• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.1
• /
• pp.13-21
• /
• 2010

The prediction of contract cancellation of customers is essential in insurance companies but it is a difficult problem because the customer database is large and the target or cancelled customers are a small proportion of the database. This paper proposes a new data mining approach to the binary classification by handling a large-scale unbalanced data. Over-sampling, clustering, regularized logistic regression and boosting are also incorporated in the proposed approach. The proposed approach was applied to a real data set in the area of insurance and the results were compared with some other classification techniques.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.21 no.1
• /
• pp.43-57
• /
• 2010

The purposes of this study are to examine how food and culture and Korean foods are reflected in the classification systems and to propose improvements of DDC to classify various subjects related to the materials of food and culture. For the study, six classification systems - DDC(Dewey Decimal Classification), UDC(Universal Decimal Classification), LCC(Library of Congress Classification), KDC(Korean Decimal Classification), NDC (Nippon Decimal Classification), China Library Classification - were analyzed in aspects of eating and drinking customs, eating etiquette, nutrition and diet, food and drink, meal and table service, beverage technology, and food technology. As a result, there were few headings about Korean food in six classification systems and it was necessary for DDC to have new headings for classifying Korean and Asian traditional foods and table services. Due to the literary warrant in classification systems, it is required to publish and disseminate various Korean food recipes and publications to add new headings or notes in future classification systems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.5
• /
• pp.894-902
• /
• 2010

This paper presents a vision-based robust off-road terrain classification method against environmental variation. As a supervised classification algorithm, we applied a neural network classifier using wavelet features extracted from wavelet transform of an image. In order to get over an effect of overall image feature variation, we adopted environment sensors and gathered the training parameters database according to environmental conditions. The robust terrain classification algorithm against environmental variation was implemented by choosing an optimal parameter using environmental information. The proposed algorithm was embedded on a processor board under the VxWorks real-time operating system. The processor board is containing four 1GHz 7448 PowerPC CPUs. In order to implement an optimal software architecture on which a distributed parallel processing is possible, we measured and analyzed the data delivery time between the CPUs. And the performance of the present algorithm was verified, comparing classification results using the real off-road images acquired under various environmental conditions in conformity with applied classifiers and features. Experiments show the robustness of the classification results on any environmental condition.

• Journal of Computing Science and Engineering
• /
• v.9 no.4
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.3
• /
• pp.1-18
• /
• 2017

This study constructed a high-resolution bioclimatic classification map of South Korea which classifies land into homogeneous zones by similar environment properties using advanced statistical techniques compared to existing ecological area classification studies. The climate data provided by WorldClim(1960-1990) were used to generate 27 bioclimatic variables affecting biological habitats, and key environmental variables were derived from Correlation Analysis and Principal Component Analysis. Clustering Analysis was performed using the ISODATA method to construct a 30'(~1km) resolution bioclimatic classification map. South Korea was divided into 21 regions and the results of classification were verified by correlation analysis with the Gross Primary Production(GPP), Actual Vegetation map made by the Ministry of Environment. Each zones' were described and named by its environmental characteristics and major vegetation distribution. This study could provide useful spatial frameworks to support ecosystem research, monitoring and policy decisions.

• Analytical Science and Technology
• /
• v.32 no.6
• /
• pp.233-242
• /
• 2019

Substance identification is the first step of the REACH registration. It is essential in terms of Classification, Labelling and Packaging (CLP) regulation and because even trace amounts of impurities or additives can affect the classification. In this study, a scheme for the screening, quantification, and interpretation of trace amounts of hazardous inorganic substances is proposed to detect the presence of more than 0.1% hazardous inorganic substances that have been affecting the hazard classification. An exemplary list of hazardous inorganic substances was created from the substances of very high concern (SVHCs) in REACH. Among 201 SVHCs, there were 67 inorganic SVHCs containing at least one or ~2-3 heavy metals, such as As, Cd, Co, Cr, Pb, Sb, and Sn, in their molecular formula. The inorganic SVHCs are listed in excel format with a search function for these heavy metals so that the hazardous inorganic substances, including each heavy metal and the calculated ratio of its atomic weight to molecular weight of the hazardous inorganic substance containing it, can be searched. The case study was conducted to confirm the validity of the established scheme with zinc oxide (ZnO). In a substance that is made of ZnO, Pb was screened by XRF analysis and measured to be 0.04% (w/w) by ICP-OES analysis. After referring to the list, the presence of Pb was interpreted just as an impurity, but not as an impurity relevant for the classification. Future studies are needed to expand on this exemplary list of hazardous inorganic substances using proper regulatory data sources.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.124-132
• /
• 2023

In this paper, we present a simple classification model based on statistical features and demonstrate the successful implementation of a brain-computer interface (BCI) based light on/off control system. This research shows study and development of light on/off control system based on BCI technology, which allows the users to control switching a lamp using electroencephalogram (EEG) signals. The logistic regression algorithm is used for classification of the EEG signal to convert it into light on, light off control commands. Training data were collected using 14-channel BCI system which records the brain signals of participants watching a screen with flickering lights and saves the data into .csv file for future analysis. After extracting a number of features from the data and performing classification using logistic regression, we created commands to switch on a physical lamp and tested it in a real environment. Logistic regression allowed us to quite accurately classify the EEG signals based on the user's mental state and we were able to classify the EEG signals with 82.5% accuracy, producing reliable commands for turning on and off the light.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.6
• /
• pp.50-63
• /
• 2000

In this paper, a new EMG pattern classification method based on soft computing techniques is proposed to help the disabled and the elderly handle rehabilitation robotic arm systems. First, it is shown that EMG is more useful than existing input devices such as voice, a laser pointer and a keypad in view of naturality, extensibility, and applicability. Then, a new procedure is proposed to select the minimal feature set. As methods of classifying the pre-defined motions, a fuzzy pattern classification and fuzzy min-max neural networks (FMMNN) are designed using the selected features. As results, the motions are recognized with success rates of 83 percent and 90 Percent using fuzzy pattern classification and FMMNN, respectively.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.31-34
• /
• 1996

The extensive researches have compared the performance of neural networks(NN) with those of various statistical techniques for the classification problem. The empirical results of these comparative studies have indicated that the neural networks often outperform the traditional statistical techniques. Moreover, there are some efforts that try to combine various classification methods, especially multivariate discriminant analysis with neural networks. While these efforts improve the performance, there exists a problem violating robust assumptions of multivariate discriminant analysis that are multivariate normality of the independent variables and equality of variance-covariance matrices in each of the groups. On the contrary, cluster analysis alleviates this assumption like neural networks. We propose a new approach to classification problems by combining the cluster analysis with neural networks. The resulting predictions of the composite model are more accurate than each individual technique.