• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.195-201
• /
• 2015

For median filtering (MF) detection in altered digital images, this paper presents a new feature vector that is formed from autoregressive (AR) coefficients via an AR model of the gradients between the neighboring row and column lines in an image. Subsequently, the defined 10-D feature vector is trained in a support vector machine (SVM) for MF detection among forged images. The MF classification is compared to the median filter residual (MFR) scheme that had the same 10-D feature vector. In the experiment, three kinds of test items are area under receiver operating characteristic (ROC) curve (AUC), classification ratio, and minimal average decision error. The performance is excellent for unaltered (ORI) or once-altered images, such as $3{\times}3$ average filtering (AVE3), QF=90 JPEG (JPG90), 90% down, and 110% up to scale (DN0.9 and Up1.1) images, versus $3{\times}3$ and $5{\times}5$ median filtering (MF3 and MF5, respectively) and MF3 and MF5 composite images (MF35). When the forged image was post-altered with AVE3, DN0.9, UP1.1 and JPG70 after MF3, MF5 and MF35, the performance of the proposed scheme is lower than the MFR scheme. In particular, the feature vector in this paper has a superior classification ratio compared to AVE3. However, in the measured performances with unaltered, once-altered and post-altered images versus MF3, MF5 and MF35, the resultant AUC by 'sensitivity' (TP: true positive rate) and '1-specificity' (FN: false negative rate) is achieved closer to 1. Thus, it is confirmed that the grade evaluation of the proposed scheme can be rated as 'Excellent (A)'.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• Journal of Korean Society on Water Environment
• /
• v.38 no.6
• /
• pp.292-305
• /
• 2022

The Yeongsan River, one of the four largest rivers in South Korea, has been facing difficulties with water quality management with respect to algal bloom. The algal bloom menace has become bigger, especially after the construction of two weirs in the mainstream of the Yeongsan River. Therefore, the prediction and factor analysis of Chlorophyll-a (Chl-a) concentration is needed for effective water quality management. In this study, Chl-a prediction model was developed, and the performance evaluated using machine and deep learning methods, such as Deep Neural Network (DNN), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). Moreover, the correlation analysis and the feature importance results were compared to identify the major factors affecting the concentration of Chl-a. All models showed high prediction performance with an R² value of 0.9 or higher. In particular, XGBoost showed the highest prediction accuracy of 0.95 in the test data.The results of feature importance suggested that Ammonia (NH₃-N) and Phosphate (PO₄-P) were common major factors for the three models to manage Chl-a concentration. From the results, it was confirmed that three machine learning methods, DNN, RF, and XGBoost are powerful methods for predicting water quality parameters. Also, the comparison between feature importance and correlation analysis would present a more accurate assessment of the important major factors.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2393-2398
• /
• 2003

In this paper, we proposes a new fuzzy inference system for modeling nonlinear systems given input and output data. In the suggested fuzzy inference system, the number of fuzzy rules and parameter values of membership functions are automatically decided by using the kernel-based method. The kernel-based method individually performs linear transformation and kernel mapping. Linear transformation projects input space into linearly transformed input space. Kernel mapping projects linearly transformed input space into high dimensional feature space. The structure of the proposed fuzzy inference system is equal to a Takagi-Sugeno fuzzy model whose input variables are weighted linear combinations of input variables. In addition, the number of fuzzy rules can be reduced under the condition of optimizing a given criterion by adjusting linear transformation matrix and parameter values of kernel functions using the gradient descent method. Once a structure is selected, coefficients in consequent part are determined by the least square method. Simulated result illustrates the effectiveness of the proposed technique.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.12C
• /
• pp.1280-1287
• /
• 2006

We propose a modified stochastic gradient-based (MSGB) filter showing that the filter is the solution to an optimization problem. This paper analyzes the properties of the MSGB filter that corresponds to the nonlinear adaptive filter with additional update terms, parameterized by the variable scaling factor. The variably parameterized MSGB filter plays a role iii connecting the fixed parameterized MSGB filter and the null parameterized MSGB filter through variably scaling parameter. The stability regions and misadjustments are shown. A system identification is utilized to perform the computer simulation and demonstrate the improved performance feature of the MSGB filter.

• 한국해양학회지
• /
• v.16 no.1
• /
• pp.12-23
• /
• 1981

A numerical experiment is made in order to clarify the mechanism of the upwelling phenomenon along the coast near the poleward edge of the western boundary current. The possibility of the upwelling is suggested from the analysis of the observational data in the east of Honshu, Japan, and in the south eastern coast of Korean Peninsula. This upwelling phenomenon is very deep and can be traced to the bottom layer. The upwelling phenomenon seems to be a general oceanic feature which characterizes the region along the west coast near the poleward edge of the western boundary current. This experiment is simulating the oceanic condition of the transition region between Kuroshio front and the Oyashio front in the east of Honshu, Japan. The possible explanations of the causes of the upwelling are as follows;In the interior of the modeled ocean the cold heavy water supplied from the north and the warm light water from the south make the north-south gradient of the pressure field and accelerate the eastward current to produce the h-orizontal divergence feld near the west coast. The divergence is compensated by the upwelling near the separation region. Another one is that the upwell-ed cold water strengthen constantly the pressure gradient which is balanced by the northward current and is weakened by the horizontal diffusion.

• Journal of Digital Contents Society
• /
• v.10 no.4
• /
• pp.597-604
• /
• 2009

For the improvement of license plate recognition system, correct extraction of a license plate region as well as character recognition is important. In this paper, with the analysis and classification of the error patterns in the process of plate region extraction, we tried to improve the extraction of the region using HoG(histogram of gradient) features and Adaboost. The results show that the HoG feature is robust to the noise and various types of the plates, and also is very effective to extract the region failed before.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.1000-1009
• /
• 2007

This paper presents a content adaptive interpolation (CAI) for intra deinterlacing. The CAI consists of three steps: pre-processing, content classification, and adaptive interpolation. There are also three main interpolation methods in our proposed CAI, i.e. modified edge-based line averaging (M-ELA), gradient directed interpolation (GDI), and window matching method (WMM). Each proposed method shows different performances according to spatial local features. Therefore, we analyze the local region feature using the gradient detection and classify each missing pixel into four categories. And then, based on the classification result, a different do-interlacing algorithm is activated in order to obtain the best performance. Experimental results demonstrate that the CAI method performs better than previous techniques.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.805-814
• /
• 1998

An efficient image processing algorithm is proposed to recognize both the height and width modulated barcodes which are rotated and printed at an arbitrary position. The main feature of this algorithm is to utilize the gradient information of a rotated barcode with a Sobel operator. The barcode area is extracted using the gradient information, and the barcode is decoded from the binary image of the extracted area. Theis algorithm is successfully applied to the 4 state and width modulated barcodes. It takes 0.86 secoden to process a letter, and the recognition rate reaches above 98% under various testing conditions. Since both the width and height modulated barcodes are processed with the proposed algorithm, it can be applied to postal service automation.