• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.649-654
• /
• 2005

In this paper, we describe an implementation of real-time face recognition system under ubiquitous computing environments. First, face image is captured by PDA with CMOS camera and then this image with user n and name is transmitted via WLAN(Wireless LAN) to the server and finally PDA receives verification result from the server The proposed system consists of server and client parts. Server uses PCA and LDA algorithm which calculates eigenvector and eigenvalue matrices using the face images from the PDA at enrollment process. And then, it sends recognition result using Euclidean distance at verification process. Here, captured image is first compressed by the wave- let transform and sent as JPG format for real-time processing. Implemented system makes an improvement of the speed and performance by comparing Euclidean distance with previously calculated eigenvector and eignevalue matrices in the learning process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.8
• /
• pp.1596-1603
• /
• 2007

In this paper, we experimented by three kind of method for feature parameter, training method and recognition algorithm of most suitable for speech recognition system and considered. We decided speech recognition system of most suitable through two kind of experiment after we make speech recognizer. First, we did an experiment about three kind of feature parameter to evaluate recognition performance of it in speech recognizer using existent MFCC and MFCC new feature parameter that change characteristic space using PCA and ICA. Second, we experimented recognition performance or HMM, SVM and RVM by studying data number. By an experiment until now, feature parameter by ICA showed performance improvement of average 1.5% than MFCC by high linear discrimination from characteristic space. RVM showed performance improvement of maximum 3.25% than HMM in an experiment by decrease of studying data. As such result, effective method for speech recognition system to propose in this paper derives feature parameters using ICA and un recognition using RVM.

• Korean Journal of Remote Sensing
• /
• v.26 no.2
• /
• pp.143-151
• /
• 2010

We carried out studies on InSAR techniques for time-series deformation monitoring using multi-temporal SAR. The PSInSAR method using permanent scatterer is much more complicate than the SBAS because it includes many non-linear equation due to the input of wrapped phase. It is conformed the PS algorithm is very sensitive to even PSC selection. On the other hand, the SBAS method using interferogram of small baseline subset is simple but sensitive to the accuracy of unwrapped phase. The SBAS is better method for expecting not significant unwrapping error while PSInSAR is more proper method for expecting local deformation within very limited area. We used 51 ERS-1/2 SAR data during 1992-2000 over Las Vegas, USA for the comparison between PSInSAR and SBAS. Both PSInSAR and SBAS show similar ground deformation value although local deformation seems to be detected in the PSInSAR method only.

• Korean Journal of Remote Sensing
• /
• v.23 no.3
• /
• pp.161-169
• /
• 2007

A study was conducted in the Hong Kong with the aim of deriving an algorithm for the retrieval of suspended sediment (SS) and sea surface salinity (SSS) concentrations from Aqua/MODIS level 1B reflectance data with 250m and 500m spatial resolutions. 'In-situ' measurements of SS and SSS were also compared with coincident MODIS spectral reflectance measurements over the ocean surface. This is the first study of SSS modeling in Southeast Asia using earth observation satellite images. Three analysis techniques such as multiple regression, linear regression, and principal component analysis (PCA) were performed on the MODIS data and the 'in-situ' measurement datasets of the SS and SSS. Correlation coefficients by each analysis method shows that the best correlation results are multiple regression from the 500m spatial resolution MODIS images, $R^2$= 0.82 for SS and $R^2$ = 0.81 for SSS. The Root Mean Square Error (RMSE) between satellite and 'in-situ' data are 0.92mg/L for SS and 1.63psu for SSS, respectively. These suggest that 500m spatial resolution MODIS data are suitable for water quality modeling in the study area. Furthermore, the application of these models to MODIS images of the Hong Kong and Pearl River Delta (PRO) Region are able to accurately reproduce the spatial distribution map of the high turbidity with realistic SS concentrations.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.107-117
• /
• 1999

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.

• Journal of Korea Water Resources Association
• /
• v.52 no.10
• /
• pp.707-718
• /
• 2019

The optimal water allocation pursues a reliable and economic supply of water resources to meet various interests in socio-economic-environmental aspects. The global water shortage has intensified due to climate change and population growth with limited water resources. Thus, the water management scheme has shifted to improve water use efficiency by proper demand management and water allocation planning. Here, a hydro-economic water allocation model, called WAMM (Water Allocation and Management Model) is introduced. The WAMM is equipped with an improved linear programming algorithm for optimal water allocation and estimates economic value of water supply as an objective of water

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

• Smart Structures and Systems
• /
• v.13 no.2
• /
• pp.257-280
• /
• 2014

In this paper, a novel PARAllel FACtor (PARAFAC) decomposition based Blind Source Separation (BSS) algorithm is proposed for modal identification of structures equipped with tuned mass dampers. Tuned mass dampers (TMDs) are extremely effective vibration absorbers in tall flexible structures, but prone to get de-tuned due to accidental changes in structural properties, alteration in operating conditions, and incorrect design forecasts. Presence of closely spaced modes in structures coupled with TMDs renders output-only modal identification difficult. Over the last decade, second-order BSS algorithms have shown significant promise in the area of ambient modal identification. These methods employ joint diagonalization of covariance matrices of measurements to estimate the mixing matrix (mode shape coefficients) and sources (modal responses). Recently, PARAFAC BSS model has evolved as a powerful multi-linear algebra tool for decomposing an $n^{th}$ order tensor into a number of rank-1 tensors. This method is utilized in the context of modal identification in the present study. Covariance matrices of measurements at several lags are used to form a $3^{rd}$ order tensor and then PARAFAC decomposition is employed to obtain the desired number of components, comprising of modal responses and the mixing matrix. The strong uniqueness properties of PARAFAC models enable direct source separation with fine spectral resolution even in cases where the number of sensor observations is less compared to the number of target modes, i.e., the underdetermined case. This capability is exploited to separate closely spaced modes of the TMDs using partial measurements, and subsequently to estimate modal parameters. The proposed method is validated using extensive numerical studies comprising of multi-degree-of-freedom simulation models equipped with TMDs, as well as with an experimental set-up.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.37-45
• /
• 2020

The development process of deep learning is an iterative task that requires a lot of manual work. Among the steps in the development process, pre-processing of learning data is a very costly task, and is a step that significantly affects the learning results. In the early days of AI's algorithm research, learning data in the form of public DB provided mainly by data scientists were used. The learning data collected in the real environment is mostly the operational data of the sensors and inevitably contains various noises. Accordingly, various data cleaning frameworks and methods for removing noises have been studied. In this paper, we proposed a method for detecting and removing noises from time-series data, such as sensor data, that can occur in the IoT environment. In this method, the linear regression method is used so that the system repeatedly finds noises and provides data that can replace them to clean the learning data. In order to verify the effectiveness of the proposed method, a simulation method was proposed, and a method of determining factors for obtaining optimal cleaning results was proposed.

• Structural Engineering and Mechanics
• /
• v.68 no.5
• /
• pp.563-573
• /
• 2018

Temperature-induced responses, such as strains and displacements, are related to the boundary conditions. Therefore, it is required to determine the boundary conditions to establish a reliable bridge model for temperature-induced responses analysis. Particularly, bridge bearings usually present nonlinear behavior with an increase in load, and the nonlinear boundary conditions cause significant effect on temperature-induced responses. In this paper, the bridge nonlinear boundary conditions were simulated as bilinear translational or rotational springs, and the boundary parameters of the bilinear springs were identified based on the measured temperature-induced responses. First of all, the temperature-induced responses of a simply support beam with nonlinear translational and rotational springs subjected to various temperature loads were analyzed. The simulated temperature-induced strains and displacements were assumed as measured data. To identify the nonlinear translational and rotational boundary parameters of the bridge, the objective function based on the temperature-induced responses is then created, and the nonlinear boundary parameters were further identified by using the nonlinear least squares optimization algorithm. Then, a beam structure with nonlinear translational and rotational springs was simulated as a numerical example, and the nonlinear boundary parameters were identified based on the proposed method. The numerical results show that the proposed method can effectively identify the parameters of the nonlinear boundary conditions. Finally, the boundary parameters of a real arch bridge were identified based on the measured strain data and the proposed method. Since the bearings of the real bridge do not perform nonlinear behavior, only the linear boundary parameters of the bridge model were identified. Based on the bridge model and the identified boundary conditions, the temperature-induced strains were recalculated to compare with the measured strain data. The recalculated temperature-induced strains are in a good agreement with the real measured data.