• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.675-686
• /
• 2005

In this paper, we propose an efficient face region detection technique for the content-based video summarization. To segment video, shot changes are detected from a video sequence and key frames are selected from the shots. We select one frame that has the least difference between neighboring frames in each shot. The proposed face detection algorithm detects face region from selected key frames. And then, we provide user with summarized frames included face region that has an important meaning in dramas or movies. Using Bayes classification rule and statistical characteristic of the skin pixels, face regions are detected in the frames. After skin detection, we adopt the projection method to segment an image(frame) into face region and non-face region. The segmented regions are candidates of the face object and they include many false detected regions. So, we design a classifier to minimize false lesion using CART. From SGLD matrices, we extract the textual feature values such as Inertial, Inverse Difference, and Correlation. As a result of our experiment, proposed face detection algorithm shows a good performance for the key frames with a complex and variant background. And our system provides key frames included the face region for user as video summarized information.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.535-542
• /
• 2013

Since case-based reasoning(CBR) has many advantages, it has been used for supporting decision making in various areas including medical checkup, production planning, customer classification, and so on. However, there are several factors to be set by heuristics when designing effective CBR systems. Among these factors, this study addresses the issue of selecting appropriate neighbors in case retrieval step. As the criterion for selecting appropriate neighbors, conventional studies have used the preset number of neighbors to combine(i.e. k of k-nearest neighbor), or the relative portion of the maximum similarity. However, this study proposes to use the absolute similarity threshold varying from 0 to 1, as the criterion for selecting appropriate neighbors to combine. In this case, too small similarity threshold value may make the model rarely produce the solution. To avoid this, we propose to adopt the coverage, which implies the ratio of the cases in which solutions are produced over the total number of the training cases, and to set it as the constraint when optimizing the similarity threshold. To validate the usefulness of the proposed model, we applied it to a real-world target marketing case of an online shopping mall in Korea. As a result, we found that the proposed model might significantly improve the performance of CBR.

• Journal of Wetlands Research
• /
• v.17 no.4
• /
• pp.428-435
• /
• 2015

Constructed wetlands (CWs) have been accepted as an attractive and economic alternative to a variety of pollution control and provided potentially valuable wildlife habitat in urban and suburban areas, as well as esthetic value within the local natural environment. CWs are known eco-friendly technology to solve the problem of the climate change and urbanization issues. Numerous studies have been published on the various aspects of a CW. However, there are current limitations about the CW operations such as few design guidelines, poor performance results regarding the simple construction. Therefore, the objective of this research was to suggest an appropriate design and maintenance guidelines for a CW by thorough investigation of site monitoring results. The research also concentrated in redefining and reclassifying CWs, based on literatures made by the Ministry of Environment (MOE) and other organizations. Investigation at 43 CWs in Korea was performed by using collected data and by performing site survey from 2013 to 2014. Based on the results, the best practices among the investigated CWs provided water treatment, wildlife habitat, environmental education, and leisure. Also these CWs conducted a regular maintenance such as vegetation, sediment dredging and cleaning of facilities. Results obtained are intended for use by academics and any organizations involved in CW management.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.679-685
• /
• 2011

This paper presents an algorithm identifying devices that generate observed mixed signals that are collected at main power-supply line. The proposed algorithm, which is necessary for low cost electric power monitoring system at appliance-level, that is non-intrusive load monitoring system, divides incoming mixed signal into multiple time intervals, calculating difference-signals between consecutive time interval, and identifies which device is operating at the time interval by analysing the difference-signals. Since the features of one device can remain when the time interval is short enough and the features are independent and additive, well-known classification algorithms can be used to classify the difference-signals with features of N individual devices, otherwise $2^N$ features might be necessary. The proposed algorithm was verified using data mixed in a laboratory with individual devices's data collected from field. When maximum 4 devices operate or stop sequentially and when features satisfy the requirements of proposed algorithm, the proposed algorithm resulted nearly 100% success rate under the constrained test condition. In order to apply the proposed algorithm in real world, the number devices shall increase, the time interval shall be smaller and the pattern of mixture shall be more diverse. However we can expect, if features used follow guidelines of proposed algorithm, future system could have certain level of performance without the guideline.

• 대한공업교육학회지
• /
• v.40 no.2
• /
• pp.175-195
• /
• 2015

This study is aimed at exploring the educational meaning of cooperative hands-on activity in the technology subject from the perspective of a student who is an education consumer. For this purpose, this study selected 12 first year student of a middle school located at G City of Gyeonggi-do Province as research participants through purposeful sampling, and conducted an in-depth interview and group discussion based on stimulated recall questionary techniques. This study utilized area analysis, classification analysis and component analysis as a data analysis method, and secured the verity of the research through the examination between research participants and triangulation. As a result of this research work, it was found that the cooperative hands-on class in the technology subject had the meaning of 'Space between a burden and excitement about the technical making', 'Clue and ignition point of technological problem solving', and 'Self-discovery through Technical capability'. To be more concrete, 'Space between a burden and excitement about the technical making' means that students, whose usual school record is excellent, felt great psychological burdens of performance assessment, but their pre-experience and interest in 'Making' induced them to feel exhilaration of hands-on activity. 'Clue and ignition point of technological problem solving' means that students get to make much of the understanding & formation of the relationship with teammates in the process of resolving an unfamiliar hands-on activity task and to have the continuous problem-solving ability. 'Self-discovery through Technical capability' means that students get to realize the importance of learning experience of one's own making through hands-on activity learning, which could be the opportunity to meet the operant demands of the inner side. This study hopes that such results could be utilized as the basic data needed for designing the hands-on activity education in the technology subject more meaningfully and systematically for the time to come.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.279-300
• /
• 2001

Data mining plays an important role in knowledge discovery process and usually various existing algorithms are selected for the specific purpose of the mining. Currently, data mining techniques are actively to the statistics, business, electronic commerce, biology, and medical area and currently numerous algorithms are being researched and developed for these applications. However, in a long run, only a few algorithms, which are well-suited to specific applications with excellent performance in large database, will survive. So it is reasonable to focus our effort on those selected algorithms in the future. This paper classifies about 30 existing algorithms into 7 categories - association rule, clustering, neural network, decision tree, genetic algorithm, memory-based reasoning, and bayesian network. First of all, this work analyzes systematic hierarchy and characteristics of algorithms and we present 14 criteria for classifying the algorithms and the results based on this criteria. Finally, we propose the best algorithms among some comparable algorithms with different features and performances. The result of this paper can be used as a guideline for data mining researches as well as field applications of data mining.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.1-8
• /
• 2016

In this study, an WiFi fingerprinting method based on the k-nn algorithm was applied to improve the accuracy of location tracking of a moving train on a platform and evaluate the performance to minimize the estimation error of location tracking. The data related to the position of the moving train are monitored by the control center for trains and used widely for the safety and comfort of passengers. The train location tracking methods based on WiFi installed by telecom companies were evaluated. In this study, a simulator was developed to consider the environments of two cases; in already installed WiFi devices and new installed WiFi devices. The developed simulator can simulate the localized estimation of the position under a variety of conditions, such as the number of WiFi devices, the area of platform and entry velocity of train. To apply location tracking algorithms, a k-nn algorithm and fuzzy k-nn algorithm were applied selectively according to the underlying condition and also four distance measurement algorithms were applied to compare the error of location tracking. In conclusion, the best method to estimate train location tracking is a combination of the k-nn algorithm and Minkoski distance measurement at a 0.5m grid unit and 8 WiFi AP installed.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.163-170
• /
• 2006

With rapidly developing Internet applications, an e-mail has been considered as one of the most popular methods for exchanging information. The e-mail, however, has a serious problem that users ran receive a lot of unwanted e-mails, what we called, spam mails, which cause big problems economically as well as socially. In order to block and filter out the spam mails, many researchers and companies have performed many sorts of research on spam filtering. In general, users of e-mail have different criteria on deciding if an e-mail is spam or not. Furthermore, in e-mail client systems, users do different actions according to a spam mail or not. In this paper, we propose a mail filtering system using such user actions. The proposed system consists of two steps: One is an action inference step to draw user actions from an e-mail and the other is a mail classification step to decide if the e-mail is spam or not. All the two steps use incremental learning, of which an algorithm is IB2 of TiMBL. To evaluate the proposed system, we collect 12,000 mails of 12 persons. The accuracy is $81{\sim}93%$ according to each person. The proposed system outperforms, at about 14% on the average, a system that does not use any information about user actions.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.3
• /
• pp.288-294
• /
• 2005

This study was conducted to evaluate the grit removal efficiency of tornado block-type vortex grit separator. Vortex grit separator was manufactured for this study, and it was characterized by the impeller and tornado block installed in separator. Impeller was installed to increase water velocity in the separator and tornado block was installed to increase the grit lifting efficiency. Pilot study was also conducted in A sewage treatment plant (STP) in Gyeonggi province from November 2003 to May 2004 (64 days). Major findings are as follows. 1. Impeller was proven to increase water velocity in the grit separator, especially in low flow rate. This influence will increase separation ratio of organics from grits, preventing those organics from sedimentation. 2. Sand (with 0.2~0.3mm size) removal efficiency was over 98 % and 96 %, at the flow rate of $500m^3/day$ and $750m^3/day$ under the condition that impeller rotation velocity kept at 15 rpm. Originally that grit separator was designed to have the capacity of $500m^3/day$. $750m^3/day$ was tried to investigate the performance of this type of grit separator under overload condition. Stable grit removal was still available to the extent of 150% of designed capacity. 3. It took less than 3 minutes for the grit separator to completely lift out 3 kgs of 0.2-0.3 mm sized, settled sand at the bottom to 2,060 mm high above water surface. But it showed the tendency to spend a little more time on lifting the grit as the grit size and the vertical height of the lift increased. 4. During experimental duration in A STP, it was found that the average amount of inlet grit was about 981 g/day (160~1,685 g/day) under $500m^3/day$ of operation condition, but it varied so severely during the experimental duration. After classification of discharged grit according to its size, grit with 0.3-0.42 mm size was found as largest part of output.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.127-136
• /
• 2012

Many research of hand gesture recognition based on vision system have been conducted which enable user operate various electronic devices more easily. 3D position calculation and meaningful gesture classification from similar gestures should be executed to recognize hand gesture accurately. A simple and cost effective method of 3D position calculation and gesture spotting (a task to recognize meaningful gesture from other similar meaningless gestures) is described in this paper. 3D position is achieved by calculation of two cameras relative position through pan/tilt module and a marker regardless with the placed position. Fuzzy garbage model is proposed to provide a variable reference value to decide whether the user gesture is the command gesture or not. The reference is achieved from fuzzy command gesture model and fuzzy garbage model which returns the score that shows the degree of belonging to command gesture and garbage gesture respectively. Two-stage user adaptation is proposed that off-line (batch) adaptation for inter-personal difference and on-line (incremental) adaptation for intra-difference to enhance the performance. Experiment is conducted for 5 different users. The recognition rate of command (discriminate command gesture) is more than 95% when only one command like meaningless gesture exists and more than 85% when the command is mixed with many other similar gestures.