Computer and Data Scientist, Systems and Software Engineer, Systems Modeler, and Applied Statistician at NT Concepts
Teddy Ko, Ph.D., is a Computer and Data Scientist, Systems and Software Engineer, Systems Modeler, and Applied Statistician with a strong Artificial Intelligence (AI), Machine Learning (ML), Computer Vision, Data Analytics and Visualization, Modeling and Simulation, Optimization, Data/Text Mining, Image/Video Processing, Biometrics Identification and Statistical Science background. He has a Ph.D. degree in Computer Science from George Washington University and a M.S. degree in Electrical Engineering from University of Virginia. He is a previous Raytheon Engineering Fellow and Sr. Principal and has 30 plus years of broad and in-depth R&D experience in supporting both government agencies and private industries. Since year 2000, he has authored and presented more than 25 papers and 2 book chapters in journals, IEEE, American Statistical Association (ASA) and National Institute of Standards and Technology (NIST) sponsored conferences and workshops, and international conferences. He has also chaired two technical sessions in international conferences and won two best paper awards in the image processing and pattern recognition categories. He is a member of IEEE, IEEE Computer Society, ACM, ASA, and INFORMS.
Track: Analytics Process
Tuesday, April 16, 11:30am–12:20pm
Pattern Identification and Analysis of Sensor Outputs by Combining Pattern Markov Chains and Explainable Machine Learning
For a highly complex system such as a major military weapons platform, it is difficult to establish a Prognostics and Health Management (PHM) program with predictive and sustainment maintenance capabilities. These platforms often monitor and interpret thousands of sensor statuses and error codes. Error codes from various sensors are often reported simultaneously, in bursts, or in sequences, and it can be difficult to separate the underlying root error condition from sympathetic error codes. In addition, the systems are frequently updated and may be reconfigured for different mission assignments. For such systems, applying analytical models without understanding the complex details of the underlying health monitoring and reporting system usually will not yield accurate health predictions. In the presentation, we describe a “Pattern Identification and Analysis of Sensor Outputs by Combining Pattern Markov Chains (PMC) and Explainable Machine Learning” to address the challenge. PMCs are used in order to provide humans with visual and intuitive understanding of the underlying error codes and to correlate sequences of codes across platforms, configurations, and updates. Machine learning can then be more intelligently employed to assess the state of the equipment and to predict remaining useful life. By creating a PMC using the sensor codes, integrated with association rule learning, we can identify associations, correlations, and likely root causes of event sequences with unspecified time/event gaps between events. PMC makes visual and interactive understanding of error reporting of a very complex system possible and enables us to diagnose and refine the monitoring and reporting system. Using the PMC together with machine learning prediction of the remaining useful life of a part in a system/subsystem can enable us to progressively establish good predictive and sustainment maintenance capabilities for a complex system.