• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2002년도 춘계학술대회 논문집
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• 비파괴검사학회지
• /
• 제34권1호
• /
• pp.1-9
• /
• 2014

A two-dimensional numerical model based on the finite element method was built to simulate the wave propagation phenomena that occur during the ultrasonic time of flight diffraction (TOFD) process. First, longitudinal-wave TOFD was simulated, and the numerical results agreed well with the theoretical results. Shear-wave TOFD was also investigated because shear waves have higher intensity and resolution. The shear wave propagation was studied using three models with different boundary conditions, and the tip-diffracted shear-to-longitudinal wave was extracted from the A-scan signal difference between the cracked and non-cracked specimens. This signal showed very good agreement between the geometrical and numerical arrival times. The results of this study not only provide better understanding of the diffraction phenomena in TOFD, but also prove the potential of shear-wave TOFD for practical application.

• 전자공학회논문지T
• /
• 제35T권1호
• /
• pp.111-119
• /
• 1998

안테나 방사패턴의 전파환경을 예측하는 것은 최적 기지국 위치 선정과 셀의 설계 등 서비스 지역을 결정하는데 매우 중요하다. 안테나 종류, 빔의 각도, 지형과 장애물에 따라 변하는 전파 예측 모델을 분석하므로써 통신망의 경제적 활동, 호의 품질, 전화가입자에 대한 서비스 향상을 기대할 수 있다. 최적 전파 예측 모델을 제안하기 위하여 나주시 세지 기지국 주변의 평원지역의 전계강도를 측정하였다. 현장측정에 대한 시뮬레이션은 Hata 모델, Egri 모델, Carey 모델과 제안 모델을 이용하였다. 그 결과 제안 모델이 다른 모델보다 우수함을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.249-268
• /
• 2014

Relevance feedback is an effective tool to bridge the gap between superficial image contents and medically-relevant sense in content-based medical image retrieval. In this paper, we propose an interactive medical image search framework based on pairwise constraint propagation. The basic idea is to obtain pairwise constraints from user feedback and propagate them to the entire image set to reconstruct the similarity matrix, and then rank medical images on this new manifold. In contrast to most of the algorithms that only concern manifold structure, the proposed method integrates pairwise constraint information in a feedback procedure and resolves the small sample size and the asymmetrical training typically in relevance feedback. We also introduce a long-term feedback strategy for our retrieval tasks. Experiments on two medical image datasets indicate the proposed approach can significantly improve the performance of medical image retrieval. The experiments also indicate that the proposed approach outperforms previous relevance feedback models.

• 한국소음진동공학회논문집
• /
• 제14권3호
• /
• pp.175-184
• /
• 2004

Ground-borne noise and vibration generated by underground transit system has been recognized as an important environmental problem. This study reviews several of the procedures that have been used to predict ground-borne vibration. The vibration responses are measured at three sites that have different soil qualities. The measured vibration levels are compared with the predicted results by previously used vibration level prediction models. There are some drawbacks to apply these prediction models to selected sites because most of the existing prediction models are primarily based on empirical data and all of them lack of analytical models for the mechanism of ground-borne vibration generation. radiation, and propagation. In this study a numerical method, which is based on explicit differential method, is used to compensate for the shortcomings of existing prediction models. Although numerically computed results are not quantitatively in good agreement with the measured results, the trends are comparable in the sense that vibration level does not decrease monotonically with distance. Also, the site with the deepest tunnel gives the highest vibration level.

• Computers and Concrete
• /
• 제20권6호
• /
• pp.627-634
• /
• 2017

Predicting the compressive strength of concrete is important to assess the load-carrying capacity of a structure. However, the use of blended cements to accrue the technical, economic and environmental benefits has increased the complexity of prediction models. Artificial Neural Networks (ANNs) have been used for predicting the compressive strength of ordinary Portland cement concrete, i.e., concrete produced without the addition of supplementary cementing materials. In this study, models to predict the compressive strength of blended cement concrete prepared with a natural pozzolan were developed using regression models and single- and 2-phase learning ANNs. Back-propagation (BP), Levenberg-Marquardt (LM) and Conjugate Gradient Descent (CGD) methods were used for training the ANNs. A 2-phase learning algorithm is proposed for the first time in this study for predictive modeling of the compressive strength of blended cement concrete. The output of these predictive models indicates that the use of a 2-phase learning algorithm will provide better results than the linear regression model or the traditional single-phase ANN models.

• Journal of Information Technology Applications and Management
• /
• 제19권1호
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• 한국전자파학회지:전자파기술
• /
• 제6권3호
• /
• pp.15-23
• /
• 1995

이동통신에서는 안테나의 높이가 낮기 때문에 송신된 전파가 빌딩과 나무, 지형굴곡에 의해 반사, 회절되어 다경로를 통해 수신되므로 진폭과 주기가 시간적으로 매우 급격히 변하게 된다. 이러한 전파의 불규칙성으로 인해 세계 각국에서는 이의 특성을 이론적으로 해석하기 보다는 많은 실험을 통해 얻어진 데이타를 이용하여 전계강도를 예측하고 있다. 본 논문에서는 국내 지형에서 전파가 나타내는 특성을 파악하기 위하여 국내 지형 을 그것이 포함하고 있는 지형 및 지물, 도로상태 둥의 특성에 따라 대도시, 중소도시, 시외지역 그리고 산악지 역의 네 종류로 분류하고 각각의 특성을 갖는 국내지역을 선정하여 무선호출 주파수 대역에서 이의 전계강도 측정을 수행하였으며, 본 측정치를 가지고 국내 환경에서의 전파특성을 검토하였으며 이를 외국의 Hata와 $\pi$REM 전파예측 모텔과 비교 분석하였다

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2000년도 춘계 학술발표회 논문집 Proceedings of EESK Conference-Spring
• /
• pp.451-457
• /
• 2000

In many dynamic problems such as foundation vibrations ultrasonic nondestructive evaluation and blasting analysts are confronted with the problem of wave propagation in an infinite or semi-infinite media. In order to simulate this situation by a finite analytical model provisions must be made to absorb the stress waves arriving at the boundary. Absorbing boundaries are mathematical artifacts used to prevent wave reflections at the boundaries of discrete models for infinite media under dynamic loads. An analytical study is carried out to examine the effectiveness of Lysmer-Kuhlemeyer model one of the most widely used absorbing boundaries. Validity of the absorbing boundary conditions suggested by Lymer-Kuhlemeyer is examined by adopting the solution of Ewing et al. to the problem of plane waves from a harmonic normal force on the surface of an elastic half-space. The Ewing's problem is than numerically simulated using the finite element method on a semi-circular mesh with and without absorbing boundaries which are represented by viscous dashpots. The absorption ratios are calculated by comparing the displacements at the absorbing boundaries to those at the free field without absorbing boudaries.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2003년도 봄 학술발표회 논문집
• /
• pp.697-700
• /
• 2003

The SASW method is a promising and effective way of profiling ground stiffness nondestructively. This method has been successfully applied to many geotechnical sites, but significant lateral variability, embedded obstacles, and pavement lead to the low reliability. To improve these problems, the horizontal wave component has been introduced to improve the reliability of the stiffness profile determined by the SASW method. To understand dispersion character of the horizontal component wave propagation in artificial profiles, FEM analysis had been performed. Used models are homogeneous half-space and two layered half- spaced layers.