Eye Movement Classification Research Articles

Optimised multi‐wavelet domain for decomposed electrooculogram‐based eye movement classification

The human eye movement tracking is possible with the assistance of the electrooculography (EOG) signals. The human eye tracking system allows researchers to analyse the participant's eye movements during certain activities. This study offers the EOG signals to control the human–computer interface systems with the help of Empirical Mean Curve Decomposition (EMCD) decomposition model. At first, the input EOG signal is provided as input to the EMCD decomposition model, later the resultant signal is given to principal component analysis for dimensional reduction, and then the dimensional reduced signal is offered to multi-wavelet decomposition model. The resultant dimensionally reduced multi-wavelet decomposed signal is passed to the proposed Feature Mapping (FM) model, using the k-means clustering model. Then, the Grey Wolf Optimization (GWO) algorithm is utilised to tune the margin. Next to mapping, the obtained features are provided to the nearest neighbour classifier, to obtain the eye movement. Next to the implementation, the proposed method is compared with the existing methods, and it is witnessed that the proposed methodology gives the superior performance in correspondence with accuracy, sensitivity, specificity, precision, false positive rate, false negative rate, negative predictive value, false discovery rate, F1 score and Mathews correlation coefficient.

Smooth Pursuit and Saccades after Sport-Related Concussion.

Smooth pursuit eye movements (SPEMs) and saccadic eye movements are both commonly impaired following sport-related concussion (SRC). Typical oculomotor assessments measure individual eye movements in a series of restrictive tests designed to isolate features such as response times. These measures lack ecological validity for athletes because athletes are adept at simple tasks designed for the general population. Yet, because eye movement metrics are sensitive and well-characterized neuroanatomically, it would be valuable to test whether athletes exhibit abnormal eye movements with more challenging tasks. To address this gap in knowledge, we collected eye-tracking data during a sport-like task to gain insight on gaze behavior during active self-motion. SPEMs and saccadic eye movements were recorded during a sport-like visual task within 24-48 h following SRC. Thirty-six Division I student-athletes were divided into SRC and control (CON) groups. All participants completed two blocks of the Wii Fit© soccer heading game (WF) while wearing a monocular infrared eye tracker. Eye movement classification systems quantified saccadic amplitude (SA), velocity (SV), and count (SC); as well as SPEM velocity (SPV) and amplitude (SPA). Separate Mann-Whitney U tests evaluated SPA and SC and found no significant effects (SPA, p = 0.11; SC, p = 0.10). A multi-variate analysis of variance (MANOVA) for remaining variables revealed SPV was significantly greater in CON (p < 0.05), but the SRC group had greater SA and SV (p < 0.05). These findings suggest that during a sport-like task, to maintain foveation SRC subjects used larger amplitude, faster saccades, but exhibited slower SPEMs. Measuring oculomotor function during ecologically valid, sport-like tasks may serve as a concussion biomarker and provide insights into eye movement control after SRC.

Model-Based Separation, Detection, and Classification of Eye Movements.

We present a physiologically motivated eye movement analysis framework for model-based separation, detection, and classification (MBSDC) of eye movements. By estimating kinematic and neural controller signals for saccades, smooth pursuit, and fixational eye movements in a mechanistic model of the oculomotor system we are able to separate and analyze these eye movements independently. We extended an established oculomotor model for horizontal eye movements by neural controller signals and by a blink artifact model. To estimate kinematic (position, velocity, acceleration, forces) and neural controller signals from eye position data, we employ Kalman smoothing and sparse input estimation techniques. The estimated signals are used for detecting saccade start and end points, and for classifying the recording into saccades, smooth pursuit, fixations, post-saccadic oscillations, and blinks. On simulated data, the reconstruction error of the velocity profiles is about half the error value obtained by the commonly employed approach of filtering and numerical differentiation. In experiments with smooth pursuit data from human subjects, we observe an accurate signal separation. In addition, in neural recordings from non-human primates, the estimated neural controller signals match the real recordings strikingly well. The MBSDC framework enables the analysis of multi-type eye movement recordings and provides a physiologically motivated approach to study motor commands and might aid the discovery of new digital biomarkers. The proposed framework provides a model-based approach for a wide variety of eye movement analysis tasks.

EOG-Based Eye Movement Classification and Application on HCI Baseball Game

Electrooculography (EOG) is considered as the most stable physiological signal in the development of human–computer interface (HCI) for detecting eye-movement variations. EOG signal classification has gained more traction in recent years to overcome physical inconvenience in paralyzed patients. In this paper, a robust classification technique, such as eight directional movements is investigated by introducing a concept of buffer along with a variation of the slope to avoid misclassification effects in EOG signals. Blinking detection becomes complicated when the magnitude of the signals are considered. Hence, a correction technique is introduced to avoid misclassification for oblique eye movements. Meanwhile, a case study has been considered to apply these correction techniques to HCI baseball game to learn eye-movements.

Parametrization of Saccade Trajectories

The problem of description and classification of rapid eye movements called saccades is considered. It is well known that the saccades are of various types. A classification of saccades is proposed according to the presence and types of pre-saccadic and post-saccadic movements. An algorithm is developed to determine the parameters that can be used to formally assign the saccade to one of the given types.

A novel evaluation of two related and two independent algorithms for eye movement classification during reading.

Nystrӧm and Holmqvist have published a method for the classification of eye movements during reading (ONH) (Nyström & Holmqvist, 2010). When we applied this algorithm to our data, the results were not satisfactory, so we modified the algorithm (now the MNH) to better classify our data. The changes included: (1) reducing the amount of signal filtering, (2) excluding a new type of noise, (3) removing several adaptive thresholds and replacing them with fixed thresholds, (4) changing the way that the start and end of each saccade was determined, (5) employing a new algorithm for detecting PSOs, and (6) allowing a fixation period to either begin or end with noise. A new method for the evaluation of classification algorithms is presented. It was designed to provide comprehensive feedback to an algorithm developer, in a time-efficient manner, about the types and numbers of classification errors that an algorithm produces. This evaluation was conducted by three expert raters independently, across 20 randomly chosen recordings, each classified by both algorithms. The MNH made many fewer errors in determining when saccades start and end, and it also detected some fixations and saccades that the ONH did not. The MNH fails to detect very small saccades. We also evaluated two additional algorithms: the EyeLink Parser and a more current, machine-learning-based algorithm. The EyeLink Parser tended to find more saccades that ended too early than did the other methods, and we found numerous problems with the output of the machine-learning-based algorithm.

Comparison of ANN and SVM for classification of eye movements in EOG signals

Nowadays, electrooculogram is regarded as one of the most important biomedical signal in measuring and analyzing eye movement patterns. Thus, it is helpful in designing EOG-based Human Computer Interface (HCI). In this research, electrooculography (EOG) data was obtained from five volunteers. The (EOG) data was then preprocessed before feature extraction methods were employed to further reduce the dimensionality of data. Three feature extraction approaches were put forward, namely statistical parameters, autoregressive (AR) coefficients using Burg method, and power spectral density (PSD) using Yule-Walker method. These features would then become input to both artificial neural network (ANN) and support vector machine (SVM). The performance of the combination of different feature extraction methods and classifiers was presented and analyzed. It was found that statistical parameters + SVM achieved the highest classification accuracy of 69.75%.

Classification of eye movements on a lesion in medical image interpretation using deep learning.

Classification of eye movements on a lesion in medical image interpretation using deep learning.

A new and general approach to signal denoising and eye movement classification based on segmented linear regression

We introduce a conceptually novel method for eye-movement signal analysis. The method is general in that it does not place severe restrictions on sampling frequency, measurement noise or subject behavior. Event identification is based on segmentation that simultaneously denoises the signal and determines event boundaries. The full gaze position time-series is segmented into an approximately optimal piecewise linear function in O(n) time. Gaze feature parameters for classification into fixations, saccades, smooth pursuits and post-saccadic oscillations are derived from human labeling in a data-driven manner. The range of oculomotor events identified and the powerful denoising performance make the method useable for both low-noise controlled laboratory settings and high-noise complex field experiments. This is desirable for harmonizing the gaze behavior (in the wild) and oculomotor event identification (in the laboratory) approaches to eye movement behavior. Denoising and classification performance are assessed using multiple datasets. Full open source implementation is included.

Gaze-in-World movement Classification for Unconstrained Head Motion during Natural Tasks.

Accurate classification of eye movements is an integral component of many psychophysical experiments. Most event classifiers are restricted to the analysis of eye-in-head (EIHv) vectors while the head is fixed, and detect two classes of gaze events, namely fixations and saccades. Classification of eye movements as Vestibular Ocular reflex (VOR) or Smooth pursuits (SP) require that we compensate gaze motion with a person's head movements. As the complexity of naturalistic behavioral paradigms increases, so does the need for gaze classification with head-free motion which could detect these complex eye movements. We propose the use of a supervised Machine Learning (ML) classifier for the automated analysis of head free gaze signal. As a preliminary test, we used a SVM classifier to label a 60 Hz test dataset from a virtual reality ball catching task into periods of fixations, saccades and pursuit. This preliminary test resulted in 94% accuracy in a sample to sample comparison with an artificially generated set of gaze movements reflective of measured gaze statistics, and visual inspection shows very high correspondence to subjective analysis of the gaze signal. This promising methodology has since been extended to the analysis of data collected during natural tasks. Five subjects' head and gaze movements were recorded using an IMU and a 120 Hz SMI Wireless ETG2 as they performed four different natural tasks for 10 minutes each. This yielded 120 minutes of angular velocity data of the gaze in world vector (GIWv) during natural tasks. Four experts manually annotated a subset of the data as periods of fixation, saccade, smooth pursuit, and blinks. Inter-labeler reliability was measured to generate a confidence metric and a cost function for misclassifications. We summarize the statistics of natural eye movements and compare various ML based temporal series classification schemes. Meeting abstract presented at VSS 2017

A Novel Wearable Forehead EOG Measurement System for Human Computer Interfaces.

Amyotrophic lateral sclerosis (ALS) patients whose voluntary muscles are paralyzed commonly communicate with the outside world using eye movement. There have been many efforts to support this method of communication by tracking or detecting eye movement. An electrooculogram (EOG), an electro-physiological signal, is generated by eye movements and can be measured with electrodes placed around the eye. In this study, we proposed a new practical electrode position on the forehead to measure EOG signals, and we developed a wearable forehead EOG measurement system for use in Human Computer/Machine interfaces (HCIs/HMIs). Four electrodes, including the ground electrode, were placed on the forehead. The two channels were arranged vertically and horizontally, sharing a positive electrode. Additionally, a real-time eye movement classification algorithm was developed based on the characteristics of the forehead EOG. Three applications were employed to evaluate the proposed system: a virtual keyboard using a modified Bremen BCI speller and an automatic sequential row-column scanner, and a drivable power wheelchair. The mean typing speeds of the modified Bremen brain–computer interface (BCI) speller and automatic row-column scanner were 10.81 and 7.74 letters per minute, and the mean classification accuracies were 91.25% and 95.12%, respectively. In the power wheelchair demonstration, the user drove the wheelchair through an 8-shape course without collision with obstacles.

Using machine learning to detect events in eye-tracking data.

Event detection is a challenging stage in eye movement data analysis. A major drawback of current event detection methods is that parameters have to be adjusted based on eye movement data quality. Here we show that a fully automated classification of raw gaze samples as belonging to fixations, saccades, or other oculomotor events can be achieved using a machine-learning approach. Any already manually or algorithmically detected events can be used to train a classifier to produce similar classification of other data without the need for a user to set parameters. In this study, we explore the application of random forest machine-learning technique for the detection of fixations, saccades, and post-saccadic oscillations (PSOs). In an effort to show practical utility of the proposed method to the applications that employ eye movement classification algorithms, we provide an example where the method is employed in an eye movement-driven biometric application. We conclude that machine-learning techniques lead to superior detection compared to current state-of-the-art event detection algorithms and can reach the performance of manual coding.

SubsMatch 2.0: Scanpath comparison and classification based on subsequence frequencies.

Our eye movements are driven by a continuous trade-off between the need for detailed examination of objects of interest and the necessity to keep an overview of our surrounding. In consequence, behavioral patterns that are characteristic for our actions and their planning are typically manifested in the way we move our eyes to interact with our environment. Identifying such patterns from individual eye movement measurements is however highly challenging. In this work, we tackle the challenge of quantifying the influence of experimental factors on eye movement sequences. We introduce an algorithm for extracting sequence-sensitive features from eye movements and for the classification of eye movements based on the frequencies of small subsequences. Our approach is evaluated against the state-of-the art on a novel and a very rich collection of eye movements data derived from four experimental settings, from static viewing tasks to highly dynamic outdoor settings. Our results show that the proposed method is able to classify eye movement sequences over a variety of experimental designs. The choice of parameters is discussed in detail with special focus on highlighting different aspects of general scanpath shape. Algorithms and evaluation data are available at: http://www.ti.uni-tuebingen.de/scanpathcomparison.html .

Efficient feature for classification of eye movements using electrooculography signals

Electrooculography (EOG) signal is widely and successfully used to detect activities of human eye. The advantages of the EOG-based interface over other conventional interfaces have been presented in the last two decades; however, due to a lot of information in EOG signals, the extraction of useful features should be done before the classification task. In this study, an efficient feature extracted from two directional EOG signals: vertical and horizontal signals has been presented and evaluated. There are the maximum peak and valley amplitude values, the maximum peak and valley position values, and slope, which are derived from both vertical and horizontal signals. In the experiments, EOG signals obtained from five healthy subjects with ten directional eye movements were employed: up, down, right, left, up-right, up-left, down-right down-left clockwise and counterclockwise. The mean feature values and their standard deviations have been reported. The difference between the mean values of the proposed feature from different eye movements can be clearly seen. Using the scatter plot, the differences in features can be also clearly observed. Results show that classification accuracy can approach 100% with a simple distinction feature rule. The proposed features can be useful for various advanced human-computer interface applications in future researches.

Low-complexity EEG-based eye movement classification using extended moving difference filter and pulse width demodulation.

This paper presents an eye movement classification algorithm for EEG-based brain-computer interface. The proposed system first used a low-complexity extended moving difference filter to acquire clean pulse waveform of eye-movement events. Then, a pulse width demodulation algorithm was designed to identify eye-movement events of left/right/up/down directions. The eye blinking events can be easily eliminated by excluding the pulses with small pulse-width, and thus the detection rate can be improved. Besides, the pulse width demodulation requires only addition operations to achieve a near 90% averaged detection. The computation complexity is much lower than those of other works in the literature.

Subliminal Reorientation and Repositioning in Immersive Virtual Environments using Saccadic Suppression.

Virtual reality strives to provide a user with an experience of a simulated world that feels as natural as the real world. Yet, to induce this feeling, sometimes it becomes necessary for technical reasons to deviate from a one-to-one correspondence between the real and the virtual world, and to reorient or reposition the user's viewpoint. Ideally, users should not notice the change of the viewpoint to avoid breaks in perceptual continuity. Saccades, the fast eye movements that we make in order to switch gaze from one object to another, produce a visual discontinuity on the retina, but this is not perceived because the visual system suppresses perception during saccades. As a consequence, our perception fails to detect rotations of the visual scene during saccades. We investigated whether saccadic suppression of image displacement (SSID) can be used in an immersive virtual environment (VE) to unconsciously rotate and translate the observer's viewpoint. To do this, the scene changes have to be precisely time-locked to the saccade onset. We used electrooculography (EOG) for eye movement tracking and assessed the performance of two modified eye movement classification algorithms for the challenging task of online saccade detection that is fast enough for SSID. We investigated the sensitivity of participants to translations (forward/backward) and rotations (in the transverse plane) during trans-saccadic scene changes. We found that participants were unable to detect approximately ±0.5m translations along the line of gaze and ±5° rotations in the transverse plane during saccades with an amplitude of 15°. If the user stands still, our approach exploiting SSID thus provides the means to unconsciously change the user's virtual position and/or orientation. For future research and applications, exploiting SSID has the potential to improve existing redirected walking and change blindness techniques for unlimited navigation through arbitrarily-sized VEs by real walking.

Online classification algorithm for eye-movement-based communication systems using two temporal EEG sensors

Real-time classification of eye movements offers an effective mode for human–machine interaction, and many eye-based interfaces have been presented in the literature. However, such systems often require that sensors be attached around the eyes, which can be obtrusive and cause discomfort. Here, we used two electroencephalography sensors positioned over the temporal areas to perform real-time classification of eye-blink and five classes of eye movement direction. We applied a continuous wavelet transform for online detection then extracted some discriminable time-series features. Using linear classification, we obtained an average accuracy of 85.2% and sensitivity of 77.6% over all classes. The results showed that the proposed algorithm was efficient in the detection and classification of eye movements, providing high accuracy and low-latency for single trials. This work demonstrates the promise of portable eye-movement-based communication systems and the sensor positions, features extraction, and classification methods used.

Predicting reading comprehension scores from eye movements using artificial neural networks and fuzzy output error

Predicting reading comprehension from eye gaze data is a difficult task. We investigate the use of artificial neural networks(ANNs) to predict reading comprehension scores from eye gaze collected from participants who read and completed an onlinetutorial in our lab. Problems such as large feature sets and small highly imbalanced data sets compound to make this task evenmore complex. We propose using fuzzy output error (FOE) as an alternative performance function to mean square error (MSE)for training feed-forward neural networks to overcome these problems. We show that the use of FOE as the performance functionfor training ANNs provides significantly better classification of eye movements to reading comprehension scores. ANNs withthree hidden layers of neurons gave the best classification results especially when FOE is used as the performance functionfor training. In these cases we found up to 50% reduction in misclassification rates compared to using MSE. We found thatANNs give optimal classification results in comparison to other classification techniques. When FOE is used as the performancefunction for training the ANNs the misclassification rates are halved compared to the other techniques. Cluster analysis wasperformed on one of the more complex data sets. Interesting reading behaviour properties were found within the data set.The intended use of this research is in the design of adaptive online learning environments that use eye gaze to predict usercomprehension from reading behavior.

Feature selection in classification of eye movements using electrooculography for activity recognition.

Activity recognition is needed in different requisition, for example, reconnaissance system, patient monitoring, and human-computer interfaces. Feature selection plays an important role in activity recognition, data mining, and machine learning. In selecting subset of features, an efficient evolutionary algorithm Differential Evolution (DE), a very efficient optimizer, is used for finding informative features from eye movements using electrooculography (EOG). Many researchers use EOG signals in human-computer interactions with various computational intelligence methods to analyze eye movements. The proposed system involves analysis of EOG signals using clearness based features, minimum redundancy maximum relevance features, and Differential Evolution based features. This work concentrates more on the feature selection algorithm based on DE in order to improve the classification for faultless activity recognition.

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.