• 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.

• Economic and Environmental Geology
• /
• v.50 no.2
• /
• pp.171-180
• /
• 2017

This study performed the analysis on the volcanic gases and hot spring waters from the Julong hot spring at Mt. Baekdu during the period from July 2015 to August 2016. Also, we confirmed the errors that $HCO_3{^-}$ concentrations of hot spring waters in the previous study (Lee et al. 2014) and tried to improve the problem. Dissolved $CO_2$ in hot spring waters was analyzed using gas chromatograph in Lee et al. (2014). Improving this, from 2015, we used TOC-IC to analysis dissolved $CO_2$. Also, we analyzed the $Na_2CO_3$ standard solutions of different concentrations using GC, and confirmed the correlation between the analytical concentrations and the real concentrations. However, because the analytical results of Julong hot spring water were in discord with the estimated values based on this correlation, we can't estimate the $HCO_3{^-}$ concentrations of 2014 samples. During the period of study, $CO_2/CH_4$ in volcanic gases are gradually decreased, and this can be interpreted in two different ways. The first interpretation is that the conditions inside the volcanic edifice are changing into more reduction conditions, and carbon in volcanic gases become more favorable to distribute into $CH_4$ or CO than $CO_2$. The second interpretation is that the interaction between volcanic gases and water becomes greater than past, and the concentrations of $CO_2$ which have much higher solubility in water decreased, relatively. In general, the effect of scrubbing of volcanic gas is strengthened during the quiet periods of volcanic activity rather than active periods. Meanwhile, the analysis of hot spring waters was done on the anion of acidic gases species, the major cation, and some trace elements (As, Cd, Re).

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.18 no.4
• /
• pp.304-309
• /
• 2015

To evaluate the degree of contamination caused by oil spill accident in the sea, the in-situ sensors which are based on the scientific method are needed in the real site. The sensors which are based on the fluorescence detection theory can provide the useful data, such as the concentration of oil. However these kinds of sensors commonly are composed of the ultraviolet (UV) light source such as UV mercury lamp, the multiple excitation/emission filters and the optical sensor which is mainly photomultiplier tube (PMT) type. Therefore, the size of the total sensing platform is large not suitable to be handled in the oil spill field and also the total price of it is extremely expensive. To overcome these drawbacks, we designed the fluorimeter for the oil spill detection which has compact size and cost effectiveness. Before the detail design process, we conducted the experiments to measure the excitation and emission spectrum of oils using five different kinds of crude oils and three different kinds of processed oils. And the fluorescence spectrometer were used to analyze the excitation and emission spectrum of oil samples. We have compared the spectrum results and drawn the each common spectrum regions of excitation and emission. In the experiments, we can see that the average gap between maximum excitation and emission peak wavelengths is near 50 nm for the every case. In the experiment which were fixed by the excitation wavelength of 365 nm and 405 nm, we can find out that the intensity of emission was weaker than that of 280 nm and 325 nm. So, if the light sources having the wavelength of 365 nm or 405 nm are used in the design process of fluorimeter, the optical sensor needs to have the sensitivity which can cover the weak light intensity. Through the results which were derived by the experiment, we can define the important factors which can be useful to select the effective wavelengths of light source, photo detector and filters.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.3
• /
• pp.322-331
• /
• 2003

As the complexity of a 3D game is increased by various factors of the game scenario, it has a problem for controlling the interrelation of the game objects. Therefore, a game system has a necessity of the coordination of the responses of the game objects. Also, it is necessary to control the behaviors of animations of the game objects in terms of the game scenario. To produce realistic game simulations, a system has to include a structure for designing the interactions among the game objects. This paper presents a method that designs the dynamic control mechanism for the interaction of the game objects in the game scenario. For the method, we suggest a game agent system as a framework that is based on intelligent agents who can make decisions using specific rules. Game agent systems are used in order to manage environment data, to simulate the game objects, to control interactions among game objects, and to support visual authoring interface that ran define a various interrelations of the game objects. These techniques can process the autonomy level of the game objects and the associated collision avoidance method, etc. Also, it is possible to make the coherent decision-making ability of the game objects about a change of the scene. In this paper, the rule-based behavior control was designed to guide the simulation of the game objects. The rules are pre-defined by the user using visual interface for designing their interaction. The Agent State Decision Network, which is composed of the visual elements, is able to pass the information and infers the current state of the game objects. All of such methods can monitor and check a variation of motion state between game objects in real time. Finally, we present a validation of the control method together with a simple case-study example. In this paper, we design and implement the supervised classification systems for high resolution satellite images. The systems support various interfaces and statistical data of training samples so that we can select the most effective training data. In addition, the efficient extension of new classification algorithms and satellite image formats are applied easily through the modularized systems. The classifiers are considered the characteristics of spectral bands from the selected training data. They provide various supervised classification algorithms which include Parallelepiped, Minimum distance, Mahalanobis distance, Maximum likelihood and Fuzzy theory. We used IKONOS images for the input and verified the systems for the classification of high resolution satellite images.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Korean Journal of Poultry Science
• /
• v.44 no.1
• /
• pp.1-9
• /
• 2017

The objective of the present study was to determine the expression of genes associated with lipopolysaccharide (LPS)-induced stressor in two breeds of chickens: the Korean native chicken (KNC) and the White Leghorn chicken (WLH). Forty chickens per breed, aged 40 weeks, were randomly allotted to the control (CON, administered the saline vehicle) and LPS-injected stress groups. Samples were collected at 0 and 48 h post-LPS injection, and total RNA was extracted from the chicken livers for RNA microarray and quantitative real-time polymerase chain reaction (qRT-PCR) analyses. In response to LPS, 1,044 and 1,193 genes were upregulated, and 1,000 and 1,072 genes were downregulated in the KNC and WLH, respectively, using a ${\geq}2$-fold cutoff change. A functional network analysis revealed that stress-related genes were downregulated in both KNC and WLH after LPS infection. The results obtained from the qRT-PCR analysis of mRNA expression of heat shock 90 (HSP90), 3-hydroxy-3-methylglutaryl-CoA reductase (HMGCR), activating transcription factor 4 (ATF4), sterol regulatory element-binding protein 1 (SREBP1), and X-box binding protein 1 (XBP1) were confirmed by the results of the microarray analysis. There was a significant difference in the expression of stress-associated genes between the control and LPS-injected KNC and WLH groups. The qRT-PCR analysis revealed that the stress-related $HSP90{\alpha}$ and HMGCR genes were downregulated in both LPS-injected KNC and WLH groups. However, the HSP70 and $HSP90{\beta}$ genes were upregulated only in the LPS-injected KNC group. The results suggest that the mRNA expression of stress-related genes is differentially affected by LPS stimulation, and some of the responses varied with the chicken breed. A better understanding of the LPS-induced infective stressors in chicken using the qRT-PCR and RNA microarray analyses may contribute to improving animal welfare and husbandry practices.

• Natural Product Sciences
• /
• v.8 no.1
• /
• pp.1-15
• /
• 2002

An International Cooperative Biodiversity Group (ICBG) program based at the University of Illinois at Chicago initiated its activities in 1998, with the following specific objectives: (a) inventory and conservation of of plants of Cuc Phuong National Park in Vietnam and of medicinal plants of Laos; (b) drug discovery (and development) based on plants of Vietnam and Laos; and (c) economic development of communities participating in the ICBG project both in Vietnam and Laos. Member-institutions and an industrial partner of this ICBG are bound by a Memorandum of Agreement that recognizes property and intellectual property rights, prior informed consent for access to genetic resources and to indigenous knowledge, the sharing of benefits that may arise from the drug discovery effort, and the provision of short-term and long-term benefits to host country institutions and communities. The drug discovery effort is targeted to the search for agents for therapies against malaria (antimalarial assay of plant extracts, using Plasmodium falciparum clones), AIDS (anti-HIV-l activity using HOG.R5 reporter cell line (through transactivation of the green fluorescent protein/GFP gene), cancer (screening of plant extracts in 6 human tumor cell lines - KB, Col-2, LU-l, LNCaP, HUVEC, hTert-RPEl), tuberculosis (screening of extracts in the microplate Alamar Blue assay against Mycobacterium tuberculosis $H_{37}Ra\;and\;H_{37}Rv),$ all performed at UIC, and CNS-related diseases (with special focus on Alzheimer's disease, pain and rheumatoid arthritis, and asthma), peformed at Glaxo Smith Kline (UK). Source plants were selected based on two approaches: biodiversity-based (plants of Cuc Phuong National Park) and ethnobotany-based (medicinal plants of Cuc Phuong National Park in Vietnam and medicinal plants of Laos). At mc, as of July, 2001, active leads had been identified in the anti-HIV, anticancer, antimalarial, and anti- TB assay, after the screening of more than 800 extracts. At least 25 biologically active compounds have been isolated, 13 of which are new with anti-HIV activity, and 3 also new with antimalarial activity. At GSK of 21 plant samples with a history of use to treat CNS-related diseases tested to date, a number showed activity against one or more of the CNS assay targets used, but no new compounds have been isolated. The results of the drug discovery effort to date indicate that tropical plant diversity of Vietnam and Laos unquestionably harbors biologically active chemical entities, which, through further research, may eventually yield candidates for drug development. Although the substantial monetary benefit of the drug discovery process (royalties) is a long way off, the UIC ICBG program provides direct and real-term benefits to host country institutions and communities.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.41 no.6
• /
• pp.875-880
• /
• 2012

This study was conducted to investigate the level of contamination of pathogenic Escherichia (E.) coli in 50 types of red pepper powders collected domestically. Pathogenic E. coli was confirmed using real-time PCR to confirm the 4 types of EAEC, EPEC, EHEC and ETEC. One sample out of 50 was contaminated with pathogenic E. coli. The type of pathogenic E. coli detected in the sample was EAEC. This study was also conducted to determine the effect of alcohol treatment on the reduction of E. coli populations in red pepper powder. The amount of E. coli in the control was $1.2{\times}10^6$ cfu/mL. The amount of E. coli in 10 minutes immersion treatment with 10% alcohol was $1.1{\times}10^6$ cfu/mL. In samples treated with over 20% alcohol, E. coli was not detected. This showed that 10 minutes of immersion in over 20% alcohol might be effective to reduce E. coli. This study was also conducted to determine the effect of UV irradiation on E. coli reduction. The number of E. coli in the control group was $5.0{\times}10^5$ cfu/mL. However, the number of E. coli in 45 min of the UV irradiated sample decreased to $1.0{\times}10^3$ cfu/mL, by $10^2$ cfu/mL. In contrast, E. coli was not detected in an over 60 min UV irradiated sample in $10^{-2}dilution$. This study showed that over 20% alcohol treatment and UV irradiation for 60 min was effective to control E. coli in red pepper powder.

• Analytical Science and Technology
• /
• v.25 no.4
• /
• pp.257-264
• /
• 2012

Penicillins belong to the ${\beta}$-lactam class of antibiotics, and are frequently used in human and veterinary medicine. Despite the positive effects of these drugs, improper use of penicillins poses a potential health risk to consumers. This study has been undertaken to determinate multi-residues of penicillins, including amoxicillin, ampicillin, oxacillin, bezylpenicillin, cloxacillin, dicloxacillin, and nafcillin, using liquid chromatographic tandem mass spectrometer (LC-MS/MS). The developed method was validated for specificity, precision, recovery, and linearity in livestock and marine products. The analytes were extracted with 80% acetonitrile and clean-up by a single reversed-phase solid-phase extraction step. Six penicillins presented recoveries higher than 76% with the exception of Amoxicillin. Relative standard deviations (RSDs) were not more than 10%. The method was applied to 225 real samples. Benzylpenicillin was detected in 12 livestock products and 7 marine products. Amoxicillin, ampicillin, cloxacilllin, dicloxacillin, nafcillin and oxacillin were not detected. The detected levels were 0.001~0.009 mg/kg in livestock products excluding eggs and milk. In marine products, the detected levels were under 0.03 mg/kg. They were under the MRL levels. As monitoring results, it is identified to be safe but it is considered that safety management of antibiotics should continue by monitoring.

• Journal of Soil and Groundwater Environment
• /
• v.7 no.4
• /
• pp.77-86
• /
• 2002

Surfactant enhanced in-situ soil flushing was performed to remediate the soil and groundwater at an oil contaminated site, where had been used as a military vehicle repair area for 40 years. A section from the contaminated site (4.5 m $\times$ 4.5 m $\times$ 6.0 m) was selected for the research, which was composed of heterogeneous sandy and silt-sandy soils with average $K_d$ of 2.0$\times$$10^{-4}$cm/sec. Two percent of sorbitan monooleate (POE 20) and 0.07% of iso-prophyl alcohol were mixed for the surfactant solution and 3 pore volumes of surfactant solution were injected to remove oil from the contaminated section. Four injection wells and two extraction wells were built in the section to flush surfactant solution. Water samples taken from extraction wells and the storage tank were analyzed on a gas-chromatography (GC) for TPH concentration in the effluent with different time. Five pore volumes of solution were extracted while TPH concentration in soil and groundwater at the section were below the Waste Water Discharge Limit (WWDL). The effluent TPH concentration from wells with only water flushing was below 10 ppm. However, the effluent concentration using surfactant solution flushing increased to 1751 ppm, which was more than 170 times compared with the concentration with only water flushing. Total 18.5 kg of oil (TPH) was removed from the soil and groundwater at the section. The concentration of heavy metals in the effluent solution also increased with the increase of TPH concentration, suggesting that the surfactant enhanced in-situ flushing be available to remove not only oil but heavy metals from contaminated sites. The removal efficiency of surfactant enhanced in-situ flushing was investigated at the real contaminated site in Korea. Results suggest that in-situ soil flushing could be a successful process to remediate contaminated sites distributed in Korea.