• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.5
• /
• pp.669-674
• /
• 2018

Data augmentation is an efficient way to reduce overfitting on models and to improve a performance supplementing extra data for training. It is more important in deep learning based industrial machine vision. Because deep learning requires huge scale of learning data to learn a model, but acquisition of data can be limited in most of industrial applications. A very generic method for augmenting image data is to perform geometric transformations, such as cropping, rotating, translating and adjusting brightness of the image. The effectiveness of data augmentation in image classification has been reported, but it is rare in defect inspections. We explore and compare various basic augmenting operations for the metal surface defects. The experiments were executed for various types of defects and different CNN networks and analysed for performance improvements by the data augmentations.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.116-122
• /
• 2001

A novel approach based on WaveARX neural network observer is proposed far the fault detect of a class of nonlinear systems which consist of known linear part and unknown nonlinear part. A linear observer is first designed, then a nonlinear compensation term in the nonlinear observer is estimated by using a deconvolution method. The WaveARX network is used to model the obtained compensation term. At last, the residual fur fault detection is generated based on the analysis of the upper bound approximate error. Simulation results have shown the feasibility and effectiveness of the method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.601-604
• /
• 1994

This paper describes an effective method to estimate a position of an automous vehicle equipped with a single CCD-camera along indoor passageways. Using the sequential image data from the self-movement of the vehicle, the position is estimated by integrating the approximated motion parameters. The detection of the yaw angle that is one of the motion parameter is difficult in general, e.g. slip or error for noise, therefore the different detection is presented, which is, without shaft encoders, based on a projection function for 2D-image data and a cross-correlation function so as to be robust for noise. The approximated geometric function to estimate the position is used to reduce the computational effort. To verify the effectiveness of the method, the analysis and the computational results are shown through the simulations. Furthermore, the experimental results by using the test vehicle for the real indoor passageway are shown.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.3
• /
• pp.333-340
• /
• 2015

In this paper, we propose a passive microwave sensor for detecting human body using microwave radiometer technologies. The proposed sensor detects human body by measuring the change of the received radiation power from fixed background object due to human body. A C-band microwave radiometer is designed and implemented. The received radiation power changes due to human body is measured by the C-band microwave radiometer, and the effectiveness of the proposed sensor is evaluated by the measurement result analysis.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.57 no.4
• /
• pp.377-382
• /
• 2008

For stator winding protection of AC generator, KCL(Kirchhoff's Current Law) is widely applied. Actually a CRDR(Current Ratio Differential Relay) based on DFT(Discrete Fourier Transform) has been used for protecting generator. It has been pointed out that defects can occur during the process of transforming a time domain signal into a frequency domain one which can lead to loss of time domain information. Wavelets techniques are proposed for the analysis of power system transients. This paper introduces an algorithm to choose a suitable Mother Wave1et for generator stator fault detection. For optimal selection, we analyzed db(Daubechies), sym(Symlets), and coif(Coiflects) of Mother Wavelet. And we compared with performance of the choice algorithm using detail coefficients energy and RMS(root mean square) error. It can be improved the reliability of the conventional DFT based CRDR. The feasibility and effectiveness of the proposed scheme is proved with simulation using collected data obtained from ATP (Alternative Transient Program) package.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.90-97
• /
• 2024

This paper focuses on detecting Alzheimer's Disease (AD). The most usual form of dementia is Alzheimer's disease, which causes permanent cause memory cell damage. Alzheimer's disease, a neurodegenerative disease, increases slowly over time. For this matter, early detection of Alzheimer's disease is important. The purpose of this work is using Magnetic Resonance Imaging (MRI) to diagnose AD. A Convolution Neural Network (CNN) model, Reset, and VGG the pre-trained learning models are used. Performing analysis and validation of layers affects the effectiveness of the model. T1-weighted MRI images are taken for preprocessing from ADNI. The Dataset images are taken from the Alzheimer's Disease Neuroimaging Initiative (ADNI). 3D MRI scans into 2D image slices shows the optimization method in the training process while achieving 96% and 94% accuracy in VGG 16 and ResNet 18 respectively. This study aims to classify AD from brain 3D MRI images and obtain better results.

• Journal of Radiation Industry
• /
• v.18 no.2
• /
• pp.101-107
• /
• 2024

Rapid screening for internal contamination by alpha- and beta-emitting radionuclides is essential in situations involving radiation workers or radiation accidents. This study focused on the use of urine samples and liquid scintillation counting to quickly and accurately assess contamination. Calibration of the alpha and beta detection areas ensured precise measurement results. The major radionuclides recommended for surveillance during accidents were also considered. This study evaluated the effectiveness of the method by examining various parameters, including the limit of detection, linearity, sensitivity, selectivity, accuracy, ruggedness, and blind test sample analysis. The liquid scintillation counting method is an effective tool for screening urinary samples to detect alpha- and beta-emitting radionuclides, particularly during radiation emergencies, despite some limitations in precision.

• Journal of Sensor Science and Technology
• /
• v.33 no.4
• /
• pp.187-195
• /
• 2024

Light detection and ranging (LiDAR), a widely used sensor in mobile robots and autonomous vehicles, has its most important function as measuring the range of objects in three-dimensional space and generating point clouds. These point clouds consist of the coordinates of each reflection point and can be used for various tasks, such as obstacle detection and environment recognition. However, several processing steps are required, such as three-dimensional modeling, mesh generation, and rendering. Efficient data processing is crucial because LiDAR provides a large number of real-time measurements with high sampling frequencies. Despite the rapid development of controller computational power, simplifying the computational algorithm is still necessary. This paper presents a method for estimating the presence of curbs, humps, and ground tilt using range measurements from a single horizontal or vertical scan instead of point clouds. These features can be obtained by data segmentation based on linearization. The effectiveness of the proposed algorithm was verified by experiments in various environments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.928-931
• /
• 2014

The detection of human behavior from social media revolutionized health, business, criminal and political prediction. Significance of it, in incentive transformation of public opinion had already proven for developed countries in improving democratic process of elections. In $3^{rd}$ World countries, voters poll votes for personal interests being unaware of party manifesto or national interest. These issues can be addressed by social media, resulting as ongoing process of improvement for presently adopted electoral procedures. On the optimistic side, people of such countries applied social media to garner support and campaign for political parties in General Elections. Political leaders, parties, and people empowered themselves with social media, in disseminating party's agenda and advocacy of party's ideology on social media without much campaigning cost. To study effectiveness of social media inferred from individual's political behavior, large scale analysis, sentiment detection & tweet classification was done in order to classify, predict and forecast election results. The experimental results depicts that social media content can be used as an effective indicator for capturing political behaviors of different parties positive, negative and neutral behavior of the party followers as well as party campaign impact can be predicted from the analysis.