• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.8
• /
• pp.5565-5570
• /
• 2015

Implicit citation sentence recognition is to locate citation sentences which lacks explicit citation markers, from articles' full-text. State-of-the-art approaches exploit word ngrams, clue words, researcher's surnames, mentions of previous methods, and distance relative to nearest explicit citation sentences, etc., reaching over 50% performance. However, most previous works have been conducted on English. As for Korean, a rule-based method using positive/negative clue patterns was reported to attain the performance of 42%, requiring further improvement. This study attempted to learn to recognize implicit citation sentences from Korean literatures' full-text using Korean lexical features. Different lexical feature units such as Eojeol, morpheme, and Eumjeol were evaluated to determine proper lexical features for Korean implicit citation sentence recognition. In addition, lexical features were combined with the position features representing backward/forward proximities to explicit citation sentences, improving the performance up to over 50%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.1
• /
• pp.147-156
• /
• 2011

With the increasing utility of the recent information system, the methods to pick up necessary products rapidly by using a lot of data has been studied. Association rule search methods to find hidden patterns has been drawing much attention, and the Apriori algorithm is a major method. However, the Apriori algorithm increases search time due to its repeated scans. This paper proposes an algorithm to reduce searching time of frequent items. The proposed algorithm creates matrix using transaction database and search for frequent items using the mean number of items of transactions at matrix and a defined minimum support. The mean number of items of transactions is used to reduce the number of transactions, and the minimum support to cut down on items. The performance of the proposed algorithm is assessed by the comparison of search time and precision with existing algorithms. The findings from this study indicated that the proposed algorithm has been searched more quickly and efficiently when extracting final frequent items, compared to existing Apriori and Matrix algorithm.

• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.1-9
• /
• 2015

Emotion recognition and regular controls are concentrated interest in computer studies to emotional changes. Thus, the quantified by objective assessment methods are essential for application of color sensibility computing situations. In this paper, it is applied to a digital color image emotion emotional computing calculations numbered recognized as one representation. Emotional computing research approach consists of a color attribute to the image recognition focused sensibility and emotional attributes of color is the color, brightness and saturation separated by. Computes the sensitivity weighted according to the score and the percentage increase or decrease in the sensitivity property tone applied to emotional expression. Sensitivity calculation is free-degree (X), and calculates the tension (Y-axis). And free-level (X-axis) coordinate of emotion, which is located the intersection of the tension (Y-axis) as a sensitivity point. The emotional effect of the Russell coordinates are utilizing the core (Core Affect). Tue numbers represent the size and sensitivity in the emotional relationship between emotional point location and quantified by computing the color sensibility.

• Convergence Security Journal
• /
• v.17 no.1
• /
• pp.31-38
• /
• 2017

As the cyber-attacks through the networks advance, it is difficult for the intrusion detection system based on the simple rules to detect the novel type of attacks such as Advanced Persistent Threat(APT) attack. At present, many types of research have been focused on the application of machine learning techniques to the intrusion detection system in order to detect previously unknown attacks. In the case of using the machine learning techniques, the performance of the intrusion detection system largely depends on the feature set which is used as an input to the system. Generally, more features increase the accuracy of the intrusion detection system whereas they cause a problem when fast responses are required owing to their large elapsed time. In this paper, we present a network intrusion detection system based on artificial neural network, which adopts a multi-objective genetic algorithm to satisfy the both requirements: accuracy, and fast response. The comparison between the proposing approach and previously proposed other approaches is conducted against NSL_KDD data set for the evaluation of the performance of the proposing approach.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.363-370
• /
• 2016

The purpose of this study was to investigate the effects of 12-week circuit weight training on their body composition and physical fitness in middle aged women. A total of 34 subjects of did not have any physical abnormalities or diseases, and the subjects were 12-week circuit weight training. The results of this study were as following : Body composition component examination showed that the body weight, body fat percentage and waist measurement showed differences that were statistically significant. And the physical fitness component examination showed that muscular endurance, flexibility, agility, and cardiovascular endurance showed differences that were statistically significant. But muscular strength and reflexes showed differences that were not statistically significant. These results suggest that the circuit weight-training had an effect on body composition and physical fitness examination results over 12-week. Therefore, we consider that the circuit weight training is recommended to middle-age women to improve body fat percentage and physical strength.

• Journal of Digital Contents Society
• /
• v.5 no.3
• /
• pp.239-244
• /
• 2004

New developments in IT already impact wide segments of a young and mobile population. It is evident that applications of information technology can be of equal benefit to the aged and the disabled. `Eye-Gaze'(EGI) technology was designed for people with paralysis in the upper body. There is a compeling need for a dedicated Korean Language interface for this system. The purpose of this study is to research 'Barrier Free' software using a control group of the mobility impaired to assess the Eye-Gaze Interface in the context of more conventional input methods. TheEGI of this study uses Quick Glance System of Eye Tech Digital Systems. The study will be evaluated on criteria based upon the needs of those with specific disabilities and mobility problems associated with aging. We also intend to explore applications of the Eye-Gaze Interface for English and Japanese devises, based upon our study using the Hangul phonology.

• Journal of the Society of Naval Architects of Korea
• /
• v.52 no.3
• /
• pp.222-235
• /
• 2015

The purpose of this study is to suggest guidelines for riser fatigue analysis in terms of selection of reasonable analysis method. Three analysis methods (spectral, regular wave, rain-flow counting) are introduced and compared. As the riser systems give non-linear response, the time-domain analysis method is more preferred than frequency-domain analysis method. The spectral fatigue analysis method, however, is still useful for identifying fatigue prone areas. Once stress RAO is established, fatigue damage can be calculated very quickly. The regular wave method and the rain-flow counting method are more time consuming but give more exact results compare to spectral method. In case of regular wave method, a set of regular waves which represent random sea states is considered for dynamic analysis. The rain-flow counting method is the most intuitive and exact method because it refers time history stresses containing most of non-linear effects of the riser system. However, it is not common for early design stage to use rain-flow counting method because of its high cost. In this study, it was confirmed that the regular wave method is the most cost effective way in specific cases. However, if the system is highly non-linear, it seems that the regular wave method gives less accurate results than rain-flow counting method. Therefore, it is imperative that the engineers select appropriate analysis method based on design stage and given engineering period. This paper also discusses the theoretical background of each calculation method and hydrodynamic aspects of marine riser systems. A steel catenary riser (SCR) line on FPSO was considered and marine dynamic program (OrcaFlex) was used for static and dynamic analysis.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.952-958
• /
• 1999

This paper presented the application of GAs as a means of finding optimal solutions over a parameter space in the controller design for a fuzzy control system. The performance can involve a weighted combination of various performance characteristics such as rise-time, settling-time, settling-time, overshoot. The results obtained here are compared with those for a traditional design obtained using the root-locus method. In contrast to traditional methods, the GA-based method does not require the usual mathematical processess or mathematical model of the system. In this paper, the Ga-based Fuzzy control system combining Fuzzy control theory with the GA, that is known to be very effective in the optimization problem, will be proposed The effectiveness of the proposed control system will be demonstrated by computer simulations using task tracking position system in stable and unstable linear systems. It is shown that the GA-based controller is better than the traditional controller used It stable and unstable linear systems.

• The Journal of the Korea Contents Association
• /
• v.18 no.6
• /
• pp.324-332
• /
• 2018

Blockchain technology has the potential to revolutionize trust models and business processes in a variety of industries. However, it is considered to be the initial stage of the system that pursues autonomy rather than efficiency, and it is necessary to monitor and inspect the distributed ledger technology from the price and introduction time as compared with the existing relational DB transaction technology. However, domestic and foreign private sectors have already been activated by applying block-chain technology in the national domain, and the block chain is devoid of doubt that it is an exaggerated technology, characterized by the invariance of the record, transparency, and autonomous execution of business rules. It has begun to be utilized in history, identity, certification and auditing in the financial industry as well as various industries. In this paper, we analyze the problems such as security weakness, insufficient regulatory environment, technical consensus and lack of common standard. In addition, the business sense and possibility of the block chain technology is expected to be the innovation of the industrial ecosystem by entering into the reality system from the concept through monitoring the actual introduction performance in the field of copyright, logistics, health care and environment.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.692-702
• /
• 2006

In this study, a weighted fuzzy min-max (WFMM) neural network model for pattern classification is proposed. The model has a modified structure of FMM neural network in which the weight concept is added to represent the frequency factor of feature values in a learning data set. First we present in this paper a new activation function of the network which is defined as a hyperbox membership function. Then we introduce a new learning algorithm for the model that consists of three kinds of processes: hyperbox creation/expansion, hyperbox overlap test, and hyperbox contraction. A weight adaptation rule considering the frequency factors is defined for the learning process. Finally we describe a feature analysis technique using the proposed model. Four kinds of relevance factors among feature values, feature types, hyperboxes and patterns classes are proposed to analyze relative importance of each feature in a given problem. Two types of practical applications, Fisher's Iris data and Cleveland medical data, have been used for the experiments. Through the experimental results, the effectiveness of the proposed method is discussed.