Detection of Cognitive and Visual Distraction Using Radial Basis Probabilistic Neural Networks

This paper suggests a real-time method for detecting a driver’s cognitive and visual distraction using lateral driving performance measures. The algorithm adopts radial basis probabilistic neural networks (RBPNNs) to construct classification models. In this study, combinations of two driving performance data measures, including the standard deviation of lane position (SDLP) and steering wheel reversal rate (SRR), were considered as measures of distraction. Data for training and testing the RBPNN models were collected under simulated conditions in which fifteen participants drove on a highway. While driving, they were asked to complete auditory recall tasks or arrow search tasks to create cognitively or visually distracted driving periods. As a result, the best performing model could detect distraction with an average accuracy of 78.0 %, which is a relatively high accuracy in the human factors domain. The results demonstrated that the RBPNN model using SDLP and SRR could be an effective distraction detector with easy-to-obtain and inexpensive inputs.     

Fault detection method for electric parking brake (EPB) systems with sensorless estimation using current ripples

A fault detection method with parity equations is proposed in this paper. Due to its low cost implementation, the velocity of the motor is not measurable in electric parking brake (EPB) systems. Therefore, residuals are not reliable when estimating the motor velocity with a low-resolution encoder. In this paper, we propose a fault detection method with sensorless estimation using current ripples that estimates the position and velocity of the motor by detecting periodical oscillations of the armature current caused by rotor slots. In addition, this method can estimate the position and velocity of the motor with less computational effort than a state observer. Moreover, the method is less sensitive to motor parameters than model-based estimation methods. The effectiveness of this method is validated with experimental data, and the simulation results show that various faults have their own residual patterns. Therefore, we can detect the presence of faults by monitoring the residual signals.     

A risk assessment model with systematical uncertainty treatment for container shipping operations

ABSTRACT

The substantial adverse effects of risk factors on container shipping and logistics promoted a deep integration of risk analysis into the decision-making process. This paper aims to develop a well-grounded quantitative model to operational risk in a container shipping context. Considering uncertainty as a primary component of the risk concept, methods were employed in an inter-complementary manner to enable not only a sense of foreseeability but also a deeper look into the weaknesses of the knowledge base. The intersubjectivity of the input extraction process was supported by the Evidential Reasoning (ER) algorithm. Risks are then assessed based on a Fuzzy Rules Bayesian Network (FRBN) model with a 2-level parameter structure before meaningful interpretations can be derived through a new risk mapping approach. Besides an illustrative case study, the model was tested by sensitivity analysis and an examination of multiple validity claims.     

Adaptive neural network based fuzzy control for a smart idle stop and go vehicle control system

Idle stop and go (ISG) is a low cost but very effective technology to improve fuel efficiency and reduce engine emissions by preventing unnecessary engine idling. In this study, a new method is developed to improve the performance of conventional ISG by monitoring traffic conditions. To estimate frontal traffic conditions, an ultra-sonic ranging sensor is employed. Several fuzzy logic algorithms are developed to determine whether the engine idling is on or off. The algorithms are evaluated experimentally using various data gathered in real areas with traffic congestion. The evaluation results show that the method developed can reduce the chance of false application of ISG significantly while improving fuel efficiency up to 15%.     

Field implementation feasibility study of cumulative travel‐time responsive (CTR) traffic signal control algorithm

The cumulative travel‐time responsive (CTR) algorithm determines optimal green split for the next time interval by identifying the maximum cumulative travel time (CTT) estimated under the connected vehicle environment. This paper enhanced the CTR algorithm and evaluated its performance to verify a feasibility of field implementation in a near future. Standard Kalman filter (SKF) and adaptive Kalman filter (AKF) were applied to estimate CTT for each phase in the CTR algorithm. In addition, traffic demand, market penetration rate (MPR), and data availability were considered to evaluate the CTR algorithm's performance. An intersection in the Northern Virginia connected vehicle test bed is selected for a case study and evaluated within vissim and hardware in the loop simulations. As expected, the CTR algorithm's performance depends on MPR because the information collected from connected vehicle is a key enabling factor of the CTR algorithm. However, this paper found that the MPR requirement of the CTR algorithm could be addressed (i) when the data are collected from both connected vehicle and the infrastructure sensors and (ii) when the AKF is adopted. The minimum required MPRs to outperform the actuated traffic signal control were empirically found for each prediction technique (i.e., 30% for the SKF and 20% for the AKF) and data availability. Even without the infrastructure sensors, the CTR algorithm could be implemented at an intersection with high traffic demand and 50–60% MPR. The findings of this study are expected to contribute to the field implementation of the CTR algorithm to improve the traffic network performance. Copyright © 2017 John Wiley & Sons, Ltd.     

Age and cross-cultural comparison of drivers’ cognitive workload and performance in simulated urban driving

Driving demands significant psychomotor attention and requires even more when drivers are engaged in secondary tasks that increase cognitive workload and divert attention. It is well established that age influences driving risk. Less is known about how culture impacts changes in attention. We conducted parallel driving simulations in the US and Korea to measure the extent to which age and culture influence dual-task performance. There were 135 participants divided into two groups: a younger group aged 20∼29, and an older group aged 60∼69. Whereas some differences by culture appeared in absolute control measures, the younger participants showed similar mean velocity and compensatory patterns associated with increased cognitive load in the urban setting; however, the results from the older samples were less similar.     

Development of the Sungkyunkwan University Driving Simulator (SKUD) for Human-Machine Interface studies of Car Navigation Systems

Driving simulators are useful tools that can be used not only to test the components of future cars, but also to evaluate the telematics service and HMI (Human-Machine Interface). However, driving simulators that are currently available cannot be implemented to test and evaluate a real commercial telematics service system because the GPS (Global Positioning System), which contains basic functional support for the telematics module, does not work in the VR (virtual reality) environment. A driving simulator, together with the GPS simulator, can be used to study the HMI to evaluate commercial CNS (Car Navigation Systems). In this paper, Sungkyunkwan University Driving Simulator (SKUD) is developed with a GPS simulator that is able to emulate GPS satellite signals and includes the NMEA-0183 protocol and RS232C communication standards. Furthermore, using the SKUD, the HMI of the real commercial CNS could be investigated with driver workload assessment methods.     

Study of RCM-based maintenance planning for complex structures using soft computing technique

To guarantee the efficiency of maintenance strategies for a complex structure, safety and cost limitations must be considered. This research introduces RCM-based (Reliability Centered Maintenance) life cycle optimization for reasonable maintenance. The design variable is the reliability of each part, which consists of a complex structure, while the objective is to minimize the total cost function in order to maintain the system within the desired system reliability. This research constructs the cost function that can reflect the current operating condition and maintenance characteristics of individual parts by generating essential cost factors. To identify the optimal reliability of each component in a system, this paper uses a Neuro-Evolutionary technique. Additionally, this research analyzes the reliability growth of a system by using the AMSAA (Army Material Systems Analysis Activity) model to estimate the failure rate of each part. The MTBF (Mean Time Between Failure) and the failure rate of the whole system, which is responding to the individual parts, are estimated based on the history data by using neural networks. Finally, this paper presents the optimal life cycle of a complex structure by applying the optimal reliability and the estimated MTBF to the RAMS (Reliability, Availability, Maintainability, and Safety) algorithm.     

MPC-BASED steering control for backward-driving vehicle using stereo vision

We propose a steering control algorithm for autonomous backward driving in a narrow corridor. Passable spaces are detected using a stereo camera, and the steering angle is controlled by a model predictive controller (MPC). For passable space detection, an UV-disparity map is calculated from the original disparity map. Information regarding passable spaces collected by the stereo camera is used in steering control. Backward driving requires the driver’s preemptive actions, which can be learned by experience because of the non-intuitive responses (the initial motion of the vehicle is opposite to the driver’s steering angle input). This occurs because a backward-driving vehicle is a non-minimum phase system. One of the most popular steering control algorithms is Stanley method, which is based on the feedback of lateral displacement error and heading angle error. The method is very intuitive and works well for forward driving, but it exhibits significant undershoot for backward driving cases. Furthermore, the method does not explicitly consider any constraints on control inputs and states. We designed a steering controller based on the MPC technique that requires future information but can handle constraints explicitly. Because we have near-future information from the stereo camera under limited passable spaces, MPC can be effectively implemented. We performed several simulations and experiments to show the performance and superiority of the suggested method over a simple feedback-based control algorithm.     

Coupled thermo-mechanical analysis and shape optimization for reducing uneven wear of brake pads

In vehicle braking systems, the non-uniform contact pressure distribution on the brake pad is a major cause of uneven wear. The experimental approach of the wear phenomenon is the time consuming and costly. For this reason, a threedimensional finite element (FE) model of a brake system is presented for numerical simulation in this paper. A coupled thermo-mechanical analysis is carried out to confirm the non-uniform contact pressure distribution. A correlation between the non-uniform contact pressure and uneven wear is confirmed by measuring the amount of wear in the brake pad. The shape optimization of the brake pad is performed to reduce the uneven wear. In addition, the simulation results, such as natural frequency and temperature, are compared to experimental results.