• Nuclear Engineering and Technology
• /
• v.43 no.2
• /
• pp.149-158
• /
• 2011

Metal waste generated from the pyroprocessing of 10 MtU of spent fuel was classified by comparing the specific activity of a relevant radionuclide with the limit value of the specific activity specified in the Korean acceptance criteria for a lowand intermediate-level waste repository. A Korean Optimized Fuel Assembly design with a 17${\times}$17 array, an initial enrichment of 4.5 weight-percent, discharge burn-up of 55 GWD/MtU, and a 10-year cooling time was considered. Initially, the mass and volume of each structural component of the assembly were calculated in detail, and a source term analysis was subsequently performed using ORIGEN-S for these components. An activation cross-section library generated by the KENO-VI/ORIGEN-S module was utilized for top-end and bottom-end pieces. As a result, an Inconel grid plate, a SUS plenum spring, a SUS guide tube subpart, SUS top-end and bottom-end pieces, and an Inconel top-end leaf spring were determined to be unacceptable for the Gyeongju low- and intermediate-level waste repository, as these waste products exceeded the acceptance criteria. In contrast, a Zircaloy grid plate and guide tube can be placed in the Gyeongju repository. Non-contaminated Zircaloy cladding occupying 76% of the metal waste was found to have a lower level of specific activity than the limit value. However, Zircaloy cladding contaminated by fission products and actinides during the decladding process of pyroprocessing was revealed to have 52 and 2 times higher specific activity levels than the limit values for alpha and $^{90}Sr$, respectively. Finally, it was found that 88.7% of the metal waste from the 17${\times}$17 Korean Optimized Fuel Assembly design should be disposed of in a deep geological repository. Therefore, it can be summarized that separation technology with a higher decontamination factor for transuranics and strontium should be developed for the efficient management of metal waste resulting from pyroprocessing.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.17-24
• /
• 2022

With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.

• Korean Journal of Radiology
• /
• v.23 no.12
• /
• pp.1251-1259
• /
• 2022

Objective: T1 mapping provides valuable information regarding cardiomyopathies. Manual drawing is time consuming and prone to subjective errors. Therefore, this study aimed to test a DL algorithm for the automated measurement of native T1 and extracellular volume (ECV) fractions in cardiac magnetic resonance (CMR) imaging with a temporally separated dataset. Materials and Methods: CMR images obtained for 95 participants (mean age ± standard deviation, 54.5 ± 15.2 years), including 36 left ventricular hypertrophy (12 hypertrophic cardiomyopathy, 12 Fabry disease, and 12 amyloidosis), 32 dilated cardiomyopathy, and 27 healthy volunteers, were included. A commercial deep learning (DL) algorithm based on 2D U-net (Myomics-T1 software, version 1.0.0) was used for the automated analysis of T1 maps. Four radiologists, as study readers, performed manual analysis. The reference standard was the consensus result of the manual analysis by two additional expert readers. The segmentation performance of the DL algorithm and the correlation and agreement between the automated measurement and the reference standard were assessed. Interobserver agreement among the four radiologists was analyzed. Results: DL successfully segmented the myocardium in 99.3% of slices in the native T1 map and 89.8% of slices in the post-T1 map with Dice similarity coefficients of 0.86 ± 0.05 and 0.74 ± 0.17, respectively. Native T1 and ECV showed strong correlation and agreement between DL and the reference: for T1, r = 0.967 (95% confidence interval [CI], 0.951-0.978) and bias of 9.5 msec (95% limits of agreement [LOA], -23.6-42.6 msec); for ECV, r = 0.987 (95% CI, 0.980-0.991) and bias of 0.7% (95% LOA, -2.8%-4.2%) on per-subject basis. Agreements between DL and each of the four radiologists were excellent (intraclass correlation coefficient [ICC] of 0.98-0.99 for both native T1 and ECV), comparable to the pairwise agreement between the radiologists (ICC of 0.97-1.00 and 0.99-1.00 for native T1 and ECV, respectively). Conclusion: The DL algorithm allowed automated T1 and ECV measurements comparable to those of radiologists.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1574-1580
• /
• 2020

Traditional pose estimation methods include using special devices or images through image processing. The disadvantage of using a device is that the environment in which the device can be used is limited and costly. The use of cameras and image processing has the advantage of reducing environmental constraints and costs, but the performance is lower. CNN(Convolutional Neural Networks) were studied for pose estimation just using only camera without these disadvantage. Various techniques were proposed to increase cognitive performance. In this paper, the effect of the skip connection on the network was experimented by using various skip connections on the joint recognition of the hand. Experiments have confirmed that the presence of additional skip connections other than the basic skip connections has a better effect on performance, but the network with downward skip connections is the best performance.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.434-440
• /
• 2022

Liver transplantation is a critical used treatment method for patients with end-stage liver disease. The number of cases of living donor liver transplantation is increasing due to the imbalance in needs and supplies for brain-dead organ donation. As a result, the importance of the accuracy of the donor's suitability evaluation is also increasing rapidly. To measure the donor's liver volume accurately is the most important, that is absolutely necessary for the recipient's postoperative progress and the donor's safety. Therefore, we propose liver segmentation in abdominal CT images from pre-operation, POD 7, and POD 63 with a two-dimensional U-Net. In addition, we introduce an algorithm to measure the volume of the segmented liver and measure the hepatectomy rate and regeneration rate of pre-operation, POD 7, and POD 63. The performance for the learning model shows the best results in the images from pre-operation. Each dataset from pre-operation, POD 7, and POD 63 has the DSC of 94.55 ± 9.24%, 88.40 ± 18.01%, and 90.64 ± 14.35%. The mean of the measured liver volumes by trained model are 1423.44 ± 270.17 ml in pre-operation, 842.99 ± 190.95 ml in POD 7, and 1048.32 ± 201.02 ml in POD 63. The donor's hepatectomy rate is an average of 39.68 ± 13.06%, and the regeneration rate in POD 63 is an average of 14.78 ± 14.07%.

• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.2-2
• /
• 2023

기후변화가 가속화로 인해 수재해의 빈도와 강도 예측이 어려워짐에 따라 실시간 홍수 모니터링에 대한 수요가 증가하고 있다. 합성개구레이다는 광원과 날씨에 무관하게 촬영이 가능하여 수재해 발생시에도 영상을 확보할 수 있다. 합성개구레이다를 활용한 수체 탐지 알고리즘 개발이 활발히 연구되어 왔고, 딥러닝의 발달로 CNN을 활용하여 높은 정확도로 수체 탐지가 기능해졌다. 하지만, CNN 기반 수체 탐지 모델은 훈련시 높은 정량적 정확성 지표를 달성하여도 추론 후 정성적 평가시 경계와 소하천에 대한 탐지 정확성이 떨어진다. 홍수 모니터링에서 특히 중요한 정보인 경계와 좁은 하천에 대해서 정확성이 떨어짐에 따라 실생활 적용이 어렵다. 이에 경계를 강화한 적대적 학습 기반의 수체 탐지 모델을 개발하여 더 세밀하고 정확하게 탐지하고자 한다. 적대적 학습은 생성적 적대 신경망(GAN)의 두 개의 모델인 생성자와 판별자가 서로 관여하며 더 높은 정확도를 달성할 수 있도록 학습이다. 이러한 적대적 학습 개념을 수체 탐지 모델에 처음으로 도입하여, 생성자는 실제 라벨 데이터와 유사하게 수체 경계와 소하천까지 탐지하고자 학습한다. 반면 판별자는 경계 거리 변환 맵과 합성개구레이다 영상을 기반으로 라벨데이터와 수체 탐지 결과를 구분한다. 경계가 강화될 수 있도록, 면적과 경계를 모두 고려할 수 있는 손실함수 조합을 구성하였다. 제안 모델이 경계와 소하천을 정확히 탐지하는지 판단하기 위해, 정량적 지표로 F1-score를 사용하였으며, 육안 판독을 통해 정성적 평가도 진행하였다. 기존 U-Net 모델이 탐지하지 못하던 영역에 대해 제안한 경계 강화 적대적 수체 탐지 모델이 수체의 세밀한 부분까지 탐지할 수 있음을 증명하였다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.16 no.1
• /
• pp.3225-3262
• /
• 1974

The purposes of this thesis are to clarify experimentally the variation of ground water temperature in tube wells during the irrigation period of paddy rice, and the effect of ground water irrigation on the growth, grain yield and yield components of the rice plant, and, furthermore, when and why the plant is most liable to be damaged by ground water, and also to find out the effective ground water irrigation methods. The results obtained in this experiment are as follows; 1. The temperature of ground water in tube wells varies according to the location, year, and the depth of the well. The average temperatures of ground water in a tubewells, 6.3m, 8.0m deep are $14.5^{\circ}C$ and $13.1^{\circ}C$, respercively, during the irrigation period of paddy rice (From the middle of June to the end of September). In the former the temperature rises continuously from $12.3^{\circ}C$ to 16.4$^{\circ}C$ and in the latter from $12.4^{\circ}C$ to $13.8^{\circ}C$ during the same period. These temperatures are approximately the same value as the estimated temperatures. The temperature difference between the ground water and the surface water is approximately $11^{\circ}C$. 2. The results obtained from the analysis of the water quality of the "Seoho" reservoir and that of water from the tube well show that the pH values of the ground water and the surface water are 6.35 and 6.00, respectively, and inorganic components such as N, PO4, Na, Cl, SiO2 and Ca are contained more in the ground water than in the surface water while K, SO4, Fe and Mg are contained less in the ground water. 3. The response of growth, yield and yield components of paddy rice to ground water irrigation are as follows; (l) Using ground water irrigation during the watered rice nursery period(seeding date: 30 April, 1970), the chracteristics of a young rice plant, such as plant height, number of leaves, and number of tillers are inferior to those of young rice plants irrigated with surface water during the same period. (2) In cases where ground water and surface water are supplied separately by the gravity flow method, it is found that ground water irrigation to the rice plant delays the stage at which there is a maximum increase in the number of tillers by 6 days. (3) At the tillering stage of rice plant just after transplanting, the effect of ground water irrigation on the increase in the number of tillers is better, compared with the method of supplying surface water throughout the whole irrigation period. Conversely, the number of tillers is decreased by ground water irrigation at the reproductive stage. Plant height is extremely restrained by ground water irrigation. (4) Heading date is clearly delayed by the ground water irrigation when it is practised during the growth stages or at the reproductive stage only. (5) The heading date of rice plants is slightly delayed by irrigation with the gravity flow method as compared with the standing water method. (6) The response of yield and of yield components of rice to ground water irrigation are as follows: \circled1 When ground water irrigation is practised during the growth stages and the reproductive stage, the culm length of the rice plant is reduced by 11 percent and 8 percent, respectively, when compared with the surface water irrigation used throughout all the growth stages. \circled2 Panicle length is found to be the longest on the test plot in which ground water irrigation is practised at the tillering stage. A similar tendency as that seen in the culm length is observed on other test plots. \circled3 The number of panicles is found to be the least on the plot in which ground water irrigation is practised by the gravity flow method throughout all the growth stages of the rice plant. No significant difference is found between the other plots. \circled4 The number of spikelets per panicle at the various stages of rice growth at which_ surface or ground water is supplied by gravity flow method are as follows; surface water at all growth stages‥‥‥‥‥ 98.5. Ground water at all growth stages‥‥‥‥‥‥62.2 Ground water at the tillering stage‥‥‥‥‥ 82.6. Ground water at the reproductive stage ‥‥‥‥‥ 74.1. \circled5 Ripening percentage is about 70 percent on the test plot in which ground water irrigation is practised during all the growth stages and at the tillering stage only. However, when ground water irrigation is practised, at the reproductive stage, the ripening percentage is reduced to 50 percent. This means that 20 percent reduction in the ripening percentage by using ground water irrigation at the reproductive stage. \circled6 The weight of 1,000 kernels is found to show a similar tendency as in the case of ripening percentage i. e. the ground water irrigation during all the growth stages and at the reproductive stage results in a decreased weight of the 1,000 kernels. \circled7 The yield of brown rice from the various treatments are as follows; Gravity flow; Surface water at all growth stages‥‥‥‥‥‥514kg/10a. Ground water at all growth stages‥‥‥‥‥‥428kg/10a. Ground water at the reproductive stage‥‥‥‥‥‥430kg/10a. Standing water; Surface water at all growh stages‥‥‥‥‥‥556kg/10a. Ground water at all growth stages‥‥‥‥‥‥441kg/10a. Ground water at the reproductive stage‥‥‥‥‥‥450kg/10a. The above figures show that ground water irrigation by the gravity flow and by the standing water method during all the growth stages resulted in an 18 percent and a 21 percent decrease in the yield of brown rice, respectively, when compared with surface water irrigation. Also ground water irrigation by gravity flow and by standing water resulted in respective decreases in yield of 16 percent and 19 percent, compared with the surface irrigation method. 4. Results obtained from the experiments on the improvement of ground water irrigation efficiency to paddy rice are as follows; (1) When the standing water irrigation with surface water is practised, the daily average water temperature in a paddy field is 25.2$^{\circ}C$, but, when the gravity flow method is practised with the same irrigation water, the daily average water temperature is 24.5$^{\circ}C$. This means that the former is 0.7$^{\circ}C$ higher than the latter. On the other hand, when ground water is used, the daily water temperatures in a paddy field are respectively 21.$0^{\circ}C$ and 19.3$^{\circ}C$ by practising standing water and the gravity flow method. It can be seen that the former is approximately 1.$0^{\circ}C$ higher than the latter. (2) When the non-water-logged cultivation is practised, the yield of brown rice is 516.3kg/10a, while the yield of brown rice from ground water irrigation plot throughout the whole irrigation period and surface water irrigation plot are 446.3kg/10a and 556.4kg/10a, respectivelely. This means that there is no significant difference in yields between surface water irrigation practice and non-water-logged cultivation, and also means that non-water-logged cultivation results in a 12.6 percent increase in yield compared with the yield from the ground water irrigation plot. (3) The black and white coloring on the inside surface of the water warming ponds has no substantial effect on the temperature of the water. The average daily water temperatures of the various water warming ponds, having different depths, are expressed as Y=aX+b, while the daily average water temperatures at various depths in a water warming pond are expressed as Y=a(b)x (where Y: the daily average water temperature, a,b: constants depending on the type of water warming pond, X; water depth). As the depth of water warning pond is increased, the diurnal difference of the highest and the lowest water temperature is decreased, and also, the time at which the highest water temperature occurs, is delayed. (4) The degree of warming by using a polyethylene tube, 100m in length and 10cm in diameter, is 4~9$^{\circ}C$. Heat exchange rate of a polyethylene tube is 1.5 times higher than that or a water warming channel. The following equation expresses the water warming mechanism of a polyethylene tube where distance from the tube inlet, time in day and several climatic factors are given: {{{{ theta omega (dwt)= { a}_{0 } (1-e- { x} over { PHI v })+ { 2} atop { SUM from { { n}=1} { { a}_{n } } over { SQRT { 1+ {( n omega PHI) }^{2 } } } } LEFT { sin(n omega t+ { b}_{n }+ { tan}^{-1 }n omega PHI )-e- { x} over { PHI v }sin(n omega LEFT ( t- { x} over {v } RIGHT ) + { b}_{n }+ { tan}^{-1 }n omega PHI ) RIGHT } +e- { x} over { PHI v } theta i}}}}{{{{ { theta }_{$\infty$ }(t)= { { alpha theta }_{a }+ { theta }_{ w'} +(S- { B}_{s } ) { U}_{w } } over { beta } , PHI = { { cpDU}_{ omega } } over {4 beta } }}}} where $\theta$$\omega$; discharged water temperature($^{\circ}C$) $\theta$a; air temperature ($^{\circ}C$) $\theta$$\omega$';ponded water temperature($^{\circ}C$) s ; net solar radiation(ly/min) t ; time(tadian) x; tube length(cm) D; diameter(cm) ao,an,bn;constants determined from $\theta$$\omega$(t) varitation. cp; heat capacity of water(cal/$^{\circ}C$ ㎥) U,Ua; overall heat transfer coefficient(cal/$^{\circ}C$ $\textrm{cm}^2$ min-1) $\omega$;1 velocity of water in a polyethylene tube(cm/min) Bs ; heat exchange rate between water and soil(ly/min)