Detection of aggressive driving behavior and fault behavior using pattern matching
Jessy George Smith, Sai Kirthi Ponnuru, Mandar Patil · 2016
In time series processing, pattern matching is often used to cater to visual perception of behaviors of interest. The selection of data representation methods and distance measures is driven by domain considerations and is critical for implementation from lab to production scale. This paper discusses use cases from different domains where select pattern matching techniques are used. In the first use case, a multi-variable pattern matching method has been used to detect and classify driving behavior. The risk associated with aggressive behavior is computed and applied to derive the driving scores that feed into the fleet performance management service. In the second use case, pattern matching algorithms are used for the real time detection and diagnosis of faults in transformer systems. The evolving risk profile is used as lead indicator of impending failure. This feature is integrated into the condition monitoring system and configured to issue maintenance work orders.