Jian W Lin

US Patent:

6340887, Jan 22, 2002

Filed:

Sep 21, 1999

Appl. No.:

09/400228

Inventors:

Kecheng Liu - Solon OH
Jian Lin - Solon OH
Paul M. Margosian - Lakewood OH

Assignee:

Picker International Inc. - Highland Heights OH

International Classification:

G01V 300

US Classification:

324309, 324306

Abstract:

A black blood magnetic resonance angiogram is produced by exciting dipoles ( ) and repeatedly inverting the resonance ( ,. . . ) to produce a series of magnetic resonance echoes ( ,. . . ). Early echoes (e. g. , ( ,. . . , 56 )) are more heavily proton density weighted than later echoes (e. g. , ( )) which are more heavily T2 weighted. The magnetic resonance echoes are received and demodulated ( ) into a series of data lines. The data lines are sorted ( ) between the more heavily proton density weighted data lines and T2 weighted data lines which are reconstructed into a proton density weighted image representation and a T2 weighted image representation. The proton density weighted and T2 weighted image representations are combined ( ) to emphasize the black blood from the T2 weighted images and the static tissue from the proton density weighted image. The combined image is a black blood magnetic resonance angiogram. The production of the angiogram is time efficient and displays enhanced vessel depiction.

US Patent:

6397096, May 28, 2002

Filed:

Mar 31, 2000

Appl. No.:

09/540341

Inventors:

Kecheng Liu - Solon OH
Paul M. Margosian - Lakewood OH
Jian Lin - Solon OH

Assignee:

Philips Medical Systems (Cleveland) Inc. - Highland Heights OH

International Classification:

A61B 5055

US Classification:

600419, 382130, 324307, 324309

Abstract:

A black blood magnetic resonance angiogram is produced by exciting dipoles ( ) and repeatedly inverting the resonance ( ,. . . ) to produce a series of magnetic resonance echoes ( ,. . . ). Early echoes (e. g. , ( )) are more heavily proton density weighted than later echoes (e. g. , ( )), which are more heavily T weighted. The magnetic resonance echoes are received and demodulated ( ) into a series of data lines. The data lines are sorted ( ) between the more heavily proton density weighted data lines and T weighted data lines which are reconstructed into a proton density weighted image representation and a T weighted image representation. The proton density weighted and T weighted image representations are combined ( ) to emphasize the black blood from the T weighted images and the static tissue from the proton density weighted image. The combination processor ( ) scales ( ) the PDW and T W images to a common maximum intensity level. The PDW and T W image representations are then combined, e. g.

US Patent:

20190347578, Nov 14, 2019

Filed:

May 10, 2018

Appl. No.:

15/976463

Inventors:

- Armonk NY, US
Matthew Elsner - Dunwoody GA, US
Jian Lin - Alpharetta GA, US
Matthew Paul Ouellette - Fredericton, CA
Yun Pan - Roswell GA, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06N 99/00
H04L 29/06

Abstract:

A machine learning (ML)-based technique for user behavior analysis that detects when users deviate from expected behavior. A ML model is trained using training data derived from activity data from a first set of users. The model is refined in a computationally-efficient manner by identifying a second set of users that constitute a “watch list.” At a given time, a differential data ingestion operation is then performed to incorporate data for the second set of users into the training data, while also pruning at least a portion of the data set corresponding to data associated with any user included in the first set but not in the second set. These operations update the training data used for the machine learning. The machine learning model is then refined based on the updated training data that incorporates the activity data ingested from the users identified in the watch list.

US Patent:

20190349391, Nov 14, 2019

Filed:

May 10, 2018

Appl. No.:

15/975799

Inventors:

- Armonk NY, US
Jian Lin - Alpharetta GA, US
Ronald Williams - Austin TX, US
Ilgen Banu Yuceer - London, GB

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

H04L 29/06
H04L 29/08
G06K 9/62

Abstract:

A machine learning-based technique for user behavior analysis that detects when users deviate from expected behavior. In this approach, a set of user groups are provided, preferably based on information provided from a user registry. A set of training data for each of the set of user groups is then obtained, preferably by collecting security events generated for a collection of the users over a given time period (e.g., a last thirty (30) days). A machine learning system is then trained using the set of training data to produce a model that includes a set of clusters in user behavior model, wherein a cluster is a learned user group that corresponds to a defined user group. Once the model is built, it is used to identify users that deviate from their expected group behavior. In particular, the system compares a current behavior of a user against the model and flags anomalous behavior. The user behavior analysis may be implemented in a security platform, such as a SIEM.