• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.512-522
• /
• 2002

In this paper, we propose a hybrid method which is mixed with frame selection and weighting model rank method, based on GMM(gaussian mixture model), for real-time text-independent speaker recognition system. In the system, maximum likelihood estimation was used for GMM parameter optimization, and maximum likelihood was used for recognition basically Proposed hybrid method has two steps. First, likelihood score was calculated with speaker models and test data at frame level, and the difference is calculated between the biggest likelihood value and second. And then, the frame is selected if the difference is bigger than threshold. The second, instead of calculated likelihood, weighting value is used for calculating total score at each selected frame. Cepstrum coefficient and regressive coefficient were used as feature parameters, and the database for test and training consists of several data which are collected at different time, and data for experience are selected randomly In experiments, we applied each method to baseline system, and tested. In speaker recognition experiments, proposed hybrid method has an average of 4% higher recognition accuracy than frame selection method and 1% higher than W method, implying the effectiveness of it.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.7-14
• /
• 2010

In this paper, we introduce a hierarchical internet application traffic classification system based on SVM as an alternative overcoming the uppermost limit of the conventional methodology which is using the port number or payload information. After selecting an optimal attribute subset of the bidirectional traffic flow data collected from the campus, the proposed system classifies the internet application traffic hierarchically. The system is composed of three layers: the first layer quickly determines P2P traffic and non-P2P traffic using a SVM, the second layer classifies P2P traffics into file-sharing, messenger, and TV, based on three SVDDs. The third layer makes specific classification of the entire 16 application traffics. By classifying the internet application traffic finely or coarsely, the proposed system can guarantee an efficient system resource management, a stable network environment, a seamless bandwidth, and an appropriate QoS. Also, even a new application traffic is added, it is possible to have a system incremental updating and scalability by training only a new SVDD without retraining the whole system. We validate the performance of our approach with computer experiments.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.6
• /
• pp.674-680
• /
• 2014

Monitoring systems of informations for ship performance have become important gradually for economical management of existing ship. Monitoring of NOx emission from marine diesel engines is one of them. The measurement of NOx emission, however has been many difficulties due to technical and costly problems. A monitoring by prediction method of NOx on-board ship according to sailing condition of ship could be an useful method. In this paper, it is discussed about modified method of one-zone model which has been utilized usually for analyzing the combustion process. The modified method is able to calculate the temperature of burned region from the result by one-zone model. Influences which excess air ratio during combustion process affected for the gas temperature and NOx emission were investigated. From the results variation of excess air ratio during combustion process could be estimated inversely through the comparison with measurement of NOx emission.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1724-1733
• /
• 2014

This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.11
• /
• pp.1094-1103
• /
• 2012

Recently, software industry regarding national defense increases system development of distributed simulation system of M&S based to overcome limit of resource and expense. It is one of key technologies for offering of mutual validation among objects and reuse of objects which are discussed for developing these systems. RTI, implementation of HLA interface specification as software providing these technologies uses Federation Object Model for exchanging information with joined federates in the federation and each federate has a characteristic that is supposed to have identical FOM in the federation. This technology is a software which is to provide the core technology which was suggested by the United state's military M&S standard framework. Simulator, virtual simulation, and inter-connection between military weapons system S/W which executes on network which is M&S's core base technology, and it is a technology which also can be used for various inter-connection between S/W such as game and on-line phone. These days although RTI is used in military war game or tactical training unit field, there is none in Korea. Also, it is used in mobile-game, distribution game, net management, robot field, and other civilian field, but the number of examples are so small and informalized. Through this developing project, we developed the core technique and RTI software and provided performance of COTS level to improve communication algorithms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.157-163
• /
• 2017

The object segmentation approach has the merit of reducing the processing cost required to detect moths of interest, because it applies a moth detection algorithm to the segmented objects after segmenting the objects individually in the moth image. In this paper, an object segmentation method for moth detection in pheromone trap images is proposed. Our method consists of preprocessing, thresholding, morphological filtering, and object labeling processes. Thresholding in the process is a critical step significantly influencing the performance of object segmentation. The proposed method can threshold very elaborately by reflecting the local properties of the moth images. We performed thresholding using global and local versions of Ostu's method and, used the proposed method for the moth images of Carposina sasakii acquired on a pheromone trap placed in an orchard. It was demonstrated that the proposed method could reflect the properties of light and background on the moth images. Also, we performed object segmentation and moth classification for Carposina sasakii images, where the latter process used an SVM classifier with training and classification steps. In the experiments, the proposed method performed the detection of Carposina sasakii for 10 moth images and achieved an average detection rate of 95% of them. Therefore, it was shown that the proposed technique is an effective monitoring method of Carposina sasakii in an orchard.

• Korean Journal of Community Nutrition
• /
• v.8 no.4
• /
• pp.603-609
• /
• 2003

This study examined the reproducibility of nutrient intakes estimated by the 24-hour recall method in a prospective cohort study (Longitudinal study of aging and health monitoring of Korean elderly) of middle-aged volunteer subjects (42 males and 49 females) in the Seoul area. The three-day 24-hour recall was administered twice at an interval of approximately 6 months. The first data were collected and a corrective procedure was performed by interviewing of the subjects and a trained dietitian. The second data were collected by mail from the subjects without the performance of any corrective procedure. The mean age of the subjects was 53.5 $\pm$ 9.6 for the males and 52.2 $\pm$ 8.9 for the females. The subjects who had above college education were 95% in the case of the males and 60% in the case of the females. The characteristics of the male subjects in this study were that they were highly educated and held professional jobs and were from the middle or upper class. Comparing the first and second 24-hour recall data, the second data showed relatively lower intakes of all nutrients, except vitamin A, vitamin Bi and cholesterol. There was no difference in the nutrients of the first and the second data with respect to vitamin A, vitamin B$_1$ and cholesterol in the males and calcium, iron, sodium, vitamin A, vitamin B$_1$, vitamin B$_2$ and cholesterol in the females. This data may indicate that the 24 hour retail method without a dietitian's help may result in lower reporting of the subject's intakes. The men had a tendency to remember less than the women. Pearson's correlation coefficients with unadjusted nutrient intakes values were ranged from 0.24 to 0.66. When energy intake was adjusted, there was a slight increase (from 0.26 to 0.71). Intra-class correlation coefficients with nutrient-unadjusted values ranged from 0.22 to 0.66, and the energy-adjusted values were ranged from 0.23 to 0.69. The weighted Kappa statistical values ranged from 0.10 to 0.40. On the average,46.3% of the subjects who were found in the lowest quartile of the nutrient intake levels based on the first 24-hour recall, were in the lowest quartile based on the second 24-hour recall. Therefore, there was a low reproducibility between the first and the second 24-hour recall. We should examine the factors influencing low reproducibility. Also, strategies should be developed to maximize the reliability of the assessment, with regard to portion-size training and telephone validation. (Korean J Community Nutrition 8(4) : 603∼609, 2003)

• The Journal of the Korea Contents Association
• /
• v.8 no.5
• /
• pp.246-259
• /
• 2008

This study was to minimize the trial and error in the primary step of the C4I system(ATCIS) of the each army corps on the front line, and test the economy and efficiency was tested by reviewing related papers and the system characteristics of other countries. The relationship was researched by analyzing the collected survey data and survey data related to the user's requirement level such as the army standards, that is, commonality, timeliness, simplification, automaticity, field availability and viability, multi-stage security and interoperability, unification. The result showed that the C4I system was efficiently operated through the system reliability for the specification of the system and operation manual, maneuverability and security, adaptability of the war field and system support and management, and good education and training about system operation, and less system maintenance and supplementary element. As a result, the development plan confirmed that the continuous operator education and the construction of the maintenance, and the upgrade digitalization(C4ISR+D) with the korean characteristics based on IT of network systems, and system development of the measurement model of the operator performance must be continuously supplemented in the near future.

• The Journal of Internal Korean Medicine
• /
• v.34 no.3
• /
• pp.231-239
• /
• 2013

Objectives : This study was performed to evaluate inter-rater and intra-rater reliability of interpretation and reproducibility of a pulse analyser (MAXMAC27-Plus). Methods : 38 of 40 volunteers completed the pulse analysis consecutively. Three Korean medical doctors who had at least 2 years of clinical experience interpreted the pulse waves for 3 aspects of size, depth and shape, then inter-rater reliability and crude agreement was obtained. Reinterpretation was done 2 weeks later and intra-rater reliability and crude agreement was obtained. Intra-rater reliability and crude agreement between 1st and 2nd measurement was calculated. Cohen's weighted kappa for size, Cohen's kappa for depth and shape were used as statistical analysis. Results : Inter-rater reliability of size, depth and shape among 3 raters was 0.598, 0.604, and 0.312, respectively, showing moderate to substantial agreement. Average intra-rater reliability between 1st and 2nd interpretation of size, depth and shape was 0.806, 0.705, and 0.638, respectively, showing substantial to almost perfect agreement. However, intra-rater reliability between consecutive measurements of size, depth and shape was 0.221, 0.121, and 0.194, respectively, which showed only poor to fair agreement. Conclusions : Intra-rater and inter-rater reliability of one pulse wave showed relatively high concordance. Training by a clinical expert may effect better concordance among raters. Test-retest reliability showed poor agreement. Improvement of measurement technique and device performance will be needed.

• Journal of Hospice and Palliative Care
• /
• v.16 no.2
• /
• pp.80-89
• /
• 2013

Purpose: We investigated how intensive care unit (ICU) nurses understand the meaning of death, death anxiety, death concern and respect for life. Methods: From November 2009 through February 2010, a survey was conducted on 230 nurses working at the ICU of 10 general hospitals located in Seoul and Gyeonggi province. Participants were asked to answer a questionnaire consisted of 67 questions under four categories of the meaning of death, death anxiety, death concern and respect for life. Results: Participants scored 4.27 points on their understanding of the meaning of death, 4.43 on death anxiety, 4.12 on death concern and 4.18 on respect for life. Participants' meaning of death was negatively correlated with death anxiety and death concern and positively with respect for life. Participants' positive meaning of death was negatively correlated with death anxiety and death concern and positively with respect for life. Participants' negative meaning of death was negatively correlated with death anxiety and death concern and positively with respect for life. Participants' death anxiety was positively correlated with death concern and negatively with respect for life. Participants' death concern was negatively correlated with respect for life. Conclusion: Compared with nurses who served at ICU for a long time, nurses with less ICU experience scored lower on the meaning of death and respect for life, while they presented high anxiety and concern about death. A training course may help nurses develop their view on the meaning of death, which in turn would enhance their performance in caring dying patients.