Search Results

There is accumulating evidence that drowsy driving is one of the leading causes of vehicle crashes and accidents worldwide. Consequently, automotive manufacturers started to develop in-vehicle drowsiness detection devices. However, due to the limited computation resources and the complexity of the vehicular environment, the existing products' performance is limited. Moreover, the vast majority of the commercialized products focus on monitoring the subject's current drowsiness level, whereas predicting drowsiness level in advance to avoid future risks is overlooked. In this research, a multi-time-scale fusion approach is proposed where prediction results from both long-term and short-term Recurrent Neural Networks (RNN) were combined to predict a person's drowsiness level. Our results indicate that the proposed fusion strategies can successfully capture both the short-term microsleep-related features and long-term sleepiness features and improve the drowsiness prediction performance.

We have developed a full virtual engine system prototyping platform with 4-cylinder engine plant model, SH-2A CPU hardware model, and object code level software including OSEK OS. The virtual engine system prototyping platform can run simulation of an engine control system and digital knock detection system including 64-pt FFT computations that provide required high-resolution DSP capability for detection and control. To help the system design, debugging, and evaluation, the virtual system prototyping consists of behavior analyzer which can provide the visualization of useful CPU internal information for control algorithm tuning, RTOS optimization, and CPU architecture development. Thus the co-simulation enables time and cost saving at validation stage as validation can be performed at the design stage before production of actual components.