• Journal of the Korean Society of Visualization
• /
• v.19 no.3
• /
• pp.22-30
• /
• 2021

Ventilated cavity shapes by varying angle of attack of a circular cavitator were predicted based on Logvinovich's Independence Principle in order to verify the cavity shape prediction method. The prediction results were compared with model experiments conducted in the high-speed cavitation tunnel. In the prediction of the cavity centerline, the movement of the cavity centerline due to the effect of gravity and cavitator's angle of attack were well predicted. In the prediction of the cavity contour, it was found that the cavity edge prediction error increased as the angle of attack increased. The error of the upper cavity contour was small at the positive angle of attack, and the error of the lower cavity contour was small at the negative angle of attack.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.10
• /
• pp.45-52
• /
• 2004

This Paper presents a modified hard decision Viterbi decoder with an error prediction circuit enhancing performance for the burst error inputs. Viterbi decoder employs the maximum likelihood decoding algorithm which shows excellent error correction capability for the random error inputs. Viterbi decoders, however, suffer poor error correction performance for the burst error inputs under the fading channel. The proposed error prediction algorithm increases error correction capability for the burst errors. The algorithm estimaties the burst error data area using the maximum path metric for the erroneous inputs, It calculates burst error intervals based on increases in the maximum values of a path metric. The proposed decoder keeps a performance the same as the conventional decoders on AWGN channels for the IEEE802.l1a WLAN system. It shows performance inproving 15% on the burst error of multi-path fading channels, widely used in mobile systems.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1439-1448
• /
• 2022

Background: We investigated the feasibility of in vitro radiosensitivity prediction with gene expression using deep learning. Methods: A microarray gene expression of the National Cancer Institute-60 (NCI-60) panel was acquired from the Gene Expression Omnibus. The clonogenic surviving fractions at an absorbed dose of 2 Gy (SF2) from previous publications were used to measure in vitro radiosensitivity. The radiosensitivity prediction model was based on the convolutional neural network. The 6-fold cross-validation (CV) was applied to train and validate the model. Then, the leave-one-out cross-validation (LOOCV) was applied by using the large-errored samples as a validation set, to determine whether the error was from the high bias of the folded CV. The criteria for correct prediction were defined as an absolute error<0.01 or a relative error<10%. Results: Of the 174 triplicated samples of NCI-60, 171 samples were correctly predicted with the folded CV. Through an additional LOOCV, one more sample was correctly predicted, representing a prediction accuracy of 98.85% (172 out of 174 samples). The average relative error and absolute errors of 172 correctly predicted samples were 1.351±1.875% and 0.00596±0.00638, respectively. Conclusion: We demonstrated the feasibility of a deep learning-based in vitro radiosensitivity prediction using gene expression.

• Journal of KSNVE
• /
• v.8 no.6
• /
• pp.1023-1029
• /
• 1998

When one attempts to construct a hologram. one finds that there are many sources of measurement errors. These errors are even amplified if one predicts the pressures close to the sources. The pressure estimation errors depend on the following parameters: the measurement spacing on the hologram plane. the prediction spacing on the prediction plane. and the distance between the hologram and the prediction plane. This raper analyzes quantitatively the errors when these are distributed irregularly on the hologram plane The sensor mismatch and inaccurate measurement location. position mismatch. are mainly addressed. In these cases. one can assume that the measurement is a sample of many measurement events. The bias and random error are derived theoretically. Then the relationship between the random error amplification ratio and the parameters mentioned above is examined quantitatively in terms of energy.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.3
• /
• pp.141-145
• /
• 2009

In this paper, we propose an efficient lossless compression algorithm using spatial and temporal information. The proposed method obtains higher lossless compression of images than other lossless compression techniques. It is divided into two parts, a motion adaptation based predictor part and a residual error coding part. The proposed nonlinear predictor can reduce prediction error by learning from its past prediction errors. The predictor decides the proper selection of the spatial and temporal prediction values according to each past prediction error. The reduced error is coded by existing context coding method. Experimental results show that the proposed algorithm has better performance than those of existing context modeling methods.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.1325-1328
• /
• 2007

When we visualize the sound field radiated from a spherical sound source, spherical acoustic holography is proper among acoustic holography methods. However, there are measurement errors due to sensor position mismatch, sensor mismatch, directivity of sensor, and background noise. These errors are amplified if one predicts the pressures close to the sources: backward prediction. The goal of this paper is to quantitatively examine the effects of the error due to sensor position mismatch on acoustic pressure estimation. This paper deals with the cases of which the measurement deviations are distributed irregularly on the hologram plane. In such cases, one can assume that the measurement is a sample of many measurement events, and the cause of the measurement error is white noise on the hologram plane. Then the bias and random error are derived mathematically. In the results, it is found that the random error is important in the backward prediction. The relationship between the random error amplification ratio and the measurement parameters is derived quantitatively in terms of their energies.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.697-710
• /
• 2021

Relative error prediction is preferred over ordinary prediction methods when relative/percentile errors are regarded as important, especially in econometrics, software engineering and government official statistics. The relative error prediction techniques have been developed in linear/nonlinear regression, nonparametric regression using kernel regression smoother, and stationary time series models. However, random effect models have not been used in relative error prediction. The purpose of this article is to extend relative error prediction to some of generalized linear mixed model (GLMM) with panel data, which is the random effect models based on gamma, lognormal, or inverse gaussian distribution. For better understanding, the real auto insurance data is used to predict the claim size, and the best predictor and the best relative error predictor are comparatively illustrated.

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.69-72
• /
• 2001

Blind equalization of transmission channel is important in communication areas and signal processing applications because it does not need training sequence, nor does it require a priori channel information. Recently, Tong et al. proposed solutions for this problem exploit the diversity induced by antenna array or time oversampling, leading to the second order statistics techniques, fur example, subspace method, prediction error method, and so on. The linear prediction error method is perhaps the most attractive in practice due to the insensitive to blind equalizer length mismatch as well as for its simple adaptive filter implementation. Unfortunately, the previous one-step prediction error method is known to be limited in arbitrary delay. In this paper, we induce the optimal delay, and propose the adaptive blind equalizer with multi-step linear prediction using RLS-type algorithm. Simulation results are presented to demonstrate the proposed algorithm and to compare it with existing algorithms.

• Journal of Information Technology Services
• /
• v.11 no.1
• /
• pp.211-221
• /
• 2012

Many metric-based classification models have been proposed to predict fault-proneness of software module. This paper presents two prediction models using Bayesian classifier which is one of the most popular modern classification algorithms. Bayesian model based on Bayesian probability theory can be a promising technique for software quality prediction. This is due to the ability to represent uncertainty using probabilities and the ability to partly incorporate expert's knowledge into training data. The two models, Na$\ddot{i}$veBayes(NB) and Bayesian Belief Network(BBN), are constructed and dimensionality reduction of training data and test data are performed before model evaluation. Prediction accuracy of the model is evaluated using two prediction error measures, Type I error and Type II error, and compared with well-known prediction models, backpropagation neural network model and support vector machine model. The results show that the prediction performance of BBN model is slightly better than that of NB. For the data set with ambiguity, although the BBN model's prediction accuracy is not as good as the compared models, it achieves better performance than the compared models for the data set without ambiguity.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.1
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.