Computational Intelligence in Automotive Applications

What is computational intelligence (CI)? Traditionally, CI is understood as a collection of methods from the fields of neural networks (NN), fuzzy logic and evolutionary computation. This edited volume is the first of its kind, suitable to automotive researchers, engineers and students. It provides a representative sample of contemporary CI activities in the area of automotive technology. The volume consists of 13 chapters, including but not limited to these topics: vehicle diagnostics and vehicle system safety, control of vehicular systems, quality control of automotive processes, driver state estimation, safety of pedestrians, intelligent vehicles. All chapters contain overviews of state of the art, and several chapters illustrate their methodologies on examples of real-world systems.

About the Editor: Danil Prokhorov began his technical career in St. Petersburg, Russia, after graduating with Honors from Saint Petersburg State University of Aerospace Instrumentation in 1992 (MS in Robotics). He worked as a research engineer in St. Petersburg Institute for Informatics and Automation, one of the institutes of the Russian Academy of Sciences. He came to the US in late 1993 for Ph.D. studies. He became involved in automotive research in 1995 when he was a Summer intern at Ford Scientific Research Lab in Dearborn, MI. Upon his graduation from the EE Department of Texas Tech University, Lubbock, in 1997, he joined Ford to pursue application-driven research on neural networks and other machine learning algorithms. While at Ford, he took part in several production-bound projects including neural network based engine misfire detection. Since 2005 he is with Toyota Technical Center, Ann Arbor, MI, overseeing important mid- and long-term research projects in computational intelligence.

Table of contents
Learning-based Driver Workload Estimation.- Visual Monitoring of Driver Inattention.- Understanding Driving Activity Using Ensemble Methods.- Computer Vision and Machine Learning for Enhancing Pedestrian Safety.- Application of Graphical Models in the Automotive Industry.- Extraction of Maximum Support Rules for the Root Cause Analysis.- Neural networks in automotive applications.- On learning machines for engine control.