• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.66-74
• /
• 2008

Criticality prediction models to identify most fault-prone modules in the system early in the software development process help in allocation of resources and foster software quality improvement. Many models for identifying fault-prone modules using design complexity metrics have been suggested, but most of them are training models that need training data set. Most organizations cannot use these models because very few organizations have their own training data. This paper builds a prediction model based on a well-known supervised learning model, error backpropagation neural net, using design metrics quantifying SDL system specifications. To solve the problem of other models, this model is trained by generated virtual training data set. Some simulation studies have been performed to investigate feasibility of this model, and the results show that suggested model can be an alternative for the organizations without real training data to predict their software qualities.

• Journal of Korea Multimedia Society
• /
• v.20 no.12
• /
• pp.1960-1969
• /
• 2017

There have been ongoing researches to identify and analyze the patterns of electric power IoT data inside sensor nodes to supplement the stable supply of power and the efficiency of energy consumption. This study set out to propose an analysis process for electric power IoT data with the K-means algorithm, which is an unsupervised learning technique rather than a supervised one. There are a couple of problems with the old K-means algorithm, and one of them is the selection of cluster number K in a heuristic or random method. That approach is proper for the age of standardized data. The investigator proposed an analysis process of selecting an automated cluster number K through principal component analysis and the space division of normal distribution and incorporated it into electric power IoT data. The performance evaluation results show that it recorded a higher level of performance than the old algorithm in the cluster classification and analysis of pitches and rolls included in the communication bodies of utility poles.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.435-439
• /
• 2007

Document categorization system is important in the internet age in which huge number of documents are created and need to be dealt with. By this reason a lot of research has been done in this field. For the development of the system, a supervised learning method is widely used. This approach needs a test collection as a prerequisite. For the case of English, several test collections are available which provide a lot of help for developing systems and doing research. But no public test collections have been reported and are not available in the case of Korean. To improve the situation for Korean we are undergoing the construction of a Korean test collection. In this paper the approaches being used and current stage of the collection will be described.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.30-39
• /
• 2007

This paper is concerned with development of system to detect an obstructive vehicle which is an essential prerequisite for autonomous driving system of ASV(Advanced Safety Vehicle). First, the boundary of driving lanes is detected by a Kalman filter through the front image obtained by a CCD camera. Then, lanes are recognized by regression analysis of the detected boundary. Second, parameters of road curvature within the detected lane are used as input in error-BP algorithm to recognize the driving direction. Finally, an obstructive vehicle that enters into the detection region can be detected through setting detection fields of the front and lateral side. The experimental results showed that the proposed system has high accuracy more than 90% in the recognition rate of driving direction and the detection rate of an obstructive vehicle.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.10
• /
• pp.105-112
• /
• 2010

In this paper, the bio-signals, such as EEG, ECG were measured with a sensor and their characters were drawn out and analyzed. With results from the analysis, four emotion of rest, concentration, tension and depression were inferred. In order to assess one's emotion, the characteristic vectors were drawn out by applying various ways, including the frequency analysis of the bio-signals like the measured EEG and HRV. RBFN, a neural network of the complex structure of unsupervised and supervised learning, was applied to classify and infer the deducted information. Through experiments, the system suggested in this thesis showed better capability to classify and infer than other systems using a different neural network. As follow-up research tasks, the recognizance rate of the measured bio-signals should be improved. Also, the technology which can be applied to the wired or wireless sensor measuring the bio-signals more easily and to wearable computing should be developed.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.7
• /
• pp.1-8
• /
• 2014

Clustering is one of the most popular unsupervised learning methods, which is widely used to form clusters with homogeneous data. Clustering was used to extract contexts corresponding to clusters and a classification method was applied to each context or cluster individually. However, it is difficult to say that the unsupervised clustering is the best context forming method from the view of classification. In this paper, a new clustering method considering classification was proposed. The proposed method tries to minimize classification error in each cluster when a classification method is applied to each context locally. For this purpose, the proposed method adds constraints forcing two data points belong to the same class to have small distances, and two data points belong to different classes to have large distances in each cluster like in linear discriminant analysis. The usefulness of the proposed method is confirmed by experimental results.

• Journal of Korea Game Society
• /
• v.9 no.1
• /
• pp.105-114
• /
• 2009

In the game of Go, the life-and-death problem is a fundamental problem to be definitely overcome when implementing a computer Go program. To solve local Go problems such as life-and-death problems, an important consideration is how to tackle the game tree's huge branching factor and its depth. The basic idea of the experiment conducted in this article is that we modelled the human behavior to get the recognized first moves to kill the surrounded group. In the game of Go, similar life-and-death problems(patterns) often have similar solutions. To categorize similar patterns, we implemented Kohonen Neural Network(KNN) based clustering and found that the experimental result is promising and thus can compete with a pattern matching method, that uses supervised learning with a neural network, for solving life-and-death problems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.379-387
• /
• 2001

We proposed an enhanced extraction method of vehicle plate, in which both the brightness variation of gray and the Hue value of HSI color model were used. For the extraction of the vehicle plate from a vehicle image, first of all, candidate regions for the vehicle plate were extracted from the image by using the property of brightness variation of the image. A real place region was determined among candidate regions by the density of pixels with the Hue value of green and white. For- extracting the feature area containing characters from the extracted vehicle plate, we used the histogram-based approach of individual characters. And we proposed and applied for the recognition of characters the enhanced ART2 algorithm which support the dynamical establishment of the vigilance threshold with the genera]iced union operator of Yager. In addition, we propose an enhanced SOSL algorithm which is integrated both enhanced ART2 and supervised learning methods. The performance evaluation was performed using 100's real vehicle images and the evaluation results demonstrated that the extraction rates of tole proposed extraction method were improved, compared with that of previous methods based un brightness variation, RGB and HSI individually . Furthermore, the recognition rates of the proposed algorithms were improved much more than that of the conventional ART2 and BP algorithms.

• The KIPS Transactions:PartC
• /
• v.11C no.5
• /
• pp.595-604
• /
• 2004

By the help of expansion of computer network and rapid growth of Internet, the information infrastructure is now able to provide a wide range of services. Especially open architecture - the inherent nature of Internet - has not only got in the way of offering QoS service, managing networks, but also made the users vulnerable to both the threat of backing and the issue of information leak. Thus, people recognized the importance of both taking active, prompt and real-time action against intrusion threat, and at the same time, analyzing the similar patterns of in-trusion already known. There are now many researches underway on Intrusion Detection System(IDS). The paper carries research on the in-trusion detection system which hired supervised learning algorithm and Fuzzy membership function especially with Neuro-Fuzzy model in order to improve its performance. It modifies tansigmoid transfer function of Neural Networks into fuzzy membership function, so that it can reduce the uncertainty of anomaly intrusion detection. Finally, the fuzzy logic suggested here has been applied to a network-based anomaly intrusion detection system, tested against intrusion data offered by DARPA 2000 Intrusion Data Sets, and proven that it overcomes the shortcomings that Anomaly Intrusion Detection usually has.