level of satisfaction was improved after the patients watched the guide video whether they had PET/CT scan before and read the PET/CT guidebook or not. Also, watching the video was effective for the reduction of perceptible waiting time. But while displaying the PET/CT guide video is useful for providing information about the scan and shortening the waiting time as one of the medical service, utilization of service was actually very poor because of the passive promotion and indifference of the patients about their examination. Therefore, from now on, it is necessary to construct the healthcare system which can be offered to more patients through the active promotion.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.