• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.04a
• /
• pp.412-420
• /
• 1993

플라스틱(수지)의 활용이 급격하게 증가함에 따라 사출성형의 중요성이 높아지고 있는 가운데, 사출성형시의 원가절감이 큰 관심사가 되어가고 있다. 원가절감의 일환으로 적절한 수지를 선정하는 일이 대두되는데, 사출성형의 재료로서 수지를 선정할 때는 성형후 사용환경에서 일정기능을 유지하도록 수지의 물성을 고려하여야 한다. 본 연구에서는 여러물성을 동시에 만족시켜야 하는 수지선정의 특수성을 감안하여 수지선정문제를 가치함수(Value Function)를 사용한 다목적 의사결정문제(Multi-Attribute Decision Problem)로 정형화하였다. 수지는 물성의 어느 범위에서는 수치의 작은차이가 중요하지만, 어느 범위에서는 크게 중요하지 않으므로 필요한 물성의 수준을 고려하여 선택을 하여야한다. 본 연구에서는 가치함수를 이용하여 이를 해결하도록 하였다. 가치함수는 Sigmoid함수를 사용하였고, 함수의 상수(parameter)를 조절하여 수지가 갖는 물성과 물성과의 관계를 평가하고 수지가 갖는 특성을 보다 정확하게 고려하여 수지선정이 되도록 하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.67-70
• /
• 1998

본 논문에서는 단어독립 음성인식 시스템을 위한 음성인식 거절(rejection)기능에 대해 기술한다. 음성인식 거절 기능은 음성인식기를 제작할 때 정해놓은 인식대상 단어 이외의 단어가 입력되었을 때 그 단어가 인식할 수 없는 단어임을 알려주는 기능이다. 본 연구에서는 단어독립 음성인식 시스템에 적용될 수 있는 발화 검증 방식에 의해 음성인식 거절 기능을 구현하였다. 특히 유사도를 결정함에 있어서 산술평균, 기하평균, 조화평균을 사용하고 각각을 비교하여, 기하 평균을 사용하는 방식이 우수한 성능을 보임을 알 수 있었다. 음성의 신뢰도(confidence score)를 정규화하기 위해서 Sigmoid 함수를 사용하는데 이 함수의 가중치(weight) 상수의 변화에 대해 인식률을 비교함으로써 가장 적절한 가중치 상수값을 결정하였다. 음성인식 테스트 결과에서는 신뢰도 임계치 값을 구하고 이 값을 사용하여 인식률을 계산하였으며, 거절의 오류까지 포함된 음성인식률은 약 76%였다. 이 연구결과는 현재 한국통신에서 시험 서비스 중인 음성인식 증권정보 안내 시스템에 적용될 예정이다.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.291-295
• /
• 2016

본 논문에서는 한국어 기본 유니트 단위로 WPM을 활용한 구글 플레이 스토어 앱의 댓글 감정분석을 수행하였다. 먼저 자동 띄어쓰기 시스템을 적용한 후, 어절단위, 형태소 분석기, WPM을 각각 적용하여 모델을 생성하고, 로지스틱 회귀(Logistic Regression), 소프트맥스 회귀(Softmax Regression), 서포트 벡터머신(Support Vector Machine, SVM)등의 알고리즘을 이용하여 댓글 감정(긍정과 부정)을 비교 분석하였다. 그 결과 어절단위, 형태소 분석기보다 WPM이 최대 25%의 향상된 결과를 얻었다. 또한 분류 과정에서 로지스틱회귀, 소프트맥스 회귀보다는 SVM 성능이 우수했으며, SVM의 기본 파라미터({'kernel':('linear'), 'c':[4]})보다 최적의 파라미터를 적용({'kernel': ('linear','rbf', 'sigmoid', 'poly'), 'C':[0.01, 0.1, 1.4.5]} 하였을 때, 최대 91%의 성능이 나타났다.

• Advances in aircraft and spacecraft science
• /
• v.7 no.4
• /
• pp.335-351
• /
• 2020

Thermal buckling of functionally graded sandwich cylindrical shells is presented in this study. Material properties and thermal expansion coefficient of FGM layers are assumed to vary continuously through the thickness according to a sigmoid function and simple power-law distribution in terms of the volume fractions of the constituents. Equilibrium and stability equations of FGM sandwich cylindrical shells with simply supported boundary conditions are derived according to the Donnell theory. The influences of cylindrical shell geometry and the gradient index on the critical buckling temperature of several kinds of FGM sandwich cylindrical shells are investigated. The thermal loads are assumed to be uniform, linear and nonlinear distribution across the thickness direction. An exact simple form of nonlinear temperature rise through its thickness taking into account the thermal conductivity and the inhomogeneity parameter is presented.

• Journal of Korean Neurosurgical Society
• /
• v.42 no.3
• /
• pp.232-234
• /
• 2007

We describe the extrusion of a ventriculoperitoneal shunt catheter from the anus after double perforation of the large bowel in a 3-year-old girl with hydrocephalus. She was admitted because the tip of the peritoneal catheter protruded 10 cm from the anus and clear cerebrospinal fluid dripped from the tip. Emergency laparotomy was performed. The distal peritoneal catheter perforated and penetrated the sigmoid colon and re-perforated into the rectal cavity. The distal peritoneal catheter was removed, the proximal catheter was exposed for external drainage, and intravenous broad-spectrum antibiotics were administered for 2 weeks. After control of infection, the shunt system was completely removed. Bowel perforation by a peritoneal catheter is a rare complication. Diagnosis is often difficult, delayed, and its incidence is likely underestimated. Most bowel perforation is the result of infection as opposed to technical errors.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.8
• /
• pp.856-867
• /
• 1990

In this paper, the convergence and the learning accuracy of the back-propagation (BP) method in neural network are investigated by 1) analyzing the reason for decelerating the convergence of BP method and examining the rapid deceleration of the convergence when the learning is executed on the part of sigmoid activation function with the very small first derivative and 2) proposing the modified logistic activation function by defining, the convergence factor based on the analysis. Learning on the output patterns of binary as well as analog forms are tested by the proposed method. In binary output patter, the test results show that the convergence is accelerated and the learning accuracy is improved, and the weights and thresholds are converged so that the stability of neural network can be enhanced. In analog output patter, the results show that with extensive initial transient phenomena the learning error is decreased according to the convergence factor, subsequently the learning accuracy is enhanced.

• Journal of Korean Neurosurgical Society
• /
• v.50 no.3
• /
• pp.260-263
• /
• 2011

Intracranial dural arteriovenous fistulas (DAVFs) are abnormal arteriovenous connections that lie within the dura. Intraosseous DAVFs involving diploic venous system are extremely rare. A 46-year-old woman presented with headache and right pulsatile tinnitus for three weeks. The tinnitus started after yelling. Digital subtraction angiography revealed DAVF within the basal portion of right parietal bone along the middle meningeal artery (MMA) groove. The fistula was fed by frontal branch of right MMA and drained into right transverse sigmoid sinus junction through dilated middle meningeal vein. The intraosseous DAVF involving diploic vein was successfully obliterated with Onyx embolization via transarterial route.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.742-745
• /
• 1994

In this paper we show the performance of neural Chandrasekhar filtering which is a special case for the new method of neural filtering using the artificial neural network systems developed recently for the filtering problems of linear and nonlinear, stationary and nonstationary stochastic signals. The neurofilter developed has either the finite impulse response(FIR) structure or the infinite impulse response(IIR) structure. The neurofilter differs from the conventional linear digital FIR and IIR filters because the artificial neural network system used in the neurofilter has nonlinear structure due to the sigmoid function. Numerical studies for the estimation of a second order Butterworth process are performed by changing the structures of the neurofilter in order to evaluate the performance indices under the changes of the output noises or disturbances. In the numerical studies both Chandrasekhar filtering estimates and true signals are used as the training signals for the neurofilter. The results obtained from the studies verified the capabilities which are essentially necessary for on-line filtering of various stochastic signals.

• International Journal of Internet, Broadcasting and Communication
• /
• v.5 no.2
• /
• pp.5-10
• /
• 2013

We proposed a novel similarity measure using weighted difference entropy (WDE) to improve the performance of the CF system. The proposed similarity metric evaluates the entropy with a preference score difference between the common rated items of two users, and normalizes it based on the Gaussian, tanh and sigmoid function. We showed significant improvement of experimental results and environments. These experiments involved changing the number of nearest neighborhoods, and we presented experimental results for two data sets with different characteristics, and results for the quality of recommendation.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.145-156
• /
• 2007

The performance of speaker identification is severely degraded in noisy environments. Recently probability weighting method based on observation membership was proposed for overcoming the noise problem[1]. In the paper[1] the observation confidence was calculated from SNR with sigmoid function. However, estimating SNR needs additive calculation amount and estimated SNR is corrupted in dynamic noisy environments. In this paper we propose estimation methods of the observation confidence based on score-based reliabilities (SBR) of entropy and dispersion measures. Generally SBRs are obtained from speaker models' probabilities. The proposed methods are evaluated with ETRI speaker recognition DB. We compared the performances of the proposed methods with those in [1][8]. The experimental results show that the proposed methods can be successfully applied for the case where SNR is not available.