• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3714-3732
• /
• 2019

With the rapid development of network, Intrusion Detection System(IDS) plays a more and more important role in network applications. Many data mining algorithms are used to build IDS. However, due to the advent of big data era, massive data are generated. When dealing with large-scale data sets, most data mining algorithms suffer from a high computational burden which makes IDS much less efficient. To build an efficient IDS over big data, we propose a classification algorithm based on data clustering and data reduction. In the training stage, the training data are divided into clusters with similar size by Mini Batch K-Means algorithm, meanwhile, the center of each cluster is used as its index. Then, we select representative instances for each cluster to perform the task of data reduction and use the clusters that consist of representative instances to build a K-Nearest Neighbor(KNN) detection model. In the detection stage, we sort clusters according to the distances between the test sample and cluster indexes, and obtain k nearest clusters where we find k nearest neighbors. Experimental results show that searching neighbors by cluster indexes reduces the computational complexity significantly, and classification with reduced data of representative instances not only improves the efficiency, but also maintains high accuracy.

• Journal of the Korean Society of Safety
• /
• v.22 no.4
• /
• pp.72-82
• /
• 2007

The purpose of this study is to put forward revitalization of the Honorary Industrial Safety Inspector System by using the survey(2006.05) of the Honorary Industrial Safety Inspector in the Construction Industry. It can be summarized to develop the system as the following: 1) If there are neither labor union nor representative of workers in a company, workers must elect the representative of workers at first and then recommendation of the honorary industrial safety inspector by the representative of workers, 2) It should regulated in the industrial safety and health act about the tenure of the representative of workers and the process of election, 3) Prohibition the honorary industrial safety inspector as the employer members in the Industrial Safety and Health Committee and exclusion of both main office supervisor and subcontract-company supervisor from the appointment of the honorary industrial safety inspector, 4) Measures to realize the prohibitive regulation of unfavorable treatment on the grounds that the inspector has performed legitimate activities as an Honorary Industrial Safety Inspector, 5) Statutory regulation of the educations' hours(primary education & professional education), 6) Specification of the professional education and increase of the frequency, 7) Support of the government(the Ministry of Labor) to revitalize the honorary industrial safety inspector system, 8) Put in a statutory form the regular hours to carry out the work of the honorary industrial safety inspector in the workplace.

• Journal of Environmental Science International
• /
• v.18 no.12
• /
• pp.1417-1426
• /
• 2009

As the damages due to natural disasters continue to increase, a growing interest is being witnessed in such studies that focus on preventive measures to reduce damages rather than on their recovery. As such, the U.S. has been actively conducting projects to develop new models that can forecast potential damages due to natural disasters and widely employing them in actual cases. With no specific models developed in Korea yet, this study aimed to introduce an overseas typhoon model as part of the advanced efforts and apply it the actual cases occurring across the nation. This model estimates wind loads by measuring the impact of a strong wind upon buildings, and measurements require a number of parameters. Those parameters should include the types and dimensions of buildings and the type of the roofs. As for the FPHLM(Florida Public Hurricane Loss Model), a precedent model for our study, we were able to take advantage of number of the statistics and detailed categorizations on the residential buildings in the U.S., which enabled us to select the representative building types and produce their wind loads. With no sufficient relevant statistics available for the nation, however, we may not be able to readily measure the wind loads on the nation's residential buildings. Therefore, this study tried to choose the representative types, heights and dimensions of the buildings for the measurement of wind loads. We consequently came up with a representative house having an area between 62.81 and $95.56m^2$, either a flat roof or hip roof, a height of 2.6 m, an side ratio of 1.5, and the width and length of the mean $85m^2$ sized house being 11,300 mm and 7,530 mm, respectively.

• KIEAE Journal
• /
• v.1 no.1
• /
• pp.35-43
• /
• 2001

The VOC, which were detected from the newly built house, exist as a certain number of types according to the characteristics of the change of VOC concentration indoors. In this paper, we aim to divide the VOC into types so that those with similar characteristics of the transition of their concentration are in the same group and select the representative compound according to each classified type, and to verify these processes statistically in order to verify and propose new method creating the representing index of the VOC concentration in indoor which is used in evaluation of the degree of air pollution. As a result, the characteristic of the change of VOC concentration in the indoor can be divided into three types. Type1; the group in which the concentration is relatively high right after the completion of the house, and then decreases rapidly. Type2; the group in which the concentration is relatively low right after the completion of the house, and then although it shows the tendency of increasing and decreasing repeatedly, it decreases overall. Type3 is the group, which show only one peak at a certain time during the measuring period. As the method like this was verified to have the statistical significance, the Ethylbenzene was selected as the representative compound of type1, and Styrene was selected as that of type2. Moreover, if considering transition of the VOC from the point of similarity, the research method of making the classification and the selection of the representative compound in this study are said to be significant method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.5
• /
• pp.22-35
• /
• 2013

With the increase in image detectors, concerns about the reliability of traffic information are increasing. In this paper, we propose a method to generate reliable traffic volume using analysis of the point detector data as a representative value. Therefore, targeting expressway, we analyzed the difference in traffic volume collected by loop and image detector, and verified statistically using t-test, and finally analyzed the error rate compare to the real traffic volume. Analysis revealed that there was a statistically difference the traffic date collected by the loop detector and the image detector, in the same period, the same time, respectively. In addition, the difference between the actual traffic volume and traffic that have been collected in a loop detector was the lowest Therefore, creating a traffic volume of representative value, we proposed a method to use loop detector than the average traffic volume collected by each detector. It shows that it is more important to use one high-quality data rather than various low-quality data to produce a representative value.

• Water Engineering Research
• /
• v.1 no.4
• /
• pp.299-307
• /
• 2000

The method for estimating the minimum instream flows required for the riverline aesthetics, proposed by the Kim et al.(1996), has been applied to the main channel reach of the Keum river basin in Korea. To determine the minimum instream flows for eight main reaches at Keum river basin, six representative stations have been selected. This paper provides an analysis of influence on the riverline aesthetics, which is affected by change of physical components of river, by using the survey-based quantification method. The developed questionnaire based on the literature, and submitted to the 326 people who visited an each representative station. This surveying had been implemented in three times at each representative station and we had been selected a different flowrate at each implementation. The results of this analysis and survey have produced the relationship between the variation of physical components and riverline aesthetics. Survey results bout the flow comparison are summarized as follows. At the view of riverline aesthetics, most of the respondents re sensitive at the change of the flow velocity and they prefer high water level to low water level. Moreover whole respondents prefer to abundant stream flows and moderate flow velocity. The minimum flows for riverline aesthetics is estimated at each representative station by using the survey-based quantification method and the estimated results of some representative station are greater than mean monthly flow at each station. The result of the analysis appears that establishing minimum instream flows for riverline aesthetics is not only a technical problem but a legal problem. Therefore in the case of establishing the instream flows in the river, the estimated results have to be considered as relative standard.

• Science of Emotion and Sensibility
• /
• v.12 no.1
• /
• pp.45-54
• /
• 2009

Categorization in a vital means for dealing with the multitudes of entities in the world surrounding people. Among others, the perceptual and the evaluative similarities factors strongly affect categorization. The conventional SD-type procedure are insufficient in this regard, since it requires an individual subject to make isolated judgments about each stimulus to identify categorization in terms of a group tendency. It disregards the individual categorization in which the similarities are of great importance. Thus in this study the phased emotional evaluation method is suggested based on the intuitive categorization of stimuli and on the similarity judgement of representative/ non-representative case in each category. To verify the effectiveness of the suggested evaluation method the scanned jewelry images are selected as test stimuli for emotional evaluation experiment. As a result of the evaluation experiment, the conventional SD-type procedure is complemented by the emotional evaluation method in phases of the task of intuitive categorization, the selection of the representative images and the setup of the evaluation score of the representative images to internally supplied anchors of evaluating non-representative images.

• Journal of Korea Water Resources Association
• /
• v.46 no.4
• /
• pp.361-372
• /
• 2013

This study used the beta distribution to analyze the independent annual maximum rainfall events from 1961 to 2010 and decided the representative rainfall event for Seoul. In detail, the annual maximum rainfall events were divided into two groups, the upper 50% and the lower 50%. For each group, a beta distribution was derived to pass the mean location of the rainfall peaks. Finally, the representative rainfall event was decided as the rainfall histogram of the arithmetic average of the two beta distributions derived. The representative rainfall event derived has a realistic shape very similar to those observed annual maximum rainfall events, especially with the higher rainfall peak compared to that of the Huff distribution. Comparison with other rainfall distribution models shows that the temporal distribution of the representative rainfall event derived in this study is most similar to the Keifer & Chu model.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.63-70
• /
• 2012

In spite of growing demand for the region specific statistics, due to the increase in the cost of making out statistics and other reasons, utilizing survey statistics has limitation on coping with it. Thus, administrative statistics could be a feasible option. In this study, we selected "representative statistics", which are frequently used in establishing regional policy and reflect regional characteristics, among the Jeollabuk-do's administrative statistics. And we suggested the way to enhance quality and credential of the administrative statistics by using systematic management. As a result, we selected 45 statistics for Jeollabuk-do's "representative statistics". The reason that we raise the issue on the necessity of selecting "representative statistics" and specify its selection process is to give guidance to systematic management and efficient utilization of the local government's administrative statistics.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.61-68
• /
• 2016

According to increasing SNS users and developing smart devices like smart phone and tablet PC recently, many techniques to classify user emotions with social network information are researching briskly. The use emotion classification stands for distinguishing its emotion with text and images listed on his/her SNS. This paper suggests a method to classify user emotions through sampling a value of a representative figure on a trigonometrical function, a representative adjective on text, and a canny algorithm on images. The sampling representative adjective on text is selected as one of high frequency in the samplings and measured values of positive-negative by SentiWordNet. Figures sampled on images are selected as the representative in figures; triangle, quadrangle, and circle as well as classified user emotions by measuring pleasure-unpleased values as a type of figures and inclines. Finally, this is re-defined as x-y graph that represents pleasure-unpleased and positive-negative values with wheel of emotions by Plutchik. Also, we are anticipating for applying user-customized service through classifying user emotions on wheel of emotions by Plutchik that is redefined the representative adjectives and figures.