RESUMEN
OBJECTIVE: Varying driver distraction algorithms were developed using vehicle kinematics and driver gaze data obtained from a camera-based driver monitoring system (DMS). BACKGROUND: Distracted driving characteristics can be difficult to accurately detect due to wide variation in driver behavior across driving environments. The growing availability of information about drivers and their involvement in the driving task increases the opportunity for accurately recognizing attention state. METHOD: A baseline for driver distraction levels was developed using a video feed of 24 separate drivers in varying naturalistic driving conditions. This initial assessment was used to develop four buffer-based algorithms that aimed to determine a driver's real-time attentiveness, via a variety of metrics and combinations thereof. RESULTS: Of those tested, the optimal algorithm included ungrouped glance locations and speed. Notably, as an algorithm's performance of detecting very distracted drivers improved, its accuracy for correctly identifying attentive drivers decreased. CONCLUSION: At a minimum, drivers' gaze position and vehicle speed should be included when designing driver distraction algorithms to delineate between glance patterns observed at high and low speeds. Distraction algorithms should be designed with an understanding of their limitations, including instances in which they may fail to detect distracted drivers, or falsely notify attentive drivers. APPLICATION: This research adds to the body of knowledge related to driver distraction and contributes to available methods to potentially address and reduce occurrences. Machine learning algorithms can build on the data elements discussed to increase distraction detection accuracy using robust artificial intelligence.
RESUMEN
BACKGROUND: Hemodynamic instability hinders activation and entrainment mapping during ventricular tachycardia ablation. The Impella 2.5 microaxial flow device (MFD; Abiomed Inc., Danvers, MA, USA) is used to prevent hemodynamic instability during electrophysiologic study. However, electromagnetic interference (EMI) generated by this device can preclude accurate electroanatomic mapping. METHODS: Impella was placed in the left ventricle of 7 canines for circulatory support. Electroanatomic mapping during sinus rhythm, ventricular pacing, and ventricular fibrillation (VF) was performed using magnet- (CARTO3, Biosense Webster Inc., Diamond Bar, CA, USA) and impedance- (EnSite Velocity System/EnSite NavX, St. Jude Medical Inc., St. Paul, MN, USA) based systems. Distance from device to points with severe EMI precluding acquisition was compared to points with mild/no EMI. Two methods were used to reduce EMI: (1) titration of MFD performance, and (2) impedance-only mapping combined with manual annotation of activation. RESULTS: Severe EMI did not occur during impedance-based mapping. Severe EMI was observed using CARTO3 at 9.4% of all points attempted at maximum performance level (P8) of device. Severe EMI occurred at points closer to device (40.1 ± 16.8 mm) versus (55.5 ± 20.0 mm) for mild/no EMI, P < 0.0001. Severe EMI using CARTO3 was resolved by either (1) reduction of performance from P8 to P6 or (2) impedance-only mapping with manual annotation. CONCLUSION: Concurrent use of MFD caused EMI to prevent acquisition of points with magnet-based mapping. Predictors for EMI were distance from device and performance level. Temporary reductions to P6 or impedance-only mapping are 2 methods to resolve EMI.