In this paper, we propose initial steps towards multi-modal driver stress (distraction) detection in urban driving scenarios involving multi-tasking, dialog system conversation, and medium-level cognitive tasks. The goal is to obtain a continuous operation-mode detection employing driver’s speech and CAN-Bus signals, with a direct application for an intelligent human-vehicle interface which wil...

This study was an unobtrusive observational analysis of 333 older and younger bus passengers in Guadalajara, Mexico. A set of data were collected for each observed passenger, as well as more general observations related to driver behaviour, bus design and bus service characteristics. There were significant differences between older and younger passengers in terms of boarding and alighting times...

continued on page 3 Mirror-based systems have evolved over the years because of the need to provide a better view to the driver and now include more than one mirror with different magnifications. However, current mirror-based systems have several limitations. First, they do not cover the whole side area of the vehicle, thus leaving what are referred to as “blind zones.” This brings the bus driv...

This paper describes recent advances in the analysis and classification of driver behavior in actual driving scenarios. We employ data obtained from the UTDrive corpus to model driving behavior and to detect if distraction due to secondary tasks is present. Hidden Markov Models (HMMs) are used to capture the sequence of driving characteristics acquired from the vehicle’s CAN-Bus (Controller Are...

In the area of optimization of public transportation there are several methods for modeling and solving vehicle and driver scheduling problems. We designed a sequential heuristic method for solving the combined (vehicle and driver scheduling) problem. Our model is based on a modification of the vehicle schedules to satisfy driver requirements. We introduced a driver friendly approach of the opt...