Junghwan X Rhee

US Patent:

8495584, Jul 23, 2013

Filed:

Mar 10, 2010

Appl. No.:

12/721141

Inventors:

Kirk A. Beaty - Goldens Bridge NY, US
Andrzej Kochut - Elmsford NY, US
Junghwan Rhee - West Lafayette IN, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 9/44
G06F 15/173
G06F 3/048

US Classification:

717127, 717128, 717129, 717130, 709224, 715764

Abstract:

A plurality of user interactions in a baseline computing system are intercepted and recorded, in an artifact file, with a benchmarking tool. The recorded user interactions from the artifact file are replayed and injected to a software stack of a system under test (whose performance is to be compared to the baseline system), using the benchmarking tool. During the replay, screen updates in the system under test are sequentially compared with expected screen images from the artifact file, until a match is observed in a given case. A response time associated with each of the matches is recorded.

US Patent:

20110131589, Jun 2, 2011

Filed:

Dec 2, 2009

Appl. No.:

12/629248

Inventors:

Kirk Alan Beaty - Hawthorne NY, US
Rajdeep Bhowmik - Johnson City NY, US
Andrzej Kochut - Hawthorne NY, US
Junghwan Rhee - West Lafayette IN, US
Hidayatullah Habeebullah Shaikh - Hawthorne NY, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - ARMONK NY

International Classification:

G06F 9/46
G06F 9/455

US Classification:

719318, 718 1

Abstract:

A system and method for transforming a legacy device into a virtualized environment includes gathering profiling data over time to represent legacy device activities and analyzing the profiling data for system applications and user applications using a processor to determine usage frequency and resource requirements of at least one application. Captured user action events are benchmarked to simulate a user workload for the at least one application to determine how resource utilization and execution times scale from a legacy environment to a virtualized environment. One or more scaling factors are determined to produce a plan to provision for legacy services in the virtualized environment. The legacy system is transformed into the virtualized environment in accordance with the plan.

US Patent:

20130290959, Oct 31, 2013

Filed:

Jun 7, 2013

Appl. No.:

13/913048

Inventors:

Rajdeep Bhowmik - Johnson City NY, US
Andrzej Kochut - Yorktown Heights NY, US
Junghwan Rhee - Princeton NJ, US
Hidayatullah H. Shaikh - Hawthorne NY, US

International Classification:

G06F 9/455

US Classification:

718 1

Abstract:

A system and method for transforming a legacy device into a virtualized environment, comprising includes analyzing the profiling data for at least one application to determine usage frequency and resource requirements of the at least one application. Captured user events are benchmarked to simulate a user workload for the at least one application to determine how resource utilization and execution times scale from a legacy environment to a virtualized environment. The legacy device is transformed into the virtualized environment in accordance with a provisioning plan.

US Patent:

20210350232, Nov 11, 2021

Filed:

Apr 27, 2021

Appl. No.:

17/241430

Inventors:

- Princeton NJ, US
Haifeng Chen - West Windsor NJ, US
Wei Cheng - Princeton NJ, US
Junghwan Rhee - Edmond OK, US
Jumpei Kamimura - South Brunswick NJ, US

International Classification:

G06N 3/08
G06N 3/04
G07C 5/08

Abstract:

Methods and systems for training a neural network model include processing a set of normal state training data and a set of fault state training data to generate respective normal state inputs and fault state inputs that each include data features and sensor correlation graph information. A neural network model is trained, using the normal state inputs and the fault state inputs, to generate a fault score that provides a similarity of an input to the fault state training data and an anomaly score that provides a dissimilarity of the input to the normal state training data.

US Patent:

20210350636, Nov 11, 2021

Filed:

Apr 27, 2021

Appl. No.:

17/241481

Inventors:

- Princeton NJ, US
Haifeng Chen - West Windsor NJ, US
Wei Cheng - Princeton NJ, US
Junghwan Rhee - Edmond OK, US
Jumpei Kamimura - South Brunswick NJ, US

International Classification:

G07C 5/08
G06N 3/04
G06N 3/08
B60W 50/02
G07C 5/00
B60W 50/035
B60W 50/038

Abstract:

Methods and systems for vehicle fault detection include collecting operational data from sensors in a vehicle. The sensors are associated with vehicle sub-systems. The operational data is processed with a neural network to generate a fault score, which represents a similarity to fault state training scenarios, and an anomaly score, which represents a dissimilarity to normal state training scenarios. The fault score is determined to be above a fault score threshold and the anomaly score is determined to be above an anomaly score threshold to detect a fault. A corrective action is performed responsive the fault, based on a sub-system associated with the fault.

US Patent:

20210081122, Mar 18, 2021

Filed:

Mar 12, 2020

Appl. No.:

16/816715

Inventors:

- Princeton NJ, US
JUNGHWAN RHEE - PRINCETON NJ, US
XIAO YU - PRINCETON NJ, US
LUAN TANG - PENNINGTON NJ, US
HAIFENG CHEN - WEST WINDSOR NJ, US
KYUNGTAE KIM - WEST LAFAYETTE IN, US

International Classification:

G06F 3/06
G06N 3/04

Abstract:

A computer-implemented method for efficient and scalable enclave protection for machine learning (ML) programs includes tailoring at least one ML program to generate at least one tailored ML program for execution within at least one enclave, and executing the at least one tailored ML program within the at least one enclave.

US Patent:

20210064751, Mar 4, 2021

Filed:

Aug 12, 2020

Appl. No.:

16/991288

Inventors:

- Princeton NJ, US
Xiao Yu - Princeton NJ, US
Junghwan Rhee - Princeton NJ, US
Haifeng Chen - West Windsor NJ, US
Qi Wang - Urbana IL, US

International Classification:

G06F 21/56
G06F 21/54
G06F 21/55
G06K 9/62

Abstract:

Systems and methods for a provenance based threat detection tool that builds a provenance graph including a plurality of paths using a processor device from provenance data obtained from one or more computer systems and/or networks; samples the provenance graph to form a plurality of linear sample paths, and calculates a regularity score for each of the plurality of linear sample paths using a processor device; selects a subset of linear sample paths from the plurality of linear sample paths based on the regularity score, and embeds each of the subset of linear sample paths by converting each of the subset of linear sample paths into a numerical vector using a processor device; detects anomalies in the embedded paths to identify malicious process activities, and terminates a process related to the embedded path having the identified malicious process activities.

US Patent:

20210064959, Mar 4, 2021

Filed:

Aug 20, 2020

Appl. No.:

16/998280

Inventors:

- Princeton NJ, US
Zhengzhang Chen - Princeton Junction NJ, US
Junghwan Rhee - Princeton NJ, US
Haifeng Chen - West Windsor NJ, US
Pengyang Wang - Rolla MO, US

International Classification:

G06N 3/04

Abstract:

Systems and methods for predicting road conditions and traffic volume is provided. The method includes generating a graph of one or more road regions including a plurality of road intersections and a plurality of road segments, wherein the road intersections are represented as nodes and the road segments are represented as edges. The method can also include embedding the nodes from the graph into a node space, translating the edges of the graph into nodes of a line graph, and embedding the nodes of the line graph into the node space. The method can also include aligning the nodes from the line graph with the nodes from the graph, and optimizing the alignment, outputting a set of node and edge representations that predicts the traffic flow for each of the road segments and road intersections based on the optimized alignment of the nodes.