• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.522-526
• /
• 2018

본 연구는 수많은 챗봇이 생성될 수 있는 챗봇 빌더 시스템에서 저비용 컴퓨팅 파워에서도 구동 가능한 가벼운 문장 분류 시스템을 제안하며, 미등록어 처리를 위해 워드 임베딩 기법인 GloVe를 이용하여 문장 벡터를 생성하고 이를 추가 자질로 사용하는 방법을 소개한다. 제안한 방법으로 자체 구축한 테스트 말뭉치를 이용하여 성능을 평가해본 결과 최대 93.06% 성능을 보였으며, 자체 보유한 CNN 모델과의 비교 평가 결과 성능은 2.5% 낮지만, 모델 학습 속도는 25배, 학습 시 메모리 사용량은 6배, 생성된 모델 파일 크기는 302배나 효율성 있음을 보였다.

• JOURNAL OF ELECTRICAL WORLD
• /
• s.241
• /
• pp.81-86
• /
• 1997

자동차의 배출가스가 가져오는 대기오염문제로 배출하지 않는 장점이 있는 전기자동차의 도입이 계획되고 있는 한편, 세계의 자동차관련메이커들은 꾸준히 개발$\cdot$개량을 추진하고 있다. 그 기술은 착실하게 진전되어 근거리역내에서의 교통수단으로서는 실용역에 이르고 있으며 앞으로 실용화를 위한 시험이 본격화될 것으로 보인다. 삼릉전기(주)에서는 보다 고성능의 전기자동차의 실용화를 위하여 유도전동기와 선진 구동제어 기술의 연구$\cdot$개발에 진력하여 유도전동기와 선진 구동제어기술을 조합한 구동시스템을 개발하였다. 유도전동기는 고속화, 냉각의 수냉화, 스테이터절연의 고내열화, 저손실코어재의 적용 등으로 소형$\cdot$경량화를 기하였다. 컨트롤러는 인버터의 파워소자에 구동$\cdot$보호회로를 내장한 IPM(Intelligent Power Module)을 채용하고 유도모터의 고효율화와 토크제어의 고응답$\cdot$고정도화를 양립시킨 고효율$\cdot$고응답벡터제어를 적용하였다. 또한 속도센서의 생략으로 코스트저감과 신뢰성의 향상을 위한 속도센서레스제어의 적용을 검토하고 있다. 이상으로 소형$\cdot$경량$\cdot$고효율$\cdot$저코스트를 조화시킨 고성능의 전기자동차구동시스템을 실현하였다.

• Journal of Korean Ophthalmic Optics Society
• /
• v.20 no.2
• /
• pp.187-193
• /
• 2015

Purpose: This study was aimed to investigate effects of increased breath alcohol concentration (BrAC) which is the standard measurement of alcohol consumption in sobriety test under current laws on visual acuity and values of objective refraction. Methods: For twenty three males in 20s (average age $21.17{\pm}2.19$ years, body mass index (BMI) $22.09{\pm}2.16$) were selected. Distance and near visual test was performed at BrAC of 0%, 0.05% and 0.08%, and objective refraction with open-field auto-refractometer was also performed at different BrAC. Results: As breath alcohol concentration is increased, distance visual acuity was decreased, which was statistically significant, but near visual acuity was not changed. Also, values of objective refraction tended to be increased towards minus as breath alcohol concentration is increased. Conclusions: As breath alcohol concentration is increased, corrected visual acuity is decreased and refractive power is towards minus, it is necessary that visual acuity test and refraction measurement should be conducted under sober condition.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.102-109
• /
• 2016

This paper proposes a noise suppression method through SNR (Singal-to Noise Ratio) estimation in the two microphone array environment of close spacing. The conventional method uses a noise suppression method for a gain function obtained through the SNR estimation based on coherence function from full band. However, this method cause performance decreased by the noise damage that affects all the feature vector component. So, we propose a noise suppression method that allocates a frequency domain signal into N constant multi frequency band and each frequency band gets a gain function through SNR estimation based on coherence function. Performance evaluation of the proposed method is shown by comparison with PESQ (Perceptual Evaluation of Speech Quality) value which is an objective quality evaluation method provided by the ITU-T (International Telecommunications Union Telecommunication).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1037-1044
• /
• 2020

Since radar wind profiler (RWP) provides wind field data with high time and space resolution in all weather conditions, their verification of the accuracy and quality is essential. The simultaneous wind measurement from rawinsonde is commonly used to evaluate wind vectors from RWP. In this study, the simulation algorithm which produces the spectrum and raw time series (I/Q) data from the average values of moments is presented as a step-by-step verification method for the signal processing algorithm. The possibility of the simulation algorithm was also confirmed through comparison with the raw data of LAP-3000. The Doppler power spectrum was generated by assuming the density function of the skew-normal distribution and by using the moment values as the parameter. The simulated spectrum was generated through random numbers. In addition, the coherent averaged I/Q data was generated by random phase and inverse discrete Fourier transform, and raw I/Q data was generated through the Dirichlet distribution.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6A
• /
• pp.450-457
• /
• 2012

For orthogonal frequency-division multiplexing (OFDM) systems, we propose a blind channel estimation scheme based on non-redundant precoding. In the proposed scheme, a modified covariance matrix is first obtained by dividing the covariance matrix of the received signal vector by the precoding matrix element-by-element. Then, the channel vector is estimated as an eigenvector corresponding to the largest eigenvalue of the modified covariance matrix. The eigenvector can be obtained by power method with low computational complexity instead of the complicated eigenvalue decomposition. We analytically derive a mean square error (MSE) of the proposed channel estimation scheme and show that the analysis result coincides well with the simulation result. Also, simulation results show that the proposed scheme has better MSE and bit error rate (BER) performance than conventional channel estimation schemes.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.3
• /
• pp.155-162
• /
• 2014

Using an isogeometric approach, a continuum-based shape design optimization method is developed for steady state power flow problems at high frequencies. In case the isogeometric method is employed to the shape design optimization, the NURBS basis functions used in CAD geometric modeling are directly utilized to embed the exact geometry into the computational framework so that the design parameterization for shape optimization is much easier than that in the finite element method and consequently provides the enhanced smoothness of design perturbations. Thus, exact geometric models can be used in both the response and the shape sensitivity analyses, where normal vector and curvature are continuous over the whole design space so that enhanced shape sensitivity can be expected. Through numerical examples, the developed isogeometric sensitivity is compared with finite difference one to provide excellent agreement. Also, it turns out that the proposed method works very well in the shape optimization problems.

• Journal of KSNVE
• /
• v.9 no.4
• /
• pp.769-777
• /
• 1999

Research on vibration of a vehicle with a transversely mounted 4-cylinder engine was performed using a vector synthesis method, Data of the engine vibration for the vector synthesis method was obtained experimentally and the data was ODS-fitted to calculate vibration level on any engine location assuming that the engine is rigid body in the frequency range of interest. In order to derive the excitation force on the vehicle body, the displacements were converted from the acceleration of engine. The transfer functions from engine mounts to toe pan on the floor were obtained experimentally. The vibration level on the toe pan was predicted by multiplying the excitation force by the transfer function. The predicted vibration level was compared with experimental data and the result was reasonable. Using the developed method, analysis was made for the effect of body fixture conditions of the vehicle when testing the engine vibration and for the effect of the transfer functions when the engine is installed or when the engine is removed. Finally the degree of contribution for 12 transfer paths was calculated.

• Journal of Internet Computing and Services
• /
• v.3 no.4
• /
• pp.27-36
• /
• 2002

The purpose of this study is to develop editor applied to vector image for the distance learning system(FVU), which enables teachers effectively to construct self-page on the screen, to reduce the size of file for teaching, and to correct many different kinds of event which was already made in the previous, The design of the editor is used UML and the editor is named VUEditor. The first page which is needed in class can be constructed by using VUEditor. The contents using VUEditor ore exported into VUAuthor through Vector-transformation. Through this procedure, the size of image file comes to be reduced, it has a low bond width. In conclusion, this VUEditor enables user to construct the first page. even without using such applied program as Image Tool and Power Point, to solve the problem of network traffic for reducing size of the file.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1050-1057
• /
• 2014

Electroencephalogram (EEG)-based brain-computer interfaces (BCI) can be used for a number of purposes in a variety of industries, such as to replace body parts like hands and feet or to improve user convenience. In this paper, we propose a method to decompose and extract motor imagery EEG signal using Empirical Mode Decomposition (EMD) and Fast Fourier Transforms (FFT). The EEG signal classification consists of the following three steps. First, during signal decomposition, the EMD is used to generate Intrinsic Mode Functions (IMFs) from the EEG signal. Then during feature extraction, the power spectral density (PSD) is used to identify the frequency band of the IMFs generated. The FFT is used to extract the features for motor imagery from an IMF that includes mu rhythm. Finally, during classification, the Support Vector Machine (SVM) is used to classify the features of the motor imagery EEG signal. 10-fold cross-validation was then used to estimate the generalization capability of the given classifier., and the results show that the proposed method has an accuracy of 84.50% which is higher than that of other methods.