• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.1
• /
• pp.30-36
• /
• 2009

Dedicated Short Range Communication (DSRC) systems in urban areas are used to collect traffic information from vehicles and to provide vehicles with information received from Roadside Equipment (RSE) having a range of 100 meters (m). However, it is not practical to use RSE with a range of 100 m for express highways. In this paper, we expand the standard cell coverage of RSE to 300 m, and adopt fixed relays to cover sites that cannot communicate with the RSE. We demonstrate that the system using the fixed relays is more economical than using only RSE.

• Journal of the Korean Magnetics Society
• /
• v.22 no.2
• /
• pp.45-48
• /
• 2012

Feed-back type 3-axis flux-gate magnetometer using Co-based amorphous ribbon (Metglass$^{(R)}$2714A) was constructed in this work. Measuring range of magnetic field and frequency were ${\pm}100\;{\mu}T$ and dc~10 Hz respectively. For the interface to computer, microcontroller and 24 bit ADC (Analog to Digital Converter) were employed and resolution of digital output was 0.1 nT. Magnetometer noise of analog output was 5 pT/$\sqrt{Hz}$ at 1 Hz. Digital output of the magnetometer showed linearity of $1{\times}10^{-4}$ and the offset drift was smaller than 0.2 nT during 1 h.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.49 no.4
• /
• pp.1-6
• /
• 2012

This paper presents the extraction and analysis of small-signal parameters of tunneling field-effect transistors (TFETs) by using TCAD device simulation. The channel lengths ($L_G$) of the simulated devices varies from 50 nm to 100 nm. The parameter extraction for TFETs have been performed by quasi-static small-signal model of conventional MOSFETs. The small-signal parameters of TFETs with different channel lengths were extracted according to gate bias voltage. The $L_G$-dependency of the effective gate resistance, transconductance, source-drain conductance, and gate capacitance are different with those of conventional MOSFET. The $f_T$ of TFETs is inverely proportional not to $L_G{^2}$ but to $L_G$.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.214-217
• /
• 2015

해상교통안전진단제도의 개정으로 인해 해상교통안전진단의 대상사업이 축소됨에 따라 안전진단대상사업에서 제외된 100미터 미만인 선박의 안전진단 결과 부두의 평면배치가 변경되는 등 안전진단제도의 맹점이 도출되고 있다. 또한 안전진단 시행이전에 사업이 승인되어 공사 작업 중에 공사구간을 운항하는 여객선이 통항시 위험성으로 인해 운항이 중단되고 있다. 홍도 방파제 안전진단에 따른 평면배치의 사례와 솔빛대교의 사례를 통해 특별안전진단의 필요성을 제안한다.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.61-66
• /
• 1992

There have been many researches that uses neural network models for automatic speech recognition, but the main trend was finding the neural network models and learning rules appropriate to automatic speech recognition. However, the choice of the input speech parameter for the neural network as well as neural network model itself is a very important factor for the improvement of performance of the automatic speech recognition system using neural network. In this paper we select 6 speech parameters from surveys of the speech recognition papers which uses neural networks, and analyze the performance for the same data and the same neural network model. We use 8 sets of 9 Korean plosives and 18 sets of 8 Korean vowels. We use recurrent neural network and compare the performance of the 6 speech parameters while the number of nodes is constant. The delta cepstrum of linear predictive coefficients showed best result and the recognition rates are 95.1% for the vowels and 100.0% for plosives.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.169-176
• /
• 2020

Recently, deep neural networks (DNNs) have brought revolutions to many mobile and embedded devices by providing human-level machine intelligence for various applications. However, high inference accuracy of such DNNs comes at high computational costs, and, hence, there have been significant efforts to reduce computational overheads of DNNs either by compressing off-the-shelf models or by designing a new small footprint DNN architecture tailored to resource constrained devices. One notable recent paradigm in designing small footprint DNN models is sharing parameters in several layers. However, in previous approaches, the parameter-sharing techniques have been applied to large deep networks, such as ResNet, that are known to have high redundancy. In this paper, we propose a parameter-sharing method for already parameter-efficient small networks such as ShuffleNetV2. In our approach, small templates are combined with small layer-specific parameters to generate weights. Our experiment results on ImageNet and CIFAR100 datasets show that our approach can reduce the size of parameters by 15%-35% of ShuffleNetV2 while achieving smaller drops in accuracies compared to previous parameter-sharing and pruning approaches. We further show that the proposed approach is efficient in terms of latency and energy consumption on modern embedded devices.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.5
• /
• pp.70-77
• /
• 1999

본 논문에서는 Wavelet을 이용한 위장 영상의 질환 부위 특징을 추출하여 질환 부위 패턴을 인식할 수 있는 알고리즘을 제안하였다. 전처리 과정으로서 위장 영상이 형태정보는 입력 영상을 DWT(Discrete wavelet transform)에 의해 4레벨 DWT 계수 행렬을 구하고 계수 행렬의 특징에 따라 저주파 계수 행렬로부터 저주파 특징 파라미터 32개, 수평 고주파 계수 행렬로부터 수평 고주파 특징 파라미터 16개, 수직 고주파 계수 행렬로부터 수직 고주파 특징 파라미터 16개, 그리고, 대각 고주파 계수 행렬로부터 대각 고주파 특징 파라미터 32개 등 모두 96개의 특징 파라미터를 추출한 후 각각의 특징 파라미터를 최대 값+0.5로 최소 값을 -0.5로 정규화 하여 신경회로망의 입력 벡터로 사용하였다. 위장 영상 패턴 인식을 위한 신경회로망은 교사 학습을 요구하는 다층 구조의 오차 역전파(Error back propagation)알고리즘으로 하였고 구조적 특성을 이용하여 입력층, 중간층, 출력층의 계층 구조로 설계하였다. 설계된 신경회로망의 학습은 학습계수를 0.2로 모우멘텀을 0.6으로 설정하여 출력층 최대오차가 0.01보다 작을 때까지 수행하였으며 약 8000회 정도 학습한 결과 설정값 보다 작은 결과를 얻었고 질환의 종류나 위치, 크기에 관계없이 100%의 인식률을 얻었다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.56-60
• /
• 1999

본 논문은, 자동차에서 발생할 수 있는 다양한 형태의 잡음이 섞인 음성을 대상으로, 잡음에 강인한 파라미터들을 사용하여 인식기들을 구축하였으며, 이들 파라미터를 비교 평가하였다. 실험에 사용된 음성 데이터는 차종, 속도, 도로 환경, 라디오 ON/OFF, 창문 개폐여부 등 다양한 잡음 환경에서 수집하였다. 실험에서 비교된 파라미터는 MFCC(Mel-Blrequency Cepstral Coefficient)와 PLP(Perceptually Linear Prediction) 이며, 각각의 파라미터에 대해서 MKM(Modified k-mean)을 이용하여 코드북을 작성하였고, DHMM(Discrete Hidden Markov Model)을 인식알고리즘으로 사용하였다. 실험 결과로서, 아스팔트 도로에서 창문을 닫고, 라디오를 켜지 않은 상태에서 60km/h로 주행시 $96.25\%$로 가장 높은 인식률을 얻었고, 고속도로에서 창문을 열고 100km/h로 주행시에는$60\%$로 가장 낮은 인식률을 얻었다.

• Journal of Korean Society of Forest Science
• /
• v.100 no.4
• /
• pp.664-671
• /
• 2011

Random Walk Model can predict the sediment areas of debris flow but it must be extracted three parameters fitted topographical environment. This study developed the method to extract the optimal values of three parameters - Once flowing volume, Stopping slope and Gravity weight - for Random Walk Model. And the extracted parameters were validated by aerial photographs of the debris flowed area. To extract the optimal parameters was randomly performed, limiting the range values of three parameters and developing an accuracy decision method that is called the rate of concordance. The set of the optimal parameters was decided on highest the rate of concordance and a consistency. As a result, the optimal parameters in Bonghwa county were showed that the once flowing volume is $1.0m^3$, the stopping slope is $4.2^{\circ}$ and the gravity weight is 2 when the rate of concordance is -0.2. The validating result of the optimal parameters showed closely that the rate of concordance is average -0.2.