Fixation Identification Research Articles

PeyeMMV: Python implementation of EyeMMV’s fixation detection algorithm

This article presents a new Python module called PeyeMMV. The module implements the two-step spatial dispersion fixation detection algorithm imported in both EyeMMV and LandRate MATLAB toolboxes. This algorithm is based on spatiotemporal criteria, belongs to the family of I-DT based algorithms and can be used as a spatial noise filtering approach during fixation identification process. PeyeMMV module could be utilized in order to extract fixation clusters among raw gaze data as well as to generate a basic plot that visualizes both gaze data and fixation centers positions. The module could be easily imported in every Python script or module.

Real-time identification of eye fixations and saccades using radial basis function networks and Markov chains

• Identification of eye saccades and fixations is critical in many applications. • We present a Concept Drift approach, called RBFNMC, designed to monitor eye movements. • RBFNMC combines Radial Basis Function Networks and Markov Chains to detect drifts. • RBFNMC models fixations as network nodes and saccade probabilities as weighted edges. • Results show robust, online and unsupervised drift detections, meeting XAI standards. Analysis of eye-movements is crucial to many applications, from medical diagnosis to gaming. A critical step in this process lies in segmenting raw gaze coordinates provided by the eye-tracker into eye saccade and fixation events. This detection is generally executed offline, as most methods require a complete dataset or large temporal windows. Many of these algorithms also rely on heuristics such as fixed velocity thresholds, yielding variations in the results depending on the user’s choice of parameters. To overcome such limitations, we designed a new approach, named RBFNMC, which combines Radial Basis Function Network (RBFN) and Markov Chains (MC) in a Concept Drift framework. Our approach is capable of automatically categorizing saccades and fixations in an online scenario. Comparisons with previous detection techniques revealed accurate predictions, while not requiring fixed threshold parameters. Our results were estimated from real eye-movement datasets collected in experiments with: (i) monkeys in a free-viewing paradigm; (ii) human subjects looking at different types of stimuli. Comparing RBFNMC with several other methods widely cited in the literature, our contribution constitutes a new computational approach to process spatial data streams in an online and unsupervised fashion. As a consequence, we provide an efficient mechanism to detect saccade and fixations which support eye-tracking research in neuroscience and other areas. Finally, it is worth emphasizing that our work additionally provides the possibility of interpreting the decision process by inspecting graph-based visualizations of RBFN and of the transition probabilities in MC.

Multicenter Validation of Natural Language Processing Algorithms for the Detection of Common Data Elements in Operative Notes for Total Hip Arthroplasty: Algorithm Development and Validation.

BackgroundNatural language processing (NLP) methods are powerful tools for extracting and analyzing critical information from free-text data. MedTaggerIE, an open-source NLP pipeline for information extraction based on text patterns, has been widely used in the annotation of clinical notes. A rule-based system, MedTagger-total hip arthroplasty (THA), developed based on MedTaggerIE, was previously shown to correctly identify the surgical approach, fixation, and bearing surface from the THA operative notes at Mayo Clinic.ObjectiveThis study aimed to assess the implementability, usability, and portability of MedTagger-THA at two external institutions, Michigan Medicine and the University of Iowa, and provide lessons learned for best practices.MethodsWe conducted iterative test-apply-refinement processes with three involved sites—the development site (Mayo Clinic) and two deployment sites (Michigan Medicine and the University of Iowa). Mayo Clinic was the primary NLP development site, with the THA registry as the gold standard. The activities at the two deployment sites included the extraction of the operative notes, gold standard development (Michigan: registry data; Iowa: manual chart review), the refinement of NLP algorithms on training data, and the evaluation of test data. Error analyses were conducted to understand language variations across sites. To further assess the model specificity for approach and fixation, we applied the refined MedTagger-THA to arthroscopic hip procedures and periacetabular osteotomy cases, as neither of these operative notes should contain any approach or fixation keywords.ResultsMedTagger-THA algorithms were implemented and refined independently for both sites. At Michigan, the study comprised THA-related notes for 2569 patient-date pairs. Before model refinement, MedTagger-THA algorithms demonstrated excellent accuracy for approach (96.6%, 95% CI 94.6%-97.9%) and fixation (95.7%, 95% CI 92.4%-97.6%). These results were comparable with internal accuracy at the development site (99.2% for approach and 90.7% for fixation). Model refinement improved accuracies slightly for both approach (99%, 95% CI 97.6%-99.6%) and fixation (98%, 95% CI 95.3%-99.3%). The specificity of approach identification was 88.9% for arthroscopy cases, and the specificity of fixation identification was 100% for both periacetabular osteotomy and arthroscopy cases. At the Iowa site, the study comprised an overall data set of 100 operative notes (50 training notes and 50 test notes). MedTagger-THA algorithms achieved moderate-high performance on the training data. After model refinement, the model achieved high performance for approach (100%, 95% CI 91.3%-100%), fixation (98%, 95% CI 88.3%-100%), and bearing surface (92%, 95% CI 80.5%-97.3%).ConclusionsHigh performance across centers was achieved for the MedTagger-THA algorithms, demonstrating that they were sufficiently implementable, usable, and portable to different deployment sites. This study provided important lessons learned during the model deployment and validation processes, and it can serve as a reference for transferring rule-based electronic health record models.

Characterization of Monochromate and Hemichromate AFm Phases and Chromate-Containing Ettringite by 1H, 27Al, and 53Cr MAS NMR Spectroscopy

The calcium aluminate hydrate AFm and AFt phases formed upon hydration of Portland cement have an important role in the stabilization and solidification of hazardous chromate ions in hardened cement. AFm monochromate (Ca4[Al(OH)6]2(CrO4)·12H2O), AFm hemichromate (Ca4[Al(OH)6]2(CrO4)0.5(OH)·12H2O) and the chromate-containing AFt phase, Ca6[Al(OH)6]2-(CrO4)3·24H2O, were synthesized and investigated by 1H, 27Al, and 53Cr MAS NMR spectroscopy. 27Al quadrupolar coupling parameters (CQ, ηQ) and isotropic chemical shifts (δiso) were determined for the three phases, including two distinct Al sites in chromate-AFt, as observed by 27Al MAS and MQMAS NMR. Two dominant peaks are apparent in the 1H MAS NMR spectra of each of the phases. For the AFm phases, these resonances are assigned to framework hydroxyl groups (1.7–2.0 ppm) and water molecules/hydroxyls (5.0–5.5 ppm) in the interlayer. For chromate-AFt, the peaks are ascribed to framework hydroxyl groups in the [Ca6Al2(OH)12]6+ columns (~1.4 ppm) and water molecules (~4.8 ppm) associated with the Ca ions. 53Cr MAS NMR spectra acquired at 22.3 T for the samples show a narrow resonance for both chromate AFm phases, whereas indications of three distinct Cr resonances are apparent for the chromate AFt. The absence of any second-order quadrupolar effects in the 53Cr NMR spectra strongly suggests that the chromate ions are highly mobile in the anionic sites of the AFm and AFt structures. The NMR data reported in this work are in agreement with the reported crystal structures for the chromate AFm and AFt phases and may be useful for identification and characterization of chromate fixation in cementitious systems, complementing information gained from conventional powder X-ray diffraction studies.

Gaze Behavior Effect on Gaze Data Visualization at Different Abstraction Levels.

Many gaze data visualization techniques intuitively show eye movement together with visual stimuli. The eye tracker records a large number of eye movements within a short period. Therefore, visualizing raw gaze data with the visual stimulus appears complicated and obscured, making it difficult to gain insight through visualization. To avoid the complication, we often employ fixation identification algorithms for more abstract visualizations. In the past, many scientists have focused on gaze data abstraction with the attention map and analyzed detail gaze movement patterns with the scanpath visualization. eye movement patterns change dramatically depending on fixation identification algorithms in the preprocessing. However, it is difficult to find out how fixation identification algorithms affect gaze movement pattern visualizations. Additionally, scientists often spend much time on adjusting parameters manually in the fixation identification algorithms. In this paper, we propose a gaze behavior-based data processing method for abstract gaze data visualization. The proposed method classifies raw gaze data using machine learning models for image classification, such as CNN, AlexNet, and LeNet. Additionally, we compare the velocity-based identification (I-VT), dispersion-based identification (I-DT), density-based fixation identification, velocity and dispersion-based (I-VDT), and machine learning based and behavior-based modelson various visualizations at each abstraction level, such as attention map, scanpath, and abstract gaze movement visualization.

Development and Calibration of an Eye-Tracking Fixation Identification Algorithm for Immersive Virtual Reality.

Fixation identification is an essential task in the extraction of relevant information from gaze patterns; various algorithms are used in the identification process. However, the thresholds used in the algorithms greatly affect their sensitivity. Moreover, the application of these algorithm to eye-tracking technologies integrated into head-mounted displays, where the subject’s head position is unrestricted, is still an open issue. Therefore, the adaptation of eye-tracking algorithms and their thresholds to immersive virtual reality frameworks needs to be validated. This study presents the development of a dispersion-threshold identification algorithm applied to data obtained from an eye-tracking system integrated into a head-mounted display. Rules-based criteria are proposed to calibrate the thresholds of the algorithm through different features, such as number of fixations and the percentage of points which belong to a fixation. The results show that distance-dispersion thresholds between 1–1.6° and time windows between s are the acceptable range parameters, with 1° and s being the optimum. The work presents a calibrated algorithm to be applied in future experiments with eye-tracking integrated into head-mounted displays and guidelines for calibrating fixation identification algorithms

Outlier-Aware, density-Based gaze fixation identification

Eye tracking is an advancing technology holding significant promise to improve our understanding of human behavior and decision making. Gaze data gathered by eye trackers contain events known as fixations. Fixations indicate visual attention and awareness, and are identified by algorithms that parse eye-tracking data into a sequence of gaze point clusters. While great potential exists, eye-tracker imprecision often results in noisy gaze data, such as what arises from calibration errors, erratic eye movements, or other system noise. Noise can cause inaccurate identification of fixations in eye-tracking applications, resulting in misleading behavioral interpretations and conclusions. Therefore, fixation identification algorithms should be robust against data noise. To resolve such inaccuracies, we propose FID+: outlier-aware fixation identification via fixation inner-density. We represent the problem of detecting outliers in fixation gaze data through a novel mixed-integer optimization formulation, and subsequently strengthen the formulation using two geometric arguments to provide enhanced bounds. We show that neither bound dominates the other, and that both are effective in reducing the overall solution runtime. Our experiments on real gaze recordings demonstrate that accommodating for the reality of fixation outliers enhances the ability to identify fixations with greater density in reasonable runtime.

Identification of fixations, saccades and smooth pursuits based on segmentation and clustering

Identification of fixations, saccades and smooth pursuits based on segmentation and clustering

Identifying Fixations in Gaze Data via Inner Density and Optimization

Eye tracking is an increasingly common technology with a variety of practical uses. Eye-tracking data, or gaze data, can be categorized into two main events: fixations represent focused eye movement, indicative of awareness and attention, whereas saccades are higher-velocity movements that occur between fixation events. Common methods to identify fixations in gaze data can lack sensitivity to peripheral points and may misrepresent positional and durational properties of fixations. To address these shortcomings, we introduce the notion of inner density for fixation identification, which concerns both the duration of the fixation and the proximity of its constituent gaze points. Moreover, we demonstrate how to identify fixations in a sequence of gaze data by optimizing for inner density. After decomposing the clustering of a temporal gaze data sequence into successive regions (chunks), we use nonlinear and linear 0–1 optimization formulations to identify the densest fixations within a given data chunk. Our approach is parametrized by a unique constant that adjusts the degree of desired density, allowing decision makers to have fine-tuned control over density during the process. Computational experiments on real data sets demonstrate the efficiency of our approach and its effectiveness in identifying fixations with greater density than existing methods, thereby enabling the refinement of key gaze metrics such as fixation duration and fixation center.

Uncovering early indicators of fixation during the concept development stage of children\u2019s design processes

In this paper, we explore the early indicators of design fixation occurring during the concept development stage of children’s design processes. This type of fixation, which we named: concept fixation, causes a blind adherence to the current (possibly unfavourable) state of a design idea. Its occurrence hampers the creative thinking processes present in a design process, which in turn stagnates the development of initial design ideas into final designs. Until now, research on design fixation has mainly focussed on creative idea generation in the early phases of the design process through analysing (intermediate) design ideas and completed artefacts. However, children’s fixation behaviours might be identified at an earlier moment through the conversations that take place in the classroom about their design ideas. To this end, we present a case study in which we explored early indicators of concept fixation of a group of 24 primary school children (ages 9–11) carrying out a co-design project. Fixation was observed through the manner in which the design teams responded to questions and comments from their peers and the client. Four categories of response behaviours indicating concept fixation emerged from the verbal data, namely: ‘band-aids’, ‘already-in-there’, ‘question-not-relevant’ and ‘it’s-not-possible’. We expect that the indicators will be helpful in identifying concept fixation during the design process, especially in an educational context. The process of identification of fixation, and reflecting on it, creates awareness. This is considered as an important step by professional designers towards guarding oneself from fixation episodes in future projects, and thus being more creative.

Comparison of fixation and saccades identification algorithms in the eye tracking recordings for medical diagnosis

The article presents a comparative analysis of selected algorithms for eye movements identification. The analysis is based on a comparison of the classification of fixation and saccades using I-VT and I-DT algorithms. For the algorithms comparison the application that implementing the identification of eye tracking data has been developed. The results of the analysis are presented in the form of graphs.

On Relationships Between Fixation Identification Algorithms and Fractal Box Counting Methods.

Fixation identification algorithms facilitate data comprehension and provide analytical convenience in eye-tracking analysis. However, current fixation algorithms for eye-tracking analysis are heavily dependent on parameter choices, leading to instabilities in results and incompleteness in reporting. This work examines the nature of human scanning patterns during complex scene viewing. We show that standard implementations of the commonly used distance-dispersion algorithm for fixation identification are functionally equivalent to greedy spatiotemporal tiling. We show that modeling the number of fixations as a function of tiling size leads to a measure of fractal dimensionality through box counting. We apply this technique to examine scale-free gaze behaviors in toddlers and adults looking at images of faces and blocks, as well as large number of adults looking at movies or static images. The distributional aspects of the number of fixations may suggest a fractal structure to gaze patterns in free scanning and imply that the incompleteness of standard algorithms may be due to the scale-free behaviors of the underlying scanning distributions. We discuss the nature of this hypothesis, its limitations, and offer directions for future work.

EyeMMV toolbox: An eye movement post-analysis tool based on a two-step spatial dispersion threshold for fixation identification

Eye movement recordings and their analysis constitute an effective way to examine visual perception. There is a special need for the design of computer software for the performance of data analysis. The present study describes the development of a new toolbox, called EyeMMV (Eye Movements Metrics & Visualizations), for post experimental eye movement analysis. The detection of fixation events is performed with the use of an introduced algorithm based on a two-step spatial dispersion threshold. Furthermore, EyeMMV is designed to support all well-known eye tracking metrics and visualization techniques. The results of fixation identification algorithm are compared with those of an algorithm of dispersion-type with a moving window, imported in another open source analysis tool. The comparison produces outputs that are strongly correlated. The EyeMMV software is developed using the scripting language of MATLAB and the source code is distributed through GitHub under the third version of GNU General Public License (link: https://github.com/krasvas/EyeMMV).

Real-time recording and classification of eye movements in an immersive virtual environment

Despite the growing popularity of virtual reality environments, few laboratories are equipped to investigate eye movements within these environments. This primer is intended to reduce the time and effort required to incorporate eye-tracking equipment into a virtual reality environment. We discuss issues related to the initial startup and provide algorithms necessary for basic analysis. Algorithms are provided for the calculation of gaze angle within a virtual world using a monocular eye-tracker in a three-dimensional environment. In addition, we provide algorithms for the calculation of the angular distance between the gaze and a relevant virtual object and for the identification of fixations, saccades, and pursuit eye movements. Finally, we provide tools that temporally synchronize gaze data and the visual stimulus and enable real-time assembly of a video-based record of the experiment using the Quicktime MOV format, available at http://sourceforge.net/p/utdvrlibraries/. This record contains the visual stimulus, the gaze cursor, and associated numerical data and can be used for data exportation, visual inspection, and validation of calculated gaze movements.

Nitrogen fixation tolerance to soil water deficit among commercial cultivars and breeding lines of peanut

Peanut is often grown in the U.S. on sandy soil with limited water holding capacity. Since nitrogen fixation activity of other grain legume species, and some peanut cultivars, has been found to be especially sensitive to soil drying, yield improvement may be possible by identifying and/or breeding cultivars with nitrogen fixation resistance to water-deficit conditions. A key in this approach will be the use of screens to identify genotypes that may express drought resistance. Two screens of differing experimental sophistication were explored in this study as potential tools to compare genotypes. The first screen was done in the greenhouse using intact plants in a flow-though acetylene reduction system to measure nitrogen fixation response to soil drying over about two weeks. Ten commercial cultivars were tested and the only significant difference in nitrogen fixation activity was between Georgia 06G and York. The threshold for the decline in the nitrogen fixation rate averaged at a relative high value of 0.37 but Georgia 06G had a relatively low value of 0.28. These thresholds are greater than have been reported for nitrogen fixation tolerance in other species. The second, less sensitive screen that can be applied to a much larger number of genotypes was done in the field by measuring nitrogen accumulation over 2–3 wks of growth on limited available soil water. There were no differences in nitrogen-to-mass accumulation ratio among the commercial cultivars during two limited-water experiments. However, data collected from the field on several breeding lines from India indicated a consistency in the identification of nitrogen fixation in the greenhouse experiment and field experiments.

Automatic eye fixations identification based on analysis of variance and covariance

Eye movement is the simplest and repetitive movement that enables humans to interact with the environment. The common daily activities, such as reading a book or watching television, involve this natural activity, which consists of rapidly shifting our gaze from one region to another. In clinical application, the identification of the main components of eye movement during visual exploration, such as fixations and saccades, is the objective of the analysis of eye movements: however, in patients affected by motor control disorder the identification of fixation is not banal. This work presents a new fixation identification algorithm based on the analysis of variance and covariance: the main idea was to use bivariate statistical analysis to compare variance over x and y to identify fixation. We describe the new algorithm, and we compare it with the common fixations algorithm based on dispersion. To demonstrate the performance of our approach, we tested the algorithm in a group of healthy subjects and patients affected by motor control disorder.

The identification of needle fixation: The development of the NEFPRO, a clinical screening tool

Aim: This article describes the development of a scale to identify needle fixation. Design: A series of statements were developed from qualitative interviews with 24 injecting drug users. The content of the interviews was used to generate 74 statements that had relevance to needle fixation. The 74 statements were developed into a 74-point questionnaire and administered to 80 injecting drug users. These statements were refined to 14 relevant questions with pairs of questions relating to a particular activity. This had a Cronbach reliability of .70. Following identification of needle fixation by interview these questions were reduced to the final 10. Participants: A total of 137 injecting drug users from Cardiff and surrounding area were used for different stages of the development. Results: The resulting 10-point scale has a utility in identifying needle fixation in individuals with the problem and specifies the role that needle fixation plays for them. Conclusions: This scale may help with the treatment of injecting drug users by identifying needle fixation.

FixTag: An algorithm for identifying and tagging fixations to simplify the analysis of data collected by portable eye trackers

Video-based eye trackers produce an output video showing where a subject is looking, the subject's Point-of-Regard (POR), for each frame of a video of the scene. This information can be extremely valuable, but its analysis can be overwhelming. Analysis of eye-tracked data from portable (wearable) eye trackers is especially daunting, as the scene video may be constantly changing, rendering automatic analysis more difficult. A common way to begin analysis of POR data is to group these data into fixations. In a previous article, we compared the fixations identified (i.e., start and end marked) automatically by an algorithm to those identified manually by users (i.e., manual coders). Here, we extend this automatic identification of fixations to tagging each fixation to a Region-of-Interest (ROI). Our fixation tagging algorithm, FixTag, requires the relative 3D positions of the vertices of ROIs and calibration of the scene camera. Fixation tagging is performed by first calculating the camera projection matrices for keyframes of the scene video (captured by the eye tracker) via an iterative structure and motion recovery algorithm. These matrices are then used to project 3D ROI vertices into the keyframes. A POR for each fixation is matched to a point in the closest keyframe, which is then checked against the 2D projected ROI vertices for tagging. Our fixation tags were compared to those produced by three manual coders tagging the automatically identified fixations for two different scenarios. For each scenario, eight ROIs were defined along with the 3D positions of eight calibration points. Therefore, 17 tags were available for each fixation: 8 for ROIs, 8 for calibration points, and 1 for “other.” For the first scenario, a subject was tracked looking through products on four store shelves, resulting in 182 automatically identified fixations. Our automatic tagging algorithm produced tags that matched those produced by at least one manual coder for 181 out of the 182 fixations (99.5% agreement). For the second scenario, a subject was tracked looking at two posters on adjoining walls of a room. Our algorithm matched at least one manual coder's tag for 169 fixations out of 172 automatically identified (98.3% agreement).

Fixation identification: The optimum threshold for a dispersion algorithm

It is hypothesized that the number, position, size, and duration of fixations are functions of the metric used for dispersion in a dispersion-based fixation detection algorithm, as well as of the threshold value. The sensitivity of the I-DT algorithm for the various independent variables was determined through the analysis of gaze data from chess players during a memory recall experiment. A procedure was followed in which scan paths were generated at distinct intervals in a range of threshold values for each of five different metrics of dispersion. The percentage of points of regard (PORs) used, the number of fixations returned, the spatial dispersion of PORs within fixations, and the difference between the scan paths were used as indicators to determine an optimum threshold value. It was found that a fixation radius of 1 degrees provides a threshold that will ensure replicable results in terms of the number and position of fixations while utilizing about 90% of the gaze data captured.

The effect of fixational eye movements on fixation identification with a dispersion-based fixation detection algorithm

Gaze data of 31 participants of a memory recall experiment was analyzed and the I-DT dispersion based algorithm of Salvucci and Goldberg (2000) was used to identify fixations. It was found that individuals differ considerably with regard to the stability of eye gaze and that fixational eye movements affect the accuracy of fixation identification and the optimum dispersion threshold. It was also found that fixation radius and the distance between the points in a fixation that are the furthest apart are the most reliable metrics for a dispersion-based fixation identification algorithm. Finally, it is argued that the correct setting of dispersion threshold is of utmost importance, especially if the participants are not homogeneous with regard to gaze stability.