Blink Number Forecasting Based on Improved Bayesian Fusion Algorithm for Fatigue Driving DetectionReportar como inadecuado




Blink Number Forecasting Based on Improved Bayesian Fusion Algorithm for Fatigue Driving Detection - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Mathematical Problems in Engineering - Volume 2015 2015, Article ID 832621, 13 pages -

Research Article

School of Information and Control, Nanjing University of Information Science & Technology, Nanjing 210044, China

Jiangsu Key Laboratory of Big Data Analysis Technology, Nanjing 210044, China

School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing 210044, China

The NEXTRANS Center, Purdue University, West Lafayette, IN 47907, USA

School of Electronic and Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China

Received 9 January 2015; Accepted 1 May 2015

Academic Editor: Yakov Strelniker

Copyright © 2015 Wei Sun et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

An improved Bayesian fusion algorithm BFA is proposed for forecasting the blink number in a continuous video. It assumes that, at one prediction interval, the blink number is correlated with the blink numbers of only a few previous intervals. With this assumption, the weights of the component predictors in the improved BFA are calculated according to their prediction performance only from a few intervals rather than from all intervals. Therefore, compared with the conventional BFA, the improved BFA is more sensitive to the disturbed condition of the component predictors for adjusting their weights more rapidly. To determine the most relevant intervals, the grey relation entropy-based analysis GREBA method is proposed, which can be used analyze the relevancy between the historical data flows of blink number and the data flow at the current interval. Three single predictors, that is, the autoregressive integrated moving average ARIMA, radial basis function neural network RBFNN, and Kalman filter KF, are designed and incorporated linearly into the BFA. Experimental results demonstrate that the improved BFA obviously outperforms the conventional BFA in both accuracy and stability; also fatigue driving can be accurately warned against in advance based on the blink number forecasted by the improved BFA.





Autor: Wei Sun, Xiaorui Zhang, Jian Wang, Jun He, and Srinivas Peeta

Fuente: https://www.hindawi.com/



DESCARGAR PDF




Documentos relacionados