Producing a neural network for monitoring driver alertness from steering actions

There is a limit to the accuracy with which we can predict a person's state of alertness from their behaviour. Driver behaviour and alertness are, however, clearly related, and this should allow us to build a predictive model. For such a model to be of use it must be very general in its ability. Such generality is available at the expense of accuracy and a trade-off between overall error rate and quantity of usable predictions must consequently be made. This paper discusses a set of methods which were applied to the task of building a neural network based system for predicting driver alertness from steering behaviour. We show how an acceptable level of generality was achieved and how the trade-off between error rate and quantity of usable predictions was managed.     

Relations between temperamental fear and risky pedestrian behavior

Objective

Child pedestrian injury poses a significant global public health challenge. This study examines relations between temperamental fear and children’s risky pedestrian behavior, utilizing mediation analytic strategies to study underlying mechanisms of the hypothesized relation.

Methods

As part of a larger study, 240 seven- and eight-year-old children completed 30 crossings in a virtual reality (VR) pedestrian environment. Three pedestrian behaviors were considered: start gap (lag after a traffic gap appears before child initiates crossing into the gap), time to contact (TTC; gap between avatar and the lead oncoming vehicle), and hits (collisions with vehicles in simulated crossings). Temperamental fear was measured by parent report.

Results

Fearful children were more likely to be struck by virtual vehicles, and the relation between fear and risky pedestrian behaviors was mediated by start gap and TTC. Specifically, children who were temperamentally more fearful were more likely to hesitate before initiating crossing, which led to shorter gaps between themselves and the oncoming vehicle, hence causing them to be more likely to be hit by virtual vehicles. Gender interacted with fear, such that fearful girls were most likely to be hit.

Conclusions

Both temperamental fear and gender influenced the risk of child pedestrian injuries. Delayed entry into traffic and shorter gaps between children and oncoming vehicles may underlie this relation. Future research should explore how these factors might influence the effectiveness of prevention programs.     

Using Genetic Algorithms to Design Experiments: A Review

Genetic algorithms (GAs) have been used in many disciplines to optimize solutions for a broad range of problems. In the last 20 years, the statistical literature has seen an increase in the use and study of this optimization algorithm for generating optimal designs in a diverse set of experimental settings. These efforts are due in part to an interest in implementing a novel methodology as well as the hope that careful application of elements of the GA framework to the unique aspects of a designed experiment problem might lead to an efficient means of finding improved or optimal designs. In this paper, we explore the merits of using this approach, some of the aspects of design that make it a unique application relative to other optimization scenarios, and discuss elements which should be considered for an effective implementation. We conclude that the current GA implementations can, but do not always, provide a competitive methodology to produce substantial gains over standard optimal design strategies. We consider both the probability of finding a globally optimal design as well as the computational efficiency of this approach. Copyright © 2014 John Wiley & Sons, Ltd.     

Ethnic differences in predictors of adolescent smoking onset and escalation: a longitudinal study from 7th to 12th grade.

The present study sought to determine whether risk factors for cigarette smoking onset have a stronger influence on Black versus White children, and whether those patterns differ for nonsmokers versus experimental smokers. As part of a larger study, 5,213 seventh graders were surveyed annually for 5 years. The survey instrument assessed cigarette smoking, along with a variety of background variables thought to influence smoking. Results indicated that rebelliousness predicted smoking onset for Black nonsmokers; peer modeling was more influential for Whites. For both ethnicities, socially isolated children were at increased risk. The variables that predicted the shift from experimental to regular smoking were for the most part different from those that predicted smoking onset. Specifically, youths who lived with smokers, viewed smoking as a means to a goal, and experienced few adverse physiological effects of smoking were more likely to increase their cigarette consumption. Overall, we found that, contrary to previous research, risk factors for smoking differed across ethnicity. Further, smoking onset appears to be shaped by forces different from those that accelerate consumption.     

The effects of shoe traction and obstacle height on lower extremity coordination dynamics during walking

This study aims to investigate the effects of shoe traction and obstacle height on lower extremity relative phase dynamics (analysis of intralimb coordination) during walking to better understand the mechanisms employed to avoid slippage following obstacle clearance. Ten participants walked at a self-selected pace during eight conditions: four obstacle heights (0%, 10%, 20%, and 40% of limb length) while wearing two pairs of shoes (low and high traction). A coordination analysis was used and phasing relationships between lower extremity segments were examined. The results demonstrated that significant behavioral changes were elicited under varied obstacle heights and frictional conditions. Both decreasing shoe traction and increasing obstacle height resulted in a more in-phase relationship between the interacting lower limb segments. The higher the obstacle and the lower the shoe traction, the more unstable the system became. These changes in phasing relationship and variability are indicators of alterations in coordinative behavior, which if pushed further may have lead to falling.     

Deposited Chromium as a Corrosion Preventative

Atmospheric corrosion tests of copper plus bright nickel plus microcracked chromium plate have shown that microcracked chromium produced by the post nickel strike method and having a minimum thickness of 0·3/μm provides corrosion resistance at least as good as microcracked chromium produced by other methods, which require a minimum thickness of 0·8 μm in order to ensure an adequate density of microcracking.     

Time-Line Interpolation Errors in Pipe Networks

An exact method of assessing numerical errors in analyses of unsteady flows in pipe networks is introduced. The assessment is valid for fixed-grid method of characteristics analyses using time-line interpolations. A pipe polynomial transfer matrix is developed and is analogous to transfer function matrices used in free oscillation theory. The influence of reachback is assessed by comparing exact numerical predictions using a polynomial transfer matrix with exact analytical predictions obtained using free oscillation theory. The investigation is part of a long-term project aimed at automating the selection of numerical grid sizes in unsteady flow analyses. The eventual goal is to enable users of unsteady flow software to prescribe required degrees of accuracy instead of specifying the numerical grid itself. This paper is only a first step toward the long-term aim, but it is a big step toward an intermediate objective of providing exact benchmarking data for the assessment of approximate methods of automatic grid selection.