• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.124-131
• /
• 2009

A reliable detection of regions in radiography is one of the most important task before the evaluation of defects on welded joints. The extracted features is to be classified into distinctive clusters for each segmented region. But conventional segmentation techniques give unsatisfactory results for this task due to the spatial superposition of intensity and low signal-to-ratio(SNR) in radiographic images. The usage of global or local processes not only provide the necessary noise resistance but also fail in classification of regions. In this paper, we presents an appropriate approach for segmentation of region-based indications in industrial Computed Radiography(CR) images. The geometric differences between welded and non-welded area which is generated on radiography as the representative regions(background, thickness, middle and welded region in steel tube image) have constructed the hierarchical structure. Although this structure is contaminated by noise, the scheme between regions can be selected by the help of local clustering based on distinctive geometric property of each region. Because of the geometric nature of the considered region and so that the region is selected layer by layer, and that the real class represents the boundary between regions, the vertical and horizontal clustering process in each layer must be judicious. In order to show the effectiveness of this approach, a comparative experiment of various segmentation method is performed on industrial steel tube CR images.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1706-1709
• /
• 2010

Sewerage Treatment Plants(STPs) are complexes systems in which a range of physical, chemical and biological processes occur. Since Activated Sludge Model(ASM) No.1 was published, a number of new mathematical models for simulating biological processes have been developed. However, these models have disadvantages in cost and simplicity due to the laboriousness and tediousness of their procedures. One of the major difficulties of these mathematical model based tools is that the field-operators mostly don't have the time or the computer-science skills to handle there models, so it mainly remains on experts or special engineers. In order to solve these situations and help the field-operators, the $KM^2BM$(K-water & More-M Mass Balance Model) based on the dynamic-mass balance model was developed. This paper presents $KM^2BM$ as a simulation tools for STPs design and optimization. This model considers the most important microbial behavioral processes taking place in a STPs to maximize potential applicability without increasing neither model parameter estimation nor wastewater characterization efforts.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.6A
• /
• pp.341-350
• /
• 2003

In this paper, we evaluate the performance of a moving average (MA) channel estimation filter when space-time block coding transmit diversity (STBC-TD) is applied to the wideband direct sequence code division multiple access (WCDMA) forward link. And we present the infinite impulse response (IIR) filter scheme that can reduce the required memory buffer and the channel estimation delay time. This paper also compares the performance between MA filter scheme and IIR filter scheme in various Rayleigh fading channel environments through the bit error rate (BER) and the frame error rate (FER). Extensive computer simulation results show that transmission with STBC-TD provides a significant gain in performance over no transmit diversity technique, particularly at pedestrian speeds. If STBC-TD technique is employed in the channel estimator based on MA filter, it provides considerable performance gains against Rayleigh fading and reduces the optimum filter tap number. Consequently, the channel estimation delay time and the complexity of the receiver are reduced. In addition, the channel estimator based on IIR filter has the advantages such as little memory requirement and no delay time compared to the MA scheme. However, IIR filter coefficients is very sensitive to the mobile speed change and it exerts a serious influence upon the performance. For that reason, it is important to set uP the optimum IIR filter coefficients.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.8
• /
• pp.787-794
• /
• 2010

Recently, with sudden increase of supplying rate of cars and quantity of goods transported, traffic noisy becomes one of important factors obstruct environment of exhibition and view facilities have purpose in calmness and unsatisfaction about this is high now. Therefore, in case of exhibition and view facilities, it has to be grasped that satisfaction degree about the noisy in and out of the exhibition room by performing effect valuation on traffic noisy from design step. However the level of internal noise cannot be measured at the design phrase of the structure due to the noise of traffic. Up until now a walls transmission loss, based on the law of mass, is predicted using this method. However measuring the internal sound level after actual construction reveals that there is a large difference from measurements made at the design stage, and it is very difficult to find a solution after the opening of the structure. From research looking from this perspective the internal sound level was predicted- calculating the internal sound absorption ability, using acoustic simulation and loss prevention of an insulated wall- based on data collected to evaluate the internal sound of an exhibition room at a Folk Museum adjacent to a freeway. The results of this research are considered to provide important data for the prediction of internal sound level at the time of construction of exhibition facilities similar to this.

• Journal of Biomedical Engineering Research
• /
• v.29 no.1
• /
• pp.66-72
• /
• 2008

The major risk associated with the use of automated power injectors is the well known complication of contrast material extravasation at the injection site. Automated injection of computed tomography (CT) contrast media can produce the compartment syndrome. The purpose of this study was to assess the ability of this device during clinically important episodes of extravasation. The extravasation detection accessory (EDA) system was composed of a strain gage, an amplifier and a computer based system. A strain gage pliable adhesive patch was applied to the skin aver the intravenous catheter and the catheter was connected to the power injector with a cable to monitor the resolution data. If the programmed monitoring, which was developed with MS Visual C++, at the extravasation occurred, then the injection was interrupted the auto injector. CT was used to demonstrate the clinically important extravasation. This study was a prospective, observational study in which the EDA system was used to monitor the automated mechanical injection of contrast material in 7 dogs. There were two true-positive cases (range of extravasation volumes: $18{\sim}22ml$), twenty three true-negative cases, three false-positive cases and no false-negative cases. The EDA system had a sensitivity of 100% and a specificity of 88% for the detection of clinically important extravasation. The EDA system had good sensitivity for the detection of clinically important extravasation and the EDA system has the clinical potential for the early detection of extravasation of the contrast medium that is administered with power injectors. The EDA system is easy to use safe and accurate for the monitoring extravasation of the intravenous injections, and this system may prove especially useful in CT applications.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.10
• /
• pp.277-284
• /
• 2021

Recently, the smart home environment is expected to be a platform that collects, integrates, and utilizes various data through convergence with wireless information and communication technology. In fact, the number of smart devices with various sensors is increasing inside smart homes. The amount of data that needs to be processed by the increased number of smart devices is also increasing, and big data processing systems are actively being introduced to handle it effectively. However, traditional big data processing systems have all requests directed to cluster drivers before they are allocated to distributed nodes, leading to reduced cluster-wide performance sharing as cluster drivers managing segmentation tasks become bottlenecks. In particular, there is a greater delay rate on smart home devices that constantly request small data processing. Thus, in this paper, we design a Apriori-based big data system for effective data processing in smart home environments where frequent requests occur at the same time. According to the performance evaluation results of the proposed system, the data processing time was reduced by up to 38.6% from at least 19.2% compared to the existing system. The reason for this result is related to the type of data being measured. Because the amount of data collected in a smart home environment is large, the use of cache servers plays a major role in data processing, and association analysis with Apriori algorithms stores highly relevant sensor data in the cache.

• Korean Journal of Optics and Photonics
• /
• v.33 no.6
• /
• pp.267-274
• /
• 2022

In this paper, we report the design and fabrication of binary diffractive optical elements (DOEs) for random-dot-pattern projection for Schlieren imaging. We selected the binary phase level and a pitch of 10 ㎛ for the DOE, based on cost effectiveness and ease of manufacture. We designed the binary DOE using an iterative Fourier-transform algorithm with binary phase optimization. During initial optimization, we applied a computer-generated pseudorandom dot pattern of uniform intensity as a target pattern, and found significant intensity nonuniformity across the field. Based on the evaluation of the initial optimization, we weighted the target random dot pattern with Gaussian profiles to improve the intensity uniformity, resulting in the improvement of uniformity from 52.7% to 90.8%. We verified the design performance by fabricating the designed binary DOE and a beam projector, to which the same was applied. The verification confirmed that the projector produced over 10,000 random dot patterns over 430 mm × 430 mm at a distance of 5 meters, as designed, but had a slightly less uniformity of 84.5%. The fabrication errors of the DOE, mainly edge blurring and spacing errors, were strong possibilities for the difference.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.233-240
• /
• 2022

Most of the recent AI researches has focused on developing AI models. However, recently, artificial intelligence research has gradually changed from model-centric to data-centric, and the importance of learning data is getting a lot of attention based on this trend. However, it takes a lot of time and effort because the preparation of learning data takes up a significant part of the entire process, and the generation of labeling data also differs depending on the purpose of development. Therefore, it is need to develop a tool with various labeling functions to solve the existing unmetneeds. In this paper, we describe a labeling system for creating precise and fast labeling data of medical images. To implement this, a semi-automatic method using Back Projection, Grabcut techniques and an automatic method predicted through a machine learning model were implemented. We not only showed the advantage of running time for the generation of labeling data of the proposed system, but also showed superiority through comparative evaluation of accuracy. In addition, by analyzing the image data set of about 1,000 patients, meaningful diagnostic indexes were presented for men and women in the diagnosis of sarcopenia.