http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Song Zuhua,Guo Dajing,Tang Zhuoyue,Liu Huan,Li Xin,Luo Sha,Yao Xueying,Song Wenlong,Song Junjie,Zhou Zhiming 대한영상의학회 2021 Korean Journal of Radiology Vol.22 No.3
Objective: To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). Materials and Methods: We retrospectively reviewed 261 patients with sICH who underwent initialNCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power. Results: The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively. The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively. Conclusion: NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.
Scheduling Algorithm of Cloud Computing Based on DAG Diagram and Game Optimal Model
Liu Jun,Guo Zuhua 보안공학연구지원센터 2015 International Journal of Grid and Distributed Comp Vol.8 No.4
In order to improve the efficiency of cloud computing task scheduling, we propose a cloud scheduling algorithm based on DAG task graph and game optimal. This method first constructed scheduling tasks of DAG task graph, and set the initial virtual machine for root and leaf nodes, then based on the optimization model of game, the effectiveness of difference between the task configuration after optimization judgment and the current task configuration until the effectiveness difference within a preset range, the experimental results show that the methods herein can achieve not only balancing scheduling between each virtual machine, but also has a faster rate scheduling.
Image Steganography in a Karhunen-Loeve Transform Optimization Model
Li-Yangbo,Guo-Zuhua 보안공학연구지원센터 2016 International Journal of Security and Its Applicat Vol.10 No.5
In allusion to such problems as large perceptual distortion and high error rate caused by high image compression ratio in existing steganography technology in the information security field, an image Steganography based on Karhunen-Loeve transform optimization is proposed in this paper. Specifically, the iterative clustering algorithm is adopted for this method to solve the covariance matrix and the clustering mean value, and relevant values are adjusted for image segmentation; then, KLT algorithm is introduced to compress the image data and the least significant bit is adopted to replace the ciphertext data for data hiding. During information extraction, the reverse linear transformation operation and the original pixel matrix are adopted to obtain the effective hidden image information. The experiment result shows: compared with common algorithms, the proposed method has improved capacity and PSNR, and the image data extracted thereby has small distortion.