• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.441-447
• /
• 2001

In general, Rough Set theory is used for classification, inference, and decision analysis of incomplete data by using approximation space concepts in information system. Information system can include quantitative attribute values which have interval characteristics, or incomplete data such as multiple or unknown(missing) data. These incomplete data cause tole inconsistency in information system and decrease the classification ability in system using Rough Sets. In this paper, we present various types of incomplete data which may occur in information system and propose INcomplete information Processing System(INiPS) which converts incomplete information system into complete information system in using Rough Sets.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.281-285
• /
• 2005

Learning and evolving are two basics for data mining. As compared with classical learning theory based on objective function with minimizing training errors, the recently evolutionary computing has had an efficient approach for constructing optimal model without the minimizing training errors. The global search of evolutionary computing in solution space can settle the local optima problems of learning models. In this research, combining co-evolving algorithm into statistical learning theory, we propose an co-evolutionary computing for statistical learning theory for overcoming local optima problems of statistical learning theory. We apply proposed model to classification and prediction problems of the learning. In the experimental results, we verify the improved performance of our model using the data sets from UCI machine learning repository and KDD Cup 2000.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.88-95
• /
• 2017

As the safety fields are expanding to a variety of industrial fields, safety technology has been developed by convergence between industrial safety fields such as mechanics, ergonomics, electronics, chemistry, construction, and information science. As the technology convergence is facilitating recently advanced safety technology, it is important to explore the trends of safety technology for understanding which industrial technologies have been integrated thus far. For studying the trends of technology, the patent is considered one of the useful sources that has provided the ample information of new technology. The patent has been also used to identify the patterns of technology convergence through various quantitative methods. In this respect, this study aims to identify the convergence patterns and fields of safety technology using association rule mining(ARM)-based patent co-classification(co-class) analysis. The patent co-class data is especially useful for constructing convergence network between technological fields. Through linkages between technological fields, the core and hub classes of convergence network are explored to provide insight into the fields of safety technology. As the representative method for analyzing patent co-class network, the ARM is used to find the likelihood of co-occurrence of patent classes and the ARM network is presented to visualize the convergence network of safety technology. As a result, we find three major convergence fields of safety technology: working safety, medical safety, and vehicle safety.

• Journal of Fisheries and Marine Sciences Education
• /
• v.29 no.3
• /
• pp.689-701
• /
• 2017

In recent offshore industries, various ambiguous terms have been used without clear definition or classification, causing difficulties in legal, technical, and educational understanding and usage. For an example, the commonly used term of 'Offshore Plant' in Korea is not an universal word technically. There has been no clear technical or legal definition about the 'Offshore Plant' and its classification is also very ambiguous; sometimes it is used to refer offshore oil and gas production platform or it is used to mean offshore renewable power generation plant in some cases. To build a conceptual framework, therefore, this paper suggests a classification of offshore units (1) using internationally agreed terms, (2) agreed with the technical classification used by the ship classification society and (3) being able to include not only the current but also future concepts of offshore units.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.10
• /
• pp.121-128
• /
• 2017

In this paper, we propose a multi-label classification method in which multi-label classification estimation techniques are applied to resolving location prediction problem. Most of previous studies related to location prediction have focused on the use of single-label classification by using contextual information such as user's movement paths, demographic information, etc. However, in this paper, we focused on the case where users are free to visit multiple locations, forcing decision-makers to use multi-labeled dataset. By using 2373 contextual dataset which was compiled from college students, we have obtained the best results with classifiers such as bagging, random subspace, and decision tree with the multi-label classification estimation methods like binary relevance(BR), binary pairwise classification (PW).

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.575-588
• /
• 2012

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.870-878
• /
• 2013

In this paper, we propose a novel fingerprint classification method to enhance the accuracy and efficiency of the fingerprint identification system, one of biometrics systems. According to the previous researches, fingerprints can be categorized into the several patterns based on their pattern of ridges and valleys. After construction of fingerprint database based on their patters, fingerprint classification approach can help to accelerate the fingerprint recognition. The reason is that classification methods reduce the size of the search space to the fingerprints of the same category before matching. First, we suggest a method to extract region of interest (ROI) which have real information about fingerprint from the image. And then we propose a feature extraction method which combines gray level co-occurrence matrix (GLCM) and wavelet features. Finally, we compare the performance of our proposed method with the existing method which use only GLCM as the feature of fingerprint by using the multi-layer perceptron and support vector machine.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.43-52
• /
• 2014

In this paper, we propose the target detection method using image displacement, and classification method using SURF(Speeded Up Robust Features) feature points and BAS(Beam Angle Statistics) in infrared images. The SURF method that is a typical correspondence matching method in the area of image processing has been widely used, because it is significantly faster than the SIFT(Scale Invariant Feature Transform) method, and produces a similar performance. In addition, in most SURF based object recognition method, it consists of feature point extraction and matching process. In proposed method, it detects the target area using the displacement, and target classification is performed by using the geometry of SURF feature points. The proposed method was applied to the unmanned target detection/recognition system. The experimental results in virtual images and real images, we have approximately 73~85% of the classification performance.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.433-442
• /
• 2018

The reservoir area is defined as the area surrounded by the planned flood level of the dam or the land under the planned flood level of the dam. In this study, supervised classification based on RF (Random Forest), which is a representative machine learning technique, was performed to detect cropland in the reservoir area. In order to classify the cropland in the reservoir area efficiently, the GLCM (Gray Level Co-occurrence Matrix), which is a representative technique to quantify texture information, NDWI (Normalized Difference Water Index) and NDVI (Normalized Difference Vegetation Index) were utilized as additional features during classification process. In particular, we analyzed the effect of texture information according to window size for generating GLCM, and suggested a methodology for detecting croplands in the reservoir area. In the experimental result, the classification result showed that cropland in the reservoir area could be detected by the multispectral, NDVI, NDWI and GLCM images of UAV, efficiently. Especially, the window size of GLCM was an important parameter to increase the classification accuracy.