• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.52-57
• /
• 2006

One of the important functions of an Intelligent Transportation System (ITS) is to classify vehicle types using a vision system. We propose a method using machine-learning algorithms for this classification problem with 3-D object model fitting. It is also necessary to detect road lanes from a fixed traffic surveillance camera in preparation for model fitting. We apply a background mask and line analysis algorithm based on statistical measures to Hough Transform (HT) in order to remove noise and false positive road lanes. The results show that this method is quite efficient in terms of quality.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.383-387
• /
• 2007

The improved accuracy of the Land Cover/Land Use Map constructed using Hyperspectal Satellite Image and the possibility of real time classification of Land Use using optimal Band Selective Factor enable the change detection from automatic classification using the existed Land Cover/Land Use Map and the newly acquired Hyperspectral Satellite Image. In this study, the effective analysis techniques for automatic generation of training regions, automatic classification and automatic change detection are proposed to minimize the expert's interpretation for automatic update of the Land Cover/Land Use Map. The proposed algorithms performed successfully the automatic Land Cover/Land Use Map construction, automatic change detection and automatic update on the image which contained the changed region. It would increase applicability in actual services. Also, it would be expected to present the effective methods of constructing national land monitoring system.

• Journal of Korean Institute of Industrial Engineers
• /
• v.38 no.3
• /
• pp.191-197
• /
• 2012

One-class classification (OCC) is one of the recent growing areas in data mining and pattern recognition. In the present study we examine a k-nearest neighbors data description (kNNDD) algorithm, one of the OCC algorithms widely used. In particular, we propose to use nonparametric estimation methods to determine the threshold of the kNNDD algorithm. A simulation study has been conducted to explore the characteristics of the proposed approach and compare it with the existing approach that determines the threshold. The results demonstrate the usefulness and flexibility of the proposed approach.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.283-285
• /
• 2005

To account for the importance of variable in multi-sensor data fusion, random forests are applied to supervised land-cover classification. The random forests approach is a non-parametric ensemble classifier based on CART-like trees. Its distinguished feature is that the importance of variable can be estimated by randomly permuting the variable of interest in all the out-of-bag samples for each classifier. Supervised classification with a multi-sensor remote sensing data set including optical and polarimetric SAR data was carried out to illustrate the applicability of random forests. From the experimental result, the random forests approach could extract important variables or bands for land-cover discrimination and showed good performance, as compared with other non-parametric data fusion algorithms.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.35-51
• /
• 2002

Inductive learning and classification techniques have been employed in various research and applications that organize textual data to solve the problem of information access. In this study, we develop hybrid model combination methods which incorporate the concepts and techniques for multiple modeling algorithms to improve the accuracy of text classification, and conduct experiments to evaluate the performances of proposed schemes. Boosted stacking, one of the extended stacking schemes proposed in this study yields higher accuracy relative to the conventional model combination methods and single classifiers.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.742-751
• /
• 2005

This paper proposes a novel text image watermarking algorithm based on word classification. The words are classified into K classes using simple features. Several adjacent words are grouped into a segment. and the segments are also classified using the word class information. The same amount of information is inserted into each of the segment classes. The signal is encoded by modifying some inter-word spaces statistics of segment classes. Subjective comparisons with conventional word-shift algorithms are presented under several criteria.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.601-604
• /
• 2000

In this paper, we compare the classification performance of both data fusion and clustering algorithms (Data Bagging, Variable Selection Bagging, Parameter Combining, Clustering) to logistic regression in consideration of various characteristics of input data. Four factors used to simulate the logistic model are (1) correlation among input variables (2) variance of observation (3) training data size and (4) input-output function. Since the relationship between input & output is not typically known, we use Taguchi design to improve the practicality of our study results by letting it as a noise factor. Experimental study results indicate the following: Clustering based logistic regression turns out to provide the highest classification accuracy when input variables are weakly correlated and the variance of data is high. When there is high correlation among input variables, variable bagging performs better than logistic regression. When there is strong correlation among input variables and high variance between observations, bagging appears to be marginally better than logistic regression but was not significant.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.633-640
• /
• 2001

In this paper we examine the machine learning issues raised by the domain of the Intrusion Detection Systems(IDS), which have difficulty successfully classifying intruders. There systems also require a significant amount of computational overhead making it difficult to create robust real-time IDS. Machine learning techniques can reduce the human effort required to build these systems and can improve their performance. Genetic algorithms are used to improve the performance of search problems, while data mining has been used for data analysis. Data Mining is the exploration and analysis of large quantities of data to discover meaningful patterns and rules. Among the tasks for data mining, we concentrate the classification task. Since classification is the basic element of human way of thinking, it is a well-studied problem in a wide variety of application. In this paper, we propose a classifier system based on genetic algorithm, and the proposed system is evaluated by applying it to IDS problem related to classification task in data mining. We report our experiments in using these method on KDD audit data.

• Asia pacific journal of information systems
• /
• v.21 no.2
• /
• pp.43-58
• /
• 2011

Support vector machines (SVMs), a machine learning technique, has been applied to not only binary classification problems such as bankruptcy prediction but also multi-class problems such as corporate credit ratings. However, in general, the performance of SVMs can be easily worse than the best alternative model to SVMs according to the selection of predictors, even though SVMs has the distinguishing feature of successfully classifying and predicting in a lot of dichotomous or multi-class problems. For overcoming the weakness of SVMs, this study has proposed an approach for selecting features for multi-class SVMs that utilize the impurity measures of classification trees. For the selection of the input features, we employed the C4.5 and CART algorithms, including the stepwise method of discriminant analysis, which is a well-known method for selecting features. We have built a multi-class SVMs model for credit rating using the above method and presented experimental results with data regarding S&P 500 companies.