• 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 the Korea Institute of Building Construction
• /
• v.9 no.4
• /
• pp.119-129
• /
• 2009

Building construction trends have been changed dramatically in terms of size and mass. With the need to maximize land usage, there has been an increase in the construction of high-rise buildings. This affects not only the entire construction duration and cost, but also subsequent construction activities, such as work to increase underground facilities and in reclamation land area construction. These types of site conditions require soft ground reinforcement and the proper uplift water pressure treatment. In general, two kinds of methods have been used for uplift water pressure treatment systems. However, there have been some problems arising as the result of a lack of research and analysis on underground construction techniques, and a reliance on experiments over actual survey and analysis of site conditions. This paper focused on the problems of conventional selection procedure, by analyzing drawings and proposing a kind of modeling for a reasonable procedure. The results were applied to OO project as a sample construction case to be verified in this research. The initial plan in the case project was the Rock Anchor System. However, as there were terrible miscalculations of basic site conditions that had an extraordinary influence on the underground water level, such as the site's proximity to the Han-river, it was necessary to change the plan to include apermanent drainage system. This achieved a direct construction cost reduction \ 406,702,000 and a maximum sayings of 4% of operational cost, based on the 50-year building Life Cycle Cost.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.5 s.21
• /
• pp.183-192
• /
• 2004

Even in Korea the number of steel structure buildings that allow internal space and easy change of their layouts in accordance with the purpose of buildings and box-type steel bridges constructed with thick plates with thickness in a rage just from a few $\beta$AE to \$100\beta$AE is increasing these days and therefore, domestic fabrication and processing technology of members for steel structures is being improved at a pace faster than in the past to meet the growing requirements of consumers for high reliability on quality control on the related steel structures. However, most domestic fabricators os steel structures who are turning out their steel products in accordance with the designs prepared by engineering companies in their respective works for the sake of cost cut more than anything else, hesitating to introduce any advanced new technology into themselves. In the case of the steel structure design application for small and mid-size buildings in particular, it is quite meaningful not only for those who are involved in steel structure business, but also for the people working at construction work fields to review the result of the study on the connections of steel structure members deigned to obtain superb quality of steel structures within short period for steel fabrication and erection at fields in economical ways, as there is a glowing tendency seeking standardization of connection of steel structure members as well as whole structure together with the development on design of construction system of buildings including their exterior and interior decoration materials, manufacture of the related members and fabrication technique structure. This paper has been prepared with the aim to review the peculiar characteristics of buildings constructed with the main frames of steel structures and actual cases of the change made ing the connections between steel structure columns and between columns and girder members in order to reduce the work period necessary for fabrication and erection of steel structures at the maximum as well as the some examples of steel structures fabricated through automatic welding by robots for box-type columns in addition to the description of the problems found in the course of fabricating those steel structures, suggesting possible counter-measures to solve them.

• Journal of the Korean Applied Science and Technology
• /
• v.34 no.4
• /
• pp.962-973
• /
• 2017

Concerns about an air pollution are gradually increasing at home and abroad. The automotive and fuel researchers are trying to reduce emissions and greenhouse gases of vehicles through a research on new engine designs and innovative after-treatment systems using clean fuels (eco-alternative fuel) and fuel quality improvements. In this paper, we stduy the emission characteristics of greenhouse gases on seven vehicles using gasoline, diesel, and LPG by legal test mode in domestic and abroad.(Urban mode, Highway mode, rapidly acceleration and deceleration, using air conditioner, low temperature condition) Regardless of fuels, most of the greenhouse gases tend to show the worst results in cold FTP-75 mode. In the case of A vehicles (2.0 MPI) and B vehicles (2.4 GDI) using a gasoline fuel, the factors that increase greenhouse gases are in order of a rapidly acceleration and deceleration, using air conditioner, low temperature condition. But G vehicles(LPLi) have different emission characteristics from another vehicles. In the case of A vehicles (2.0 w/o DPF) and B vehicles (2.2 with DPF) using a diesel fuel, the factors that increase greenhouse gases are in order of a rapidly acceleration and deceleration, using air conditioner, low temperature condition. However, the factor of F vehicles are in order of low temperature condition, using air conditioner, rapidly acceleration and deceleration. In conclusion, it will be an effective method to apply different technologies of emission reduction for each fuel.

• Journal of the Korean Applied Science and Technology
• /
• v.34 no.4
• /
• pp.874-882
• /
• 2017

As the interest on the air-pollution is gradually rising up at home and abroad, automotiv e and fuel researchers have been working on the exhaust emission reduction from vehicles through a lot of approaches, which consist of new engine design, innovative after-treatment systems, using clean (eco-friendly alternative) fuels and fuel quality improvement. This research has brought forward three main issues : evaporative, performance, air pollution. In addition, researcher studied the environment problems of the bio-ethanol, bio-butanol, bio-ETBE (Ethyl Tertiary Butyl Ether), MTBE (Methyl Tert iary Butyl Ether) fuel contained in the fuel as octane number improver. The researchers have many dat a about the health effects of ingestion of octane number improver. However, the data support the con clusion that octane number improver is a potential human carcinogen at high doses. Based on the bio-fuel and octane number improver types (bio-ethanol, bio-butanol, bio-ETBE, MTBE), this paper dis cussed the influence of gasoline fuel properties on the evaporative emission characteristics. Also, this p aper assessed the acceleration and power performance of gasoline vehicle for the bio-fuel property. As a result of the experiment, it was found that all the test fuels meet the domestic exhaust gas standards, and as a result of measurement of the vapor pressure of the test fuels, the bio - ethanol : 15 kPa and the biobutanol : 1.6 kPa. thus when manufacturing E3 fuel, Increasing the biobutanol content reduces evaporation gas and vapor pressure. In addition, Similar accelerating and powering performance was shown for the type of biofuel and when bio-butanol and bio-ethanol were compared accelerated perf ormance was improved by about 3.9% and vehicle power by 0.8%.

• Journal of Korean Philosophical Society
• /
• no.119
• /
• pp.129-159
• /
• 2017

The study of Freud's Moses and the background of the establishment of monotheism has become a subject of attention in the new atmosphere of the spreading of political theology and the recent rediscovery of Egyptology. This paper examines the publishing background and intentions of Freud's last book, Moses and Monotheism. And it will emphasize the fact that the Moses-Egyptian theory and his criticism of monotheism hid political theological intentions to prevent the spread of anti-Semitism in Nazi Germany. According to the Egyptologist Jan Assmann, there is a difference in that Moses' Judaism is monotheism, but Akhenaten's Aton-religion is a cosmotheism, and while Freud emphasizes Moses the 'historical figure' of that name, Assmann refers to Moses as a 'mnemohistorical figure.' Just as Freud said that the source of Jewish hatred is in Moses himself who established monotheism, Assmann argues also, monotheism is based on the so-called "Mosaic distinction" that distinguishes between true religion and false religion, thus it is possible to dismantle oppression and violence through the abolition of the Mosaic distinction. Assmann estimates that Freud had a clear stance to stop the spread of anti-Semitism as "the most explicit opponent of the Mosaic distinction." While anti-Semitic hatred spread to Christians in the Nazi era, Freud regards the real founder of Christianity, a jew Paul, as both a "Judaism destroyer" and a "successor to Judaism." At this point, Taubes began to see Paul's theology from a political theological point of view, and Assmann succeeded it. The "historical Moses" described by Freud are not "Prophet Moses" but "Moses as lawmaker and political reformer", and Jewish hatred has arisen in his distinction. Thus, Freud's monotheistic criticism as "disintegration by historical reduction"(Nietzsche) has political theological power. Just as Taubes interpreted Paul as a political theologian, Assmann found political theological elements in Freud's criticism of monotheism.

• Journal of Astronomy and Space Sciences
• /
• v.36 no.1
• /
• pp.21-33
• /
• 2019

This paper focuses on the interpretation of radiation fluxes from active galactic nuclei. The advantage of positron annihilation spectroscopy over other methods of spectral diagnostics of active galactic nuclei (therefore AGN) is demonstrated. A relationship between regular and random components in both bolometric and spectral composition of fluxes of quanta and particles generated in AGN is found. We consider their diffuse component separately and also detect radiative feedback after the passage of high-velocity cosmic rays and hard quanta through gas-and-dust aggregates surrounding massive black holes in AGN. The motion of relativistic positrons and electrons in such complex systems produces secondary radiation throughout the whole investigated region of active galactic nuclei in form of cylinder with radius R= 400-1000 pc and height H=200-400 pc, thus causing their visible luminescence across all spectral bands. We obtain radiation and electron energy distribution functions depending on the spatial distribution of the investigated bulk of matter in AGN. Radiation luminescence of the non-central part of AGN is a response to the effects of particles and quanta falling from its center created by atoms, molecules and dust of its diffuse component. The cross-sections for the single-photon annihilation of positrons of different energies with atoms in these active galactic nuclei are determined. For the first time we use the data on the change in chemical composition due to spallation reactions induced by high-energy particles. We establish or define more accurately how the energies of the incident positron, emitted ${\gamma}-quantum$ and recoiling nucleus correlate with the atomic number and weight of the target nucleus. For light elements, we provide detailed tables of all indicated parameters. A new criterion is proposed, based on the use of the ratio of the fluxes of ${\gamma}-quanta$ formed in one- and two-photon annihilation of positrons in a diffuse medium. It is concluded that, as is the case in young supernova remnants, the two-photon annihilation tends to occur in solid-state grains as a result of active loss of kinetic energy of positrons due to ionisation down to thermal energy of free electrons. The single-photon annihilation of positrons manifests itself in the gas component of active galactic nuclei. Such annihilation occurs as interaction between positrons and K-shell electrons; hence, it is suitable for identification of the chemical state of substances comprising the gas component of the investigated media. Specific physical media producing high fluxes of positrons are discussed; it allowed a significant reduction in the number of reaction channels generating positrons. We estimate the brightness distribution in the ${\gamma}-ray$ spectra of the gas-and-dust media through which positron fluxes travel with the energy range similar to that recorded by the Payload for Antimatter Matter Exploration and Light-nuclei Astrophysics (PAMELA) research module. Based on the results of our calculations, we analyse the reasons for such a high power of positrons to penetrate through gas-and-dust aggregates. The energy loss of positrons by ionisation is compared to the production of secondary positrons by high-energy cosmic rays in order to determine the depth of their penetration into gas-and-dust aggregations clustered in active galactic nuclei. The relationship between the energy of ${\gamma}-quanta$ emitted upon the single-photon annihilation and the energy of incident electrons is established. The obtained cross sections for positron interactions with bound electrons of the diffuse component of the non-central, peripheral AGN regions allowed us to obtain new spectroscopic characteristics of the atoms involved in single-photon annihilation.

• Korea Science and Art Forum
• /
• v.37 no.4
• /
• pp.297-308
• /
• 2019

Air pollution due to the fine dust level updating every day, and the problem of indoor air pollution due to ventilation difficulties and indoor discharge pollutants is also serious. In order to improve the indoor air quality, the air purification effect using the plants is prominent. In this study was started to investigated the living environment of modern people, the risk of indoor air pollution and the improvement function of plants, and to activate plant application. The purpose of this study is to analyze the main functions and design status of domestic and overseas plant - related applications, and to understand the actual use of modern plant applications and to help them learn more convenient plant - related knowledge. Therefore, this paper attempted to establish a basis for suggesting a new plant application by conducting a survey on the health effects of indoor air pollution and user awareness of plant - related applications. The results and contents of the study are as follows. First, as a theoretical review, indoor air pollution is more dangerous to modern people who have a high proportion of indoor living time and adversely affects their health. In order to solve such a problem, it has been shown that air conditioning and stress reduction can be effectively achieved by placing plants in the indoor space. Second, the analysis of the previous study shows the risk of indoor air pollution and its adverse effects on health. In addition, I have been able to find some researches related to the improvement of the indoor air by using the air purifying plants, and I can see the improvement of the user's behavior through the development or improvement of the application. Third, as a result of the survey on the status of domestic and overseas plant application, the main function of the application having high installation number was watering notification, provision of basic information of plants, and most of the functions were plant discerment through cameras. Fourth, most of the survey respondents have either raised or raised plants. Those who have little experience with plant applications have also shown positive feedback in the future on the use of plant-related applications. In addition, due to social problems such as air pollution, air purification using plants and functional plants showed high interest. Based on these results, we propose the need for a multi-functional plant application that can improve the indoor air pollution and facilitate the provision of information related to it.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.431-438
• /
• 2020

In this paper, the method to extract lip contour by multiple threshold is proposed. Spyridonos et. el. proposed a method to extract lip contour. First step is get Q image from transform of RGB into YIQ. Second step is to find lip corner points by change point detection and split Q image into upper and lower part by corner points. The candidate lip contour can be obtained by apply threshold to Q image. From the candidate contour, feature variance is calculated and the contour with maximum variance is adopted as final contour. The feature variance 'D' is based on the absolute difference near the contour points. The conventional method has 3 problems. The first one is related to lip corner point. Calculation of variance depends on much skin pixels and therefore the accuracy decreases and have effect on the split for Q image. Second, there is no analysis for color systems except YIQ. YIQ is a good however, other color systems such as HVS, CIELUV, YCrCb would be considered. Final problem is related to selection of optimal contour. In selection process, they used maximum of average feature variance for the pixels near the contour points. The maximum of variance causes reduction of extracted contour compared to ground contours. To solve the first problem, the proposed method excludes some of skin pixels and got 30% performance increase. For the second problem, HSV, CIELUV, YCrCb coordinate systems are tested and found there is no relation between the conventional method and dependency to color systems. For the final problem, maximum of total sum for the feature variance is adopted rather than the maximum of average feature variance and got 46% performance increase. By combine all the solutions, the proposed method gives 2 times in accuracy and stability than conventional method.

• Economic and Environmental Geology
• /
• v.54 no.2
• /
• pp.285-297
• /
• 2021

Globally, nuclear-decommissioning facilities have been increased in number, and thereby hundreds of thousands of wastes, such as concrete, soil, and metal, have been generated. For this reason, there have been numerous efforts and researches on the development of technology for volume reduction and recycling of solid radioactive wastes, and this study reviewed and examined thoroughly such previous studies. The waste concrete powder is rehydrated by other processes such as grinding and sintering, and the processes rendered aluminate (C3A), C4AF, C3S, and ��-C2S, which are the significant compounds controlling the hydration reaction of concrete and the compressive strength of the solidified matrix. The review of the previous studies confirmed that waste concretes could be used as recycling cement, but there remain problems with the decreasing strength of solidified matrix due to mingling with aggregates. There have been further efforts to improve the performance of recycling concrete via mixing with reactive agents using industrial by-products, such as blast furnace slag and fly ash. As a result, the compressive strength of the solidified matrix was proved to be enhanced. On the contrary, there have been few kinds of researches on manufacturing recycled concretes using soil wastes. Illite and zeolite in soil waste show the high adsorption capacity on radioactive nuclides, and they can be recycled as solidification agents. If the soil wastes are recycled as much as possible, the volume of wastes generated from the decommissioning of nuclear power plants (NPPs) is not only significantly reduced, but collateral benefits also are received because radioactive wastes are safely disposed of by solidification agents made from such soil wastes. Thus, it is required to study the production of non-sintered cement using clay minerals in soil wastes. This paper reviewed related domestic and foreign researches to consider the sustainable recycling of concrete waste from NPPs as recycling cement and utilizing clay minerals in soil waste to produce unsintered cement.