• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.4
• /
• pp.109-118
• /
• 2022

The data of the missing section among the vertex surface sea temperature observation data was imputed using the Bidirectional Recurrent Neural Network(BiRNN). Among artificial intelligence techniques, Recurrent Neural Networks (RNNs), which are commonly used for time series data, only estimate in the direction of time flow or in the reverse direction to the missing estimation position, so the estimation performance is poor in the long-term missing section. On the other hand, in this study, estimation performance can be improved even for long-term missing data by estimating in both directions before and after the missing section. Also, by using all available data around the observation point (sea surface temperature, temperature, wind field, atmospheric pressure, humidity), the imputation performance was further improved by estimating the imputation data from these correlations together. For performance verification, a statistical model, Multivariate Imputation by Chained Equations (MICE), a machine learning-based Random Forest model, and an RNN model using Long Short-Term Memory (LSTM) were compared. For imputation of long-term missing for 7 days, the average accuracy of the BiRNN/statistical models is 70.8%/61.2%, respectively, and the average error is 0.28 degrees/0.44 degrees, respectively, so the BiRNN model performs better than other models. By applying a temporal decay factor representing the missing pattern, it is judged that the BiRNN technique has better imputation performance than the existing method as the missing section becomes longer.

• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.177-182
• /
• 2012

We propose effective motion and observation models for the position of a WiFi-equipped smartphone user in large indoor environments. Three component motion models provide better proposal distribution of the pedestrian's motion. Our Gaussian interpolation-based observation model can generate likelihoods at locations for which no calibration data is available. These models being incorporated into the particle filter framework, our WiFi fingerprint-based localization algorithm can track the position of a smartphone user accurately in large indoor environments. Experiments carried with an Android smartphone in a multi-story building illustrate the performance of our WiFi localization algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.31-37
• /
• 2004

Wavelet transform is a useful tool for analysis and process of image. This showed good performance in image compression and noise reduction. Wavelet coefficients can be effectively modeled by hidden Markov tree(HMT) model. However, in application of HMT model to image interpolation, training procedure is needed. Moreover, the parameters obtained from training procedure do not match input image well. In this paper, the structure of HMT is used for image interpolation, and the parameters of HMT are obtained from statistical characteristics across wavelet subbands without training procedure. In the proposed method, wavelet coefficient is modeled as Gaussian mixture model(GMM). In GMM, state transition probabilities are determined from statistical transition characteristic of coefficient across subbands, and the variance of each state is estimated using the property of exponential decay of wavelet coefficient. In simulation, the proposed method shows improvement of performance compared with conventional bicubic method and the method using HMT model with training.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.3
• /
• pp.295-304
• /
• 2008

This paper comprises two specific objectives. The first is to examine the applicability of Ordinary Kriging interpolation(OK) to finite element method that is based on variogram modeling in conjunction with different allowable limits of separation distance. The second is to investigate the accuracy according to theoretical variograms such as polynomial, Gauss, and spherical models. For this purpose, the weighted least square method is applied to obtain the estimated new stress field from the stress data at the Gauss points. The weight factor is determined by experimental and theoretical variograms for interpolation of stress data apart from the conventional interpolation methods that use an equal weight factor. The validity of the proposed approach has been tested by analyzing two numerical examples. It is noted that the numerical results by Gauss model using 25% allowable limit of separation distance show an excellent agreement with theoretical solutions in literature.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.3
• /
• pp.29-41
• /
• 2010

In this study, the prediction errors of various spatial interpolation methods used to model values at unmeasured locations was compared and the accuracy of these predictions was evaluated. The root mean square (RMS) was calculated by processing different parameters associated with spatial interpolation by using techniques such as inverse distance weighting, kriging, local polynomial interpolation and radial basis function to known elevation data of the east coastal area under the same condition. As a result, a circular model of simple kriging reached the smallest RMS value. Prediction map using the multiquadric method of a radial basis function was coincident with the spatial distribution obtained by constructing a triangulated irregular network of the study area through the raster mathematics. In addition, better interpolation results can be obtained by setting the optimal power value provided under the selected condition.

• Journal of Navigation and Port Research
• /
• v.35 no.1
• /
• pp.51-56
• /
• 2011

In this paper, we presents an algorithm which restores lost data or increases resolution of a DTM(Digital terrain model) using fractal theory. Terrain information(fractal dimension and standard deviation) around the patch to be restored is extracted and then with this information and original data, the elevations of cells are interpolated using the random midpoint displacement method. The results of the proposed algorithm are compared with those of the bilinear and bicubic methods on a fractal terrain map.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.16 no.1
• /
• pp.119-132
• /
• 1998

For the purpose of producing of grid D.E.M based on National Digital Map accurately and efficiently, We must carefully consider arrangement and numbers of it's elevation information, supplement interpolation method of control point information for maintaining accuracy. According to each combination, each of them has an effect on estimate elevations. This study, after finishing experimental analysis of several grid distance and interpolation methods, aims at presenting the optimal grid distance and interpolation method in the production of grid D.E.M by using of National Digital Map. The results are as follows: First, The result of experimental analysis shows that the method of Kriging is a very excellent interpolation method in the production of grid D.E. M by using National Digital Map. Second, For the purpose of determining grid distance, this study present that twice of the amount of contour interval to make producing grid D.E.M is optimal distance.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.63-66
• /
• 2011

유연도법 기반의 공식화에서는 변위영역의 형상함수를 라그랑지언(Lagrangian)보간법에 의한 곡률로부터 횡방향 변위를 유도한다. 곡률변위보간법으로 유도한 매트릭스를 사용한 기하학적 비선형 해석방법과 강성도법을 기반으로 한 비선형 기존의 유한요소 해석 프로그램의 결과를 비교하여 적용이 가능함을 확인하였고, Spacone의 이론을 확장시켜 기하학적 비선형 거동을 예측할 수 있는 유연도법의 알고리즘을 제안하였다. 예제를 통하여 실제 문제에 대한 기하학적 비선형 해석을 수행하였다.

• Proceedings of the Korean Society of Applied Pharmacology
• /
• 1993.04a
• /
• pp.97-97
• /
• 1993

본 연구과제에서는 적출판류간실험법 (isolated perfused liver technique)을 약물의 간독성 유발 및 보간작용에 관한 실험법으로 개발하고자 butylated hydroxyanisole (BHA) 을 이용하여 보간실험을 하였다. BHA를 식이투여한 흰쥐로부터 적출한 간에 간독성 모델물질로 2,6-dichlorophenolindophenol (DCPIP) 을 관류시켜 관류액내의 DCPIP의 유리형, 환원형, glucuronide, sulfate 포합체의 대사체를 측정하여 DCPIP 외 대사양상을 관찰하였으며, 동시에 간세포 손상으로 관류액내로 유출된 lactate dehydrogenase (LDH)의 활성도를 측정하여 DCPIP예 의할 간세포독성 유발정도를 간접적으로 측정하여 대조군과 비교하였다. 그리고 BHA에 의한 보간작용이 약물대사효소의 변와에 기인한 것인가를 관찰하기 위하여 모델약물로 7-ethoxycoumarin (EC) 이나 EC의 phase I 대사산물인 7-hydroxycoumarin (HC) 을 관류시켜 관류액내의 HC의 유리체, glucuronide 포합체, sulfate 포합체로의 대사량을 측정하여 약물대사시 약물의 활성화에 관계하는 phase I mixed function oxidase (MFO) 효소와 약물의 해독화에 관계하는 phase II 포합효소 (UDP-glucuronyltranesferase(UDPGT)와 sulfotransferase (ST))의 활성도 변화를 측정하여 대조군과 비교하였다. 간독성 모델물질인 DCPIP를 적출한 흰쥐의 간에 관규시켰을때 BHA 전처리군이 LDH가 유출되기 시작하는 시간이 대조군에 비하여 유의적으로 늦었으며, LCH가 유출량도 유의적으로 감소되어 DCPIP에 의한 간독성 유발능력이 BHA에 의하여 감소됨을 관찰하였다. 아울러 DCPIP의 대사체중 환원체와 glucuronide 포합체의 생성량이 증가되어 BHA에 의하여 quinone reductase와 UDPGT 활성도가 증가되었음을 알 수 있었다. 그리고 BHA 전처리에 의하여 MFO효소계와 ST의 활성도에는 변화가 없었으나 UDOGT 의 활성도는 약 2.2배 증가되었다. 이상의 결과로 BHA에 의한 보간작용은 간독성 물질을 활성화시키는 phase I MFO 효소의 활성도에는 변화없이 해독작용에 관여하는 phase II효소들의 활성도 증가에 기인된 것을 알 수 있었다. 그리고 이러한 결과는 적출한 관류간실험법은 여러 약물의 보간효과를 관찰하는 실험법으로 적합할 것으로 사료되었다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.