Gm Global Technolgoy Operations, Inc.

T-mobile Innovations LLC

Faisal Waris

Marco T Carnevale

Yanbing Su

Srikrishna Srinivasan

Matthew Kelly Titsworth

Gregory Gerald Macdonald

Jia Yan

Pradeep Christopher Cruz

In various examples, description data may be used by an engine to correlate a subset of alarms representing a network incident. A machine learning model may then be used to predict a likelihood that one or more of the alarms within the subset is a root cause of the network incident. This root cause may then be displayed on a graphical user interface. As a result, alarm fatigue experienced by network administrators may be reduced.

Root cause incident detection using an alarm correlation engine

A method implemented in a smartphone associated with a transportation apparatus to detect a crash of the transportation apparatus, comprises receiving a signal generated in time domain by a sensor of the smartphone in response to an event triggered by motion of the smartphone. The method further comprises transforming the signal to a delay domain to generate a two-dimensional representation of the signal in the delay domain. The method further comprises processing the two-dimensional representation using a Hough transform to select lines from the two-dimensional representation having a parameter greater than or equal to a predetermined threshold. The method further comprises determining a pattern associated with the selected lines, comparing the pattern to a predetermined pattern indicating crash event of the transportation apparatus, and determining based on the comparison whether the event indicates crash event of the transportation apparatus.

Crash detection using smartphone sensor data

Growing community of inventors

Rochester Hills, MI, United States of America

Faisal Waris