• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1284-1291
• /
• 2012

Ship object detection is a technique to detect the existence and the location of ship when ship objects are shown on input image sequence, and there are wide variations in accuracy due to environmental changes and noise of input image. In order to solve this problem, in this paper, we propose multiple ship object detection based on background registration technique and morphology operation. The proposed method consists of the following five steps: background elimination step, noise elimination step, object standard position setting step, object restructure step, and multiple object detection steps. The experimental results show accurate and real-time ship detection for 15 different test sequences with a detection rate of 98.7%, and robustness against variable environment. The proposed method may be helpful as the base technique of sea surface monitoring or automatic ship sailing.

• Journal of Korean Home Economics Education Association
• /
• v.7 no.1
• /
• pp.47-55
• /
• 1995

The purpose of this study were to identify the importance of father’s roles on children. A survey was carried out on 458(227 boys and 231 girls) 6th-graders at randomly chosen 4 elementary schools in Kwangju. Frequency, percentage, average, standard deviation and Pearson’s coefficient were checked and one-way ANOVA, Duncan’s multiple range test and multiple regression analysis were also carried out on the collected data. The results were as follows; 1. Evaluation of fathers’role performance depending on background variables ranged from 46.17 to 58.51 points(equivalent to 61.56∼78.01 points in the 100-point scale). Background variables that caused statistically significant difference were children’s sex, fathers’religion (whether they had one or not) fathers’education, monthly family income and decision-makers at home. The degrees of fathers’role performance were higher when the answerers were girls, when fathers had religions, when fathers educational level was higher, when the family income was higher, and when all family members participated in the decision-making. 2. Evaluation of children’s achievement motivation depending on background variables ranged from 77.17 to 84.34 points( equivalent to 68.90∼75.35 points in the 100-point scale). Background variables that caused statistically significant differences were children∼s sex and decision-makers at home. Children∼s achievement motivation were higher in the case of girls and when all family members participated in the decision-making. 3. When it comes to the children’s achievement motivation in relation to father’s role performance, 1)The overall aspect of fathers’ role performance caused significant differences in children’s achievement motivation. 2) The influence of fathers’role performance on children’s achievement motivation was highest in the investigation-faciliator role (${\beta}$=2.5) and then the economic role (${\beta}$=.14) and the valuetransmitter role (${\beta}$=.14). The explanative power of these variables was 22%.

• Journal of The Korean Society of Integrative Medicine
• /
• v.8 no.3
• /
• pp.63-69
• /
• 2020

Purpose : Various research studies are needed to raise the perception of the CE of Korean physical therapists. However, there are little studies have been conducted, and relatively few studies are available to read on online. The purpose of the study is to find out the differences in the perception of CE according to the physical therapist's academic background. In this way, this article intends to strengthen the perception of the CE of health-care workers, such as physical therapists and occupational therapists in the Republic of Korea so that contributing to the development of national health. Methods : Present study showed that 431 out of 563 people who participated in the two meetings of CE conducted by the Gwangju Metropolitan City of the Korea Physical Therapy Association responded in the survey in 2015. Among them, only 238 people were surveyed on the awareness of CE in 2014, excluding 181 questionnaires due to poor responses and 112 questionnaires that did not participate in CE in the previous year. Descriptive analyses were conducted to identify the perception among those who experienced CE, and simple linear regression analysis was performed using dummy variables to identify awareness of the education based on their academic background. Results : Question 3 (p=.000, R2=.067) was significant in the significance test of the regression equation for perception of the CE (p<.05). Question 1 (p=.687), 2 (p=.066), 4 (p=.430), 5 (p=.085), and 6 (p=.054), 7 (p=.111), 8 (p=.088), 9 (p=.213), 10 (p=.191) and 11 (p=. 169), the regression formula was not significant (p>.05). Conclusion : Physical therapists had a moderate perception of the need for a CE and had the idea that improvements were required in what was provided in that education. In addition, there was no statistically significant difference, although there was a greater awareness of CE in the Master of Science Course or higher than college or university graduates.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.3
• /
• pp.216-224
• /
• 2014

In this paper, we propose a new method to drastically reduce computational complexity in Gaussian Mixture Model (GMM)-based Speaker Identification (SI). Generally, GMM-based SI systems have very high computational complexity proportional to the length of the test utterance, the number of enrolled speakers, and the GMM size. These make the SI systems difficult to be used in various real applications in spite of their broad applicability. Thus, a trade-off between computational complexity and identification accuracy is considered as a primary issue for practical applications. In order to reduce computational complexity sharply with a little loss of accuracy, we introduce a method based on the Universal Background Model (UBM) clustering approach and then we show that it can be used successfully in real-time applications. In experiments with the proposed algorithm, we obtained a speed-up factor of 6 with a negligible loss of accuracy.

• Journal of Digital Contents Society
• /
• v.17 no.5
• /
• pp.375-381
• /
• 2016

Recently, a foreground-background segmentation using codebook model has been researched actively. The codebook is created one for each pixel in the image. The codewords are vector-quantized representative values of same positional training samples from the input image sequences. The training is necessary for a long time in the most of codebook-based algorithms. In this paper, the initial codebook model is generated simply using median operation with several image frames. The initial codebook is updated to adapt the dynamic changes of backgrounds based on the frequencies of codewords that matched to input pixel during the detection process. We implemented the proposed algorithm in the environment of visual c++ with opencv 3.0, and tested to some of the public video sequences from PETS2009. The test sequences contain the various scenarios including quasi-periodic motion images, loitering objects in the local area for a short time, etc. The experimental results show that the proposed algorithm has good performance compared to the GMM algorithm and standard codebook algorithm.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.216-221
• /
• 1999

A mental task combined with noise background is an effective model of laboratory stress for study of psychophysiology of the autonomic nervous system (ANS). The intensity of the background noise significantly affects both a subjective evaluation of experienced stress level during test and the physiological responses associated with mental load in noisy environments. Providing tests of similar difficulties we manipulated the background noise intensity as a main factor influencing a psychophysiological outcome and the analyzed reactivity along withe the noise intensity dimension. The goal of this study was to identify the patterns of ANS responses and the relevant subjective stress scores during performance of word recognition tasks on the background of white noise (WN) of the different intensities (55, 70 and 85 dB). Subjects were 27 college students (19-24 years old). BIOPAC, Grass Neurodata System and AcqKnowlwdge 3.5 software were used to record ECG, PPG, SCL, skin temperature, and respiration. Experimental manipulations were effective in producing subjective and physiological responses usually associated with stress. The results suggested that the following potential autonomic mechanisms might be involved in the mediation of the observed physiological responses: A sympathetic activation with parasympathetic withdrawal during mild 55 and 70dB noise (featured by similar profiles) and simultaneous activation of sympathetic and parasympathetic systems during intense 85dB WN. The parasympathetic activation in this case might be a compensatory effect directed to prevent sympathetic domination and to maintain optimal arousal state for the successful performance on mental stress task. It should be mentioned that obtained results partially support Gellhorn's (1960; 1970) "tuning phenomenon" as a possible mechanism underlying stress response.

• Physical Therapy Korea
• /
• v.28 no.1
• /
• pp.47-52
• /
• 2021

Background: Compared with normal people, stroke patients have decreased voluntary craniocervical motion, which affects their balance. Objects: This study was conducted in order to examine the effects of active craniocervical movement training using a cognitive game on stroke patient's cervical movement control ability, balance, and functional mobility. Methods: The subject of this study were 29chronic stroke patients who were randomly allocated to either an experimental, cognitive game group (n = 15), or control group (n = 14), to which only neuro-developmental treatment (NDT) was applied. The intervention was conducted 5 times per week, 30 minutes per each time, for a total of 4 weeks. Active angle reproduction test, static stability test, limits of stability test, and Time up and Go (TUG) test, respectively, were carried out in order to evaluate cervical movement control ability, static balance, dynamic balance, and functional mobility. Paired t-test was used in order to compare differences between prior to after the intervention, along with an independent-test in order to compare prior to and after-intervention differences between the two groups. Results: After the craniocervical training with a body-driven cognitive game, the experimental group showed significant differences in flexion, extension, and lateral flexion on the affected side, and rotation on the affected side in the active angle reproduction test. The experimental group indicated significant differences in sway length both with eyes-open and with eyesclosed in the static stability test and in limits of stability test and TUG test. The control group to which NDT was applied had significant differences in flexion in the active angle reproduction test and in limits of stability test and TUG test. Conclusion: The above results mean that craniocervical training using a body-driven cognitive game positively influences stroke patient's cervical movement control ability and as a result their balance and functional mobility.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• Architectural research
• /
• v.8 no.2
• /
• pp.11-16
• /
• 2006

The purpose of this study is to scrutinize the effect of office layouts and ambient office sounds on the performance of office workers involved with a proof-reading test (simple task). Twenty subjects, who were professional researchers and computer programmers, were from three different office layouts: 1) Nine subjects from a combined office type with open meeting places and closed individual offices; 2) five from an open office with rectangular individual workstations, and 3) six from an open office with triangular individual workstations. Architects and consultants working in the field of office have reported from interviews and their own observations that occupants' satisfaction differs as their office layouts vary although the sizes are the same. This finding leads to the hypothesis of this experiment. Proof-reading test results were obtained from three different office layouts (combined office type, rectangular and triangular individual workstations in open offices) under two different sound conditions (quiet background sound and ambient sound of their own workplace) for 10 minutes. The test analysis shows the mean test score of subjects from the triangular individual workstations in open offices is significantly different from the mean test scores of subjects from the combined office type and the rectangular individual workstations in open offices.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.2
• /
• pp.981-986
• /
• 2013

Background: The Pap smear has an important value in the early diagnosis of cervical cancer, a serious problem in womens health. This study aimed to determine the status of Turkish women regarding participation in Pap smear testing and affecting factors. Materials and Methods: This descriptive study was conducted on married women between 18-61 years of age selected from those who applied to the Obstetrics and Gynaecology Polyclinic of Atat$\ddot{u}$rk University in Erzurum between June-August 2010 for any reason. Data were collected using a questionnaire determining socio-demographic features and analyzed by descriptive statistics (mean, Sd, range, frequency, percentage) and Chi-square test. A level of p<0.05 was considered statistically significant. Results: Sixty six of the 301 women (21.9%) indicated that they heard a Pap smear test and 16.6% of women had experienced a test. The number of women participating increased with age, duration of marriage, number of births, knowledge about the Pap smear and perception of risk for cervical cancer. Conclusions: The importance of the Pap smear test needs to be explained to Turkish women by health staff, to increase awareness and participation in regular screening.