• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.1-9
• /
• 2022

Most factories deal with toxic or flammable chemicals in their industrial processes. These hazardous substances pose a risk of leakage due to accidents, such as fire and explosion. In the event of chemical release, massive casualties and property damage can result; hence, quantitative risk prediction and assessment are necessary. Several methods are available for evaluating chemical dispersion in the atmosphere, and most analyses are considered neutral in dispersion models and under far-field wind condition. The foregoing assumption renders a model valid only after a considerable time has elapsed from the moment chemicals are released or dispersed from a source. Hence, an initial dispersion model is required to assess risk quantitatively and predict the extent of damage because the most dangerous locations are those near a leak source. In this study, the dispersion model for initial consequence analysis was developed with three-dimensional unsteady advective diffusion equation. In this expression, instantaneous leakage is assumed as a puff, and wind velocity is considered as a coordinate transform in the solution. To minimize the buoyant force, ethane is used as leaked fuel, and two different diffusion coefficients are introduced. The calculated concentration field with a molecular diffusion coefficient shows a moving circular iso-line in the horizontal plane. The maximum concentration decreases as time progresses and distance increases. In the case of using a coefficient for turbulent diffusion, the dispersion along the wind velocity direction is enhanced, and an elliptic iso-contour line is found. The result yielded by a widely used commercial program, ALOHA, was compared with the end point of the lower explosion limit. In the future, we plan to build a more accurate and general initial risk assessment model by considering the turbulence diffusion and buoyancy effect on dispersion.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• Journal of Sensor Science and Technology
• /
• v.31 no.1
• /
• pp.51-56
• /
• 2022

In this study an efficient method for detecting and monitoring engine misfiring, focusing on minute speed changes in the crankshaft is proposed., Its validity is verified using various misfiring cases. Typically, the crankshaft speed fluctuates around the normal value depending on the engine misfiring status. Even a minute speed change in the crankshaft can be estimated by measuring the rotation time of each tooth of the 118-tooth flywheel attached to the crankshaft with a 2-MHz timer. Therefore, a speed pattern for an in-line six-cylinder engine consists of 236 tooth rotation speeds corresponding to the two rotations of the crankshaft, in which all the cylinders complete four-stroke cycle. FFT analysis can reduce the number of components of a speed pattern from 236 to just four major components: - fundamental frequency_(f), 2f, 3f, 6f., - This makes the comparison of the misfiring cases simpler and faster. In the experiment, five engine status cases (one normal firing and, four misfiring cases) were simulated. While the 6f component was the largest for the normal case, the f component increased as misfiring occurred one, two apart, and two consecutive times. The 3D FFT pattern comprising the ratio of f, 2f, and 3f, 6f showed that the distance between the misfiring and normal states was larger

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2991-3007
• /
• 2022

Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Progress in Medical Physics
• /
• v.21 no.2
• /
• pp.153-164
• /
• 2010

To determine the clinical target volumes considering vascularity and cellularity of tumors, the software was developed for mapping of the analyzed biological clinical target volumes on anatomical images using regional cerebral blood volume (rCBV) maps and apparent diffusion coefficient (ADC) maps. The program provides the functions for integrated registrations using mutual information, affine transform and non-rigid registration. The registration accuracy is evaluated by the calculation of the overlapped ratio of segmented bone regions and average distance difference of contours between reference and registered images. The performance of the developed software was tested using multimodal images of a patient who has the residual tumor of high grade gliomas. Registration accuracy of about 74% and average 2.3 mm distance difference were calculated by the evaluation method of bone segmentation and contour extraction. The registration accuracy can be improved as higher as 4% by the manual adjustment functions. Advanced MR images are analyzed using color maps for rCBV maps and quantitative calculation based on region of interest (ROI) for ADC maps. Then, multi-parameters on the same voxels are plotted on plane and constitute the multi-functional parametric maps of which x and y axis representing rCBV and ADC values. According to the distributions of functional parameters, tumor regions showing the higher vascularity and cellularity are categorized according to the criteria corresponding malignant gliomas. Determined volumes reflecting pathological and physiological characteristics of tumors are marked on anatomical images. By applying the multi-functional images, errors arising from using one type of image would be reduced and local regions representing higher probability as tumor cells would be determined for radiation treatment plan. Biological tumor characteristics can be expressed using image registration and multi-functional parametric maps in the developed software. The software can be considered to delineate clinical target volumes using advanced MR images with anatomical images.

• Journal of Christian Education in Korea
• /
• v.62
• /
• pp.161-186
• /
• 2020

This study was conducted with the aim of opening a new horizon in understanding the church, which is a community of faith, in the context of losing social credibility with selfishness and closedness, and spreading social distance due to the epidemic. First, the concept and meaning of 'Ecclesia', a representative term for the church, was studied historically, biblically, and theologically, and Paul's intention was frequently used. Second, we explored the new horizons of the community of faith through a discussion of Roberto Esposito's Communitas and Immunitas, which unraveled the relationship between community and individual with an immunological concept. Not only dis lose social trust for a variety of reasons, but it has been pointed out as a target of social distancing due to the spread of the epidemic virus and is facing a crisis of weakening or loss of the faith community of the "church". Since the second epidemic has been predicted since Covid-19, the partial loss of daily life and the weakening and loss of meeting worship and fellowship in the church are inevitable. The church in the future needs to transform and build a true community of faith that understands the concept of immunity and can lead the transformation of society while revealing the spirit and life scent of Jesus Christ. To this end, innovation and practice of the paradigm of the community of faith appropriate to the rapidly changing times and situations is required. In Chapter 1 of this paper, we propose innovation by pointing out the problems of the church and the faith community, which have lost social credibility, and which are the objects of social distance, with selfishness and closedness. Chapter 2 studies and analyzes the 'Ecclesia' used in ancient Greek to transform the paradigm of the faith community, and identifies the intention of the apostle Paul to apply the 'Ecclesia' to the church's faith community. Chapter 3-4 discusses the concept of immunity, summarizes the reinterpretation of Esposito, who looked at the relationship between the individual and the community through the concept of positive immunity beyond negative immunity. And It draws application points for transforming the faith community of various communities, individuals, and churches. In conclusion, Chapter 5 restores precious gatherings and participation that are weakened and lost through the meaning of 'Ecclesia' and suggests expansion to higher level public gatherings and democratic participation. In addition, based on the reinterpretation of the concept of immunity, we present unity in diversity and diversity in unity as alternatives to the church and community of faith.

• Journal of KIISE:Software and Applications
• /
• v.30 no.9
• /
• pp.829-842
• /
• 2003

In this Paper, we propose the new face detection and tracking method based on template matching for real-time applications such as, teleconference, telecommunication, front stage of surveillance system using face recognition, and video-phone applications. Since the main purpose of paper is to track a face regardless of various environments, we use template-based face tracking method. To generate robust face templates, we apply wavelet transform to the average face image and extract three types of wavelet template from transformed low-resolution average face. However template matching is generally sensitive to the change of illumination conditions, we apply Min-max normalization with histogram equalization according to the variation of intensity. Tracking method is also applied to reduce the computation time and predict precise face candidate region. Finally, facial components are also detected and from the relative distance of two eyes, we estimate the size of facial ellipse.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.11
• /
• pp.42-47
• /
• 2007

In this paper, influence of lossy ground and gap variation between lossy ground and UWB antenna on impulse propagation in time domain for impulse ground penetrating radar (GPR) is numerically and experimentally investigated. For this study, a novel planar UWB fat dipole antenna is developed. First, influence of lossy ground and gap variation between lossy ground and UWB antenna is simulated. For verification, a test field of sand and wet clay soil is built and using the developed dipole antenna, transmission behavior is investigated at the test field. With an aid of IDFT (inverse discrete Fourier transform), time domain impulse response for transmission coefficient measured and simulated in frequency domain is obtained. Measurement and simulation show that the frequency of maximum transmission coefficient and transmission coefficient are increased with higher dielectric constant and larger gap distance. In time domain, it is shown that for higher dielectric constant, the amplitude of the received signal in time domain is higher and reflected signals are seriously modified. Also, it is found that variation of gap between antenna and ground surface makes timing of peak value changed.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.471-478
• /
• 2009

Recently, researches for user interface are remarkably processed due to the explosive growth of 3-dimensional contents and applications, and the spread class of computer user. This paper proposes a novel method to manipulate windows efficiently using only the intuitive motion of hand. Previous methods have some drawbacks such as burden of expensive device, high complexity of gesture recognition, assistance of additional information using marker, and so on. To improve the defects, we propose a novel visual touchless interface. First, we detect hand region using hue channel in HSV color space to control window using hand. The distance transform method is applied to detect centroid of hand and curvature of hand contour is used to determine position of fingertips. Finally, by using the hand motion information, we recognize hand gesture as one of predefined seven motions. Recognized hand gesture is to be a command to control window. In the proposed method, user can manipulate windows with sense of depth in the real environment because the method adopts stereo camera. Intuitive manipulation is also available because the proposed method supports visual touch for the virtual object, which user want to manipulate, only using simple motions of hand. Finally, the efficiency of the proposed method is verified via an application based on our proposed interface.