Verbal Learning as a predictor of risks of accidents in elderly drivers

ABSTRACT Background: Age-related cognitive decline impacts cognitive abilities essential for driving. Objective: We aimed to measure main cognitive functions associated with a high number of traffic violations in different driving settings. Methods: Thirty-four elderly individuals, aged between 65 and 90 years, were evaluated with a driving simulator in four different settings (Intersection, Overtaking, Rain, and Malfunction tasks) and underwent a battery of cognitive tests, including memory, attention, visuospatial, and cognitive screening tests. Individuals were divided into two groups: High-risk driving (HR, top 20% of penalty points) and normal-risk driving (NR). Non-parametric group comparison and regression analysis were performed. Results: The HR group showed higher total driving penalty score compared to the NR group (median=29, range= 9-44 vs. median=61, range= 47-97, p<0.001). The HR group showed higher penalty scores in the Intersection task (p<0.001) and the Overtaking and Rain tasks (p<0.05 both). The verbal learning score was significantly lower in the HR group (median=33, range=12-57) compared with the NR group (median=38, range=23-57, p<0.05), and it was observed that this score had the best predictive value for worse driving performance in the regression model. General cognitive screening tests (Mini-Mental State Examination and Addenbrooke's Cognitive Evaluation) were similar between the groups (p>0.05), with a small effect size (Cohen’s d=0.3 both). Conclusion: The verbal learning score may be a better predictor of driving risk than cognitive screening tests. High-risk drivers also showed significantly higher traffic driving penalty scores in the Intersection, Overtaking, and Rain tests.

Identification of High-Risk Driving Behavior and Sections for Rail Systems

Risk assessment is an important process for railway safety. Current practices for assessing the risks of driving behaviors aim to inspect the driving record generated by automatic train protection systems. This paper proposes an automatic process to access detailed data contained in driving data, and identifies six high-risk driving behaviors. The modules can assess the competency of drivers and evaluate the frequency of high-risk behaviors in each section. Moreover, an integrated risk index for driving behaviors is proposed to compare each driver and section. An empirical study for drivers and sections is performed to demonstrate the feasibility of applying the proposed modules in practice. Results reveal that 20% of high-risk drivers contribute to 74% of the total risk, while 15% of high-risk sections contribute to 80% of the total risk. The proposed modules identify the drivers and sections with high risk. By enabling the operators of railway systems to take countermeasures, this methodology could enable them to improve the safety of railway systems more efficiently.

Characterization of the Driving Style by State–Action Semantic Plane Based on the Bayesian Nonparametric Approach

The quantification and estimation of the driving style are crucial to improve the safety on the road and the acceptance of drivers with level2–level3(L2–L3) intelligent vehicles. Previous studies have focused on identifying the difference in driving style between categories, without further consideration of the driving behavior frequency, duration proportion properties, and the transition properties between driving style and behaviors. In this paper, a novel methodology to characterize the driving style is proposed by using the State–Action semantic plane based on the Bayesian nonparametric approach, i.e., hierarchical Dirichlet process–hidden semi–Markov model (HDP–HSMM). This method segments the time series driving data into fragment clusters with similar characteristics and construct the State–Action semantic plane based on the statistical characteristics of the state and action layer to label and interpret the fragment clusters. This intuitively and simply visualizes the driving performance of individual drivers, while the risk index of the individual drivers can also be obtained through semantic plane. In addition, according to the joint mutual information maximization (JIMI) approach, seven transition probabilities of driving behaviors are extracted from the semantic plane and applied to identify driving styles of drivers. We found that the aggressive drivers prefer high–risk driving behaviors, and the total duration and frequency of high–risk behaviors are greater than those of cautious and normal drivers. The transition probabilities among high–risk driving behaviors are also greater compared with low–risk behaviors. Moreover, the transition probabilities can provide rich information about driving styles and can improve the classification accuracy of driving styles effectively. Our study has practical significance for the regulation of driving behavior and improvement of road safety and the development of advanced driver assistance systems (ADAS).

Jus in vi

Jus in vi is the set of moral principles governing how limited force is used. Taking the traditionalist jus in bello principles as a starting point, this chapter interrogates what necessity, proportionality, and distinction look like in a limited force context and makes the case for the novel psychological risk principle by evaluating how concepts such as “excessive,” “military advantage,” and “harms” and “goods” fit into our thinking about vim. The keystone of jus in vi is the predisposition toward maximal restraint maxim. The chapter thus begins by making the case for why jus in vi principles should be more restrictive than their jus in bello counterparts. It continues by exploring how a circumscribed view of necessity sets the groundwork for constraining proportionality calculations and shaping the way we think about distinction in more restricted ways. The notion of jus in vi proportionality is then explored, with concerns about escalation and psychological risk driving the analysis. Drawing insights from revisionist just war theory to consider jus in vi distinction, the chapter concludes by making the case for affording greater protections to both combatants and non-combatants compared to standard just war accounts. Unlike war, in which almost any soldier can be targeted, in a context of limited force only those who are an active threat can be justly targeted. Both innocent non-combatants and non-threatening combatants should be preserved from the more predictable harms of limited force, though this differs depending on whether the use of limited force is protective, preventive, or punitive.

Part V The Scope of Refugee Protection, Ch.38 The Internal Protection Alternative

This chapter discusses the Internal Protection Alternative (IPA), which stems from the premise that if there is a safe place within an individual’s State of nationality or habitual residence where they can relocate, they are not a refugee. Examples of the application of the IPA could include relocating from the countryside to the city where an individual is less likely to be found by their persecutors; or relocating to an area where a clan, tribe, militia, or international organization could provide protection. As refugee law lacks an international mechanism capable of providing a common interpretation of the Refugee Convention, the IPA’s interpretation has primarily been left to Contracting States by means of domestic court decisions. Using the rules of treaty interpretation, it is nonetheless possible to distil a minimum binding standard of relevant IPA criteria from both State practice and the text of the Refugee Convention itself. These criteria are that (i) the proposed IPA must be accessible to the applicant, (ii) there is no risk of exposure to the original risk of persecution, and (iii) there must be no new risk of persecution or of refoulement in the proposed IPA, and the conditions there must not be so unreasonable as to risk driving the individual to a place where there is a risk of persecution.

Evaluating Older Drivers in Their Everyday Driving Environments

Developing tools that accurately detect at-risk driving behaviors is a public-health priority. There is a need for a measure that accurately assesses older drivers’ level of competence on familiar roadways. The objective of this presentation is to describe the development of the procedures and scoring of a new approach, the Electronic Driving Observation Schedule (eDOS), to observe everyday driving in the community. The eDOS was used to record and compare the driving environment and performance of older drivers and low-risk younger drivers during their everyday driving. Older (n=160, &gt;74y) and younger (n=60, 35-64y) drivers completed a 20-30-minute drive from their home to destinations of their choice. Older drivers drove on simpler routes with fewer intersections and lane changes. Both groups made few driving errors, which were mostly low-risk. Younger drivers tended to demonstrate poor driving habits (not signaling, speeding, poor lane position) and compliance with road rules. Part of a symposium sponsored by Transportation and Aging Interest Group.

Improving the Accuracy and Transparency of Underwriting with AI to Transform the Life Insurance Industry

Life insurance provides trillions of dollars of financial security for hundreds of millions of individuals and fami­lies worldwide. To simultaneously offer affordable products while managing this financial ecosystem, life-insurance companies use an underwriting process to assess the mortality risk posed by individual applicants. Traditional underwriting is largely based on examining an applicant’s health and behavioral profile. This manual process is incompatible with expectations of a rapid customer experience through digital capabilities. Fortunately, the availability of large historical data sets and the emergence of new data sources provide an unprecedented opportunity for artificial intelligence to transform under­writing in the life-insurance industry with standard measures of mortality risk. We combined one of the largest application data sets in the industry with a responsible artificial intelligence framework to develop a mortality model and life score. We describe how the life score serves as the primary risk-driving engine of deployed algorithmic underwriting systems and demonstrate its high level of accuracy, yielding a nine-percent reduction in claims within the healthiest pool of applicants. Additionally, we argue that, by embracing transparency, the industry can build consumer trust and respond to a dynamic regulatory environment focused on algorithmic decision-making. We present a consumer-facing tool that uses a state-of-the-art method for interpretable machine learning to offer transparency into the life score.

The Effect of Educational Intervention on Safe and High-Risk Driving Behaviors in Taxi Drivers

Background: High-risk driving behaviors is one of the leading causes of death and disability. Objectives: The aim of this study was to determine the effect of educational intervention on promoting safe-driving behaviors and reducing high risk-driving behaviors in taxi drivers based on the health belief model and planned behavior theory. Methods: A quasi-experimental study of interventional and control drivers (n = 40) selected by a cluster sampling method was conducted. The participants were selected from taxi stations. The intervention group was divided into 4 groups, including 10 people. The contents of the training program were based on driving laws, avoiding high-risk behaviors, and advising on safe driving behaviors. The driving behaviors were measured at baseline and 3-month post-intervention. Constructs of the health belief model and theory of planned behavior were used as an interventional program framework. Independent t-test and Paired t-test were used to compare the scores between intervention and control drivers and the intervention group before and after the intervention at each of the variables, respectively. Results: Three months post-intervention, the scores of safe driving behaviors in the intervention group were higher than the control group, and high-risk driving behaviors in the intervention group were less than the control group. After the intervention, a significant difference was observed in the mean scores of perceived barriers, self-efficacy, cues to action, attitude, subjective norms, and perceived behavioral control between two groups (P < 0.05). Conclusions: Educational intervention within the framework of the combined constructs of the health belief model and theory of planned behavior can reduce high-risk driving behaviors and promote safe driving behaviors in taxi drivers.

Driving Fatigue Prediction Model considering Schedule and Circadian Rhythm

Driver fatigue level was considered an accumulated result contributed by circadian rhythms, hours of sleep before driving, driving duration, and break time during driving. This article presents an investigation into the regression model between driver fatigue level and the above four time-related variables. With the cooperation of one commercial transportation company, a Naturalistic Driving Study (NDS) was conducted, and NDS data from thirty-four middle-aged drivers were selected for analysis. With regard to the circadian rhythms, commercial drivers operated the vehicle and started driving at around 09:00, 14:00, and 21:00, respectively. Participants’ time of sleep before driving is also surveyed, and a range from 4 to 7 hours was selected. The commercial driving route was the same for all participants. After getting the fatigue level of all participants using the Karolinska Sleepiness Scale (KSS), the discrete KSS data were converted into consecutive value, and curve fitting methods were adopted for modeling. In addition, a linear regression model was proposed to represent the relationship between accumulated fatigue level and the four time-related variables. Finally, the prediction model was verified by the driving performance measurement: standard deviation of lateral position. The results demonstrated that fatigue prediction results are significantly relevant to driving performance. In conclusion, the fatigue prediction model proposed in this study could be implemented to predict the risk driving period and the maximum consecutive driving time once the driving schedule is determined, and the fatigue driving behavior could be avoided or alleviated by optimizing the driving and break schedule.