• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1444-1447
• /
• 2004

The vacuum-cleaner had made the burden of house chore lighten but the operation labour of a vacuum-cleaner had been so severe. Recently, the cleaning robot was producted to perfectly solve the cleaning labour of a house but it also was not successful because it still had a problem of mess-cleaning, which is the clean-up of big trash and the arrangement of newspapers, clothes, etc. The cleaning robot is to just vacuum dust and small trash and has no function to arrange and take away before the automatic vacuum-cleaning. For this reason, the market for the cleaning robot is not yet built up. So, we need a design method and technological algorithm of new automatic machine to solve the problem of mess-cleanup in house. In this paper, a Home Mess-Cleanup Robot(HMR), which has a practical function of the automatic mess-cleanup, is developed. It need functions of agile automatic navigation, novel manipulation system for mess-cleanup. The automatic navigation system has to be controlled for the full scanning of living room, to recognize the absolute position and orientation of the self, the precise tracking of the desired path, and to distinguish the mess object to clean-up from obstacle object to just avoid. The manipulation system, which is not needed in the vacuum-cleaning robot, must have the functions, how to distinguish big trash to clean from mess objects to arrange, how to grasp in according to the form of mess objects, how to move to the destination in according to mess objects and arrange them. Then, it should be an intelligent system so that the mess cleaning task can be autonomously performed in a wide variety of situations and environments. It need to also has the entertainment functions for the good communication between the human and HMR. Therefore, the Home Mess-cleanup Robot with Entertainmental Human Interface is developed in this paper. Finally, the good performance of the designed machine, HMR'4, is confirmed through the results of the mess clean-up and arrangement.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.12
• /
• pp.1011-1019
• /
• 2005

In this paper, Ubiquitous Home Mess-Cleanup Robot(UHMR), which has a practical function of the automatic mess-cleanup, is developed. The vacuum-cleaner had made the burden of house chore lighten but the operation labour of a vacuum-cleaner had been so severe. Recently, the cleaning robot was producted to perfectly solve the cleaning labour of a house but it also was not successful because it still had a problem of mess-cleaning, which was the clean-up of big trash and the arrangement of newspapers, clothes, etc. The cleaning robot is to just vacuum dust and small trash but has no function to arrange and take away before the automatic vacuum-cleaning. For this reason, the market for the cleaning robot is not yet built up. So, we need a design method and technological algorithm of new automatic machine to solve the problem of mess-cleanup in house. It needs functions of agile automatic navigation, novel manipulation system for mess-cleanup. The automatic navigation system has to be controlled for the full scanning of living room, to recognize the absolute position and orientation of tile self, the precise tracking of the desired path, and to distinguish the mess object to clean-up from obstacle object to just avoid. The manipulate,, which is not needed in the vacuum-cleaning robot, must have the functions, how to distinguish big trash to clean from mess objects to arrange, how to grasp in according to the form of mess objects, how to move to the destination in according to mess objects and arrange them. We use the RFID system to solve the problems in this paper and propose the reading algorithm of RFID tags installed in indoor objects and environments. Then, it should be an intelligent system so that the mess cleaning task can be autonomously performed in a wide variety of situations and environments. It needs to also has the entertainment functions for the good communication between the human and UHMR. Finally, the good performance of the designed UHMR is confirmed through the results of the mess clean-up and arrangement.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1612-1616
• /
• 2005

In this paper, a Home Mess-Cleanup Robot(HMR), which has a practical function of the automatic mess-cleanup, is developed. The vacuum-cleaner had made the burden of house chore lighten but the operation labour of a vacuum-cleaner had been so severe. Recently, the cleaning robot was producted to perfectly solve the cleaning labour of a house but it also was not successful because it still had a problem of mess-cleaning, which was the clean-up of big trash and the arrangement of newspapers, clothes, etc. The cleaning robot is to just vacuum dust and small trash but has no function to arrange and take away before the automatic vacuum-cleaning. For this reason, the market for the cleaning robot is not yet built up. So, we need a design method and technological algorithm of new automatic machine to solve the problem of mess-cleanup in house. It needs functions of agile automatic navigation, novel manipulation system for mess-cleanup. The automatic navigation system has to be controlled for the full scanning of living room, to recognize the absolute position and orientation of the self, the precise tracking of the desired path, and to distinguish the mess object to clean-up from obstacle object to just avoid. The manipulator, which is not needed in the vacuum-cleaning robot, must have the functions, how to distinguish big trash to clean from mess objects to arrange, how to grasp in according to the form of mess objects, how to move to the destination in according to mess objects and arrange them. We use the RFID system to solve the problems in this paper and propose the reading algorithm of RFID tags installed in indoor objects and environments. Then, it should be an intelligent system so that the mess cleaning task can be autonomously performed in a wide variety of situations and environments. It needs to also has the entertainment functions for the good communication between the human and HMR. Finally, the good performance of the designed HMR is confirmed through the results of the mess clean-up and arrangement.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.1
• /
• pp.59-59
• /
• 2012

Self-consistent mathematical model of the exotic object OTJ 071126+440405= CSS 081231:071126+440405 is discussed. The system was discovered as a polar at the New year night 31.12.2008/01.01.2009 by D.Denisenko (VSNET Circ), and we have initiated an international campaign of photometric and polarimetric observations of this object (totally -80 runs in Ukraine, Korea, Slovakia, Finland, USA) as a part of the "Inter-Longitude Astronomy" (ILA) project on monitoring of variable stars of different classes (Andronov et al., 2003). Here we present the geometrical and physical model of the system in the low luminosity state and in the intermediate luminosity state as well as in the high luminosity state. As the system is of -20 mag at minimum, no spectral observations were made to determine parameters of the red dwarf. From the statistical relationship, the mass of the red dwarf is estimated to be -0.165 solar masses, for the white dwarf (from eclipse duration) - from 0.5 to 1.76 solar masses. As the system resembles ER UMa in some characteristics, the lower value may be assumed. The inclination of the system and other physical parameters are estimated. The object is an excellent laboratory to study multiple physical processes in the magnetic systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.157-163
• /
• 2013

In this paper, we propose a human detection technique using thermal imaging camera. The proposed method is useful at night or rainy weather where a visible light imaging cameras is not able to detect human activities. Under the observation that a human is usually brighter than the background in the thermal images, we estimate the preliminary human regions using the statistical confidence measures in the gray-level, brightness histogram. Afterwards, we applied Gaussian filtering and blob labeling techniques to remove the unwanted noise, and gather the scattered of the pixel distributions and the center of gravities of the blobs. In the final step, we exploit the aspect ratio and the area on the unified object region as well as a number of the principal components extracted from the object region images to determine if the detected object is a human. The experimental results show that the proposed method is effective in environments where visible light cameras are not applicable.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Journal of English Language & Literature
• /
• v.53 no.2
• /
• pp.219-241
• /
• 2007

This study takes its point of departure from Lacanian psychoanalysis and explores the point that an irremediable gap in the human subject can be illuminated in terms of the Lacanian categories, fantasy, symptom, gaze or voice as cause of desire of the Other. With respect to the category of the symptom, Lacan claims that the Other is always already there in the constitution of the subject, that is, the relation of the subject to the Other that is overwhelming as well as attracting the subject. Chapter II deals with the unthought, excessive ground of the conscious that borders on the subject, as is the case of self-excentric aspect of the man. Indeed, in Lacan's early work, the subject is essentially a relationship to the Other as desire(objet petit a), and there is no such thing as a symptom or fantasy without some subjective involvement. Lacanian unknown real, perpetual excess as the cause of desire animates the subject even as it threatens to blast it apart. The structures that establish the lines of desire in every individual are derived from an ineluctably intersubjective field. The Other is always already there in the constitution of the subject. In the final years of Lacan's teaching we find a kind of universalization of the symptom and almost everything that is becomes in a way symptom. Symptom, embodied in Laura in "Goblin Market," is her only substance, the only positive support of her being. By looking at the Laura's symptom in chapter III we gain an insight into the forbidden domain, into a real space that should be left unseen and unthought. The voice of goblin men therefore functions as a sublime object that is animating as well as dominating element even as it threatens to disintegrate the subject. Objet petit a as a sublime object that must be excluded in reality returns in the real, taking on a certain materiality which has an effect on Laura, that is, animates Laura's desire. Objet petit a is a real object, signifying nothing. In conclusion, the theoretical importance of Lacanian psychoanalysis is the relation between a subject and an Other as Objet petit a.

• The Journal of the Korea Contents Association
• /
• v.8 no.12
• /
• pp.176-189
• /
• 2008

The purpose of this study was to analyze self-regulation about changing heart rate and perceived arousal variation when actors start their performance. Object of this study were 5 actors who belong to the theater selected using the purposive sampling method. This study used a measuring instrument of heart rate to measure arousal status, used behavior observation paper to observe and record self-regulation behavior and executed personal consultation after ending performance. There was graph mad by variation transition which calculated average and standard deviation about variation of heart rate each time of performance. The results of this study were as follows. First, there were high variation of awake level that actor's heart rates were rising before starting performance and the most high level of arousal was from 20minutes to 5minutes before starting performance. Second, there were self-regulation behaviors appeared such as deep breathing, breath controling, self talking, talking with other actors, concentrating an script, going to toilet, smoking, checking closes before starting performance. Third, when performance start, actors used psychological self-regulational method such as relaxation, self concentration, confidence reinforcement, coping with state or accommodation for controling raised arousal status.

• Journal of dental hygiene science
• /
• v.12 no.3
• /
• pp.217-225
• /
• 2012

The purpose of this study is to measure the relation of employment stress and self-esteem in some health college students and to consider a proper means for the solution. The population of the research is some randomly chosen health college students located in Seoul City during the period from May 10 to June 11 2010, and the sample of 295 students were recruited as the analysis object group. The data on general characteristics and employment stress were collected by a questionnaire survey. The collected data were analyzed with the SPSS WIN 12.0 program. The following shows the results of this study. 1. Employment stress was low in high group of satisfaction in campus life. It was statistically significant(p<0.001). 2. Mean scores of total self-esteem in study population were 3.1 and positive self-esteem level(3.76) were higher than negative ones (2.44)(p<0.001). 3. The relation between employment stress and selfesteem(r=0.132) revealed significant correlation. 4. In regression analysis, home economy, competence for a schoolwork, satisfaction in campus life, self-esteem(p<0.001) were proved as significant factors that is related to the employment stress. In other words, It is significant statistically that the lower home economy, competence for a schoolwork, satisfaction in campus life, self-esteem, the higher employment stress level. I suggest with the result of the study that for coping effectively employment stress of health college students, we will need to open an educational development considering self-esteem and an exclusive employment counsel window for better administrationwelfare service in campus, to expand industry-academic cooperation in community. Because of students are independent responsibility of employment, active effort must take precedence in order for the solution of problem by themselves. Also, we will need to create better academic environment and show more concern, consideration, love in family.