Eye-tracking Software Research Articles

Eye tracking technologies to visualize secure coding behavior

Secure coders' experiences and performances vary greatly and any missed security flaws in source code may lead to costly consequences. Their behavior to analyze source code and develop mitigation techniques is not well understood. Our objective is to gain insight into the strategies and techniques from both novice and experienced developers. Proper understanding can help us to inform inexperienced coders to efficiently and accurately approach, discover, and mitigate security flaws. Our research relies upon eye tracking hardware and software to collect and analyze the eye gazes. Unlike existing approaches, we incorporate a wide range of tasks simultaneously reading documentation, writing code, and using security coding analysis tools. We analyze both static and dynamic (interactive) stimuli in a realistic software development environment. Our pictorial visualizations represent a coder's eye gazes that visually demonstrates their behavior and patterns. In addition, we provide the full context of the stimuli that a participant observed. This allows for investigating the behavior at a range of tasks for a single participant and between participants. Our secure coding tasks include reading documentation, reading source code, and writing source code for a web application as well as utilizing security code scanning tools. Our contributions also include (1) novel visualization techniques to present transitions among components within and between applications, and (2) presentations of coders' attention levels during secure coding by investigating the change of pupil sizes. The eye tracking collection and analysis techniques support both modifiable stimuli and stimuli presented in different sequences based upon individual participant's behavior. • Gain Insight into Secure Coders' Behavior and Methodologies Using Eye Trackers. • Visualizations Of Eye Gazes to Understand Approaches to Secure Coding. • Investigate Behavior When Discovering and Mitigating Source Code Flaws. • Evaluation Of Hands-On Secure Coding Learning Modules. • Dynamic Eye-Tracking Stimuli for Realistic Software Development Environment.

Comparing infrared and webcam eye tracking in the Visual World Paradigm

Visual World eye tracking is a temporally fine-grained method of monitoring attention, making it a popular tool in the study of online sentence processing. Recently, while infrared eye tracking was mostly unavailable, various web-based experiment platforms have rapidly developed webcam eye tracking functionalities, which are now in urgent need of testing and evaluation. We replicated a recent Visual World study on the incremental processing of verb aspect in English using ‘out of the box’ webcam eye tracking software (jsPsych; de Leeuw, 2015) and crowdsourced participants, and fully replicated both the offline and online results of the original study. We furthermore discuss factors influencing the quality and interpretability of webcam eye tracking data, particularly with regards to temporal and spatial resolution; and conclude that remote webcam eye tracking can serve as an affordable and accessible alternative to lab-based infrared eye tracking, even for questions probing the time-course of language processing.

Influence of dynamic content on visual attention during video advertisements

PurposeDynamic advertising, including television and online video ads, demands new theory and tools developed to understand attention to moving stimuli. The purpose of this study is to empirically test the predictions of a new dynamic attention theory, Dynamic Human-Centred Communication Systems Theory, versus the predictions of salience theory.Design/methodology/approachAn eye-tracking study used a sample of consumers to measure visual attention to potential areas of interest (AOIs) in a random selection of unfamiliar video ads. An eye-tracking software feature called intelligent bounding boxes (IBBs) was used to track attention to moving AOIs. AOIs were coded for the presence of static salience variables (size, brightness, colour and clutter) and dynamic attention theory dimensions (imminence, motivational relevance, task relevance and stability).FindingsStatic salience variables contributed 90% of explained variance in fixation and 57% in fixation duration. However, the data further supported the three-way interaction uniquely predicted by dynamic attention theory: between imminence (central vs peripheral), relevance (motivational or task relevant vs not) and stability (fleeting vs stable). The findings of this study indicate that viewers treat dynamic stimuli like real life, paying less attention to central, relevant and stable AOIs, which are available across time and space in the environment and so do not need to be memorised.Research limitations/implicationsDespite the limitations of small samples of consumers and video ads, the results of this study demonstrate the potential of two relatively recent innovations, which have received limited emphasis in the marketing literature: dynamic attention theory and IBBs.Practical implicationsThis study documents what does and does not attract attention to video advertising. What gets attention according to salience theory (e.g. central location) may not always get attention in dynamic advertising because of the effects of relevance and stability. To better understand how to execute video advertising to direct and retain attention to important AOIs, advertisers and advertising researchers are encouraged to use IBBs.Originality/valueThis study makes two original contributions: to marketing theory, by showing how dynamic attention theory can predict attention to video advertising better than salience theory, and to marketing research, showing the utility of tracking visual attention to moving objects in video advertising with IBBs, which appear underutilised in advertising research.

Differences in Attention Allocation in Relation to Music Teacher Experience and Expertise

To assess allocation of attention by music teachers with different levels of experience and expertise, we recruited five participant flautists: an artist teacher, two graduate students, and two undergraduates, all of whom observed nine brief video recordings of flute, clarinet, and saxophone players; a juggler; a baseball batter; and a ballerina. We tracked participants’ gaze using wearable eye-tracking hardware and software, and we analyzed the targets and durations of over 1,300 visual fixations and the paths of participants’ eye movements while observing the videos. The gaze behavior of the artist teacher and one of the graduate students, when they observed flute playing, was much like that of the experts in other domains of human experience. These two participants’ fixations were longer than those of the other three participants, and the sequence of fixation targets reflected a hierarchical prioritization of the fundamentals of flute playing. These same features were not apparent when these same two participants observed the other videos, and they were not observed in the gaze behavior of the other three participants in any of the videos observed. The results of this study demonstrate that allocation of attention, as indicated by gaze behavior, is reflective of expertise in music teaching as it is in other domains.

The Use of Corpora in Translation Into the Second Language: A Project-Based Approach

This manuscript investigates to what extent the use of corpora could help translation trainees while translating from Arabic into English and vice versa. Forty Yemeni trainees, who were enrolled in an advanced course in Arabic-English translation during the academic year 2020, participated in the study. They participated in translation projects from which the data for this study was collected, using thinking aloud protocols and computational observation. The translation process was investigated using the translation process software Transalog, an eye-tracking software and the screen recording software Screen-O-Matic. This kind of computational observation enabled a researcher to discover the extent to which the participants were able to employ corpora in their translation projects. At the end of the study, the participants were given a questionnaire with the aim of finding out their perceptions toward the use of corpora in their translation projects, and toward the project-based training approach adopted in the study. The findings of the translation process indicated that the trainees employed various kinds of corpora in their translation projects. Results from the questionnaire showed that the trainees have very positive attitudes toward the progress in their instrumental translation sub-competence, the utilization of corpora tools, and the project-based training approach adopted in this study.

Влияние ориентационных характеристик изображения на распределение зрительных фиксаций при решении простых когнитивных задач

Optimization of the educational process, including distance learning, requires orderly arrangement of the information presented, which translates into the need to factor in oculomotor reactions accompanying the search for solutions to simple cognitive tasks. This need supports the relevance of the present study, which aimed to investigate the age-dependent parameters of the oculomotor reactions occurring in solving a simple cognitive task. The sample included 97 persons, 47 males and 50 females, ages 21 to 36. For the purpose of rating the oculomotor reactions, the sample was divided into age groups: 21–26 years (n = 34); 27–32 years (n = 29); 33–36 years (n = 34). The methodology that governed the rating procedures was developed by the authors of the study and relied on the Tobii EyeX eye tracking hardware and software solution (GazeControl software). The study revealed a significant correlation between orientation of the image (presentation angle) and distribution of the visual fixations: regardless of the image presentation angle and its properties (schematic monochrome or full color image), the fixations tend to fall predominantly into the top and left parts of the image (the first quadrant). Other findings include a) a significant dependence of the capability to solve simple cognitive tasks and recognize the contents of the image on the spatial orientation of the presented stimuli, and b) the number of errors made in image contents recognition increasing with age, this dependence being significant and observed for both the schematic monochrome image (p1 = 0.014; p2 = 0.016; p3 = 0.014) and the full-color image (p1 = 0.015; p2 = 0.015; p3 = 0.017). The researchers have also identified the significant angles of rotation of the presented face images that stably caused recognition errors.

Eye tracking provides valuable insights in neuroscience: An empirical brand perception food marketing study

This study examines the importance of product packaging as a marketing medium. Using the example of commercially available pasta, the research focuses on key visual aspects of its packaging, such as colour, shape, packaging material and logo. The findings from studies like this are particularly important to food and beverage companies as they help marketers better understand the consumer purchase decision process. The study analyses data gathered from surveys administered through Google Modules, and visualisation data obtained using iMotions eye-tracker software. The results confirm the importance of packaging design elements such as colour and product information when it comes to consumer buying behaviour.

The methodology of conducting an experimental study of the perception of the graphical interface using eye-tracking technology

This article describes the methodology developed by the authors for conducting an experimental study of the perception of the graphical interface of remote control systems for dynamic objects using eye-tracking technology. The developed methodology is an integral part of research on the perception of visual information. The object of the study is a graphical interface of dynamic object control systems. The subject of the study is dashboards in a stimulus slide, their internal content (type, size, quantity). The methodology includes the development of a set of dashboards with different values of the displayed parameter, made in three types of diagrams (linear, columnar, curly quantitative) and in three sizes. The stimulus material of the experiment was developed using a special software module. This module performed the task of filling the stimulus with dashboards randomly. To conduct the experiment, an eye-tracking software and hardware complex was used, which captures the objective parameters of the eye pattern and allows you to shoot arrays of experimental data. Standard methods of mathematical statistics, such as analysis of variance, are used to process the results of the experiment. The developed technique was tested on a limited group. The scientific novelty of this work lies in the development of a methodology for conducting an experimental study on the influence of the factor of the number, type and size of diagrams in a graphic composition, its perception by the viewer.

Smile Arc Esthetics in Middle-Aged Man from the Layperson’s Perspective Via Eye-Tracking

Objective: To evaluate the perceptions of smile esthetics associated with variations in the vertical plane of the maxillary incisors in the smile arc using eye-tracking software. Material and Methods: An image of a 59-year-old Caucasian male model was adapted and edited to make three changes in the vertical plane, simulating a convex, straight, and reverse smile arc. Four areas of interest were inserted at the right and left eyes, nose, and mouth. Forty laypeople raters between 18 and 45 years of age participated of the study. Eye-tribe hardware and Ogama software were used to perform eye-tracking. Attractiveness and age-perception questions were also incorporated into the study. ANOVA test and Pearson’s correlation coefficient, at p < 0.05. Results: The most observed AOI in images with convex, straight, and reverse smiles, as assessed using heatmaps and point maps, was the mouth, followed by the right eye. A significant difference for the eye (p=0.02) was found when comparing convex and reverse smiles, whereas a significant difference for the mouth was observed between the straight and reverse smiles (p=0.03). Conclusion: Convex and straight smile arcs were associated with equal levels of attractiveness; the reverse smile was less attractive. No significant difference was noticed regarding age perception and the smile arcs. However, the reverse smile recorded a more complete fixation time.

Eye-Tracking Assistive Technologies for Individuals With Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis, also known as ALS, is a progressive nervous system disorder that affects nerve cells in the brain and spinal cord, resulting in the loss of muscle control. For individuals with ALS, where mobility is limited to the movement of the eyes, the use of eye-tracking-based applications can be applied to achieve some basic tasks with certain digital interfaces. This paper presents a review of existing eye-tracking software and hardware through which eye-tracking their application is sketched as an assistive technology to cope with ALS. Eye-tracking also provides a suitable alternative as control of game elements. Furthermore, artificial intelligence has been utilized to improve eye-tracking technology with significant improvement in calibration and accuracy. Gaps in literature are highlighted in the study to offer a direction for future research.

Optimizing Fixation Filters for Eye-Tracking on Small Screens.

The study of consumer responses to advertising has recently expanded to include the use of eye-tracking to track the gaze of consumers. The calibration and validation of eye-gaze have typically been measured on large screens in static, controlled settings. However, little is known about how precise gaze localizations and eye fixations are on smaller screens, such as smartphones, and in moving feed-based conditions, such as those found on social media websites. We tested the precision of eye-tracking fixation detection algorithms relative to raw gaze mapping in natural scrolling conditions. Our results demonstrate that default fixation detection algorithms normally employed by hardware providers exhibit suboptimal performance on mobile phones. In this paper, we provide a detailed account of how different parameters in eye-tracking software can affect the validity and reliability of critical metrics, such as Percent Seen and Total Fixation Duration. We provide recommendations for producing improved eye-tracking metrics for content on small screens, such as smartphones, and vertically moving environments, such as a social media feed. The adjustments to the fixation detection algorithm we propose improves the accuracy of Percent Seen by 19% compared to a leading eye-tracking provider’s default fixation filter settings. The methodological approach provided in this paper could additionally serve as a framework for assessing the validity of applied neuroscience methods and metrics beyond mobile eye-tracking.

Testing potential disclosures for e-cigarette sponsorship on social media

ObjectivesFew e-cigarette social media posts are authentic posts to friends; most come from commercially sponsored influencers. Potential disclosure strategies need to be tested to confirm whether users recognize such posts as commercially sponsored. MethodsBetween July – August 2019, young adult (ages 16–24; n = 200) participants were recruited to view their native Instagram feed on a laboratory mobile device. Posts from e-cigarette influencers were manipulated to add either #ad or #sponsored while eye tracking software measured visual attention. Participants self-reported their interpretation of the hashtags in open-ended responses. Logistic regression analyses compared recognition of commercial content by condition, and qualitative content analyses summarized the key themes related to the hashtags. ResultsThe #ad condition had nearly twice the odds of commercial recognition compared to #sponsored (OR = 1.98, CI: 1.14–3.38). Every second of attention paid to the hashtag significantly increased the odds of commercial recognition by 22% (OR: 1.22, CI: 1.00–1.33). ConclusionThe #ad disclosure attracted visual attention and significantly increased recognition of commercial sponsorship from young social media users. Labeling commercially sponsored content on social media is a promising strategy to better inform users about paid social media influence.

User Experiences of Eye Gaze Classroom Technology for Children With Complex Communication Needs

This study examines interactions between students with atypical motor and speech abilities, their teachers, and eye tracking devices under varying conditions typical of educational settings (e.g., interactional style, teacher familiarity). Twelve children (aged 4–12 years) participated in teacher-guided sessions with eye tracking software that are designed to develop augmentative and alternative communication (AAC) skills. Assessments of expressive communication skills before and after the testing period demonstrated significant improvements. 164 sessions conducted over a 3-month period were analyzed for positive engagement (e.g., gaze direction, session time) and system effectiveness (e.g., lag time, gaze registration) between integrated and non-integrated systems. Findings showed that integrated systems were associated with significantly longer sessions, more time spent looking at the screen, greater proportion of gaze targets registered by the system, and higher response rate to prompts from teachers. We discuss the implications for the facilitated use of eye tracking devices in special education classrooms.

Potential use and benefits of automation for traffic control in roadway construction

This paper addresses the impact of using automated flagging devices in road construction instead of using construction workers. To examine the efficacy of automating this construction activity, a group of drivers with diverse characteristics/demographics was involved in the study. The diverse characteristics included gender, age, years of driving experience, and level of formal education (e.g., high school, college, and graduate degrees). Each participant was requested to view road construction scenarios involving the use of traffic control means/devices. The participants were requested to complete a questionnaire after viewing the scenarios to determine the drivers’ perceptions (that is, comfort/discomfort) in each scenario. The scenarios were displayed on a computer, and an eye-tracking software was used to determine where drivers focused their attention as they approached the road construction zones. During the viewing of the scenarios, the eye-tracking software recorded the driver’s eye movements, determined the screen coordinates where the driver was looking, and noted the time spent at each coordinate. The results did not show significant differences in the drivers’ perceptions for the use of traditional flagging methods and the automated ones. However, the traditional methods (that is, involving labor) scored higher on the visibility questions, and the automated systems were judged more effective by younger drivers. Moreover, the use of automated systems did not present any noteworthy obstacles for construction companies in implementing traffic control plans during roadway improvements or repair. Key words: Site traffic management, automated flagging, construction industry, traditional flagging.

Eye-tracking emulation software: a promising urban design tool

The human brain is designed as a social engagement system hard-wired to take in and respond to other people. This study begins to explore how this hidden brain design also directs our engagement with the built environment, in this instance, determining our behaviour around buildings. Using eye-tracking emulation software, this study tracked the unconscious responses people have to new-urbanist and more typical, car-centric suburban American house facades (elevations). It found that this kind of emulation software can help demonstrate how new urbanist homes and streetscapes were implicitly easier for people to take in and focus on, than those in car-centric subdivisions. The implications of these findings are that urban designers and architects can employ eye-tracking emulation software to explore the ways that humans unconsciously handle visual stimuli, subject to validation from alternative data sources.

Eye-tracking in Second Language Reading

In this study eye tracking software was used to analyse the ways in which university students, adult competent speakers of English at C1 level, process information when reading texts in the target language, and which strategies they use in order to summarise a given text. Research results point to four different reading techniques used by the participants in the study: partly selective fast linear, partly selective slow linear, selective structural and nonselective reading strategies. In comparison with previous research with reading tasks in L1, results show that readers take more time when reading in L2. In addition, there is a need for skill enhancement for the purpose of improved text structuring in reading tasks in the English language.

How to predict choice using eye-movements data?

In recent decades, eye-movement detection technology has improved significantly, and eye-trackers are available not only as standalone research tools but also as computer peripherals. This rapid spread gives further opportunities to measure the eye-movements of participants. The current paper provides classification models for the prediction of food choice and selects the best one. Four choice sets were presented to 112 volunteered participants, each choice set consisting of four different choice tasks, resulting in altogether sixteen choice tasks. The choice sets followed the 2-, 4-, 6- and 8-alternative forced-choice paradigm. Tobii X2-60 eye-tracker and Tobii Studio software were used to capture and export gazing data, respectively. After variable filtering, thirteen classification models were elaborated and tested; moreover, eight performance parameters were computed. The models were compared based on the performance parameters using the sum of ranking differences algorithm. The algorithm ranks and groups the models by comparing the ranks of their performance metrics to a predefined gold standard. Techniques based on decision trees were superior in all cases, regardless of the choice tasks and food product categories. Among the classifiers, Quinlan's C4.5 and cost-sensitive decision trees proved to be the best-performing ones. Future studies should focus on the fine-tuning of these models as well as their applications with mobile eye-trackers.

Abstract P753: Comparison of Calibration vs Non-Calibration Techniques in the Automated Capture of Eye Movement Data: Initial Validation of the Roadie Device for Detecting Posterior Circulation Stroke

Background: Posterior circulation stroke (PCS) accounts for ~20% of ischemic strokes. Existing EMS screening tools lack accuracy in the diagnosis of PCS. We aim to develop an automated screening tool to detect abnormal eye movements in patients presenting with PCS. Methods: As an initial step, we built a portable platform called RoADIE (Rolling Apparatus to Detect Impairment of the Eyes), equipped with eye-tracking software to acquire gaze data from patients presenting with PCS, acute vestibular syndrome, and normal controls. We first performed a validation study in 19 healthy controls comparing calibration (C) vs non-calibration (NC) techniques. Eye movements were captured using a standard H-Test exam. The NC condition was performed first for each volunteer to avoid a learning effect. Correlation between C and NC tests was determined using the Spearman coefficient (r). Results: Conjugate gaze (i.e. ability of eyes to track in unison) demonstrated strong correlation along the horizontal [r = 0.976 (C), 0.922 (NC)] and vertical axes [r= 0.866 (C), 0.881(NC)]. Smooth pursuit (i.e. ability of each eye to track moving target) also showed strong correlation in the horizontal plane: right eye [r = 0.945 (C), 0.946 (NC), left eye [r=0.945 (C), 0.943 (NC)]. Vertical tracking showed moderate correlation: right eye [r=0.652 (C), 0.575 (NC), left eye [r=0.678 (C), 0.550 (NC)]. Conclusion: In this initial validation test of a portable eye tracking platform, we demonstrated strong correlation for both conjugate gaze and smooth pursuit in the horizontal axis, and moderate correlation for eye tracking in the vertical axis. Given similar performance in non-calibrated tests, a calibration procedure may not be necessary for future data capture. Next steps will include validation of the eye tracking device in prospective patients presenting with PCS and acute vestibular syndrome. Acknowledgement: Funding support through AHA Innovative Project Award 19IPLOI34760692

Intelligent Car

INTELLIGENT CAR (ICAR) is a car, developed on eye-tracking software using a camera. The ICAR the first Intelligent car that works with eye control and automatic driving. You can ride a car and move around where ever you want. The car drives Right, left, forward and stop using your eyes with the help of camera and coding. You need to sit facing the camera to control it. The main advantage is the car drives without any hassle in the roadways because of sensors i.e without any accidents/hitting any objects. It requires some hardware along with software along with a camera. Roads are easy and cost-effective for travelling through vehicles and walking people. Physically challenged people can also travel easily by I-Car, they need not call any person for help on the roads or depend on anyone to move from one place to another.

Assessment of eye movements and selected vision function tests in three pupils with albinism: A case study in Tanzania

Albinism is a huge challenge both socially and educationally in Tanzania and many other countries. Pupils with albinism are normally encouraged to read with a fixed gaze due to their nystagmus, and there are doubts about whether refraction improves their reading. The aim is to get more knowledge about their functional vision as a fundament for educating pupils with albinism. The article presents a case study with three pupils from a primary school in Tanzania who went through a functional assessment of vision using standardized methods and a new eye-tracker software measuring smooth pursuits. The assessment reveals large individual differences not only in visual acuity but also in ocular motor functions. There is a need for better understanding of the vision challenges these pupils face so that professionals can develop more suitable methods in school for securing their education.