• Journal of the Korean Geophysical Society
• /
• v.2 no.2
• /
• pp.143-152
• /
• 1999

We have studied a denoising technique involving wavelet transform for improving the quality of geophysical data during the preprocessing stage. To assess the effectiveness of this technique, we have made synthetic data contaminated by random noises and compared the results of denoising with those obtained by conventional low-pass filtering. The low-pass filtering of the sinusoidal signal having a sharp discontinuity between the first and last sample values shows apparent errors related to Gibbs' phenomena. For the case of bump signal, the low-pass filtering induces maximum errors on peak values by removing some high-frequency components of signal itself. The wavelet transform technique, however, denoises these signals with much less adverse effects owing to its pertinent properties on locality of wavelet and easy discrimination of noise and signal in the wavelet domain. The field data of gravity tide are denoised by using soft threshold, which shrinked all the wavelet coefficients toward the origin, and the G-factor is determined by comparing the denoised data and theoretical data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.291-296
• /
• 2015

The tire damage classification method is researched on the periodicity detection of ramdomness ultrasonic signals to occur at the driving vehicle tire. Setting method of adaptive threshold is proposed in order to valid pulse detection by tire damage in ultrasonic noise on the road and used low pass filter for decrease signal ramdomness as preprocessing. Time interval of detected pulse is setted the density function depend on the vehicle's speed and the method of tire damage detection is proposed that measuring the first peak's time of time density function.The result of time density function in case of one damage material, the first peak's time is measured within the error limit of tire's rotation period, 169.8ms and 97.9ms and 81.8ms, about the speed of 50km/h and 80km/h and 100km/h. In case of more than one damage material, the sum of each peak's time is measured within the error limit of tire's rotation period about the speed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.437-444
• /
• 2016

Most methods for detecting arrhythmia require pp interval, diversity of P wave morphology, but it is difficult to detect the p wave signal because of various noise types. Therefore it is necessary to use noise-free R wave. In this paper, we propose algorithm for premature contraction arrhythmia classification through ECG pattern analysis and template threshold. For this purpose, we detected R wave through the preprocessing method using morphological filter, subtractive operation method. Also, we developed algorithm to classify premature contraction wave pattern using weighted average, premature ventricular contraction(PVC) and atrial premature contraction(APC) through template threshold for R wave amplitude. The performance of R wave detection, PVC classification is evaluated by using 6 record of MIT-BIH arrhythmia database that included over 30 PVC and APC. The achieved scores indicate the average of 99.77% in R wave detection and the rate of 94.91%, 95.76% in PVC and APC classification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.790-792
• /
• 2017

As the demand of digital image processing devices has been rapidly increased recently, the excellent image quality is required. However, degradation can be occurred with multiple causes during transmission and processing process. Therefore, the needs to eliminate the noise are increased and the noise elimination technology became the major study area. Therefore, image restoration algorithm was suggested to apply the filter differently by edge and non-edge areas, using modified edge detection with preprocessing process so as to relieve the effect of additive white Gaussian noise(AWGN) which is added in the image, in this article. In addition, it was compared with the existing methods using peak signal to noise ratio(PSNR) as the objective determination standard of the improvement effect.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.248-251
• /
• 2016

This thesis has discussed how to recognize and convert raised letters on tire to data and collect such data. Unlike the existing recognition system, the system presented by this thesis recognizes raised letters on tire through detecting letters after converting the Kinect camera image into image data in the preprocessing stage. After then, numbers and letters are analyzed through image improvement by use of binary images, noise filter, etc. In the recognition stage, letter distinction is used and raised letters on tire are recognized 100% through correction of errors by way of the correction algorithm for tire data recognition errors. In this paper it will be the development of a method of recognizing characters and the tire technology. Although there are many ways to the already recognized characters, Tire characters requires a technique different from the more general character recognition. For this reason and to develop additional technical methods and algorithms for character recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.1
• /
• pp.43-48
• /
• 2014

Usually, image deconvolution is applied as a preprocessing step in surveillance systems to reduce the effect of motion or out-of-focus blur problem. In this paper, we propose a blind-image deconvolution filtering approach based on genetic programming (GP). A numerical expression is developed using GP process for image restoration which optimally combines and exploits dependencies among features of the blurred image. In order to develop such function, first, a set of feature vectors is formed by considering a small neighborhood around each pixel. At second stage, the estimator is trained and developed through GP process that automatically selects and combines the useful feature information under a fitness criterion. The developed function is then applied to estimate the image pixel intensity of the degraded image. The performance of developed function is estimated using various degraded image sequences. Our comparative analysis highlights the effectiveness of the proposed filter.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.101-109
• /
• 2012

In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation inTRUS images using support vectors and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. Gabor filter bank for extracting the texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. The boundary of prostate is extracted by the snake-like contour algorithm. The results showed that this new algorithm extracted the prostate boundary with less than 9.3% relative to boundary provided manually by experts.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• The Journal of Information Systems
• /
• v.30 no.2
• /
• pp.147-163
• /
• 2021

Purpose The study aims to predict real estate prices by utilizing regional characteristics. Since real estate has the characteristic of immobility, the characteristics of a region have a great influence on the price of real estate. In addition, real estate prices are closely related to economic development and are a major concern for policy makers and investors. Accurate house price forecasting is necessary to prepare for the impact of house price fluctuations. To improve the performance of our predictive models, we applied LSTM, a widely used deep learning technique for predicting time series data. Design/methodology/approach This study used time series data on real estate prices provided by the Ministry of Land, Infrastructure and Transport. For time series data preprocessing, HP filters were applied to decompose trends and SOM was used to cluster regions with similar price directions. To build a real estate price prediction model, SVR and LSTM were applied, and the prices of regions classified into similar clusters by SOM were used as input variables. Findings The clustering results showed that the region of the same cluster was geographically close, and it was possible to confirm the characteristics of being classified as the same cluster even if there was a price level and a similar industry group. As a result of predicting real estate prices in 1, 2, and 3 months, LSTM showed better predictive performance than SVR, and LSTM showed better predictive performance in long-term forecasting 3 months later than in 1-month short-term forecasting.

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.185-192
• /
• 2022

Early detection of mild cognitive impairment can help prevent the progression of dementia. The purpose of this study was to design and validate a machine learning model that automatically differential diagnosed patients with mild cognitive impairment and identified cognitive decline characteristics compared to a control group with normal cognition using resting-state quantitative electroencephalogram (qEEG) with eyes closed. In the first step, a rectified signal was obtained through a preprocessing process that receives a quantitative EEG signal as an input and removes noise through a filter and independent component analysis (ICA). Frequency analysis and non-linear features were extracted from the rectified signal, and the 3067 extracted features were used as input of a linear support vector machine (SVM), a representative algorithm among machine learning algorithms, and classified into mild cognitive impairment patients and normal cognitive adults. As a result of classification analysis of 58 normal cognitive group and 80 patients in mild cognitive impairment, the accuracy of SVM was 86.2%. In patients with mild cognitive impairment, alpha band power was decreased in the frontal lobe, and high beta band power was increased in the frontal lobe compared to the normal cognitive group. Also, the gamma band power of the occipital-parietal lobe was decreased in mild cognitive impairment. These results represented that quantitative EEG can be used as a meaningful biomarker to discriminate cognitive decline.