Hui F Cheng

US Patent:

8233704, Jul 31, 2012

Filed:

Jun 10, 2008

Appl. No.:

12/136138

Inventors:

Feng Han - Lawrenceville NJ, US
Hui Cheng - Bridgewater NJ, US
Jiangjian Xiao - Plainsboro NJ, US
Harpreet Singh Sawhney - West Windsor NJ, US

Assignee:

SRI International - Menlo Park CA

International Classification:

G06K 9/62
G06E 1/00
G06E 3/00
G06F 15/18
G06G 7/00

US Classification:

382159, 706 20

Abstract:

A method for automatically generating a strong classifier for determining whether at least one object is detected in at least one image is disclosed, comprising the steps of: (a) receiving a data set of training images having positive images; (b) randomly selecting a subset of positive images from the training images to create a set of candidate exemplars, wherein said positive images include at least one object of the same type as the object to be detected; (c) training a weak classifier based on at least one of the candidate exemplars, said training being based on at least one comparison of a plurality of heterogeneous compositional features located in the at least one image and corresponding heterogeneous compositional features in the one of set of candidate exemplars; (d) repeating steps (c) for each of the remaining candidate exemplars; and (e) combining the individual classifiers into a strong classifier, wherein the strong classifier is configured to determine the presence or absence in an image of the object to be detected.

US Patent:

8634638, Jan 21, 2014

Filed:

Jun 22, 2009

Appl. No.:

12/488911

Inventors:

Feng Han - Melville NY, US
Hui Cheng - Bridgewater NJ, US
Jiangjian Xiao - Plainsboro NJ, US
Harpreet Singh Sawhney - West Windsor NJ, US
Rakesh Kumar - Monmouth Junction NJ, US
Yanlin Guo - Vienna VA, US

Assignee:

SRI International - Menlo Park CA

International Classification:

G06K 9/62

US Classification:

382159

Abstract:

The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.

US Patent:

20120106800, May 3, 2012

Filed:

Oct 28, 2010

Appl. No.:

12/913861

Inventors:

Saad Masood Khan - Hamilton NJ, US
Hui Cheng - Bridgewater NJ, US
Dennis Lee Matthies - Princeton NJ, US
Harpreet Singh Sawhney - West Windsor NJ, US
Chris Broaddus - Philadelphia PA, US
Bogdan Calin Mihai Matei - Monmouth Junction NJ, US
Ajay Divakaran - Monmouth Junction NJ, US

International Classification:

G06K 9/68

US Classification:

382104

Abstract:

A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.

US Patent:

20190284554, Sep 19, 2019

Filed:

Mar 7, 2017

Appl. No.:

16/082852

Inventors:

- Bethesda MD, US
- Rockville MD, US
Zhong Chen - Bethesda MD, US
Hui Cheng - Falls Church VA, US

Assignee:

The United States of America, as represented by the Secretary, Dept. of Health and Human Services - Bethesda MD
miRecule, Inc. - Rockville MD

International Classification:

C12N 15/113
A61P 35/00
A61K 47/69
A61K 47/68
A61K 31/7088
A61K 45/06
C12Q 1/6886

Abstract:

Disclosed herein are methods of treating a tumor in a subject, including administering to the subject one or more miRNA nucleic acids or variants (such as mimics or mimetics) thereof with altered expression in the tumor. Also disclosed herein are compositions including one or more miRNA nucleic acids. In some examples, the miRNA nucleic acids are modified miRNAs, for example, and miRNA nucleic acid including one or more modified nucleotides and/or a 5′-end and/or 3′-end modification. In particular examples, the modified miRNA nucleic acid is an miR-30a nucleic acid. Further disclosed herein are methods of diagnosing a subject as having a tumor with altered expression of one or more miRNA nucleic acids. In some embodiments, the methods include detecting expression of one or more miRNAs in a sample from the subject and comparing the expression in the sample from the subject to a control.

US Patent:

20160110433, Apr 21, 2016

Filed:

Dec 18, 2015

Appl. No.:

14/974871

Inventors:

- Menlo Park CA, US
Jayakrishnan Eledath - Robbinsville NJ, US
Ajay Divakaran - Monmouth Junction NJ, US
Mayank Bansal - Sunnyvale CA, US
Hui Cheng - Bridgewater NJ, US

International Classification:

G06F 17/30

Abstract:

Methods and apparatuses of the present invention generally relate to generating actionable data based on multimodal data from unsynchronized data sources. In an exemplary embodiment, the method comprises receiving multimodal data from one or more unsynchronized data sources, extracting concepts from the multimodal data, the concepts comprising at least one of objects, actions, scenes and emotions, indexing the concepts for searchability; and generating actionable data based on the concepts.

US Patent:

20150254231, Sep 10, 2015

Filed:

May 21, 2015

Appl. No.:

14/718669

Inventors:

- Menlo Park CA, US
Jayakrishnan Eledath - Robbinsville NJ, US
Ajay Divakaran - Monmouth Junction NJ, US
Mayank Bansal - Plainsboro NJ, US
Hui Cheng - Bridgewater NJ, US

International Classification:

G06F 17/27
G06F 17/30

Abstract:

A computer-implemented method comprising collecting data from a plurality of information sources, identifying a geographic location associated with the data and forming a corresponding event according to the geographic location, correlating the data and the event with one or more topics based at least partly on the identified geographic location and storing the correlated data and event and inferring the associated geographic location if the data does not comprise explicit location information, including matching the data against a database of geo-referenced data.