Look right! The influence of bicycle crossing design on drivers’ approaching behavior
One of the most frequent crashes between cyclists and motor vehicles is the so-called “turning into” accident, where a motor vehicle turns into the main road and collides with a cyclist riding on the main road and crossing the vehicle’s course. Previous studies mainly examined this type of crash and its causes with accident analyses or observational approaches. This study uses a driving simulator to examine the effect of possible countermeasures like the drivers’ expectancy towards crossing cyclists, the view into the junction, and various bicycle crossing designs. N = 66 participants passed T-junctions that differ in the mentioned measures. Gaze and driving data were collected to assess the criticality of each approach. Results indicate that drivers approach marked bicycle crossings at a lower speed than unmarked crossings. Furthermore, crossings with pronounced designs showed more uncritical approaches. However, an alarming percentage of all approaches were critical because drivers showed no appropriate gaze behavior. This was even increased when the view into the junction was limited. The findings suggest that especially the view at junctions must not be obstructed to provide sufficient fields of view. Pronounced bicycle crossing, however, can enhance drivers’ approaching behavior and might help to reduce the frequency of “turning into” accidents.
Machine learning based approach for exploring online shopping behavior and preferences with eye tracking
In light of advancements in information technology and the widespread impact of the COVID-19 pandemic, consumer behavior has undergone a significant transformation, shifting from traditional in-store shopping to the realm of online retailing. This shift has notably accelerated the growth of the online retail sector. An essential advantage offered by e-commerce lies in its ability to accumulate and analyze user data, encompassing browsing and purchase histories, through its recommendation systems. Nevertheless, prevailing methodologies predominantly rely on historical user data, which often lack the dynamism required to comprehend immediate user responses and emotional states during online interactions. Recognizing the substantial influence of visual stimuli on human perception, this study leverages eye-tracking technology to investigate online consumer behavior. The research captures the visual engagement of 60 healthy participants while they engage in online shopping, while also taking note of their preferred items for purchase. Subsequently, we apply statistical analysis and machine learning models to unravel the impact of visual complexity, consumer considerations, and preferred items, thereby providing valuable insights for the design of e-commerce platforms. Our findings indicate that the integration of eye-tracking data into e-commerce recommendation systems is conducive to enhancing their performance. Furthermore, machine learning algorithms exhibited remarkable classification capabilities when combined with eye-tracking data. Notably, during the purchase of hedonic products, participants primarily fixated on product images, whereas for utilitarian products, equal attention was dedicated to images, prices, reviews, and sales volume. These insights hold significant potential to augment the effectiveness of e-commerce marketing endeavors.
Eye Tracking Glasses
Software
Machine Learning in Driver Drowsiness Detection: A Focus on HRV, EDA, and Eye Tracking
Drowsy driving continues to be a significant cause of road traffic accidents, necessitating the development of robust drowsiness detection systems. This research enhances our understanding of driver drowsiness by analyzing physiological indicators – heart rate variability (HRV), the percentage of eyelid closure over the pupil over time (PERCLOS), blink rate, blink percentage, and electrodermal activity (EDA) signals. Data was collected from 40 participants in a controlled scenario, with half of the group driving in a non-monotonous scenario and the other half in a monotonous scenario. Participant fatigue was assessed twice using the Fatigue Assessment Scale (FAS).The research developed three machine learning models: HRV-Based Model, EDA-Based Model, and Eye-Based Model, achieving accuracy rates of 98.28%, 96.32%, and 90% respectively. These models were trained on the aforementioned physiological data, and their effectiveness was evaluated against a range of advanced machine learning models including GRU, Transformers, Mogrifier LSTM, Momentum LSTM, Difference Target Propagation, and Decoupled Neural Interfaces Using Synthetic Gradients. The HRV-Based Model and EDA-Based Model demonstrated robust performance in classifying driver drowsiness. However, the Eye-Based Model had some difficulty accurately identifying instances of drowsiness, likely due to the imbalanced dataset and underrepresentation of certain fatigue states. The study duration, which was confined to 45 minutes, could have contributed to this imbalance, suggesting that longer data collection periods might yield more balanced datasets. The average fatigue scores obtained from the FAS before and after the experiment showed a relatively consistent level of reported fatigue among participants, highlighting the potential impact of external factors on fatigue levels. By integrating the outcomes of these individual models, each demonstrating strong performance, this research establishes a comprehensive and robust drowsiness detection system. The HRV-Based Model displayed remarkable accuracy, while the EDA-Based Model and the Eye-Based Model contributed valuable insights despite some limitations. The research highlights the necessity of further optimization, including more balanced data collection and investigation of individual and external factors impacting drowsiness. Despite the challenges, this work significantly contributes to the ongoing efforts to improve road safety by laying the foundation for effective real-time drowsiness detection systems and intervention methods.
Eye Tracking Glasses
Software
Multimodal Turn Analysis and Prediction for Multi-party Conversations
This paper presents a computational study to analyze and predict turns (i.e., turn-taking and turn-keeping) in multiparty conversations. Specifically, we use a high-fidelity hybrid data acquisition system to capture a large-scale set of multi-modal natural conversational behaviors of interlocutors in three-party conversations, including gazes, head movements, body movements, speech, etc. Based on the inter-pausal units (IPUs) extracted from the in-house acquired dataset, we propose a transformer-based computational model to predict the turns based on the interlocutor states (speaking/back-channeling/silence) and the gaze targets. Our model can robustly achieve more than 80% accuracy, and the generalizability of our model was extensively validated through cross-group experiments. Also, we introduce a novel computational metric called “relative engagement level" (REL) of IPUs, and further validate its statistical significance between turn-keeping IPUs and turn-taking IPUs, and between different conversational groups. Our experimental results also found that the patterns of the interlocutor states can be used as a more effective cue than their gaze behaviors for predicting turns in multiparty conversations.
Eye Tracking Glasses
Software
Multivariate Analysis of Gaze Behavior and Task Performance Within Interface Design Evaluation
Eye tracking technologies have frequently been used in sport research to understand the interrelations between gaze behavior and performance, using a paradigm known as vision-for-action. This methodology has not been robustly applied within the field of interface design. The present work demonstrates the benefit of employing a vision-for-action paradigm for interface evaluation. This is demonstrated through the evaluation of a novel task-specific symbology set presented on a head-up-display (HUD), developed to support pilots conduct ground operations in low-visibility conditions. HUD gaze behavior was correlated with task performance to determine whether certain combinations of gaze behavior could produce effective predictive performance models. A human-in-the-loop experiment was conducted with 11 professional pilots who were required to taxi in a fixed-base flight simulator using the HUD symbology, while gaze data toward the different HUD symbology elements was collected. Performance was measured as centerline deviation error and taxiing speed. Results revealed that appropriately timed gaze behavior toward task-specific elements of the HUD were associated with superior performance. During turns, attention toward an undercarriage lateral position indicator was associated with reduced centerline deviation (p < 0.05). The findings are interpreted alongside detailed posttrial user-feedback of the HUD symbology to illustrate how eye tracking methodologies can be incorporated into interface usability evaluations. The joint interpretation of these data demonstrates these novel procedures, the findings contribute to enhancing the wider domain of interface design evaluation.
On the relationship between occlusion times and in-car glance durations in simulated driving
Drivers have spare visual capacity in driving, and often this capacity is used for engaging in secondary in-car tasks. Previous research has suggested that the spare visual capacity could be estimated with the occlusion method. However, the relationship between drivers’ occlusion times and in-car glance duration preferences has not been sufficiently investigated for granting occlusion times the role of an estimate of spare visual capacity. We conducted a driving simulator experiment (N = 30) and investigated if there is an association between drivers’ occlusion times and in-car glance durations in a given driving scenario. Furthermore, we explored which factors and variables could explain the strength of the association. The findings suggest an association between occlusion time preferences and in-car glance durations in visually and cognitively low demanding unstructured tasks but that this association is lost if the in-car task is more demanding. The findings might be explained by the inability to utilize peripheral vision for lane-keeping when conducting in-car tasks and/or by in-car task structures that override drivers’ preferences for the in-car glance durations. It seems that the occlusion technique could be utilized as an estimate of drivers’ spare visual capacity in research – but with caution. It is strongly recommended to use occlusion times in combination with driving performance metrics. There is less spare visual capacity if this capacity is used for secondary tasks that interfere with the driver’s ability to utilize peripheral vision for driving or preferences for the in-car glance durations. However, we suggest that the occlusion method can be a valid method to control for inter-individual differences in in-car glance duration preferences when investigating the visual distraction potential of, for instance, in-vehicle infotainment systems.
Eye Tracking Glasses
Simulator
Pilot study: Effect of roles and responsibility training on driver’s use of adaptive cruise control between younger and older adults
With the development of driver support systems (SAE Levels 1 – 2), drivers must take on new monitoring and supervision tasks in additional to manual driving. Training is necessary to clarify drivers' new roles and promote safe usage and trust in these systems. Providing training for lower-levels of automation may also benefit drivers’ acceptance of future Fully Automated Vehicles (FAVs, SAE Level 5). However, younger and older drivers differ in training preferences (e.g., owner's manual vs on-road trial and error) and hold different attitudes towards automation. This study investigates the effects of additional training on drivers' roles and responsibilities when using Adaptive Cruise Control (ACC, SAE Level 1) for younger and older drivers. Thirty-nine adults (20 younger + 19 older) were trained on one of two ACC training protocols: basic (system functionality, operational procedures, and limitations) and comprehensive (basic training + ACC background and roles of responsibilities). Participants’ situational trust and ACC usage was evaluated before, during, and after experiencing an emergency event while using ACC in a driving simulator study. Results showed that the comprehensive training promoted drivers' situational trust in ACC, ACC usage, and the acceptance of FAVs. Compared to younger drivers, older drivers used ACC less, reported less dynamic situational trust, higher levels of workload, and lower acceptance. Overall, comprehensive training resulted in older drivers behaving similarly to younger drivers. The comprehensive training also promoted the acceptance of FAVs for both younger and older drivers. In conclusion, training of drivers’ roles and responsibilities has an impact on drivers’ usage of ACC and may be particularly useful for older drivers.
Quiet eye duration and performance outcome in petanque
Petanque is a competitive skill sport that is popular in Malaysia. Athletes often must perform in a high-pressure situation during a game. The purpose of the research is to understand the influence of the quiet eye duration on the performance outcome across different difficulties amongst the athletes. Ergoneer Dikablis (v3.55) eye-tracking system was used to collect the quiet eye duration of 8 Malaysian petanque athletes in a field setting at the National Sports Council (MSN), Keramat. The athletes were required to shoot the single ball (SB) and double ball (DB) (right ball only) across five different distances from the starting point alternately. The arrangement of a double ball is more difficult compared to a single ball. Three trials were permitted for each distance. Successful trials were recorded when the targeted ball was displaced from its original position in SB (whole ball) and in DB (ball on the right). A previous study found that athletes with higher levels of expertise and successful performance had longer QE duration. The performance outcome and the quiet eye duration were analysed for normality. The Mann-Whitney U-test and Kruskal-Wallis tests were conducted using SPSS statistical software. From the statistical findings, it was found that irrespective of distance, there is a difference in the quiet eye between a single ball and a double ball. As p=0.846, which is greater than p=0.05, there is no significant difference between distance and quiet eye for a single ball. As p=0.865, which is greater than 0.05, there is no significant difference between the distance and quiet eye for the double ball. In conclusion, the duration of the quiet eye is influenced by the difficulty level of the ball arrangement. The performance outcome was not found to be influenced by the quiet eye.
Eye Tracking Glasses
Software
Quiet eye training during the rugby union goal-kick: Practice and transfer effects in low-and high-pressure conditions
The present study aimed to examine the effect of a quiet eye training (QET) intervention compared to a technical training (TT) intervention on the visual control and performance of rugby union goal-kickers. Male rugby union players (n = 18, M age = 21.35 years, SD = 2.03) were randomly assigned into a QET or TT group. Participants completed a pre-test, retention test 1, pressure test, and retention test 2 over six weeks, including a two-week intervention programme. The QET focussed on the QE and performance, while TT focussed on technical aspects of rugby goal-kicking. Each participant performed a total of 50 kicks that consisted of 15 kicks during the pre-test, retention test 1, and retention test 2, and five kicks during the pressure test. Using a Dikablis eye-tracker the QE was measured before (QE-pre), and during (QE-online), the run-up of the goal-kick. The results indicated that QE-pre durations increased from the pre-test to both retention tests and the pressure test for the QET group only (all p's < 0.05, all d's ≥ 0.08). The QET group also displayed longer QE-pre durations during the pressure and retention tests (all p's < 0.05, all d's ≥ 0.80), and longer QE-online durations during the pressure test (d = 0.73), compared to the TT group. Finally, the QET group outperformed the TT group during the pressure test (d = 0.72). Thus, overall, our results revealed that a short QET intervention benefitted attentional control and goal-kicking performance, particularly under high-pressure.
Eye Tracking Glasses
Software
