• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.132-140
• /
• 2023

In this paper, we propose a method for performance enhancement of speech declipping using clipping detector. Clipping occurs when the input speech level exceeds the dynamic range of microphone, and it significantly degrades the speech quality. Recently, many methods for high-performance speech declipping based on machine learning have been developed. However, they often deteriorate the speech signal because of degradation in signal reconstruction process when the degree of clipping is not high. To solve this problem, we propose a new approach that combines the declipping network and clipping detector, which enables a selective declipping operation depending on the clipping level and provides high-quality speech in all clipping levels. We measured the declipping performance using various metrics and confirmed that the proposed method improves the average performance over all clipping levels, compared with the conventional methods, and greatly improves the performance when the clipping distortion is small.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.27-33
• /
• 2024

The environment of academic research is continuously changing due to the increase of information, which raises the need for an effective way to analyze and organize large amounts of documents. In this paper, we propose Performance Improvement of Topic Modeling using BART(Bidirectional and Auto-Regressive Transformers) based Document Summarization. The proposed method uses BART-based document summary model to extract the core content and improve topic modeling performance using LDA(Latent Dirichlet Allocation) algorithm. We suggest an approach to improve the performance and efficiency of LDA topic modeling through document summarization and validate it through experiments. The experimental results show that the BART-based model for summarizing article data captures the important information of the original articles with F1-Scores of 0.5819, 0.4384, and 0.5038 in Rouge-1, Rouge-2, and Rouge-L performance evaluations, respectively. In addition, topic modeling using summarized documents performs about 8.08% better than topic modeling using full text in the performance comparison using the Perplexity metric. This contributes to the reduction of data throughput and improvement of efficiency in the topic modeling process.

• Nuclear industry
• /
• v.27 no.4 s.290
• /
• pp.46-50
• /
• 2007

고리 1호기는 한국에서 최초로 규제 기관에 계속운전을 신청한 원전이다. 2007년 6월에 설계 수명 기간 만료가 되는 고리 1호기는 규제 기관으로부터 계속운전(Continued Operation)에 대한 안전성 심사를 받고 있다. 한수원은 고리 1호기 계속운전 승인을 금년 12월에 받기 위해 최선을 다하고 있으며 지역 주민의 사회적 수용성 확보를 위해 노력중이다. 고리 1호기의 계속운전 기간 동안 안전성을 평가하고 정리한 안전성평가보고서를 한수원은 2006년 6월에 정부에 제출하였다. 고리 1호기는 웨스팅하우스의 2루프 가압경수로이다. 이와 동일한 원전인 일본의 미하마 1,2호기와 겐까이1호기가 계속운전중이며, 미국의 기네이와 포인트 비치 1,2호기가 계속운전 승인을 받았다. 제출한 안전성평가보고서에 대해 한국원자력안전기술원이 심사중이며, 해외 원전과 같이 계속운전을 할 수 있을 것으로 예상하고 있다. 또한 계속운전을 위한 사회적 수용성(Public Acceptance) 확보는 설비의 철저한 안전성 확보 및 지역 주민의 공감대 형성을 통해서 이루어질 것이다. 설계 수명 이후 원자력발전소를 계속 운전하는 것은 이미 선진국에서 시행되고 있다. 2007년 3월 기준으로 미국에서 48기가 운영 허가 갱신 승인을 받았고, 영국은 8기, 일본은 12기가 계속운전중이다. 고리 1호기 성능 지표를 개선시키기 위해서 한수원은 증기발생기, 저압 터빈, 원자로 냉각재 펌프 내장품, 주변압기, 주발전기 등을 교체하였으며, 수명관리 연구, 주기적안전성 평가, 환경 영향 평가를 수행하였다. 2005년 9월에는 미국의 운영 허가 갱신 제도를 참조하여 원자력법이 개정되었다. 이에 한수원은 개정된 원자력법에 맞추어 주기적 안전성평가, 주요 기기에 대한 수명 평가 및 방사능 환경 영향평가를 하였다. 이 세가지 보고서들로 구성된 안전성평가보고서를 2006년 6월에 규제 기관에 제출하였다. 계속운전은 한국을 비롯하여 부존 자원이 부족한 국가들에게는 에너지 자원의 효율적 활용 및 온실 가스 배출을 고려할 때 반드시 필요한 것이다.

• Journal of the Society of Disaster Information
• /
• v.7 no.4
• /
• pp.259-265
• /
• 2011

After the commercial opening of the KTX in 2005, the high speed railroad has been rapidly emerged as the major transportation means due to its high energy efficiency. Recently, the government has announced its plan to build the future transportation system around the high speed railroad. Based on this policy, the existing lines as well as the lines under construction or design are planning to increase design speed. In this paper, the suitability of the mid-span PSC girder bridges for the high speed railroad is evaluated via dynamic analysis. IT, Precom, and WPC girder bridges are considered for the purpose of this study and, for comparison, the identical modeling method and the analysis technique are utilized. The performance indices used for dynamic performance evaluation are the natural frequency, the vertical displacement, the end axial displacement, track irregularity, etc. The KTX train is utilized as a dynamic load, and the dynamic analysis is performed up to the train speed of 420km/hr with the increment of 10km/hr.

• Progress in Medical Physics
• /
• v.21 no.3
• /
• pp.281-290
• /
• 2010

Cone-beam digital tomosynthesis (CBDT) has greatly been paid attention in the image-guided radiation therapy because of its attractive advantages such as low patient dose and less motion artifact. Image quality of tomograms is, however, dependent on the imaging conditions such as the scan angle (${\beta}_{scan}$) and the number of projection views. In this paper, we describe the principle of CBDT based on filtered-backprojection technique and investigate the optimization of imaging conditions. As a system performance, we have defined the figure-of-merit with a combination of signal difference-to-noise ratio, artifact spread function and floating-point operations which determine the computational load of image reconstruction procedures. From the measurements of disc phantom, which mimics an impulse signal and thus their analyses, it is concluded that the image quality of tomograms obtained from CBDT is improved as the scan angle is wider than 60 degrees with a larger step scan angle (${\Delta}{\beta}$). As a rule of thumb, the system performance is dependent on $\sqrt{{\Delta}{\beta}}{\times}{\beta}^{2.5}_{scan}$. If the exact weighting factors could be assigned to each image-quality metric, we would find the better quantitative imaging conditions.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.4
• /
• pp.261-268
• /
• 2019

Climate change and drought stress are having profound impacts on crop growth and development by altering crop physiological processes including photosynthetic activity. But finding a rapid, efficient, and non-destructive method for estimating environmental stress responses in the leaf and canopy is still a difficult issue for remote sensing research. We compared the relationships between photochemical reflectance index(PRI) and various optical and experimental indices on soybean drought stress under climate change conditions. Canopy photosynthesis trait, biomass change, chlorophyll fluorescence(Fv/Fm), stomatal conductance showed significant correlations with midday PRI value across the drought stress period under various climate conditions. In high temperature treatment, PRI were more sensitive to enhanced drought stress, demonstrating the negative effect of the high temperature on the drought stress. But high CO₂ concentration alleviated the midday depression of both photosynthesis and PRI. Although air temperature and CO₂ concentration could affect PRI interpretation and assessment of canopy radiation use efficiency(RUE), PRI was significantly correlated with canopy RUE both under climate change and drought stress conditions, indicating the applicability of PRI for tracking the drought stress responses in soybean. However, it is necessary to develop an integrated model for stress diagnosis using PRI at canopy level by minimizing the influence of physical and physiological factors on PRI and incorporating the effects of other vegetation indices.

• Korean Journal of Remote Sensing
• /
• v.33 no.2
• /
• pp.135-147
• /
• 2017

We, for the first time, estimated daily and monthly surface nitrogen dioxide ($NO_2$) volume mixing ratio (VMR) using three regression models with $NO_2$ tropospheric vertical column density (OMIT-rop $NO_2$ VCD) data obtained from Ozone Monitoring Instrument (OMI) in Seoul in South Korea at OMI overpass time (13:45 local time). First linear regression model (M1) is a linear regression equation between OMI-Trop $NO_2$ VCD and in situ $NO_2$ VMR, whereas second linear regression model (M2) incorporates boundary layer height (BLH), temperature, and pressure obtained from Atmospheric Infrared Sounder (AIRS) and OMI-Trop $NO_2$ VCD. Last models (M3M & M3D) are a multiple linear regression equations which include OMI-Trop $NO_2$ VCD, BLH and various meteorological data. In this study, we determined three types of regression models for the training period between 2009 and 2011, and the performance of those regression models was evaluated via comparison with the surface $NO_2$ VMR data obtained from in situ measurements (in situ $NO_2$ VMR) in 2012. The monthly mean surface $NO_2$ VMRs estimated by M3M showed good agreements with those of in situ measurements(avg. R = 0.77). In terms of the daily (13:45LT) $NO_2$ estimation, the highest correlations were found between the daily surface $NO_2$ VMRs estimated by M3D and in-situ $NO_2$ VMRs (avg. R = 0.55). The estimated surface $NO_2$ VMRs by three modelstend to be underestimated. We also discussed the performance of these empirical modelsfor surface $NO_2$ VMR estimation with respect to otherstatistical data such asroot mean square error (RMSE), mean bias, mean absolute error (MAE), and percent difference. This present study shows a possibility of estimating surface $NO_2$ VMR using the satellite measurement.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.318-325
• /
• 2019

Recently, research and development on agricultural robots have been on the rise as the interest in smart farming has increased. Robots used in smart greenhouses should be taken into account with the working characteristics and growing environment. This study examined cleaning robots developed through the environmental analysis of smart greenhouses. This study assessed the evaluation method considering the requirements of the pest control robot applicable to the smart greenhouse. The performance and quality assessment criteria were established to conduct tests through the requirements of robots. The required functions and goals of the pest control robot were derived by referring to the robot-related standards. A driving and working ability test was conducted to assess the performance of the robot. The driving test was conducted on the driving performance of the robot and the work capability was tested on the pest control performance. In addition, a durability test was conducted to assess the quality of the robot. The required factors for smart greenhouse robots were derived from the test results. The study results are expected be a standard for an evaluation of a variety of robots for applications to smart greenhouses.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.2C
• /
• pp.112-118
• /
• 2011

In this paper, we conduct an objective performance analysis of the crosstalk cancellation scheme studied in [11]. While the conventional scheme is only applicable to a listener on the optimal listenable region (sweetspot), the space skew/crosstalk cancellation (SS/CC) scheme in [11] can mitigate crosstalk regardless of the listener's position by using listener position tracking (LPT) system. The SS/CC scheme is composed of two parts: LPT-based SS and CC parts. In this paper, the SS/CC scheme is evaluated by some criteria such as follows: condition number, and the balance characteristic, its root mean square error, and running average.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.