http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
KyungSang Sung,Wonshik Na,Kun-Soo Oh,HaeSeok Oh 보안공학연구지원센터 2007 International Journal of Smart Home Vol.1 No.1
ReferencesUser should monitor the home network environment periodically so to maintain his optimal conditions. User should also collect the information about the environments of electronic devices within home network, analyze them through learning algorithm and seize the disposition of user under the collected information. In addition, after seizing the disposition of user, home network should be controlled to provide optimal environment to user through continuous monitoring. And more enhanced services that can analyze users' pattern of behaviors and reflect individual tendency in the service should be offered so that users can obtain the information they want much faster. Thus, an intellectual control model will be discussed herein, which can offer active service based on a pattern of users' behaviors, in order to suggest a device that predicts users' activities and operates in a more intelligent way.
Advanced Daily Prediction Model for National Suicide Numbers with Social Media Data
KyungSang Lee,Hyewon Lee,Woojae Myung,GilYoung Song,Kihwang Lee,Ho Kim,Bernard J. Carroll,DohKwan Kim 대한신경정신의학회 2018 PSYCHIATRY INVESTIGATION Vol.15 No.4
Objective-Suicide is a significant public health concern worldwide. Social media data have a potential role in identifying high suicide risk individuals and also in predicting suicide rate at the population level. In this study, we report an advanced daily suicide prediction model using social media data combined with economic/meteorological variables along with observed suicide data lagged by 1 week. Methods-The social media data were drawn from weblog posts. We examined a total of 10,035 social media keywords for suicide prediction. We made predictions of national suicide numbers 7 days in advance daily for 2 years, based on a daily moving 5-year prediction modeling period. Results-Our model predicted the likely range of daily national suicide numbers with 82.9% accuracy. Among the social media variables, words denoting economic issues and mood status showed high predictive strength. Observed number of suicides one week previously, recent celebrity suicide, and day of week followed by stock index, consumer price index, and sunlight duration 7 days before the target date were notable predictors along with the social media variables. Conclusion-These results strengthen the case for social media data to supplement classical social/economic/climatic data in forecasting national suicide events.
Sparse-View Spectral CT Reconstruction Using Spectral Patch-Based Low-Rank Penalty
Kyungsang Kim,Jong Chul Ye,Worstell, William,Jinsong Ouyang,Rakvongthai, Yothin,El Fakhri, Georges,Quanzheng Li IEEE 2015 IEEE transactions on medical imaging Vol.34 No.3
<P>Spectral computed tomography (CT) is a promising technique with the potential for improving lesion detection, tissue characterization, and material decomposition. In this paper, we are interested in kVp switching-based spectral CT that alternates distinct kVp X-ray transmissions during gantry rotation. This system can acquire multiple X-ray energy transmissions without additional radiation dose. However, only sparse views are generated for each spectral measurement; and the spectra themselves are limited in number. To address these limitations, we propose a penalized maximum likelihood method using spectral patch-based low-rank penalty, which exploits the self-similarity of patches that are collected at the same position in spectral images. The main advantage is that the relatively small number of materials within each patch allows us to employ the low-rank penalty that is less sensitive to intensity changes while preserving edge directions. In our optimization formulation, the cost function consists of the Poisson log-likelihood for X-ray transmission and the nonconvex patch-based low-rank penalty. Since the original cost function is difficult to minimize directly, we propose an optimization method using separable quadratic surrogate and concave convex procedure algorithms for the log-likelihood and penalty terms, which results in an alternating minimization that provides a computational advantage because each subproblem can be solved independently. We performed computer simulations and a real experiment using a kVp switching-based spectral CT with sparse-view measurements, and compared the proposed method with conventional algorithms. We confirmed that the proposed method improves spectral images both qualitatively and quantitatively. Furthermore, our GPU implementation significantly reduces the computational cost.</P>
KyungSang Lee,YoungMin Park,SeungHwan Lee 대한신경정신의학회 2012 PSYCHIATRY INVESTIGATION Vol.9 No.3
Objective-The loudness dependence of the auditory evoked potential (LDAEP) is suggested to be a marker of serotonin system function. This study explored the LDAEP of multiple mood statuses (depression, mania, and euthymia) and its clinical implication in bipolar disorder patients. Methods-A total of 89 subjects, comprising 35 patients with bipolar disorder, 32 patients with schizophrenia, and 22 healthy controls were evaluated. The bipolar disorder cases comprised 10 depressed patients, 15 patients with mania, and 10 euthymic patients. The N1/P2 peak-to-peak amplitudes were measured at 5 stimulus intensities, and the LDAEP was calculated as the slope of the linear regression. Both cortical and source LDAEP values were calculated. Results-LDAEP varied according to mood statuses, and was significantly stronger in cases of euthymia, depression, and mania. Cortical LDAEP was significantly stronger in patients with bipolar euthymia compared with schizophrenia, stronger in bipolar depression than in schizophrenia, stronger in healthy controls than in schizophrenia patients, and stronger in healthy controls than in patients with bipolar mania. Source LDAEP was significantly stronger in patients with bipolar euthymia, bipolar depression, and bipolar mania compared with schizophrenia, stronger in bipolar euthymia than in bipolar mania. Psychotic features weakened the source LDAEP relative to nonpsychotic features. The severity of the depressive symptom was negatively correlated with source LDAEP. Conclusion-These findings suggest that the serotonin activity of patients with bipolar disorder may vary according to mood status. A longitudinal follow-up study should be pursued using drug-naive subjects.
Kim, Kyungsang,Lee, Taewon,Seong, Younghun,Lee, Jongha,Jang, Kwang Eun,Choi, Jaegu,Choi, Young Wook,Kim, Hak Hee,Shin, Hee Jung,Cha, Joo Hee,Cho, Seungryong,Ye, Jong Chul Published for the American Association of Physicis 2015 Medical physics Vol.42 No.9
<P>In digital breast tomosynthesis (DBT), scatter correction is highly desirable, as it improves image quality at low doses. Because the DBT detector panel is typically stationary during the source rotation, antiscatter grids are not generally compatible with DBT; thus, a software-based scatter correction is required. This work proposes a fully iterative scatter correction method that uses a novel fast Monte Carlo simulation (MCS) with a tissue-composition ratio estimation technique for DBT imaging.</P>
Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting
Kim, Kyungsang,Wu, Dufan,Gong, Kuang,Dutta, Joyita,Kim, Jong Hoon,Son, Young Don,Kim, Hang Keun,El Fakhri, Georges,Li, Quanzheng IEEE 2018 IEEE transactions on medical imaging Vol.37 No.6
<P>Motivated by the great potential of deep learning in medical imaging, we propose an iterative positron emission tomography reconstruction framework using a deep learning-based prior. We utilized the denoising convolutional neural network (DnCNN) method and trained the network using full-dose images as the ground truth and low dose images reconstructed from downsampled data by Poisson thinning as input. Since most published deep networks are trained at a predetermined noise level, the noise level disparity of training and testing data is a major problem for their applicability as a generalized prior. In particular, the noise level significantly changes in each iteration, which can potentially degrade the overall performance of iterative reconstruction. Due to insufficient existing studies, we conducted simulations and evaluated the degradation of performance at various noise conditions. Our findings indicated that DnCNN produces additional bias induced by the disparity of noise levels. To address this issue, we propose a local linear fitting function incorporated with the DnCNN prior to improve the image quality by preventing unwanted bias. We demonstrate that the resultant method is robust against noise level disparities despite the network being trained at a predetermined noise level. By means of bias and standard deviation studies via both simulations and clinical experiments, we show that the proposed method outperforms conventional methods based on total variation and non-local means penalties. We thereby confirm that the proposed method improves the reconstruction result both quantitatively and qualitatively.</P>