• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.31-39
• /
• 2019

A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.63-69
• /
• 2015

There are various researches which proposed an automatic instance generation from freetext on the web. Existing researches that focused on English, adopts pattern representation which is generated by simple rules and regular expression. These simple patterns achieves high performance, but it is not suitable in Korean due to differences of characteristics between Korean and English. Thus, this paper proposes a novel method for generating patterns and instances which focuses on Korean. A proposed method generates high quality patterns by taking advantages of dependency relations in a target sentences. In addition, a proposed method overcome restrictions from high degree of freedom of word order in Korean by utilizing postposition and it identifies a subject and an object more reliably. In experiment results, a proposed method shows higher precision than baseline and it is implies that proposed approache is suitable for self-knowledge learning system.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.5
• /
• pp.1-11
• /
• 2010

The success of semantic web depends largely on the semantic annotation which systematizes knowledge for the construction and production of ontology. Therefore, the efficiency of semantic annotation is very important in order to change many knowledge expressions and generate into ontology instances. In this paper, we presents a generation system of rule-based ontology instances which are produced accurately and efficiently via semantic annotation in conventional web sites. In conventional studies, the manual process is necessary for finding relevant information, comparing it with ontology, and entering information. We propose a new method that manages keyword data regarding extracted information and rule information separately. Thus, it is quite practical to extract information efficiently from various web documents by adding a small number of keywords and rules. The proposed method shows the possibility of ontology instance generation which reuses the rules and keywords from the various websites.

• ETRI Journal
• /
• v.23 no.4
• /
• pp.168-176
• /
• 2001

This paper discusses two important issues of corpus-based synthesis: synthesis unit generation based on phrase break strength information and pruning redundant synthesis unit instances. First, the new sentence set for recording was designed to make an efficient synthesis database, reflecting the characteristics of the Korean language. To obtain prosodic context sensitive units, we graded major prosodic phrases into 5 distinctive levels according to pause length and then discriminated intra-word triphones using the levels. Using the synthesis unit with phrase break strength information, synthetic speech was generated and evaluated subjectively. Second, a new pruning method based on weighted vector quantization (WVQ) was proposed to eliminate redundant synthesis unit instances from the synthesis database. WVQ takes the relative importance of each instance into account when clustering similar instances using vector quantization (VQ) technique. The proposed method was compared with two conventional pruning methods through objective and subjective evaluations of synthetic speech quality: one to simply limit the maximum number of instances, and the other based on normal VQ-based clustering. For the same reduction rate of instance number, the proposed method showed the best performance. The synthetic speech with reduction rate 45% had almost no perceptible degradation as compared to the synthetic speech without instance reduction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1174-1182
• /
• 2017

The research and development on Web of Data to realize the opening and sharing of diverse, heterogonous data on the Web has been actively accomplished. As a standard data model for this effort, LOD (Linked Open Data) based on ontology has been proposed. A specialized instance generation system is vital to the development of LOD-based system effectively. This paper implements i-Manager as an appropriate environment for the development of LOD instances, considering the requirements of LOD systems and the practical development environment of the diverse application domains. i-Manager separates the instance layer from the ontology layer by way of LOD Interface Sheet (LIS) and implements the specialized functions requested in LOD instance development, such as instance edit/store, visualization and SPARQL query processing. This paper proposes a new approach for LOD instance development, and i-Manager can be applied for the practical LOD development environment in the diverse application areas.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6A
• /
• pp.848-854
• /
• 2000

Network management in TMN concerns to the operating system and communication equipments in network, and defines them as objects. GDMO(guidelines for the Definition of Managed Objects) is used to describe those objects. GDMO is not directly used for managing the network, but translated into a language with object-oriented paradigm. And GDMO refers to ASN.1(Abstract Syntax Notation One) for manage objects. This paper presents design and implementation techniques for the translator which automatically translates the specification of ASN.1 and GDMO to the object-oriented language for generating MIB(Managed object Instance Base). This system, unlike the existing source code generator, is designed to generate various object-oriented languages automatically, which are used to generate Managed object Instance Base(MIB). And the system includes various graphic user interface to enhance the development environment of ASn.1 and GDMO

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.14-21
• /
• 2005

Even though mainly statistical methods have been used in anomaly network intrusion detection, to detect various attack types, machine learning based anomaly detection was introduced. Machine learning based anomaly detection started from research applying traditional learning algorithms of artificial intelligence to intrusion detection. However, detection rates of these methods are not satisfactory. Especially, high false positive and repeated alarms about the same attack are problems. The main reason for this is that one packet is used as a basic learning unit. Most attacks consist of more than one packet. In addition, an attack does not lead to a consecutive packet stream. Therefore, with grouping of related packets, a new approach of group-based learning and detection is needed. This type of approach is similar to that of multiple-instance problems in the artificial intelligence community, which cannot clearly classify one instance, but classification of a group is possible. We suggest group generation algorithm grouping related packets, and a learning algorithm based on a unit of such group. To verify the usefulness of the suggested algorithm, 1998 DARPA data was used and the results show that our approach is quite useful.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.1-5
• /
• 2010

정렬 알고리즘에서 사용한 원소 간 비교횟수를 기준으로, 비교횟수가 많게 되는 순열을 최악의 인스턴스(worst-case instance)라 명명하고 이를 찾기 위해 유전 알고리즘(genetic algorithm)을 사용하였다. 잘 알려진 퀵 정렬(quick sort), 머지 정렬(merge sort), 힙 정렬(heap sort), 삽입 정렬(insertion sort), 쉘 정렬(shell sort), 개선된 퀵 정렬(advanced quick sort)에 대해서 실험하였다. 머지 정렬과 삽입 정렬에 대해 탐색한 인스턴스는 최악의 인스턴스에 거의 근접하였다. 퀵 정렬은 크기가 증가함에 따라 최악의 인스턴스 탐색이 어려웠다. 나머지 정렬에 대해서 찾은 인스턴스는 최악의 인스턴스인지 이론적으로 보장할 수 없지만, 임의의 1,000개 순열을 정렬해서 얻은 비교횟수들의 평균치보다는 훨씬 높았다. 본 논문의 최악의 인스턴스를 탐색하는 시도는 알고리즘의 성능 검증을 위한 테스트 데이터를 생성한다는 점에서 의미가 크다.

• 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.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.8 s.179
• /
• pp.1885-1898
• /
• 2000

Welding quality is closely related to the arc state. So, it is very important to estimate the arc state in real time. In the short circuit transfer region of CO2 are welding, the spatter , as it is well known, is mainly generated on an instance of short circuit or on an instance that the are is ignited after short circuit, or on the cases of an instantaneous short circuit. If the short circuit period or the arc time is irregular, the spatter is generated more than it is regular. Thus there is a close relationship of the amount of the spatter generation with the arc stability. In this paper, to develop the index for estimating the arc stability in short circuit transfer range Of CO2 arc welding, the welding current and are voltage waveforms were measured and the spatter generated was captured and measured. The correlation analysis of the measured amount of the spatter with the factors (the components and the standard deviations of the components) was performed, and the factors that have a considerable influence on the spatter generation among all factors were selected. And some cases of models consisted of the factors were presented, and a mathematical index model which can make an estimation the amount of the spatter from these models with multiple regression analysis. Also, it was compared how much the amount of the spatter generated under the selected welding conditions do these index models fit, and the index model to estimate the arc stability which represent the spatter generation most appropriately was developed