• 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.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.11
• /
• pp.20-25
• /
• 2007

In this paper, It was reported the dielectric constant in organic inorganic hybrid silica material such as SiOC film modeling of bond structure by annealing in organic properties. The organic inorganic hybrid silica material were deposited using bis-trimethylsilymethane (BTMSM, [(CH3)3Si]2CH2) and oxygen gas precursor by a plasma chemical vapor deposition (CVD). The organic inorganic hybrid silica material have three types according to the deposition condition. The dielectric constant of the films were performed MIS(Al/Si-O-C film/p-Si) structure. The C 1s spectra in organin inorganic silica materials with the flow rate ratio of O2/BTMSM=1.5 was organometallic carbon with the peak 282.9 eV by XPS. It means that organometallic carbon component is the cross-link bonding structure with good stability. The dielectric constant was the lowest at annealed films with cross-link bonding structure.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.22-29
• /
• 2018

Over the decades, neural networks have been successfully used in numerous applications from speech recognition to image classification. However, these neural networks cannot explain their results and one needs to know how and why a specific conclusion was drawn. Most studies focus on extracting binary rules from neural networks, which is often impractical to do, since data sets used for machine learning applications contain continuous values. To fill the gap, this paper presents an algorithm to extract logic rules from a trained neural network for data with continuous attributes. It uses hyperplane-based linear classifiers to extract rules with numeric values from trained weights between input and hidden layers and then combines these classifiers with binary rules learned from hidden and output layers to form non-linear classification rules. Experiments with different datasets show that the proposed approach can accurately extract logical rules for data with nonlinear continuous attributes.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.554-557
• /
• 2021

NLTKo는 한국어 분석 도구들을 NLTK에 결합하여 사용할 수 있게 만든 도구이다. NLTKo는 전처리 도구, 토크나이저, 형태소 분석기, 세종 의미사전, 분류 및 기계번역 성능 평가 도구를 추가로 제공한다. 이들은 기존의 NLTK 함수와 동일한 방법으로 사용할 수 있도록 구현하였다. 또한 세종 의미사전을 제공하여 한국어 동의어/반의어, 상/하위어 등을 제공한다. NLTKo는 한국어 자연어처리를 위한 교육에 도움이 될 것으로 믿는다.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.165-181
• /
• 2009

This paper presents an effective representation scheme for the shape analysis of the hippocampal structure and a stereoscopic-haptic environment to enhance sense of realism. The parametric model and the 3D skeleton represent various types of hippocampal shapes and they are stored in the Octree data structure. So they can be used for the interactive shape analysis. And the 3D skeleton-based pose normalization allows us to align a position and an orientation of the 3D hippocampal models constructed from multimodal medical imaging data. We also have trained Support Vector Machine (SVM) for classifying between the normal controls and epileptic patients. Results suggest that the presented representation scheme provides various level of shape representation and the SVM can be a useful classifier in analyzing the shape differences between two groups. A stereoscopic-haptic virtual environment combining an auto-stereoscopic display with a force-feedback (or haptic) device takes an advantage of 3D applications for medicine because it improves space and depth perception.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.417-424
• /
• 2010

In this paper the real-time face region was detected by suggesting the rectangular feature-based classifier and the robust detection algorithm that satisfied the efficiency of computation and detection performance was suggested. By using the detected face region as a recognition input image, in this paper the face recognition method combined with PCA and the multi-layer network which is one of the intelligent classification was suggested and its performance was evaluated. As a pre-processing algorithm of input face image, this method computes the eigenface through PCA and expresses the training images with it as a fundamental vector. Each image takes the set of weights for the fundamental vector as a feature vector and it reduces the dimension of image at the same time, and then the face recognition is performed by inputting the multi-layer neural network.

• Proceedings of the KIEE Conference
• /
• 2005.07c
• /
• pp.1868-1869
• /
• 2005

이 논문은 반도전 실리콘 고무 표면에 코로나 방전 처리하여 이종의 실리콘 고무와의 접착 특성을 나타낸 것이다. 반도전 실리콘 고무 표면 상태를 발수성 등급에 따른 분류와 FTIR(Fourier Transform Infrared Spectroscopy)를 사용하여 평가하였다. 표면 상태 변화에 따른 반도전 실리콘 고무의 접착 특성은 T-peel test로 접착강도를 시험하였다. 실험 결과 고에너지의 코로나 방전으로 반도전 실리콘 고무의 결합쇄가 절단되었고 이 부분에 산소가 결합되어 극성 관능기를 생성하여 표면을 산화시켰다. 이러한 표면 상태 변화에 따른 접착강도는 초기 상태일 때 보다 코로나 방전 처리 후 증가하는 것을 확인 할 수 있었다. 이 논문을 통하여 코로나 방전 처리는 이종 계면의 접착 특성을 향상시킬 수 있으며, 이종 계면에서 발생하는 절연 파괴 전압을 높여 전기절연 성능을 향상시키는데 도움이 될 것이다.

• The korean journal of orthodontics
• /
• v.39 no.5
• /
• pp.320-329
• /
• 2009

Objective: The aim of this study was to evaluate the effect of metal primers and thermocycling on shear bond strength between the orthodontic bracket and gold alloy. Methods: For this study, 80 specimens made of dental gold alloy were divided into 8 groups based on the combination of metal primers (none, Alloy primer, Metaltite, V-primer) and thermocycling (with and without thermocycling). Shear bond strength testing was performed with a universal testing machine. Bond failure sites were classified by a modified ARI (Adhesive Remnant Index) score. Results: All metal primer treated groups showed a significantly higher shear bond strength than the only sandblasting treated group without thermocycling (p < 0.05). There were no significant differences on shear bond strength in the groups with thermocycling (p > 0.05). Bond failure sites of the metal primer treated group without thermocycling occurred at gold alloy/adhesive interface, whereas there were no differences on bonding failure sites in the groups with thermocycling. Conclusions: These findings suggest that using metal primer on gold alloy enhances the initial bracket bond strength. But, this effect was not shown with thermocycling.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.777-784
• /
• 2003

In this Paper. we propose a recognition method of machine printed characters based on the combination of recognition units using multiple neural networks. In our recognition method, the input character is classified into one of 7 character types among which the first 6 types are for Hangul character and the last type is for non-Hangul characters. Hangul characters are recognized by several MLP (multilayer perceptron) neural networks through two stages. In the first stage, we divide Hangul character image into two or three recognition units (HRU : Hangul recognition unit) according to the combination fashion of graphemes. Each recognition unit composed of one or two graphemes is recognized by an MLP neural network with an input feature vector of pixel direction angles. In the second stage, the recognition aspect features of the HRU MLP recognizers in the first stage are extracted and forwarded to a subsequent MLP by which final recognition result is obtained. For the recognition of non-Hangul characters, a single MLP is employed. The recognition experiments had been performed on the character image database collected from 50,000 real letter envelope images. The experimental results have demonstrated the superiority of the proposed method.