• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.65-82
• /
• 2021

Stock market investors are generally split into foreign investors, institutional investors, and individual investors. Compared to individual investor groups, professional investor groups such as foreign investors have an advantage in information and financial power and, as a result, foreign investors are known to show good investment performance among market participants. The purpose of this study is to propose an investment strategy that combines investor-specific transaction information and machine learning, and to analyze the portfolio investment performance of the proposed model using actual stock price and investor-specific transaction data. The Korea Exchange offers daily information on the volume of purchase and sale of each investor to securities firms. We developed a data collection program in C# programming language using an API provided by Daishin Securities Cybosplus, and collected 151 out of 200 KOSPI stocks with daily opening price, closing price and investor-specific net purchase data from January 2, 2007 to July 31, 2017. The self-organizing map model is an artificial neural network that performs clustering by unsupervised learning and has been introduced by Teuvo Kohonen since 1984. We implement competition among intra-surface artificial neurons, and all connections are non-recursive artificial neural networks that go from bottom to top. It can also be expanded to multiple layers, although many fault layers are commonly used. Linear functions are used by active functions of artificial nerve cells, and learning rules use Instar rules as well as general competitive learning. The core of the backpropagation model is the model that performs classification by supervised learning as an artificial neural network. We grouped and transformed investor-specific transaction volume data to learn backpropagation models through the self-organizing map model of artificial neural networks. As a result of the estimation of verification data through training, the portfolios were rebalanced monthly. For performance analysis, a passive portfolio was designated and the KOSPI 200 and KOSPI index returns for proxies on market returns were also obtained. Performance analysis was conducted using the equally-weighted portfolio return, compound interest rate, annual return, Maximum Draw Down, standard deviation, and Sharpe Ratio. Buy and hold returns of the top 10 market capitalization stocks are designated as a benchmark. Buy and hold strategy is the best strategy under the efficient market hypothesis. The prediction rate of learning data using backpropagation model was significantly high at 96.61%, while the prediction rate of verification data was also relatively high in the results of the 57.1% verification data. The performance evaluation of self-organizing map grouping can be determined as a result of a backpropagation model. This is because if the grouping results of the self-organizing map model had been poor, the learning results of the backpropagation model would have been poor. In this way, the performance assessment of machine learning is judged to be better learned than previous studies. Our portfolio doubled the return on the benchmark and performed better than the market returns on the KOSPI and KOSPI 200 indexes. In contrast to the benchmark, the MDD and standard deviation for portfolio risk indicators also showed better results. The Sharpe Ratio performed higher than benchmarks and stock market indexes. Through this, we presented the direction of portfolio composition program using machine learning and investor-specific transaction information and showed that it can be used to develop programs for real stock investment. The return is the result of monthly portfolio composition and asset rebalancing to the same proportion. Better outcomes are predicted when forming a monthly portfolio if the system is enforced by rebalancing the suggested stocks continuously without selling and re-buying it. Therefore, real transactions appear to be relevant.

• Tuberculosis and Respiratory Diseases
• /
• v.65 no.2
• /
• pp.110-115
• /
• 2008

Background: Congenital cystic adenomatoid malformation of the lung (CCAM) is a rare congenital developmental anomaly of the lower respiratory tract. Most cases are diagnosed within the first 2 years of life, so adult presentation of CCAM is rare. We describe here six adult cases of CCAM and the patients underwent surgical resection, and all these patients were seen during a five and a half year period. The purpose of this study was to analyze the clinical, radiological and histological characteristics of adult patients with CCAM. Methods: Through medical records analysis, we retrospectively reviewed the clinical characteristics, the chest pictures (X-ray and CT) and the histological characteristics. Results: Four patients were women and the mean age at diagnosis was 23.5 years (range: 18~39 years). The major clinical presentations were lower respiratory tract infection, hemoptysis and pneumothorax. According to the chest CT scan, 5 patients had multiseptated cystic lesions with air fluid levels and one patient had multiple cavitary lesions with air fluid levels, and these lesions were surrounded by poorly defined opacities at the right upper lobe. All the patients were treated with surgical resection. 5 patients underwent open lobectomy and one patient underwent VATS lobectomy. On the pathological examination, 3 were found to be CCAM type I and 3 patients were CCAM type II, according to Stocker's classification. There was no associated malignancy on the histological studies of the surgical specimens. Conclusion: As CCAM can cause various respiratory complications and malignant changes, and the risks associated with surgery are extremely low, those patients who are suspected of having or who are diagnosed with CCAM should go through surgical treatment for making the correct diagnosis and administering appropriate treatment.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.5 no.1
• /
• pp.70-82
• /
• 1994

Present study was to evaluate the validity and the clinical utility of the Korean version of Luria-Nebraska Neuropsychological Battery for Children(LNNB-C) in various groups including normal, brain damaged attention deficit hyperactivity disordered(ADHD), and psychiatrically disordered. The Korean version of LNNB-C and BGT were administered to clinical groups consisted of 51 patients(19 brain damaged, 16 ADHD. and 16 psychiatric controls), and to normal group composed of 147 children between the age of 8 and It Also KEDI-WISC was administered D clinical groups as a part of comprehensive psychological assessment There were significant differences between the brain damaged and the normals on all scales of LNNB-C, and between the normals and the ADHD on 11 clinical scales and 3 summary scales, which indicate the clinical validity for the scales of the Korean version of LNNB-C. The significant differences between the ADHD and the brain damaged on 3 summary scales were found, suggesting that the summary scales might play an important role id discriminating between two groups. Multiple discriminant analysis showed that the Korean version of LNNB-C significantly discriminates 3 groups - normals, ADHD, and brain damaged. Percentages of correct classification were ranged from 62.5% in the ADHD to 98.6Ta in the normals. For further evaluating the discriminant validity of the LNNB-C, the discriminant power of each items were calculated, and 131 of the 147 items discriminated significantly between the brain damaged and the normals. The scales of LNNB-C significantly correlated with the error scores of BGT and the most of scales of KEDI-WISC. These results put together : strongly support the concurrent and the discriminant validity of the Korean version of LNNB-C in diagnosing brain damage. The limitations of present study and several issues for the luther study were discussed.

• Journal of Yeungnam Medical Science
• /
• v.2 no.1
• /
• pp.11-22
• /
• 1985

Femur neck fracture is well known as one of the major death cause after trauma in elderly patients, and unsolved fracture due to its frequent association with complications such as avascular necrosis and nonunion. Through meticulous evaluation of the patient, hip and surgeon's experiences, reduction of mortality and morbidity as well as rapid recovery of the patient to the preinjury social and ambulatory status without local complications and revision after treatment is urgently needed. Many factors about this fracture In itself were noted, but we have analyzed 18 femur neck fractures of the patients older than 50 years preliminarily according to age, fracture pattern, osteoporosis, etiology and method of treatment with its delay in association with major complications especially avascular necrosis and nonunion. The results are as follows; 1. Of these 18 fractures, 11 were in females, 8 were caused by minor trauma such as slip-down accident and 4 were associated with definite osteoporosis according to the Sing's classification. 2. Fracture pattern of these 18 are undisplaced in 4, displaced subcapital in 11, displaced transcervical in 3. 11 fractures in the patients older than 60 year are composed of 3 undisplaced or impacted fractures and 8 displaced subcapital fractures. 3. These 18 fractures were treated by closed reduction and Internal fixation with multiple pins in 13, and hemiarthroplasty in 4, but one was not treated to die after discharge from hospital. 4. 4 undisplaced or impacted fractures and 3 displaced transcervical fractures were not associated with any complications such as avascular necrosis or nonunion. But 4 of 6 displaced subcapital fractures were complicated by avascular necrosis, 3 of which were reduced in the varus position within 1 week, and the other was reduced in the good position on 1 week after trauma. There was no complication in 2 displaced subcapital fractures reduced in valgus position within 3 days after trauma. According to the above results, the prognosis of the femur neck fracture is dependent upon the fracture pattern and delay in its treatment. So it is inevitable to reduce the fracture in anatomical or valgus position as early as possible. But the arthroplasty may be needed in displaced subcapital fractures delayed for several days, with its reluction in extreme varus position or impossible and with pre-existing disease in the same hip Joint (total hip replacement).

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.42 no.6
• /
• pp.101-110
• /
• 2014

This study analyzes the validity of the type classification of the type and design changes of apartment landscaping planting construction design changes that were completed in the private sector, efficiently manages the design changes that are displayed over landscaping planting work in general in the future, and performs research by placing the object underlying the presentation. The results are as follows. First, the percentage that occurred in the planting construction of design changes that have occurred in the apartment landscaping construction was carried out in the private sector and accounted for 61.8%. This indicates that part of the planting is a major design change. Second, as the cause of such a design change to be those associated with the field conditions such as lack of main construction period. In particular, due to a change in oral, appeared 7-48 times design changes of one review design change approval is complex, design changes of planting construction had shown a feature that occurs in multiple simultaneous. Third, the 7 types of Design Changes in planting design were delineated as 'design changes for consideration of the user', 'design changes for image improvement', 'design changes for ease of maintenance', 'design changes due to the mismatch of design statement', 'design changes due to the relationship with the engineering species of other', 'design changes due to lack of field study', and 'design changes due to the consideration of feasibility.' Fourth, 'design changes for consideration of the user' and 'design changes for image improvement' were found in more than half of the frequency of the overall changes. This differed from the results shown in public corporations. Fifth, if planting construction design change process, private companies, it was found that is showing the approval of the practice after the previous construction of the construction cost savings due to construction time. However, in the case of a public corporation, these exhibited a different aspect from the private sector and show a design change procedure that reflects the changes after the design change events in the field have occurred. The above results, the type of landscaping works in planting design change of public enterprises, regardless of the private sector, is the same in the seven types, the main reason of and procedures for design changes, indicating that there are other respects. In design change, it may be desirable to apply becomes liquidity rationality and efficiency of the dimension, depending on the nature of the landscape construction.

• Korea journal of population studies
• /
• v.11 no.1
• /
• pp.50-57
• /
• 1988

This study focused on the anding of Inchon's identity The empirical method and ethnomethodological approaches were used to collect the data. Among members ofcitizen movement groups,government workers,and students who are living inInchon were selected as 613 samples using a purposive sampling method. MultipleClassification Analysis (MCA) and cross-tabulation methods were used in theanalysisThe study of identity in an area is important in terms of providing the solution ofthe problem in a region and social integration of the citizens. The scores of the indexabout Inchon's identity are quite low and more than half of the respondents to allthree groups showed the middle position of the scores from the identity index. By thecharacteristics of the respondents,female,unmarried single,30 years or more,lowerincome groups showed relatively higher identity index scores than other counter-parts . And professional,administrative,clerical workers'identity index scores werehigher than people who work at sales,service,and agricultural sectors. Respondentswith 2 years of college or more,with intentions to donate special monies for cultural, social welfare, environmental reform,persons who want to live in Inchon for along period of time equipped with a stronger identity index.For the character of Inchon's identity,there are no identity,making it fromnow on,capacity or broad-minded city,vanguard pioneer,displeased, Oiversity/multiplicity of the city,defense spirit from foreign invasion,entrancecity from the world in that order. Therefore,it is hard to say what exactly Inchon'simage is in a single word. However,Inchon can be characterized as a diverse citywith capacity to live together without any serious conflicts among citizens who come from Seoul,Kyunggi-Do,Chungchung-Do,Chunla-Do,Kyungsang-Do,and foreign countries including North Korea. These facts imply that Inchon should continue topursue this image as a diverse city with capacity as an identity pursuing towardsworld city and hub city of North East Asia.ty as an identity pursuing towardsworld city and hub city of North East Asia. East Asia.

• Korean Journal of Heritage: History & Science
• /
• v.53 no.4
• /
• pp.198-215
• /
• 2020

Official development assistance refers to assistance provided by governments and other public institutions in donor countries, aimed at promoting economic development and social welfare in developing countries. The purpose of this research is to examine the construction process of the "Myanmar Cultural Heritage Management System" that is underway as part of the ODA project to strengthen cultural and artistic capabilities and analyze the achievements and challenges of the Digital Cultural Heritage ODA. The digital cultural heritage management system is intended to achieve the permanent preservation and sustainable utilization of tangible and intangible cultural heritage materials. Cultural heritage can be stored in digital archives, newly approached using computer analysis technology, and information can be used in multiple dimensions. First, the Digital Cultural Heritage ODA was able to permanently preserve cultural heritage content that urgently needed digitalization by overcoming and documenting the "risk" associated with cultural heritage under threat of being extinguished, damaged, degraded, or distorted in Myanmar. Second, information on Myanmar's cultural heritage can be systematically managed and used in many ways through linkages between materials. Third, cultural maps can be implemented that are based on accurate geographical location information as to where cultural heritage is located or inherited. Various items of cultural heritage were collectively and intensively visualized to maximize utility and convenience for academic, policy, and practical purposes. Fourth, we were able to overcome the one-sided limitations of cultural ODA in relations between donor and recipient countries. Fifth, the capacity building program run by officials in charge of the beneficiary country, which could be the most important form of sustainable development in the cultural ODA, was operated together. Sixth, there is an implication that it is an ODA that can be relatively smooth and non-face-to-face in nature, without requiring the movement of manpower between countries during the current global pandemic. However, the following tasks remain to be solved through active discussion and deliberation in the future. First, the content of the data uploaded to the system should be verified. Second, to preserve digital cultural heritage, it must be protected from various threats. For example, it is necessary to train local experts to prepare for errors caused by computer viruses, stored data, or operating systems. Third, due to the nature of the rapidly changing environment of computer technology, measures should also be discussed to address the problems that tend to follow when new versions and programs are developed after the end of the ODA project, or when developers have not continued to manage their programs. Fourth, since the classification system criteria and decisions regarding whether the data will be disclosed or not are set according to Myanmar's political judgment, it is necessary to let the beneficiary country understand the ultimate purpose of the cultural ODA project.

• Journal of the Korean Orthopaedic Association
• /
• v.56 no.3
• /
• pp.234-244
• /
• 2021

Purpose: To date, studies of firearm and explosive injuries in the Korean military have been limited compared to its importance. To overcome this, this study examined the characteristics of musculoskeletal damages in soldiers who have suffered firearm and explosive injuries over the past four years. Materials and Methods: From January 2015 to July 2019, military forces who had suffered musculoskeletal injuries from firearms or explosive substances were included. The medical records and radiographs were reviewed retrospectively, and telephone surveys about Short Musculoskeletal Functional Assessment (SMFA) for this group were conducted. To compare the functional outcomes, statistical analysis was performed using a t-test for the types of weapons, and ANOVA for others. Results: Of the 61 patients treated for firearms and explosives injuries, 30 patients (49.2%) were included after undergoing orthopedic treatment due to musculoskeletal injury. The average age at injury was 26.4 years old (21-52 years old). The number of officers and soldiers was similar. Eleven were injured by gunshot and 19 by an explosive device. Sixteen were treated in the Armed Forces Capital Hospital and 10 at private hospitals. More than half of the 16 patients (53.3%) with a fracture had multiple fractures. The most common injury site was the hand (33.3%), followed by the lower leg (30.0%). There were 14 patients (46.7%) with Gustilo-Anderson classification 3B or higher who required a soft tissue reconstruction. Fifteen patients agreed to join the SMFA survey for the functional outcomes. Between officers and soldiers, officers had better scores in the Bother Index compared to soldiers (p=0.0045). Patients treated in the Armed Forces Capital Hospital had better scores in both the Dysfunction and Bother Index compared to private hospitals (p=0.0008, p=0.0149). Conclusion: This is the first study to analyze of weapons injuries in the Korean military. As a result of the study, the orthopedic burden was high in the treating patients with military weapon injuries. In addition, it is necessary to build a military trauma registry, including firearm and explosive injuries, for trauma treatment evaluation and development of military trauma system.