• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.4
• /
• pp.384-398
• /
• 2015

In this paper, the high-resolution Weather Research and Forecasting/Noah-MultiParameterization (WRF/Noah-MP) modeling system is configured for the Cheongmicheon Farmland site in Korea (CFK), and its performance in land and atmospheric simulation is evaluated using the observed data at CFK during the 2014 special observation period (21 August-10 September). In order to explore the usefulness of turning on Noah-MP dynamic vegetation in midterm simulations of surface and atmospheric variables, two numerical experiments are conducted without dynamic vegetation and with dynamic vegetation (referred to as CTL and DVG experiments, respectively). The main results are as following. 1) CTL showed a tendency of overestimating daytime net shortwave radiation, thereby surface heat fluxes and Bowen ratio. The CTL experiment showed reasonable magnitudes and timing of air temperature at 2 m and 10 m; especially the small error in simulating minimum air temperature showed high potential for predicting frost and leaf wetness duration. The CTL experiment overestimated 10-m wind and precipitation, but the beginning and ending time of precipitation were well captured. 2) When the dynamic vegetation was turned on, the WRF/Noah-MP system showed more realistic values of leaf area index (LAI), net shortwave radiation, surface heat fluxes, Bowen ratio, air temperature, wind and precipitation. The DVG experiment, where LAI is a prognostic variable, produced larger LAI than CTL, and the larger LAI showed better agreement with the observed. The simulated Bowen ratio got closer to the observed ratio, indicating reasonable surface energy partition. The DVG experiment showed patterns similar to CTL, with differences for maximum air temperature. Both experiments showed faster rising of 10-m air temperature during the morning growth hours, presumably due to the rapid growth of daytime mixed layers in the Yonsei University (YSU) boundary layer scheme. The DVG experiment decreased errors in simulating 10-m wind and precipitation. 3) As horizontal resolution increases, the models did not show practical improvement in simulation performance for surface fluxes, air temperature, wind and precipitation, and required three-dimensional observation for more agricultural land spots as well as consistency in model topography and land cover data.

• Journal of Science Education
• /
• v.32 no.1
• /
• pp.33-46
• /
• 2008

The purpose of this study was to know whether or not any wrongful description or simple errors were in photosynthesis unit of Biology II textbook under 7th national curriculum and if so, to know whether or not high school teachers recognized and corrected properly the mistakes. The mistakes in photosynthesis unit of text books were determined by the comparison with several reference books and through examination by three plant physiologists in 8 different Biology II textbooks. After the mistakes were analysed, the survey using contents of textbook containing the mistakes was conducted on high school teachers teaching Biology II. As a result, 48 mistakes were determined in 13 subjects. As many as four mistakes were found even in one subject in a certain textbook and a same mistake was found repeatedly in several textbooks. The survey result showed that the teachers who pointed exactly the mistakes out corrected properly, however, the percentage of these ones out of 35 teachers replied to survey was less than 50%. The ratios of correction out of total number of responses were high in question #6 (43%), #4-3 (40%), and #1-2 (32%) which were containing a simple mistake in graph, a wrong word and a wrong picture, respectively. But, no one pointed out and made correction in question #5-1 and #5-2 which were containing Z scheme of light reaction without the legend of vertical axis that should be explained as electron energy or standard reduction potential. The result indicates the possibility that the mistakes in photosynthesis unit of Biology II textbook can be corrected and teached properly by teachers may be low. In order to reduce the possibility that students may have misconceptions about photosynthesis, the list of print's errors should be provided to the teachers and/or the training program and/or workshop for in-service high school biology teachers was recommended.

• Journal of KIISE:Information Networking
• /
• v.29 no.6
• /
• pp.595-612
• /
• 2002

One of the most important issues in guaranteeing the high degree of QoS on mobile computing is how to reduce hand-off drops caused by lack of available bandwidth in a new cell. Each cell can request bandwidth reservation to its adjacent cells for hand-off calls. This reserved bandwidth can be used only for hand-offs, not for new calls. It is also important to determine how much of bandwidth should be reserved for hand-off calls because reserving too much would increase the probability of a new call being blocked. Therefore, it is essential to develop a new mechanism to provide QoS guarantee on a mobile computing environment by reserving an appropriate amount of bandwidth and call admission control. In this paper. bandwidth reservation and call admission control mechanisms are proposed to guarantee a consistent QoS for multimedia traffics on a mobile computing environment. For an appropriate bandwidth reservation, we propose an adaptive bandwidth reservation mechanism based on an MPP and a 2-tier cell structure. The former is used to predict a next move of the client while the latter to apply our mechanism only to the client with a high hand-off probability. We also propose a call admission control that performs call admission test only on PNC(Predicted Next Cell) of a client and its current cell. In order to minimize a waste of bandwidth caused by an erroneous prediction of client's location, we utilize a common pool and QoS adaptation scheme. In order evaluate the performance of our call admission control mechanism, we measure the metrics such as the blocking probability of new calls, dropping probability of hand-off calls, and bandwidth utilization. The simulation results show that the performance of our mechanism is superior to that of the existing mechanisms such as NR-CAT2, FR-CAT2, and AR-CAT2.

• Journal of the Korean Geographical Society
• /
• v.30 no.1
• /
• pp.68-92
• /
• 1995

Recentry the structure of the retail trade have been chanaed with its environmantal changes. Some studies may be necessary on the changing process of environment and fundamental structure analyses of the retail trade. This study analyzes the location of retail trades, inhabitants' behavior in retail tredes and their desirable utilization scheme of them in Kwangju-si. Some study methods, contents and coming-out results are as follows: 1. Retail trades can be classified into independent stores, chain-stores (supermarket, voluntary chain and frenchiise system and convenience store), department stores, cooperative associations, traditional, markets mail-order marketing, automatic vending and others by service levels, selling-items, prices, managements, methods of retailing and store or nonstore type. 2. In Kwangju, the environment of retail trades is related to the consumers of population structure: chanes in consumers pattern, trends toward agings and nuclear family, increase of leisur: time and female advances to society. Rapid structural shift in retail trade has also been occurred due to these social changes. Traditionl and premodern markets until 1970s altere to supermarkets or department stores in 1980s, and various types, large enterprises and foreign capitals came into being in 1990s. 3. The locational characteristics of retail trades are resulted from the spatial analysis of the total population distribution, and from the calculation of segregation index in the light of potential demand. The densely-populated areas occurs in newly-built apartment housing complex which is distributed with a ring-shaped pattern around the old urban core. The numbers and rates of the aged over sixty in Kwangsan-gu and the circumference area of Mt.Moodeung, are larger and higher where rural elements are remarkable. A relation between population distribution and retail trade are analysed by the index of population per shop. The index of the population number per shop is lower in urban center, as a whole, being more convenient for consumers. In newly-formed apartment complex areas, on the other, the index more than 1,000 per shop, meeting not the demands for consumers. Because both the younger and the aged are numerous in these areas, the retail trade pattern pertinent to both are needed. Urban fringes including Kwangsan-gu and the vicinity of Mt.Moodeung have some problems owing to the most of population number per shop (more than 1, 500) and the most extensive as well. 4. The regional characteristic of retail trade is analyzed through the location quotient of shops by locational patterns and centerality index. Chungkum-dong is the highest-order central place in CBD. It is the core of retail trades, which has higher-ordered specialty store including three big department stores, supermarkets and large stores. Taegum-dong, Chungsu-dong, Taeui-dong, and Numun-dong that are neiahbored to Chungkum-dong fall on the second group. They have a central commercial section where large chain stores, specialty shopping streets, narrow-line retailing shops (furniture, amusement service, and gallary), supermarkets and daily markets are located. The third group is formed on the axis of state roads linking to Naju-kun, Changseong-kun, Tamyang-kun, Hwasun-kun and forme-Songjeong-eup. It is related to newly, rising apartment housing complex along a trunk road, and characterized by markets and specialty stores. The fourth group has neibourhood-shopping centers including older residential area and Songjeong-eup area with independent stores and supermarkets as main retailing functions. The last group contains inner residential area and outer part of a city including Songjeong-eup. Outer part of miscellaneous shops being occasionally found is rural rather than urban (Fig. 7). 5. The residents' behaviors using retail trade are analyzed by factors of goods and facilities. Department stores are very high level in preference for higher-order shopping-goods such as clothes for full dress in view of both diversity and quality of goods(28.9%). But they have severe traffic congestions, and high competitions for market ranges caused by their sma . 64.0% of respondents make combined purpose trips together with banking and shopping. 6. For more efficiency of retail-trading, it is necessary to induce spatial distribution policy with regard to opportunity frequency of goods selection by central place, frontier regions and age groups. Also we must consider to analyze competition among different types of retail trade and analyze the consumption behaviors of working females and younger-aged groups, in aspects of time and space. Service improvement and the rationalization of management should be accomplished in such as cooperative location (situation) must be under consideration in relations to other functions such as finance, leisure & sports, and culture centers. Various service systems such as installment, credit card and peremium ticket, new used by enterprises, must also be carried service improvement. The rationalization and professionalization in for the commercial goods are bsically requested.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.9
• /
• pp.58-67
• /
• 2009

This paper presents a fully digital gain control system with a new high bandwidth and wide dynamic range power detector for DVB-S2 application. Because the peak-to-average power ratio (PAPR) of DVB-S2 system is so high and the settling time requirement is so stringent, the conventional closed-loop analog gain control scheme cannot be used. The digital gain control is necessary for the robust gain control and the direct digital interface with the baseband modem. Also, it has several advantages over the analog gain control in terms of the settling time and insensitivity to the process, voltage and temperature variation. In order to have a wide gain range with fine step resolution, a new AGC system is proposed. The system is composed of high-bandwidth digital VGAs, wide dynamic range power detectors with RMS detector, low power SAR type ADC, and a digital gain controller. To reduce the power consumption and chip area, only one SAR type ADC is used, and its input is time-interleaved based on four power detectors. Simulation and measurement results show that the new AGC system converges with gain error less than 0.25 dB to the desired level within $10{\mu}s$. It is implemented in a $0.18{\mu}m$ CMOS process. The measurement results of the proposed IF AGC system exhibit 80-dB gain range with 0.25-dB resolution, 8 nV/$\sqrt{Hz}$ input referred noise, and 5-dBm $IIP_3$ at 60-mW power consumption. The power detector shows the 35dB dynamic range for 100 MHz input.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.9
• /
• pp.868-882
• /
• 2009

In this paper, channel model and wireless link performance analysis for the short-range wireless communication system applications in the terahertz frequency which is currently interested in many countries will be described. In order to realize high data rates above 10 Gbps, the more wide bandwidths will be required than the currently available bandwidths of millimeter-wave frequencies, therefore, the carrier frequencies will be pushed to THz range to obtain larger bandwidths. From the THz atmospheric propagation characteristics based on ITU-R P.676-7, the available bandwidths were calculated to be 68, 48 and 45 GHz at the center frequencies of 220, 300 and 350 GHz, respectively. With these larger bandwidths, it was shown from the simulation that higher data rate above 10 Gbps can be achieved using lower order modulation schemes which have spectral efficiency of below 1. The indoor propagation delay spread characteristics were analyzed using a simplified PDP model with respect to building materials. The RMS delay spread was calculated to be 9.23 ns in a room size of $6\;m(L){\times}5\;m(W){\times}2.5\;m(H)$ for the concrete plaster with TE polarization, which is a similar result of below 10 ns from the Ray-Tracing simulation in the reference paper. The indoor wireless link performance analysis results showed that receiver sensitivity was $-56{\sim}-46\;dBm$ over bandwidth of $5{\sim}50\;GHz$ and antenna gain was calculated to be $26.6{\sim}31.6\;dBi$ at link distance of 10m under the BPSK modulation scheme. The maximum achievable data rates were estimated to be 30, 16 and 12 Gbps at the carrier frequencies of 220, 300 and 350 GHz, respectively, under the A WGN and LOS conditions, where it was assumed that the output power of the transmitter is -15 dBm and link distance of 1 m with BER of $10^{-12}$. If the output power of transmitter is increased, the more higher data rate can be achieved than the above results.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.10 no.5
• /
• pp.209-217
• /
• 2015

Development of food industry and increased city life induced enlarged generation of food waste which is currently reused in a wide range of way. In this study, treatment of food waste generated from the public agricultural product wholesale markets (they are categorized as business places which imposes the duty for reducing the food waste discarded) in Korea was investigated, and subsequently, a scheme for improving the food waste recycling business was suggested. The food waste treatment plants are mainly located in Kyeongki-do at 39.5% of total plants in Korea and the other provinces have less than 10% of the total numbers, among which public treatment plant was 38.0% and private plant was 62.0%. The treatment methods included recycling as animal feed at 47.5%, as compost at 36.4%, and the rest of food waste (12.6%) was treated in other ways. Remarkably, it was noticed that the amount of food waste treated in anaerobic digestion have been increased up to 5.4% since 2011. This implied that food waste treated in anaerobic digestion method is gradually increased according to government policy. Amongst 33 public agricultural product wholesale markets distributed all over the country, the trading volume dealt in Garakdong market in Seoul, Gangseo market in Seoul, Daegu market in Daeju, Eomgung market in Busan, Guri market in Guri accounted for 34.67, 7.47, 6.98, 5.41, and 5.30% of the total trading volume in Korea, respectively. 2.65% of the total trading agricultural products dealt in the markets were remained as food waste and treated. In 2006, Ministry of Agriculture, Food and Rural Affairs implemented the package policy for radish and Chinese cabbage in order to reduce the amount of food waste and indeed, food waste generated in Garakdong market declined to one third of the food waste before the package policy implementation. In 2010, the food waste amount treated by 'dehydration', 'discarding as raw materials', and 'drying after dehydration' accounted for 56.3%, 33.7%, and 10.0% of the total food waste generated in the public agricultural product wholesale market. However, in 2013, discarding as raw materials accounted for the most at 56.3% followed by dehydration at 37.5%, and by drying after dehydration at 6.3%. The remarkable increment of the food waste discarded as raw materials was attributed to the increase of them in Garakdong market in Seoul. In general, the agricultural food waste contains high amount of moisture at 88% in average and low amount of salt at 0.02% in average. Therefore, it is highly recommended to treat the agricultural food waste through drying after dehydration in order for improving the treatment capability. Also, this recommendation can be supported by the fact that the end-products via drying after dehydration can be utilized as compost material. Overall, the agricultural food waste recycling business can be developed through integration of the treatment via 'drying after dehydration' and compost production.

• Journal of the Korean association of regional geographers
• /
• v.4 no.1
• /
• pp.77-98
• /
• 1998

In general, spatial imbalance in regional growth is a major cause of social and political conflicts within a state. In Korea, this inequality has functioned as a threat to the state's integration. With the economic development policies by regional industrialization over the past three decades, most of the industrial activities have been concentrated in Seoul and Pusan metropolitan areas, which are surrounded by Kyonggi, Kyongnam provinces respectively. Compared to these areas, Chonnam and Chonbuk provinces have lagged behind in economic development. Therefore, in order to increase the regional economic development of the southwestern region in Korea, the central government has been enforcing several policies aimed at regional industrialization since the 1980s. The purpose of this study focuses on the regional economic impacts of a newly established industrial estate-Yulchon industrial complex- which would act as a regional growth center in the Kwangyang bay area. The Kwangyang bay area consists of several industrial estates such as Kwangyang Iron and Steel Co. and its related industrial complex, Chuam rural industrial estate, Yeochon industrial complex, and so on. In addition, the Kwangyang container port was constructed in 1997. The Kwangyang bay area has been changing to a new industrial district in the southwestern part of Korea as a result of industrialization policies which were activated by central government. The Yulchon industrial complex, which is expected to be completed in 2001, would draw many manufacturing plants. For example, Hyundai Motors Co. has a plan to locate a new automobile assembly plant within the estate. As the plan has high probability to be realized, it will be interesting to study the effects a new automobile assembly plant and its related production linkages have on the region. This study is to estimate the expected structural characteristics of automobile production activities in Yulchon. The following details will be discussed: the regional economic impacts of a new automobile industry in Yulchon industrial complex, the production linkage formation via hierarchical subcontracting systems, the alternative strategies to promote the growth of regional economies, and the scheme to improve the auto-parts and components industry in Kwangju and Chonnam provinces by establishing auto-mobile production function. Automoblie industry generally gives great influences on not only regional economies but the related industries, for example, the firms producing automotive components. If a new plant producing automobiles and its related firms producing components are to be established in Yulchon, they will affect on the regional development directions and change the regional characteristics of industrial structure. In order to increase the spread effects of the new industry in Yulchon industrial complex, almost all of the automobile production processes must be organized concurrently within a limited range of distance. There is an imperative that the co-operation system should be structured between the assembly firm and many firms producing its components. In addition to those, it would be required such as the effective division of labors between the firms, much more capabilities in the technical innovations, and the reconstruction of interrelationship between the labor unions and the firms' managers.