Search

Your search keyword '"Yu, Denny"' showing total 36 results
Start Over Author "Yu, Denny" Journal proceedings of the human factors and ergonomics society annual meeting
36 results on '"Yu, Denny"'

11. Predicting Automated Vehicle Takeover Decision During the Nighttime

Author

Liang, Nade, Lim, Chiho, Yu, Denny, Prakah-Asante, Kwaku O., and Pitts, Brandon J.

Abstract

Conditionally automated vehicles require drivers to take over control occasionally. To date, takeover performance has been mostly evaluated using only re-engagement time and quality metrics. However, the appropriateness of takeover decisions, which has not been considered by previous research, should also be included as a performance indicator as it reflects one’s situation awareness of the takeover scenario. The goal of this study was to use eye-tracking, demographic factors, workload, and non-driving-related task (NDRT) conditions to predict takeover decisions. Forty-three participants drove a simulated conditionally automated vehicle while performing visual NDRTs and needed to decide the most appropriate maneuver around a roadway obstacle. Six classifiers were used to predict takeover decisions. The Random Forest model achieved the best performance, and driving experience and perceived workload were the most influential features. Findings may be used to assist in the design of adaptive algorithms that support drivers taking over from automated vehicles.

Published
2023
Full Text
View/download PDF

12. Relating in-vivoStrain of the Flexor Digitorum Superficialis Tendon with Grip Force

Author

Houghton, Frederick C., Huff, Reece D., Earl, Conner C., Ghajar-Rahimi, Elnaz, Dogra, Ishan, Darling, Andrew J., Damen, Frederick W., Zhou, Guoyang, Yu, Denny, Goergen, Craig J., Harris-Adamson, Carisa, and O’Connell, Grace D.

Abstract

Epidemiological studies have shown a relationship between hand exertion and risk of developing distal upper extremity musculoskeletal disorders (DUEMSDs). Recently, fatigue-failure models were proposed for estimating the risk of DUEMSD development. However, models that incorporate tendon strain are primarily based on in-vitrodata and may be better informed using in-vivodata. This methodological pilot study aimed to establish an approach for correlating grip force and spatiotemporal strains of the flexor digitorum superficialis (FDS) tendon using ultrasound imaging. Three image texture correlation techniques to measure in-vivostrains were explored and compared: digital image correlation, direct deformation estimation, and StrainNet, a novel deep learning neural network for strain prediction. StrainNet resulted in more accurate strain measurements than conventional image assessment tools, enabled continuous prediction of FDS tendon strain, and allowed for comparison of median bulk tissue strain during isometric contraction to grip force. Future work will study more participants and viscoelastic behavior.

Published
2023
Full Text
View/download PDF

23. Machine Learning for Prediction of Driver Takeover Time in Automated Driving: Insights from Non-urgent Low Consequence Scenarios

Author

Villarreal, Ryan Thomas, Liang, Nade, Pitts, Brandon, Nasir, Mansoor, and Yu, Denny

Abstract

This work investigates driver takeover times in non-urgent, low consequence scenarios within conditionally automated driving. Using physiological and behavioral data from 46 participants in a driving simulator, classification algorithms were applied to predict metrics of takeover time following a takeover request (TOR). Eye-tracking, heart rate variability, and computer-vision based body posture features were analyzed for their predictive power. The Naïve Bayes algorithm outperformed other models, achieving an accuracy of 78% when predicting the time to first gaze in the driving scene following a TOR. Results from feature selection showed eye-tracking metrics to have the most predictive power. These results suggest that eye-tracking metrics and simple, computationally efficient, 2-class algorithms may be sufficient for predicting takeover time in non-urgent, low-consequence scenarios. This research provides evidence for integration of physiological sensing into adaptive automated driving systems (ADS) to develop context-aware TOR alert systems to improve road safety.

Published
2024
Full Text
View/download PDF

36. Alternative 2D and 3D Visualization Methods for Microsurgery

Author

Yu, Denny, Sackllah, Michael, Woolley, Charles, Kasten, Steven, and Armstrong, Thomas

Abstract

The use of minimally invasive surgeries, like laparoscopy and microsurgery, is increasing due to its benefits to the patient; however, the equipment necessary for the surgeries imposes postural constraints on the surgeons and increases their risk for discomfort and injuries. In microsurgery, the microscope limits surgeon movement and the long length of the surgeries exposes surgeons to prolonged sustained postures. Stereoscopic displays may reduce these constraints and maintain surgeon performance. Six subjects with no surgical experience performed microsurgical skills tests using three visualization methods: 2D visualization, 3D visualization, and the traditional microscope. Task performance was measured through video analysis and subjective data was gathered on discomfort, posture, and equipment usability. Tasks performed on the microscopes had the highest performance efficiency and the least errors. The 3D visualization method had the lowest performance efficiency. However, subjects experienced higher back and neck discomfort using the microscopes. The 3D visualization method was ranked poorly in all usability factors and subjects particularly reported problems with focusing the depth of view. Although 3D visualization methods can provide stereoscopic information to aid in task performance and decrease postural constraints on the surgeon, hardware improvements are necessary before this technology can be easily accessible in healthcare.

Published
2011
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results