• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.617-622
• /
• 2004

In this work, we suggested the method which improves the efficiency of the face detection algorithm using Pulse-Coupled Neural Network. Face detection algorithm which uses the color information is independent on pose, size and obstruction of a face. But the use of color information encounters some problems arising from skin-tone color in the background, intensity variation within faces, and presence of random noise, and so on. Depending on these conditions, we obtained the mean and variance of the skin-tone colors by experiments. Then we introduce a preprocess that the pixel with a mean value of skin-tone colors has highest level value (255) and the other pixels in the skin-tone region have values between 0 and 255 according to a normal distribution with a variance. This preprocess leads to an easy decision of the linking coefficient of Pulse-Coupled Neural Network.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.4
• /
• pp.71-83
• /
• 2008

The recent advances of the information technology have motivated lots of research efforts to develop new computer-aided teaching and learning methodologies on various computer science topics, such as data structures, operating system, computer networks, and computer architecture. However, there have been only few studies to educate the database subject although it is one of the most important topics in the computer science. Specifically, among the various issues in the database subject, a learner often suffers to understand the mechanism of the concurrency control and recovery of database transaction in the database because it highly interacts with other functions in the database. Obviously, an intelligent visualization tool can help a learner to understand the process of the concurrency control and the recovery of database transaction. The purpose of this study is to develop an efficient visualization tool which can help users understand the two phase locking protocol (2PLP)-based concurrency control. Specifically, this visualization tool is designed to encourage a users' participation and raise their interest by visualizing the process of transactions and allowing users to specify and manipulate their own transactions.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.93-102
• /
• 1998

In noisy environments, human speech productions are influenced by noises(Lombard effect), and speech signals are contaminated. These distortions dramatically reduce the performance of speech recognition systems. This paper proposes a method of the Lombard effect compensation and noise suppression in order to improve speech recognition performance in noise environments. To estimate the intensity of the Lombard effect which is a nonlinear distortion depending on the ambient noise levels, speakers, and phonetic units, we formulate the measure of the Lombard effect level based on the acoustic speech signal, and the measure is used to compensate the Lombard effect. The distortions of speech under noisy environments are cancelled out as follows. First, spectral subtraction and band-pass filtering are used to cancel out noise. Second, energy nomalization is proposed to cancel out the variation of vocal intensity by the Lombard effect. Finally, the Lombard effect level controls the transform which converts Lombard speech cepstrum to clean speech cepstrum. The proposed method was validated on 50 korean word recognition. Average recognition rates were 82.6%, 95.7%, 97.6% with the proposed method, while 46.3%, 75.5%, 87.4% without any compensation at SNR 0, 10, 20 dB, respectively.

• Journal of Korean Society of Disaster and Security
• /
• v.10 no.1
• /
• pp.75-84
• /
• 2017

This study is concerned with the estimation of daily instantaneous maximum wind velocity in the meteorological major cities (selected each 17 points) during the yearly 1973-2016. The purpose of this paper is to present the turbulence statistic characteristics (probability distribution, correlation coefficient, turbulency intensity, shear velocity, roughness length, turbulence integral length, skewness, and kurtosis) of the daily instantaneous maximum wind velocity. In the processes of analysis, used observations data obtained at Korea Meteorological Adminstration (KMA). The estimation of non-Gaussian load effects for design applications has often been treated tacitly by invoking a conventional wind design load on the basis of Gaussian processes. This assumption breaks down when the instantaneous wind velocity processes exhibits non-Gaussianity. From the analysis results, the probability distribution of the daily instantaneous maximum wind velocity shows a very closed with non-Gaussian in the ensemble population 748, the correlation coefficient shows larger at inland area more than coastal area.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.1
• /
• pp.46-53
• /
• 1996

Adaptive LMS algorithm has been used in many application areas due to its low complexity. In this paper input signal is transformed into the subbands with arbitrary bandwidth. In each subbands the dynamic range can be reduced, so that the independent filtering in each subbands has faster convergence rate than the full band system. The DCT transform domain LMS adaptive filtering has the whitening effect of input signal at each bands. This leads the convergence rate to very high speed owing to the decrease of eigen value spread Finally, the filtered signals in each subbands are synthesized for the output signal to have full frequency components. In this procedure wavelet filter bank guarantees the perfect reconstruction of signal without any interspectra interference. In simulation for the case of speech signal added additive white gaussian noise, the suggested algorithm shows better performance than that of conventional NLMS algorithm at high SNR.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.5
• /
• pp.123-132
• /
• 2002

The purpose of this study is to predict the shear behavior of the weathered mudstone soil using dynamic neural network which mimics the biological system of human brain. SNN and RNN, which are kinds of the dynamic neural network realizing continuously a pattern recognition as time goes by, are used to predict a nonlinear behavior of soil. After analysis, parameters which have an effect on learning and predicting of neural network, the teaming rate, momentum constant and the optimum neural network model are decided to be 0.5, 0.7, 8$\times$18$\times$2 in SU model and 0.3, 0.9, 8$\times$24$\times$2 in R model. The results of appling both networks showed that both networks predicted the shear behavior of soil in normally consolidated state well, but RNN model which is effective fir input data of irregular patterns predicted more efficiently than SNN model in case of the prediction in overconsolidated state.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.5769-5777
• /
• 2015

According to the forming or bending deformation in the press die, the thin plate occurs a work-hardening, the sheet hardening and cam unit's deformation causes incomplete forming during the cam molding process by the reacting spring forces. This study treated the input parameters of the stress and strain as given properties and also used Cam forming pressure considering the sheet hardening in the forming process of the aluminum sheet. The Hyperstudy are operated be linked with the Abaqus of the finite element analysis tool and the shape of Cam were carried out with non-linear shape optimization analysis. As a result removing the deformation of plate, the cam shape were optimized under conditions reduced deformation, having a minimum stress range and the minimum deformation. Therefore, a stress-strain curve and a normal distribution of stress-thickness can be obtained and optimization could be obtained for the shape of the stress and strain on the die plate hardened cam considering the thickness and reaction force of gas spring as iteration process.

• Journal of the Korean Society of Radiology
• /
• v.13 no.1
• /
• pp.103-110
• /
• 2019

The objective of this study was to prepare the baseline data for vocational key competence of radiologists by analyzing the communication skills, problem-solving skills, self-development capability, interpersonal skills, and vocational ethics, which are required by NCS job descriptions for radiologists, of college students majoring in radiology. This study surveyed 79 sophomore and junior college students majoring in radiology at S University from Nov 19 to Nov 30, 2018, using questionnaires and analyzed the levels of vocational key competencies. The analysis results of vocational key competences levels showed that the level of interpersonal skills was the highest (71.2 points for juniors and 74.9 points for seniors). The levels of problem-solving skills and self-development capability were low. Conflict management capability, which is a sub-domain of interpersonal skills, was 77.5 and 80.5 points for juniors and seniors, respectively, which were the highest, while leadership ability was the lowest. When the sub-domains of self-development capability were analyzed, self-recognition capability was the highest (70.0 points for juniors and 74.8 points for seniors) and the career development capability was the lowest. Colleges are required to develop a customized regular curriculum that is well-linked to the clinic in order to improve the vocational key competencies required by the NCS job description to prepare for the blind hiring process. Colleges also put efforts to educate radiologists who can actively cope with rapidly changing medical environment by running various non-regular programs.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Journal of The Korean Association For Science Education
• /
• v.26 no.3
• /
• pp.330-341
• /
• 2006

This study investigated whether science museum field trips over a duration of 7 months would effect student preference and awareness of science museums. 32 eighth and ninth graders were sampled from a middle school in Seoul and asked about their preference, awareness and the effect of the science museum visits both before and after a field trip. Findings showed a preference for science museums which dealt with themes and topics of student interest. After a field trip, student responded that science museums were information providers which yielded opportunity to explore forthcoming science feats, science in everyday life, developmental histories of science and technology, science-related news, social issues, and science rationale. Even though science museums in Korea leave much to be desired in terms of quantity and quality, field trips were positively received by students. This reception and its usefulness implied that expansion publizing and active use of formal/informal education relating to science museum facilities need to be top-priority business.