Unraveling the relation between cycling accidents and built environment typologies: Capturing spatial heterogeneity through a latent class discrete outcome model.

Today, cities seek to transition to more sustainable transportation modes. Cycling is critical in this shift, promoting a more beneficial lifestyle for most. However, cyclists are exposed to many hazardous circumstances or environments, resulting in accidents, injuries, and even death. Transport authorities must understand why accidents occur, to reduce the risk of those who cycle. This study applies a new modeling framework to analyze cycling accident severities. We employ a latent class discrete outcome model, where classes are derived from a Gaussian-Bernoulli mixture, applied to data from Berlin, and augmented with volunteered geographic information. We jointly estimate model components, combining machine learning and econometric approaches, allowing for more intricate and flexible representations while maintaining interpretability. Results show the potential of our approach. Risk factors are indexed depending on where accidents occurred and their contribution. We can discover complex relations between specific built environments and accident characteristics and uncover differences in the impact of certain accident factors on one environment typology but not others. Using multiple data sources also proves helpful as an additional layer of knowledge, providing unique value to understand and model cycling accidents. Another critical aspect of our approach is the potential for simulation, where locations can be examined through simulated accident features to understand the inherent risk of various locations. These findings highlight the ability to capture heterogeneity in accidents and their relation to the built environment. Capturing such relations allows for more direct countermeasures to risky situations or policies to be designed, simulated, and targeted.

Gender disparities in observed motorcycle helmet use in Madagascar: female motorcyclists behave safer but have lower overall protection.

BACKGROUND: Although motorcycle helmets can save lives in case of a crash, no helmet use data are available for many countries. When data is available, it is often only analysed as a global average, preventing targeted road safety education and legislative action. In this study, we conducted a detailed analysis of motorcycle helmet use in the capital of Madagascar. METHODS: Using a cross-sectional observational field survey framework, we observed 17 230 individual motorcycles. We systematically recorded motorcycle riders' helmet use, position on the motorcycle, rider numbers and gender. RESULTS: We found a general helmet use of 76.1%. Observed drivers had a significantly higher helmet use (84.6%) than passengers (47.7%), and subsequently helmet use per motorcycle decreased significantly when the number of riders per motorcycle increased. Female drivers had significantly higher helmet use than male drivers, and female passengers had significantly higher helmet use than male passengers. That is, on the same position of the motorcycle, female riders behaved safer than male riders. However, since female riders were more often passengers than drivers, their average helmet use was lower than that of male riders overall. Contrary to findings from other countries, motorcycle helmet use did not differ significantly throughout the day but was relatively constant. CONCLUSION: Our results show the potential for injury and fatality prevention in Madagascar through increased passenger helmet use. This increase would also proportionally benefit female riders more than male riders. Findings regarding road safety legislation's applied impact, education, enforcement and future research needs are discussed.

Computer vision-based helmet use registration for e-scooter riders - The impact of the mandatory helmet law in Copenhagen.

PROBLEM: E-scooters are a new form of mobility used more frequently in urban environments worldwide. As there is evidence of an increased risk of head injuries, helmets are recommended and (less frequently) legislated. Denmark has enacted mandatory e-scooter helmet use legislation from January 1, 2022. So far, it is unclear how this newly implemented law influenced helmet use of e-scooter riders in Denmark immediately after its implementation. METHOD: In this observational study, we register and compare e-scooter helmet use before the mandatory helmet use legislation (December 2021) and after (February 2022). As observational survey data collection in the field can be highly time-consuming, we conducted a video-based observation survey. We trained and applied a computer vision algorithm to automatically register e-scooter helmet use in the video data. RESULTS: The trained algorithm produces accurate helmet use data, which does not differ significantly from human-registered helmet use. In applying the algorithm to video data collected in December 2021 and February 2022, we register an overall e-scooter helmet use of 4.4% in n = 1054 riders. Splitting the observation between the time before and after the implementation of the helmet use law reveals a significant increase in helmet use from 1.80% to 5.56%. DISCUSSION: In this study, we successfully train and apply an object detection algorithm to register accurate helmet use data in videos collected in Copenhagen, Denmark. Using this algorithm, we find a significant impact of a new mandatory e-scooter helmet use law on e-scooter riders' helmet use behavior. Limitations of the study as well as future research needs, are discussed. PRACTICAL APPLICATIONS: Computer vision algorithms can be used for accurate e-scooter helmet assessments. Implementing a mandatory helmet use law can increase helmet use of e-scooters at specific observation sites.

GaVe: A Webcam-Based Gaze Vending Interface Using One-Point Calibration.

Gaze input, i.e., information input via eye of users, represents a promising method for contact- free interaction in human-machine systems. In this paper, we present the GazeVending interface (GaVe), which lets users control actions on a display with their eyes. The interface works on a regular webcam, available on most of today's laptops, and only requires a short one-point calibration before use. GaVe is designed in a hierarchical structure, presenting broad item cluster to users first and subsequently guiding them through another selection round, which allows the presentation of a large number of items. Cluster/item selection in GaVe is based on the dwell time, i.e., the time duration that users look at a given Cluster/ item. A user study (N=22) was conducted to test optimal dwell time thresholds and comfortable human-to-display distances. Users' perception of the system, as well as error rates and task completion time were registered. We found that all participants were able to quickly understand and know how to interact with the interface, and showed good performance, selecting a target item within a group of 12 items in 6.76 seconds on average. We provide design guidelines for GaVe and discuss the potentials of the system.

The Influence of Distance and Lateral Offset of Follow Me Robots on User Perception.

Robots that are designed to work in close proximity to humans are required to move and act in a way that ensures social acceptance by their users. Hence, a robot's proximal behavior toward a human is a main concern, especially in human-robot interaction that relies on relatively close proximity. This study investigated how the distance and lateral offset of "Follow Me" robots influences how they are perceived by humans. To this end, a Follow Me robot was built and tested in a user study for a number of subjective variables. A total of 18 participants interacted with the robot, with the robot's lateral offset and distance varied in a within-subject design. After each interaction, participants were asked to rate the movement of the robot on the dimensions of comfort, expectancy conformity, human likeness, safety, trust, and unobtrusiveness. Results show that users generally prefer robot following distances in the social space, without a lateral offset. However, we found a main influence of affinity for technology, as those participants with a high affinity for technology preferred closer following distances than participants with low affinity for technology. The results of this study show the importance of user-adaptiveness in human-robot-interaction.

Calibration-Free Gaze Interfaces Based on Linear Smooth Pursuit.

Since smooth pursuit eye movements can be used without calibration in spontaneous gaze interaction, the intuitiveness of the gaze interface design has been a topic of great interest in the human-computer interaction field. However, since most related research focuses on curved smooth-pursuit trajectories, the design issues of linear trajectories are poorly understood. Hence, this study evaluated the user performance of gaze interfaces based on linear smooth pursuit eye movements. We conducted an experiment to investigate how the number of objects (6, 8, 10, 12, or 15) and object moving speed (7.73 ˚/s vs. 12.89 ˚/s) affect the user performance in a gaze-based interface. Results show that the number and speed of the displayed objects influence users' performance with the interface. The number of objects significantly affected the correct and false detection rates when selecting objects in the display. Participants' performance was highest on interfaces containing 6 and 8 objects and decreased for interfaces with 10, 12, and 15 objects. Detection rates and orientation error were significantly influenced by the moving speed of displayed objects. Faster moving speed (12.89 ˚/s) resulted in higher detection rates and smaller orientation error compared to slower moving speeds (7.73 ˚/s). Our findings can help to enable a calibration-free accessible interaction with gaze interfaces.

Detecting motorcycle helmet use with deep learning.

The continuous motorization of traffic has led to a sustained increase in the global number of road related fatalities and injuries. To counter this, governments are focusing on enforcing safe and law-abiding behavior in traffic. However, especially in developing countries where the motorcycle is the main form of transportation, there is a lack of comprehensive data on the safety-critical behavioral metric of motorcycle helmet use. This lack of data prohibits targeted enforcement and education campaigns which are crucial for injury prevention. Hence, we have developed an algorithm for the automated registration of motorcycle helmet usage from video data, using a deep learning approach. Based on 91,000 annotated frames of video data, collected at multiple observation sites in 7 cities across the country of Myanmar, we trained our algorithm to detect active motorcycles, the number and position of riders on the motorcycle, as well as their helmet use. An analysis of the algorithm's accuracy on an annotated test data set, and a comparison to available human-registered helmet use data reveals a high accuracy of our approach. Our algorithm registers motorcycle helmet use rates with an accuracy of -4.4% and +2.1% in comparison to a human observer, with minimal training for individual observation sites. Without observation site specific training, the accuracy of helmet use detection decreases slightly, depending on a number of factors. Our approach can be implemented in existing roadside traffic surveillance infrastructure and can facilitate targeted data-driven injury prevention campaigns with real-time speed. Implications of the proposed method, as well as measures that can further improve detection accuracy are discussed.

Patterns of motorcycle helmet use - A naturalistic observation study in Myanmar.

Developing countries are subject to increased motorization, particularly in the number of motorcycles. As helmet use is critical to the safety of motorcycle riders, the goal of this study was to identify observable patterns of helmet use, which allow a more accurate assessment of helmet use in developing countries. In a video based observation study, 124,784 motorcycle riders were observed at seven observation sites throughout Myanmar. Recorded videos were coded for helmet use, number of riders on the motorcycle, rider position, gender, and time of day. Generally, motorcycle helmet use in Myanmar was found to be low with only 51.5% percent of riders wearing a helmet. Helmet use was highest for drivers (68.1%) and decreased for every additional passenger. It was lowest for children standing on the floorboard of the motorcycle (11.3%). During the day, helmet use followed a unimodal distribution, with the highest use observed during the late morning and lowest use observed in the early morning and late afternoon. Helmet use varied significantly between observation sites, ranging from 74.8% in Mandalay to 26.9% in Pakokku. In Mandalay, female riders had a higher helmet use than male riders, and helmet use decreased drastically on a national holiday in the city. Helmet use of motorcycle riders in Myanmar follows distinct patterns. Knowledge of these patterns can be used to design more precise helmet use evaluations and guide traffic law policy and police enforcement measures. Video based observation proved to be an efficient tool to collect helmet use data.

Introducing a multivariate model for predicting driving performance: the role of driving anger and personal characteristics.

INTRODUCTION: Maladaptive driving is an important source of self-inflicted accidents and this driving style could include high speeds, speeding violations, and poor lateral control of the vehicle. The literature suggests that certain groups of drivers, such as novice drivers, males, highly motivated drivers, and those who frequently experience anger in traffic, tend to exhibit more maladaptive driving patterns compared to other drivers. Remarkably, no coherent framework is currently available to describe the relationships and distinct influences of these factors. METHOD: We conducted two studies with the aim of creating a multivariate model that combines the aforementioned factors, describes their relationships, and predicts driving performance more precisely. The studies employed different techniques to elicit emotion and different tracks designed to explore the driving behaviors of participants in potentially anger-provoking situations. Study 1 induced emotions with short film clips. Study 2 confronted the participants with potentially anger-inducing traffic situations during the simulated drive. RESULTS: In both studies, participants who experienced high levels of anger drove faster and exhibited greater longitudinal and lateral acceleration. Furthermore, multiple linear regressions and path-models revealed that highly motivated male drivers displayed the same behavior independent of their emotional state. The results indicate that anger and specific risk characteristics lead to maladaptive changes in important driving parameters and that drivers with these specific risk factors are prone to experience more anger while driving, which further worsens their driving performance. Driver trainings and anger management courses will profit from these findings because they help to improve the validity of assessments of anger related driving behavior.