Student: Katharine Woodruff, Graduate Student in Industrial Engineering, University of Iowa
Faculty Advisor: Thomas Schnell
Employing Machine Learning Algorithms to Search for Unique X-ray Sources
My research project will be conducted through the Operator Performance Laboratory (OPL) at the University of Iowa. OPL conducts ingenious research related to human factors in aviation to increase the safety, productivity, and inter-operability of the pilot. OPL is led by my project mentor and employer, Dr. Thomas Schnell. My research is related to electroencephalogram (EEG) and electrocardiogram (ECG) signals. EEG signals represent the electrical activity of the brain via the scalp. ECG measures the electrical activity of the heartbeat. EEG and EKG can give great spatial and temporal resolution with real-time results and activity
captured across the brain and heart. Currently, the lab I work at uses ECG software to detect heartbeat variability and calculate the real-time workload of the pilot. I will be utilizing software provided by BrainVision: cEEGrid and LiveAmp. The cEEGrids consist of 16 electrodes on a sticker in the shape of a ‘C’ that is easily applied around the ears. The EEG waves are then recorded to the LiveAmp that shows real-time data wirelessly. Currently, there is very little data on the EEG waves of pilots because of bulky EEG caps that must be placed underneath the helmet. As well, the meaning behind cognitive workload using ECG alone can be ambiguous. EEG data has well-developed markers for workload data. Using EEG and ECG together better insight into cognitive workload can be achieved. This simplified and reliable setup will drive advances in aeronautics to enhance the knowledge of the pilot’s brain waves during flight operations. My findings in the EEG field will bring helpful insights to the NASA mission by providing quantitative data to better understand the inner workings of cognitive workload during flight.
captured across the brain and heart. Currently, the lab I work at uses ECG software to detect heartbeat variability and calculate the real-time workload of the pilot. I will be utilizing software provided by BrainVision: cEEGrid and LiveAmp. The cEEGrids consist of 16 electrodes on a sticker in the shape of a ‘C’ that is easily applied around the ears. The EEG waves are then recorded to the LiveAmp that shows real-time data wirelessly. Currently, there is very little data on the EEG waves of pilots because of bulky EEG caps that must be placed underneath the helmet. As well, the meaning behind cognitive workload using ECG alone can be ambiguous. EEG data has well-developed markers for workload data. Using EEG and ECG together better insight into cognitive workload can be achieved. This simplified and reliable setup will drive advances in aeronautics to enhance the knowledge of the pilot’s brain waves during flight operations. My findings in the EEG field will bring helpful insights to the NASA mission by providing quantitative data to better understand the inner workings of cognitive workload during flight.