• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.21-44
• /
• 2018

In recent years, the rapid development of internet technology and the popularization of smart devices have resulted in massive amounts of text data. Those text data were produced and distributed through various media platforms such as World Wide Web, Internet news feeds, microblog, and social media. However, this enormous amount of easily obtained information is lack of organization. Therefore, this problem has raised the interest of many researchers in order to manage this huge amount of information. Further, this problem also required professionals that are capable of classifying relevant information and hence text classification is introduced. Text classification is a challenging task in modern data analysis, which it needs to assign a text document into one or more predefined categories or classes. In text classification field, there are different kinds of techniques available such as K-Nearest Neighbor, Naïve Bayes Algorithm, Support Vector Machine, Decision Tree, and Artificial Neural Network. However, while dealing with huge amount of text data, model performance and accuracy becomes a challenge. According to the type of words used in the corpus and type of features created for classification, the performance of a text classification model can be varied. Most of the attempts are been made based on proposing a new algorithm or modifying an existing algorithm. This kind of research can be said already reached their certain limitations for further improvements. In this study, aside from proposing a new algorithm or modifying the algorithm, we focus on searching a way to modify the use of data. It is widely known that classifier performance is influenced by the quality of training data upon which this classifier is built. The real world datasets in most of the time contain noise, or in other words noisy data, these can actually affect the decision made by the classifiers built from these data. In this study, we consider that the data from different domains, which is heterogeneous data might have the characteristics of noise which can be utilized in the classification process. In order to build the classifier, machine learning algorithm is performed based on the assumption that the characteristics of training data and target data are the same or very similar to each other. However, in the case of unstructured data such as text, the features are determined according to the vocabularies included in the document. If the viewpoints of the learning data and target data are different, the features may be appearing different between these two data. In this study, we attempt to improve the classification accuracy by strengthening the robustness of the document classifier through artificially injecting the noise into the process of constructing the document classifier. With data coming from various kind of sources, these data are likely formatted differently. These cause difficulties for traditional machine learning algorithms because they are not developed to recognize different type of data representation at one time and to put them together in same generalization. Therefore, in order to utilize heterogeneous data in the learning process of document classifier, we apply semi-supervised learning in our study. However, unlabeled data might have the possibility to degrade the performance of the document classifier. Therefore, we further proposed a method called Rule Selection-Based Ensemble Semi-Supervised Learning Algorithm (RSESLA) to select only the documents that contributing to the accuracy improvement of the classifier. RSESLA creates multiple views by manipulating the features using different types of classification models and different types of heterogeneous data. The most confident classification rules will be selected and applied for the final decision making. In this paper, three different types of real-world data sources were used, which are news, twitter and blogs.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.28 no.2
• /
• pp.127-136
• /
• 2010

This study is aimed at reviewed and analyzed in order to suggest the improved plans related to natural monuments. The summary of this study is as followings; First, Replacing the current term 'cultural properties', which denotes the meaning of 'goods', we need to devise an new categorization that separates such properties into cultural heritage and natural heritage under the national heritage framework. Second, the designation criteria for natural monuments should be divided into the individual realm for animals and plants respectively, since they are not divided in the current Act. Third, the guidelines for naming of natural monuments should be established with the following new categories in accordance with the clear standards. Fourth, such imbalances require us to give priority to the relatively neglected types and areas. Fifth, as the big and old trees account for more than a half of the designated plants, it is necessary to search out new resources(wet plant communities, seashores, sand dune plant communities, etc.) such as geological resources, mineral springs, hot springs, and fossils that are in danger of completely being exploited and exhausted. While most of the designated animals are protected nationally, the existing designation system is required to protect habitats and breeding places for the systematic and efficient conservation. Sixth, as long as we need to preserve those historical and cultural resources for the future generations from national and global perspectives, we should enhance their values by designating them as natural monuments even though they are protected by other regulations such as the natural environment area. Seventh, as a result of the survey, we found that more budgets and experts in the local governments, more empowered organizations, more active public participation should be provided for the better Natural Monument management in Korea. Eighth, the Lap of Natural Heritage in the National Research Institute of Cultural Heritage needs to be developed to the Natural Heritage Institute to conduct the diverse activities such as researches, restoration, exhibition and education programs in a systematic and efficient way. Ninth and the last, major damages to natural monuments can be generally categorized into the artificial one and natural one, respectively. The artificial damages include toxics, soil covering, excessive humidity, fire, construction and management works, unlawful damages, fishing, oil spillage, etc, and the natural ones include lightning, storms(typhoons), heavy snowfalls, damage by insects and diseases, lack of prey, etc. This study will become meaningful in that it proposes specific measures for the improvement of the institutions, designation, and management of natural monuments on the basis of the comprehensive analysis on natural monuments. We wish to leave the other subjects related with this study to the future researches.

• Korean Journal of Heritage: History & Science
• /
• v.37
• /
• pp.65-89
• /
• 2004

Up to now, the studies for a pond of ancient palace of Korea are mainly achieved in a landscape architectural field. In fact, we can't grasp the general aspects but we are only heard about the fragmentary ruins and remains by the people who are in charge of an archaeological excavation. In this thesis, therefore, I attempt to grasp the relational categories of the ponds of an ancient palace of Korea, and find out the ideological backgrounds of the ponds of a palace construction through classify them excavated so far. The ancient ponds of Korea are divided to the class of square ponds(I) and curved ponds(II) according a shapes of planes. The class of square ponds(I) are subdivided to the form IA of the class of square ponds and form IB of the class of square ponds by whether it has an island, artificial hill and ornamental stone or not. And the class of the curved ponds(II) are divided to the form IIC that is only composed of curves in shore and the form IID that is composed of curves and straight lines. According the size, it is divided to a small size that is below the maximal diameter, 20m, and a large size that is more than 45m, after all, the ponds of the ancient palaces are devided to IAa, IAb, IBa, II Ca, IICb, IIDa. The square ponds and the curved ponds are co-exist from the initial stage when a pond of a place was found in our country and are succeeded or changed after Silla unified the three Kingdoms. In other words, we can infer a continuity from the earlier stage from the fact that there is a flat figure ground mainly constituted by the ponds of a palace mixed up of a straight line and a curved line in United Silla Kingdom while it succeeds the ponds of a palace that has a square form of Goguryo in Balhai. Different from the successional relation of the flat figure grounds, in an aspect of the elements of the construction, the site of the arbor at the top of the island and the bridge facilities in a field of a palace those are not exist in three Kingdoms period are appeared in United Silla Kingdom. The point that this aspect is simultaneously appeared in a neighboring country, or Japan, allows us to infer that there may be some motivations cause the changes in a construction of the ponds of a palace of Korea, China and Japan from the latter half of the 7th century to the first half of the 8th century. The ideological backgrounds of the ponds of a palace construction are divided roughly into Taoism and Buddhism. We can recognize that the ponds of a palace made up of the islands, the artificial hills and the garden rocks reflect Taiosm, considering the records of the ponds a palace of Korea and China are all use the term, Taoism, or the concrete statement represents that the islands, the artificial hills and the garden rocks are used in the description of the ponds of a palace of Korea. Both two are, therefore, obviously differentiated from the ponds of a palace that doesn't include them. We can conclude that the ponds of a palace that doesn't include them are colored by Buddhism since they are overtly distinguished from the class of curved ponds that reflect Taoism at the same period and they are identical with the site of an ancient temples in an aspect of their type and construction.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Journal of Applied Biological Chemistry
• /
• v.57 no.4
• /
• pp.307-312
• /
• 2014

Chocolate is restricted for obese and diabetic patients due to high in sugar contents. We investigated shell-chocolate fillings with low calorie content and low glycemic indexes using alternative sweeteners such as tagatose and xylose and adding coffee grounds. Chocolate filling was made with sugar, cacao and butter in the original recipe. Sugar was substituted with tagatose or xylose and 3% coffee ground was added in each chocolate filling and substituted for 3% of the cocoa. Water retention and spreadability of the chocolate filling was significantly higher in the tagatose+coffee ground group in comparison to the sugar. In the chromaticity test, chocolate filling made with tagatose was darker in comparison to that made with sugar: brightness (L) was lower and redness (a) and yellowness (b) were higher than the sugar filling. Sensory evaluation revealed that chocolate filling made with tagatose had high score in 4 categories such as taste, smell, texture of foreign substance, overall acceptance. After consuming 60 g of the chocolate with different fillings, blood glucose levels of subjects at 1 and 2 h were significantly lower in the tagatose and tagatose+coffee ground groups than the other groups. In conclusion, using tagatose as the sweetener in chocolate filling has a beneficial effect on lowering blood glucose levels and increasing water retention, spreadability and sensory scores. Coffee ground did not have additive effect on quality of chocolate filling and blood glucose levels. These results indicate that shell chocolate made with tagatose can be used as a snack for diabetic patients.

• Journal of Hospice and Palliative Care
• /
• v.7 no.2
• /
• pp.232-237
• /
• 2004

Purpose: DNR order is generally accepted for cancer patients near the end of life at Hospice Ward. It means not only no CPR when cardiopulmonary arrest develops but no aggressive meaningless medical interventions. Usually on admission, we discuss with the patients' family about DNR order at the Hospice Ward. Recently, we experienced a terminal lung cancer patient who had been on the ventilator for two months after pulmonary arrest. CPR and artificial ventilation were performed because patient's family refused DNR order. There is no consensus when, who, and how DNR order could be written for terminal cancer patients in Korea, yet. Methods: Hospice charts of 60 patients who admitted between Jan and Jun 2003 to Hospice Ward were reviewed retrospectively. Results: The median age was 66(range $31{\sim}93$) and there were 31 males and 29 females. Their underlying cancers were lung (12), stomach (12), biliary tract (7), colon (6), pancreas (4) and others (19). The persons who signed DNR order were son (22), spouse(19), daughter (16) and others (3). But, there was no patients who signed DNR order by oneself. Thirty families of 60 patients signed on day of admission and 30 signed during hospitalization when there were symptom aggravation (19), vital sign change (4), organ failure (3) and others (4). There were 13 patients who died within 5 days after DNR order. Most of patients died at our hospice ward, except in 1 patient. The level of care was mostly 1, except in 2 patients. (We set level of care as 3 categories. Level 1 is general medical care: 2 is general nursing care: 3 is terminal care.) Conclusion: We have to consider carefully discussing DNR order with terminal cancer patients in the future & values on withholding futile intervention.

• Journal of architectural history
• /
• v.3 no.1
• /
• pp.83-99
• /
• 1994

Ch'ang-Ts'al-Ts'un is a rural Village near Lung-jing City in Yen-pien Korean Autonomous Province of China. It was formed about 100 years ago by Korean Immigrants and has been developed maintaing the characteristics of traditional Korean architecture. Therefore investigating the spatial structure of this village is a meanigful work to confirm and explore one branch of Korean architecture. This study aims at analyzing the spatial structure of the village using direct data collected from the field work and indirect data from books and maps. The field work consists of on-the-site survey of the village layout, interviews of residents, observation notes and photography. Ch'ang-Ts'ai-Ts'un is located 360-370 m high above the sea level and at the side of a long valley. A river flows in the middle of the valley and relatively flat arable land exists at the both sides of the river. The location of the village related to the surrounding river and mountains suggests that the site of the village was chosen according to Feng-Shui, Chinese and Korean traditional architectural theory. The main direction of the house layouts is South-western. The village has been growing gradually until today. Therefore it is meaningful to make the village layout before Liberation(1946 A.D.) because the characteristics of Korean architecture prevailed more in that period. The area of the previous village is limited to the west side of the creek. New houses were later added to the east of the creek, forming a 'New Village'. Previously the village was composed of 3 small villages: Up, Middle and Down. Also the main access roads connecting the village with the neighboring villages were penetrating the village transversely. Presently the main access road comes to the village longitudinally from the main highway located in front of the village. The retrospective layout shows the existence of well-formed Territory, Places and Axes, thus suggesting a coherent Micro-cosmos. The boundary of imaginery territory perceived by present residents could be defined by linking conspicous outside places sorrounding the village such as Five-mountains, Front-mountain, Shin-dong village, Standing-rock, Rear-mountain and Myong-dong village. Inside the territory there are also the important places such as Bus-stop, Memorial tower of patriots, Road-maitenance building and the village itself. And inside it 5 transverse and 1 longitudinal axes exist in the form of river, roads and mountains. The perceived spatial structure of the village formed by Places, Axes and Territory is geometrical and well-balanced and suggests this village is fit for human settlement. The administrative area of the village is about 738 ha, 27 % of which is cultivated land and the rest is mountain area. Initially the village and surrounndings were covered with natural forest But the trees have been gradually cut down for building and warning houses, resulting in the present barren and artificial landscape with bare mountains and cultivated land. At present the area of the village occupied by houses is wedge-shaped, 600 m wide and 220 m deep in its maximum. The total area of the village is $122,175m^{2}$. The area and the rate of each sub-division arc as follow. 116 house-lots $91,465m^{2}$ (74.9 %) Land for public buildings and shops $2,980m^{2}$ (2.4 %) Roads $17,106m^{2}$ (14.0 %) Creek $1,356m^{2}$ (1.1 %) Vacant spaces and others $9,268m^{2}$ (7.6 %) TOTAL $122,175m^{2}$ (100.0 %) Each lot is fenced around with vertical wooden pannels 1.5-1.8 m high and each house is located to the backside of the lot. The open space of a lot is sub-divided into three areas using the same wooden fence: Front yard, Back yard and Access area. Front and back yards are generally used for crop-cultivation, the custom of which is rare in Korea. The number of lots is 116 and the average size of area is $694.7m^{2}$. Outdoor spaces in the village such as roads, vacant spaces, front yard of the cultural hall, front yard of shops and spacse around the creek are good 'behavioral settings' frequently used by residents for play, chatting, drinking and movie-watching. The road system of the village is net-shaped, having T-junctions in intersections. The road could be graded to 4 categories according to their functions: Access roads, Inner trunk roads, Connecting roads and Culs-de-sac. The total length of the road inside the village is 3,709 m and the average width is 4.6 m. The main direction of the road in the village is NNE-SSE and ESE-WNW, crossing with right angles. Conclusively, the spatial structure of Ch'ang-Ts'ai-Ts'un village consists of various components in different dimensions and these components form a coherent structure in each dimension. Therefore the village has a proper spatial structure meaningful and appropriate for human living.

• Phonetics and Speech Sciences
• /
• v.11 no.1
• /
• pp.29-40
• /
• 2019

The paper investigates the minimal pair of Korean phonemes quantitatively. To achieve this goal, I calculated the number of consonant minimal pairs in the syllable-initial position as both raw counts and relative counts, and analyzed the part of speech relations of the two words in the minimal pair. "Urimalsaem" was chosen as the object of this study because it was judged that the minimal pair analysis should be done through a dictionary and it is the largest among Korean dictionaries. The results of the study are summarized as follows. First, there were 153 types of minimal pairs out of 337,135 examples. The ranking of phoneme pairs from highest to lowest was 'ㅅ-ㅈ, ㄱ-ㅅ, ㄱ-ㅈ, ㄱ-ㅂ, ㄱ-ㅎ, ${\ldots}$, ㅆ-ㅋ, ㄸ-ㅋ, ㅉ-ㅋ, ㄹ-ㅃ, ㅃ-ㅋ'. The phonemes that played a major role in the formation of the minimal pair were /ㄱ, ㅅ, ㅈ, ㅂ, ㅊ/, in that order, which showed a high proportion of palatals. The correlation between the raw count of minimal pairs and the relative count of minimal pairs was found to be quite high r=0.937. Second, 87.91% of the minimal pairs shared the part of speech (same syntactic category). The most frequently observed type has been 'noun-noun' pair (70.25%), and 'vowel-vowel' pair (14.77%) was the next ranking. It can be indicated that the minimal pair could be grouped into similar categories in terms of semantics. The results of this study can be useful for various research in Korean linguistics, speech-language pathology, language education, language acquisition, speech synthesis, and artificial intelligence-machine learning as basic data related to Korean phonemes.

• Journal of Food Hygiene and Safety
• /
• v.36 no.3
• /
• pp.248-256
• /
• 2021

A total of 120 samples corresponding to 12 categories of dried processed fishery products distributed in Gyeonggi-do were examined for radioactivity contamination (¹³¹I, ¹³⁴Cs, ¹³⁷Cs) and heavy metals (lead, cadmium, arsenic, and mercury). One natural radioactive material, ⁴⁰K, was detected in all products, while the artificial radioactive materials ¹³¹I, ¹³⁴Cs and ¹³⁷Cs were not detected at above MDA (minimum detectable activity) values. The detection ranges of heavy metals converted by biological basis were found as follows: Pb (N.D.-0.332 mg/kg), Cd (N.D.-2.941 mg/kg), As (0.371-15.007 mg/kg), Hg (0.0005-0.0621 mg/kg). Heavy metals were detected within standard levels when there was an acceptable standard, but the arsenic content was high in most products, although none of the products had a permitted level of arsenic. In the case of dried processed fishery products, there are products that are consumed by restoring moisture to its original state, but there are also many products that are consumed directly in the dry state, so it will be necessary to set permitted levels for heavy metals considering this situation in the future. In addition, Japan has decided to release contaminated water from the Fukushima nuclear power plant into the ocean, so there is high public concern about radioactivity contamination of food, including fishery products. Therefore, continuous monitoring of various food items will be necessary to ease consumers' anxiety.

• Journal of Environmental Impact Assessment
• /
• v.32 no.1
• /
• pp.1-14
• /
• 2023

When carrying out development projects around Ardeidae breeding habitats, we intend to devise a plan for sustainable coexistence by presenting measures to select and reduce key evaluation items so that conflicts can be prevented in advance at the environmental impact assessment stage. The results of the study are as follows. The main evaluation items are animal and plant items for preservation of Ardeidae breeding habitats and odor and noise items that can evaluate the effects of odors and noise in Ardeidae breeding habitats. First, the scope of the survey in animals and plants categories is not limited to legal guardian species, but includes egrets breeding and feeding grounds corresponding to major species breeding grounds and migratory birds, and preservation measures are established according to the reduction of the area of breeding and feeding grounds. Second, in the odor category, the irradiation period includes the period when the odor generation is the highest from the end of June to the end of July. The odor evaluation standard is based on the complex odor discharge standard, which is a concentration regulation, and the odor concentration felt by humans shall be 2 to 5OU/m³ and the frequency shall be 2% or less. Third, in the noise category, the timing of the survey is measured every month from May to August, including when the sound of egrets and young birds is combined to maximize noise generation. Since the noise of Ardeidae, a bird in summer, occurs only for a certain period of time, measures are taken to reduce noise by securing separation distances, securing buffer green areas, and installing construction rather than installing artificial structures such as soundproof walls. In order for existing Ardeidae breeding sites to maintain an appropriate density of populations and not move populations elsewhere, it is necessary to manage nesting tree and maintain stable habitat quantity and quality.