Yan K Liu

US Patent:

8019838, Sep 13, 2011

Filed:

May 21, 2008

Appl. No.:

12/124560

Inventors:

Michael Zhihe Z Jiang - Lake in the Hills IL, US
Yan Liu - Hanover Park IL, US
John C. Strassner - North Barrington IL, US
Jing Zhang - Schaumburg IL, US

Assignee:

Motorola Solutions, Inc. - Schaumburg IL

International Classification:

G06F 15/177

US Classification:

709221, 709224, 370225

Abstract:

A system, method, and information processing system for managing a configuration of a network device. A current state associated with at least one network device () is determined (). A set of commands () available for the current state of the network device () is retrieved (). A next state associated with a current command is determined () for each command in the set of commands (). A transition from the current state to the next state is created () in response to determining a next state associated with a current command. A transition is determined to have been created for each command in the set of commands (). An extended finite state machine () is created that includes at least the current state, the next state, and the transition for each of the commands in the set of commands ().

US Patent:

8505047, Aug 6, 2013

Filed:

Nov 20, 2010

Appl. No.:

12/951014

Inventors:

Yan Liu - Hanover Park IL, US
Bhavan Ghandhi - Vernon Hills IL, US
Srinivasa C. Samudrala - Richardson TX, US
Kabe Vanderbaan - Arlington Heights IL, US
Jing Zhang - Hanover Park IL, US

Assignee:

Motorola Solutions, Inc. - Schaumburg IL

International Classification:

H04N 7/10
H04N 7/025

US Classification:

725 35, 725 34, 725 36, 725116, 725146, 705 11, 705 1443

Abstract:

A content provider broadcasts content to subscribers through a content distribution system. The content distribution system operator can capture broadcast content in accordance with policies established by the content provider and make the content available subsequent to the original broadcast in accordance with applicable business policies. Business policies are created by the content provider by modifying template information models which have associated rules. The content distributor stores the business policies and evaluates rules indicated by the business policies against attributes of a content asset to determine availability of the content asset.

US Patent:

7996440, Aug 9, 2011

Filed:

Apr 30, 2007

Appl. No.:

11/742215

Inventors:

Katharina Probst - Chicago IL, US
Rayid Ghani - Chicago IL, US
Andrew E. Fano - Lincolnshire IL, US
Marko Krema - Evanston IL, US
Yan Liu - New York City NY, US

Assignee:

Accenture Global Services Limited - Dublin

International Classification:

G06F 17/30

US Classification:

707803, 704275

Abstract:

One or more classification algorithms are applied to at least one natural language document in order to extract both attributes and values of a given product. Supervised classification algorithms, semi-supervised classification algorithms, unsupervised classification algorithms or combinations of such classification algorithms may be employed for this purpose. The at least one natural language document may be obtained via a public communication network. Two or more attributes (or two or more values) thus identified may be merged to form one or more attribute phrases or value phrases. Once attributes and values have been extracted in this manner, association or linking operations may be performed to establish attribute-value pairs that are descriptive of the product. In a presently preferred embodiment, an (unsupervised) algorithm is used to generate seed attributes and values which can then support a supervised or semi-supervised classification algorithm.

US Patent:

20090327172, Dec 31, 2009

Filed:

Jun 27, 2008

Appl. No.:

12/163295

Inventors:

Yan Liu - Hanover Park IL, US
Michael Zhihe Z. Jiang - Lake in the Hills IL, US
John C. Strassner - North Barrington IL, US
Jing Zhang - Schaumberg IL, US

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G06F 15/18

US Classification:

706 12

Abstract:

A method, information processing system, and network select machine learning algorithms for managing autonomous operations of network elements. A state () of at least one problem () and at least one context associated with the problem are received as input. A machine learning algorithm () is selected () based on the problem and context of the problem that have been received. The machine learning algorithm () that has been selected is outputted to an autonomic controller.

US Patent:

20090328133, Dec 31, 2009

Filed:

Jun 27, 2008

Appl. No.:

12/163343

Inventors:

John C. Strassner - North Barrington IL, US
Gregory W. Cox - Schaumburg IL, US
Zhi Fu - Lake Zurich IL, US
Yan Liu - Hanover Park IL, US

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

H04L 9/00
G06F 15/173

US Classification:

726 1, 709223

Abstract:

A method, information processing system, and system manage network entities. At least a portion of at least one information model () for a first managed entity () and at least a second managed entity () is accessed. The portion of the at least one information model () includes a set of capabilities () associated with the first managed entity () and second managed entity (), respectively. A first set of capabilities () supported by the first managed entity () and a second set of capabilities () supported by the second managed entity () are identified based on the portion of the at least one information model (). A set of common capabilities () from the first set of capabilities () and the second set of capabilities () that is supported by both of the first managed entity () and the second managed entity () is determined.

US Patent:

20120054163, Mar 1, 2012

Filed:

Aug 27, 2010

Appl. No.:

12/869958

Inventors:

Yan Liu - Hanover Park IL, US
Zhi Fu - Herndon VA, US
Kabe Vanderbaan - Arlington Heights IL, US

Assignee:

MOTOROLA, INC. - Schaumburg IL

International Classification:

G06F 17/30

US Classification:

707694, 707E17007

Abstract:

In a method for classifying policy conflicts in a managed system, a plurality of separate attributes of a policy rule is identified. The plurality of separate attributes is compared with attributes of previously stored policies rules to determine whether one or more policy conflicts exist. In response to a determination that one or more policy conflicts exist, the one or more policy conflicts are classified according to a predefined schedule.

US Patent:

20210312612, Oct 7, 2021

Filed:

Apr 3, 2020

Appl. No.:

16/839733

Inventors:

- Chicago IL, US
- Otawara-shi, JP
Yan Liu - Vernon Hills IL, US
Zhou Yu - Vernon Hills IL, US

Assignee:

The University of Chicago - Chicago IL
CANON MEDICAL SYSTEMS CORPORATION - Otawara-shi

International Classification:

G06T 7/00
A61B 6/03

Abstract:

A method and apparatus uses multi-material decomposition of three or more material components to generate material-component images from spectral images reconstructed from spectral computed tomography data. In three-component material decomposition e.g., the Mendonça method is used for multi-material decomposition when the attenuation values satisfy an assumed volume fraction condition (i.e., for a given voxel, the attenuation values are within a triangle having vertices given by unit volume fractions of three respective material components). However, when the volume fraction condition fails (e.g., the attenuation values are outside the triangle), either a shortest-Hausdorff-distance method or a closest-edge method is used for multi-material decomposition. For example, the attenuation values of the voxel are projected onto a lower-dimensional space (e.g., the space of a closest edge) and decomposed into a pair/single material component(s) of the lower-dimensional space.

US Patent:

20210290193, Sep 23, 2021

Filed:

Jun 4, 2021

Appl. No.:

17/339093

Inventors:

- Otawara-shi, JP
Ruoqiao ZHANG - Arlington Heights IL, US
Zhou YU - Wilmette IL, US
Yan LIU - Vernon Hills IL, US

Assignee:

CANON MEDICAL SYSTEMS CORPORATION - Otawara-shi

International Classification:

A61B 6/00
G06T 11/00
G06T 5/20
G06T 5/10
G06N 3/08
G06N 3/04
G06T 5/50

Abstract:

A deep learning (DL) network corrects/performs sinogram completion in computed tomography (CT) images based on complementary high- and low-kV projection data generated from a sparse (or fast) kilo-voltage (kV)-switching CT scan. The DL network is trained using inputs and targets, which respectively generated with and without kV switching. Another DL network can be trained to correct sinogram-completion errors in the projection data after a basis/material decomposition. A third DL network can be trained to correct sinogram-completion errors in reconstructed images based on the kV-switching projection data. Performance of the DL network can be improved by dividing a 3D convolutional neural network (CNN) into two steps performed by respective 2D CNNs. Further, the projection data and DLL can be divided into high- and low-frequency components to improve performance.