公开(公告)号：US10438699B2

公开(公告)日：2019-10-08

申请号：US15150608

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hai-Hui Huang ,  Xiao-Ying Liu

IPC: G06N7/02 ,  G16H50/20 ,  G06N5/02

Abstract: A system and a method for determining an association of one or more biological features with a medical condition provides empirical results and simulations confirming that the involvement of both L1/2-regularized logistic regression and L2-regularized logistic regression in the regression model is highly competitive against usual approaches like Lasso, L1/2, SCAD-L2, and Elastic net in analyzing high dimensional and low sample sizes data.

公开(公告)号：US10192642B2

公开(公告)日：2019-01-29

申请号：US15150639

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hua Chai ,  Xiao-Ying Liu

IPC: G06F19/00 ,  G06F19/12 ,  G16H50/50

Abstract: A system and a method for determining an association of at least one biological feature with a medical condition, in particularly, but not exclusively, a system and a method of determining an association of at least one biological feature in form of a gene expression with cancer or a subtype of cancer that can include the generation of a simplified protein-protein interaction network based on processed biological data. The system and respective method is especially suitable for analysis of high dimensional and low sample size biological datasets such as in cancer research.

公开(公告)号：US20170329926A1

公开(公告)日：2017-11-16

申请号：US15150639

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hua Chai ,  Xiao-Ying Liu

IPC: G06F19/00 ,  G06F19/12

CPC classification number: G16H50/50 ,  G06F19/00 ,  G06F19/12

Abstract: A system and a method for determining an association of at least one biological feature with a medical condition, in particularly, but not exclusively, a system and a method of determining an association of at least one biological feature in form of a gene expression with cancer or a subtype of cancer that can include the generation of a simplified protein-protein interaction network based on processed biological data. The system and respective method is especially suitable for analysis of high dimensional and low sample size biological datasets such as in cancer research.

公开(公告)号：US10515724B2

公开(公告)日：2019-12-24

申请号：US15150732

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hai-Hui Huang ,  Xiao-Ying Liu

IPC: G06N7/02 ,  G16H50/20

Abstract: A method and a system for determining an association of at least one biological feature with a medical condition utilizes the novel L1/2 penalized network-constraint regression model to achieve an improved biological analysis, in particular by solving high-dimensional problems. The method and the system of the present invention attain high accuracy and preciseness.

公开(公告)号：US20170329925A1

公开(公告)日：2017-11-16

申请号：US15150580

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hua Chai ,  Zi-yi Yang ,  Xiao-Ying Liu

IPC: G06F19/00 ,  G06F17/18

CPC classification number: G16H50/50 ,  Y02A90/26

Abstract: A system and a method for determining an estimated survival time of a subject with a medical condition utilizes the novel RS-AFT model and is especially suitable and highly advantageous for survival analysis based on microarray gene expression data because of its exceptional performance of gene selection, stable noise resistance, and high prediction precision.

公开(公告)号：US20170329913A1

公开(公告)日：2017-11-16

申请号：US15150732

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hai-Hui Huang ,  Xiao-Ying Liu

IPC: G06F19/00 ,  G06N7/00

Abstract: A method and a system for determining an association of at least one biological feature with a medical condition utilizes the novel L1/2 penalized network-constraint regression model to achieve an improved biological analysis, in particular by solving high-dimensional problems. The method and the system of the present invention attain high accuracy and preciseness.

公开(公告)号：US20170329912A1

公开(公告)日：2017-11-16

申请号：US15150608

申请日：2016-05-10

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Hai-Hui Huang ,  Xiao-Ying Liu

IPC: G06F19/00 ,  G06N5/02

CPC classification number: G16H50/20 ,  G06N5/02 ,  G06N7/023 ,  G06N20/00

Abstract: A system and a method for determining an association of one or more biological features with a medical condition provides empirical results and simulations confirming that the involvement of both L1/2-regularized logistic regression and L2-regularized logistic regression in the regression model is highly competitive against usual approaches like Lasso, L1/2, SCAD-L2, and Elastic net in analyzing high dimensional and low sample sizes data.

公开(公告)号：US09600861B2

公开(公告)日：2017-03-21

申请号：US14835692

申请日：2015-08-25

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Zong Ben Xu ,  Liang-Yong Xia ,  Xiao-Ying Liu

IPC: G06T3/00 ,  G06T3/40

CPC classification number: G06T3/4053

Abstract: A super-resolution method for generating a high-resolution (HR) image from a low-resolution (LR) blurred image is provided. The method is based on a transform-invariant directional total variation (TI-DTV) approach with Schattenp=1/2 (S1/2-norm) and L1/2-norm penalties. The S1/2-norm and the L1/2-norm are used to induce a lower-rank component and a sparse component of the LR blurred image so as to determine an affine transform to be adopted in the TI-DTV approach. In particular, the affine transform is determined such that a weighted sum of the S1/2-norm and the L1/2-norm is substantially minimized. Based on the alternating direction method of multipliers (ADMM), an iterative algorithm is developed to determine the affine transform. The determined affine transform is used to transform a candidate HR image to a transformed image used in computing a directional total variation (DTV), which is involved in determining the HR image.

公开(公告)号：US20170024855A1

公开(公告)日：2017-01-26

申请号：US14835692

申请日：2015-08-25

Applicant: Macau University of Science and Technology

Inventor： Yong Liang ,  Zong Ben Xu ,  Liang-Yong Xia ,  Xiao-Ying Liu

IPC: G06T3/40 ,  G06T3/00

CPC classification number: G06T3/4053

Abstract: A super-resolution method for generating a high-resolution (HR) image from a low-resolution (LR) blurred image is provided. The method is based on a transform-invariant directional total variation (TI-DTV) approach with Schattenp=1/2 (S1/2-norm) and L1/2-norm penalties. The S1/2-norm and the L1/2-norm are used to induce a lower-rank component and a sparse component of the LR blurred image so as to determine an affine transform to be adopted in the TI-DTV approach. In particular, the affine transform is determined such that a weighted sum of the S1/2-norm and the L1/2-norm is substantially minimized. Based on the alternating direction method of multipliers (ADMM), an iterative algorithm is developed to determine the affine transform. The determined affine transform is used to transform a candidate HR image to a transformed image used in computing a directional total variation (DTV), which is involved in determining the HR image.

Abstract translation: 提供了用于从低分辨率（LR）模糊图像生成高分辨率（HR）图像的超分辨率方法。 该方法基于Schattenp = 1/2（S1 / 2-规范）和L1 / 2-范数惩罚的变换不变方向总变异（TI-DTV）方法。 S1 / 2范数和L1 / 2-范数用于引导LR模糊图像的较低等级分量和稀疏分量，以便确定在TI-DTV方法中采用的仿射变换。 特别地，确定仿射变换使得S1 / 2-范数和L1 / 2-范数的加权和基本上最小化。 基于乘法器（ADMM）的交替方向法，开发了一种迭代算法来确定仿射变换。 所确定的仿射变换用于将候选HR图像变换为用于计算方向总变化（DTV）中使用的变换图像，其涉及确定HR图像。