Publication Hub

Impact of online courses on University student visual attention during the COVID-19 pandemic

Background: Under the threat of COVID-19, many universities offer online courses to avoid student gatherings, which prevent teachers from collecting responses and optimizing courses. This work collected eye movement data to analyze attention allocation and proposed instruction for improving the courses. Methods: Subjects were recruited to watch three online courses. Meanwhile, their eye movement data were collected through Dikablis Glasses. Mayer’s multimedia cognitive theory was adopted to discriminate the pivotal components of online course, and the Mann–Whitney relevance analysis demonstrated that different representations of courses affected the viewers’ attention differently. Results: Three subjects watched three different types of political courses. Course 1, which combined text and explanation, attracted the most attention. Course 2 was shown to be less attractive than course 1 and better than course 3, but the subjects were distracted by the animations in course 2. Course 3, which did not use any technique to present learning content, attracts the least attention from the subjects. A correlation analysis shows that course 1 and course 3 have similar results compared with course 2. Conclusion: Online courses have become a norm during the COVID-19 pandemic. Improving the quality of online courses can effectively reduce the impact of the epidemic on teaching. These experiment results suggest that text + commentary in the design of online courses can effectively attract the attention of the listeners and achieve better learning results. Attention gradually rises in the early stage and then falls after reaching a peak. At this time, the proper introduction of animation can effectively reverse the attention curve, while individual text or commentary results in quickly losing the listener’s attention.

Eye Tracking Glasses

Software

6 versions available

Impact of sender and peer-feedback characteristics on performance, cognitive load, and mindful cognitive processing

Mixed research findings on peer feedback indicate that its efficiency seems to be influenced by its characteristics, its mindful cognitive processing, and the presence of justifications. Further, these aspects seem to positively or negatively affect cognitive load in the recipient. In a 2 × 3 design, we systematically varied types of peer feedback (elaborated specific feedback with/without justifications) on an essay and sender’s competence (high/average/low). We measured cognitive load during the peer-feedback reading and performance tasks and correlated eye tracking data with performance measures to infer mindful cognitive processing. We found an interaction effect of justifications and sender’s competence on text-revision performance. The impact of justifications on text-revision performance was moderated by cognitive load. Mindful cognitive processing seemed to increase when more transitions between text elements occurred, however, more intense mindful cognitive processing did not necessarily lead to better performance but rather served a compensatory purpose to sustain performance.

Eye Tracking Glasses

Simulator

4 versions available

Interaction strategies with advanced driver assistance systems

When using advanced driver assistance systems (ADAS) drivers need to calibrate their level of trust and interaction strategy to changes in the driving context and possible consequent reduction of system reliability (e.g. in harsh weather conditions). By investigating and identifying categories of drivers who choose inadequate interaction strategies, it is possible to address unsafe usage with e.g. tutoring lessons tailored to the respective driver category. This paper presents two studies investigating categories of drivers who apply different interaction strategies when using ADAS. Study I was designed as an exploratory field study with 37 participants interacting with a SAE level 2 system. For the exploratory study, it was important to observe and understand the interaction strategies in a driving context which entails the real complexity of the driving task. The experimental set-up of study II (simulator study), however, allowed to clearly interpret the interaction strategies as either calibrated or un-calibrated by varying the situational risk. Participants (N = 33) were driving in a situation where the system was either working reliably (low-risk condition) or in a situation where the system displayed repeatedly errors under harsh weather conditions (high-risk condition). Cluster analyses with the variables trust, monitoring behavior towards the system and usage behavior were performed to analyze potential categories of drivers. Extreme driver categories with interaction strategies indicative for both misuse and disuse were observed in both studies. In study I, drivers were categorized as either highly trusting attentive, moderately trusting attentive, moderately inattentive, inattentive or skeptical. In study II, drivers were categorized as either un-calibrated, calibrated, inconsistent or skeptical. Taken together, results underline the need of tutoring systems that are tailored for different driver categories.

Eye Tracking Glasses

Simulator

5 versions available

Interruption management in the context of take-over-requests in conditional driving automation

Drivers of partially automated vehicles are relieved from parts of the driving tasks allocated to the automated driver. This reduction in driving demands encourages them to engage with nondriving related tasks, which may impair awareness of the road environment once a takeover request (TOR) is initiated. This article examined the four suggested strategies drivers that take to regain control following a TOR, from the perspective of interruption management principles. Thirty students participated in a simulated study of two drives, where we manipulated TOR alerts, time to regain control, and potential road hazards. We hypothesized that all four interruption management strategies will be observed. Our hypothesis was confirmed. Four strategies were identified. Most drivers chose strategy 2 to accept and initiate the takeover immediately after the TOR started. The second frequent strategy was to reject the TOR but look at the road. Drivers’ strategy choices changed following alert type and the chronological drive order. With simulated driving experience (i.e., second drive), drivers postponed taking control, adapting to the time budget. Yet, inaccurate understanding of the situation or over-trust affected the chosen strategy. We conclude that interruption management principles are beneficial for studying how drivers respond to TORs and evaluating options to improve TOR performance.

Eye Tracking Glasses

Simulator

2 versions available

Investigating the Performance of Sensor-Driven Biometrics for the Assessment of Cognitive Workload

This study investigates the performance of sensor-driven biometrics for the assessment of cognitive workload. Traditional methods for evaluating cognitive workload often rely on subjective self-assessments or take significant time and resources to administer and interpret. Sensor-driven biometrics, such as heart rate variability, skin conductance, and eye tracking, offer a potential alternative. By continuously and non-invasively monitoring physiological responses, these biomarkers can provide real-time insights into cognitive workload. Understanding the relationship between biometric data and cognitive workload can improve efficiency and effectiveness in environments where cognitive demands fluctuate. This research explores the viability of various biometric sensors and analytical techniques to accurately measure and interpret cognitive workload.

Eye Tracking Glasses

Software

3 versions available

Machine Learning Bandwidth Optimization of Interactive Live Free-Viewpoint Multiview Video for Sporting Events

Live free-viewpoint MultiView Video (MVV) allows users to experience their own personalized experience to gaze within a video environment created by a linear array of adjacent cameras that span the playing area of a live sporting event. This technology allows each user to look around as if they are physically at the sporting event. While the broadcast television transport is efficient at transporting the same live video within a one-to-many environment, the broadcast television transport for video does not lend itself to providing each user their own personalized live free-viewpoint MVV content. This dissertation shows that by using machine learning, a broadcast-Internet hybrid system can intelligently predict a population maxima of the viewers’ most desired future free-viewpoint MVV content to transport over the efficient broadcast transport while minimizing the Internet network bandwidth. Accordingly, test results show that by using machine learning, overall bandwidth efficiency is significantly improved while meeting each viewer’s personalized free-viewpoint MVV content demands. Notably, the test results show that by using machine learning, overall bandwidth efficiencies of 91+% to 98+% are obtainable using the broadcast transport alone. Moreover, this dissertation includes (1) machine learning algorithm implementation details, and (2) test results that show overall system bandwidth efficiency improvements based on the use of actual ground-truth soccer video and dataset data over a wide range of worst-case conditions. Overall, this dissertation demonstrates that machine learning may be used to learn the characteristics of sporting events to meaningfully improve overall system bandwidth efficiency for the transport of personalized free-viewpoint MVV content.

Simulator

Software

1 version available:

Multi-dimensional and objective assessment of motion sickness susceptibility based on machine learning

Background: As human transportation, recreation, and production methods change, the impact of motion sickness (MS) on humans is becoming more prominent. The susceptibility of people to MS can be accurately assessed, which will allow ordinary people to choose comfortable transportation and entertainment and prevent people susceptible to MS from entering provocative environments. This is valuable for maintaining public health and the safety of tasks. Objective: To develop an objective multi-dimensional MS susceptibility assessment model based on physiological indicators that objectively reflect the severity of MS and provide a reference for improving the existing MS susceptibility assessment methods. Methods: MS was induced in 51 participants using the Coriolis acceleration stimulation. Some portable equipment were used to digitize the typical clinical manifestations of MS and explore the correlations between them and Graybiel's diagnostic criteria. Based on significant objective parameters and selected machine learning (ML) algorithms, several MS susceptibility assessment models were developed, and their performances were compared. Results: Gastric electrical activity, facial skin color, skin temperature, and nystagmus are related to the severity of MS. Among the ML assessment models based on these variables, the support vector machine classifier had the best performance with an accuracy of 88.24%, sensitivity of 91.43%, and specificity of 81.25%. Conclusion: The severity of symptoms and signs of MS can be objectively quantified using some indicators. Multi-dimensional and objective assessment models for MS susceptibility based on ML can be successfully established.

Eye Tracking Glasses

Simulator

5 versions available

Multi-modal user experience evaluation on in-vehicle HMI systems using eye-tracking, facial expression, and finger-tracking for the smart cockpit

The trend toward intelligent connected vehicles (ICVs) led to numerous more novel and more natural human-vehicle relationships, which will bring about tremendous changes in smart cockpit functions and interaction methods. However, most in-vehicle human-machine interaction (HMI) systems focus on adding more functions, while few of them focus on the user experience (UX) of the system. This study presents an evaluation method of UX based on eye-tracking, finger movement tracking, and facial expression, the study also proposed a pleasantness prediction based on multi-layer perception (MLP) algorithm using multi-modal data. Through the UX experiment on two in-vehicle HMI systems, the study verified that the proposed evaluation method can be objective and efficient to evaluate the in-vehicle HMI system. Based on the MLP algorithm, the study trained the pleasantness prediction model using multi-modal data. Besides, we collected new data of the third in-vehicle HMI system to test the trained model and presented excellent test results.

Eye Tracking Glasses

Software

7 versions available

Multimodal natural human–computer interfaces for computer-aided design: A review paper

Computer-aided design (CAD) systems have advanced to become a critical tool in product design. Nevertheless, they still primarily rely on the traditional mouse and keyboard interface. This limits the naturalness and intuitiveness of the 3D modeling process. Recently, a multimodal human–computer interface (HCI) has been proposed as the next-generation interaction paradigm. Widening the use of a multimodal HCI provides new opportunities for realizing natural interactions in 3D modeling. In this study, we conducted a literature review of a multimodal HCI for CAD to summarize the state-of-the-art research and establish a solid foundation for future research. We explore and categorize the requirements for natural HCIs and discuss paradigms for their implementation in CAD. Following this, factors to evaluate the system performance and user experience of a natural HCI are summarized and analyzed. We conclude by discussing challenges and key research directions for a natural HCI in product design to inspire future studies.

Simulator

Software

6 versions available

Pedestrians’ Understanding of a Fully Autonomous Vehicle’s Intent to Stop: Utilizing Video-based Crossing Scenarios

Background. External human-machine interfaces (eHMI) indicate Fully Autonomous Vehicles' (FAVs) intents, contributing to their communication with pedestrians. We still do not know enough about how eHMI propositions lead pedestrians to comply in conflicting situations. Objective. Findings on fixed crossing scenes suggest that pedestrians' decision-making depends on the eHMI implementation and the 'vehicle's distance from the crossing. We aim to enhance this work, looking at dynamic crossing situations. Method. Thirty-four adult participants observed 56 road-crossing video scenarios as if they were pedestrians intending to cross. A single FAV drove at 40 km/h. Scenarios differed by car size, eHMI message type, and the FAV's initial distance from the crossing place. Participants had to decide whether to cross or not by pressing designated buttons. Following each scenario, their subjective Understanding of the FAV's intention was obtained. Decision measurements and eye-tracking data were collected. Results. Eye-tracking data confirmed that all pedestrians fixated on the eHMI, yet only 53% of the responses were compatible with its proposition. More incompatible responses were observed for the close distance. An interaction between distance and eHMI proposition revealed that when the eHMI indicated participants to cross, and the FAV's initial location was close, most participants decided not to cross. Distance influenced participants' response time; pedestrians decided faster in the closer distance. Overall, subjective Understanding of the FAV's intention was low. Conclusion. Using video-based scenarios, we showed the combined effect of context and eHMI meaning on pedestrians' crossing decisions. Relative to fixed scenes, pedestrians were more conservative and relied less on the eHMI suggestions. Interactions of distance and message meaning affected compatibility and response time. Even when pedestrians understood the eHMI message, they did not necessarily comply. Distance of the vehicle from the crossing place influenced the crossing decision, as it does today.

Eye Tracking Glasses

Simulator

1 version available:

Company

Publication Hub

Filter menu

Impact of online courses on University student visual attention during the COVID-19 pandemic

Impact of sender and peer-feedback characteristics on performance, cognitive load, and mindful cognitive processing

Interaction strategies with advanced driver assistance systems

Interruption management in the context of take-over-requests in conditional driving automation

Investigating the Performance of Sensor-Driven Biometrics for the Assessment of Cognitive Workload

Machine Learning Bandwidth Optimization of Interactive Live Free-Viewpoint Multiview Video for Sporting Events

Multi-dimensional and objective assessment of motion sickness susceptibility based on machine learning

Multi-modal user experience evaluation on in-vehicle HMI systems using eye-tracking, facial expression, and finger-tracking for the smart cockpit

Multimodal natural human–computer interfaces for computer-aided design: A review paper

Pedestrians’ Understanding of a Fully Autonomous Vehicle’s Intent to Stop: Utilizing Video-based Crossing Scenarios

Explore Cutting-Edge Research in Human Factors and Ergonomics