Eye Movement Analysis Research Articles

Analysis of smooth pursuit eye movements in a clinical context by tracking the target and eyes

In the evaluation of smooth pursuit eye movements (SPEMs), recording the stimulus onset time is mandatory. In the laboratory, the stimulus onset time is recorded by electrical signal or programming, and video-oculography (VOG) and the visual stimulus are synchronized. Nevertheless, because the examiner must manually move the fixation target, recording the stimulus onset time is challenging in daily clinical practice. Thus, this study aimed to develop an algorithm for evaluating SPEMs while testing the nine-direction eye movements without recording the stimulus onset time using VOG and deep learning–based object detection (single-shot multibox detector), which can predict the location and types of objects in a single image. The algorithm of peak fitting–based detection correctly classified the directions of target orientation and calculated the latencies and gains within the normal range while testing the nine-direction eye movements in healthy individuals. These findings suggest that the algorithm of peak fitting–based detection has sufficient accuracy for the automatic evaluation of SPEM in clinical settings.

Diagnosis of colour vision deficits using eye movements

We set out to develop a simple objective test of functional colour vision based on eye movements made in response to moving patterns. We exploit the finding that while the motion of a colour-defined stimulus can be cancelled by adding a low-contrast luminance-defined stimulus moving in the opposite direction, the “equivalent luminance contrast” required for such cancellation is reduced when colour vision is abnormal. We used a consumer-grade infrared eye-tracker to measure eye movements made in response to coloured patterns drifting at different speeds. An automated analysis of these movements estimated individuals’ red-green equiluminant point and their equivalent luminance contrast. We tested 34 participants: 23 colour vision normal controls, 9 deuteranomalous and 2 protanomalous individuals. We obtained reliable estimates of strength of directed eye movements (i.e. combined optokinetic and voluntary tracking) for stimuli moving at 16 deg/s and could use these data to classify participants’ colour vision status with a sensitivity rate of 90.9% and a specificity rate of 91.3%. We conclude that an objective test of functional colour vision combining a motion-nulling technique with an automated analysis of eye movements can diagnose and assess the severity of protanopia and deuteranopia. The test places minimal demands on patients (who simply view a series of moving patterns for less than 90 s), requires modest operator expertise, and can be run on affordable hardware.

Visual analysis of eye movements during micro-stories reading

Visual analysis of eye movements during micro-stories reading

Eye movement analysis of children's attention for midline diastema.

No previous studies have investigated eye-movement patterns to show children’s information processing while viewing clinical images. Therefore, this study aimed to explore children and their educators’ perception of a midline diastema by applying eye-movement analysis using the hidden Markov models (EMHMM). A total of 155 children between 2.5 and 5.5 years of age and their educators (n = 34) viewed pictures with and without a midline diastema while Tobii Pro Nano eye-tracker followed their eye movements. Fixation data were analysed using data-driven, and fixed regions of interest (ROIs) approaches with EMHMM. Two different eye-movement patterns were identified: explorative pattern (76%), where the children’s ROIs were predominantly around the nose and mouth, and focused pattern (26%), where children’s ROIs were precise, locating on the teeth with and without a diastema, and fixations transited among the ROIs with similar frequencies. Females had a significantly higher eye-movement preference for without diastema image than males. Comparisons between the different age groups showed a statistically significant difference for overall entropies. The 3.6–4.5y age groups exhibited higher entropies, indicating lower eye-movement consistency. In addition, children and their educators exhibited two specific eye-movement patterns. Children in the explorative pattern saw the midline diastema more often while their educators focussed on the image without diastema. Thus, EMHMMs are valuable in analysing eye-movement patterns in children and adults.

The effect of frequency of exposure on the processing and learning of collocations: A comparison of first and second language readers’ eye movements

AbstractThis study examined the processing and acquisition of novel words and their collocates (i.e., words that frequently co-occur with other words) from reading and the effect of frequency of exposure on this process. First and second language speakers of English read a story with 1) eight exposures of adjective-pseudoword collocations, 2) four exposures of the same collocations, or 3) eight exposures of control collocations. Results of recall and recognition tests showed that participants acquired knowledge not only of the form and meaning of the pseudowords but also of their collocates. The analysis of eye movements showed a significant effect of exposure on the processing of novel collocations for both first and second language readers, with reading times decreasing as a function of exposure. Eight exposures to novel adjective-pseudoword collocations were enough to develop processing speed comparable to that of known collocations. However, when analyzing the processing of the individual components of the collocations, results showed that eight exposures to the pseudowords were not enough for second language readers to develop processing speed comparable to known words. The frequency manipulation in the present study (four vs. eight exposures) did not lead to differences in the learning or processing of collocations. Finally, reading times were not a significant predictor of vocabulary gains.

Role of Eye Tracking in Human Computer Interaction

With the invention of computers arises the need of an interface for users and interacting with a computer has become a natural practice. For all the opportunities a machine can bring, it is now a limiting factor for humans and their interaction with machines. This has given rise to a significant amount of research in the area of human computer interaction to make it more intuitive, simpler, and efficient. Human interaction with computers is no longer confined to printers and keyboards. Traditional input devices give way to natural inputs like voice, gestures, and visual computing using eye tracking. This paper provides useful insights in understanding the use of eye gaze tracking technology for human-machine interaction. A case study was conducted with 15 participants to analyze eye movements on an educational website. Visual attention was measured using eye gaze fixations data and heat maps were utilized to illustrate the results.

Understanding children's attention to traumatic dental injuries using eye-tracking.

Background/AimTraumatic dental injuries (TDIs) in the primary dentition may result in tooth discolouration and fractures. The aim of this child‐centred study was to explore the differences between preschool children's eye movement patterns and visual attention to typical outcomes following TDIs to primary teeth.Materials and MethodsAn eye‐tracker recorded 155 healthy preschool children's eye movements when they viewed clinical images of healthy teeth, tooth fractures and discolourations. The visual search pattern was analysed using the eye movement analysis with the Hidden Markov Models (EMHMM) approach and preference for the various regions of interest (ROIs).ResultsTwo different eye movement patterns (distributed and selective) were identified (p < .05). Children with the distributed pattern shifted their fixations between the presented images, while those with the selective pattern remained focused on the same image they first saw.ConclusionsPreschool children noticed teeth. However, most of them did not have an attentional bias, implying that they did not interpret these TDI outcomes negatively. Only a few children avoided looking at images with TDIs indicating a potential negative impact. The EMHMM approach is appropriate for assessing inter‐individual differences in children's visual attention to TDI outcomes.

Understanding Children’s Attention to Dental Caries through Eye-Tracking

Visual attention is a significant gateway to a child’s mind, and looking is one of the first behaviors young children develop. Untreated caries and the resulting poor dental aesthetics can have adverse emotional and social impacts on children’s oral health-related quality of life due to its detrimental effects on self-esteem and self-concept. Therefore, we explored preschool children’s eye movement patterns and visual attention to images with and without dental caries via eye movement analysis using hidden Markov models (EMHMM). We calibrated a convenience sample of 157 preschool children to the eye-tracker (Tobii Nano Pro) to ensure standardization. Consequently, each participant viewed the same standardized pictures with and without dental caries while an eye-tracking device tracked their eye movements. Subsequently, based on the sequence of viewed regions of interest (ROIs), a transition matrix was developed where the participants’ previously viewed ROI informed their subsequently considered ROI. Hence, an individual’s HMM was estimated from their eye movement data using a variational Bayesian approach to determine the optimal number of ROIs automatically. Consequently, this data-driven approach generated the visual task participants' most representative eye movement patterns. Preschool children exhibited two different eye movement patterns, distributed (78%) and selective (21%), which was statistically significant. Children switched between images with more similar probabilities in the distributed pattern while children remained looking at the same ROI than switching to the other ROI in the selective pattern. Nevertheless, all children exhibited an equal starting fixation on the right or left image and noticed teeth. The study findings reveal that most preschool children did not have an attentional bias to images with and without dental caries. Furthermore, only a few children selectively fixated on images with dental caries. Therefore, selective eye-movement patterns may strongly predict preschool children’s sustained visual attention to dental caries. Nevertheless, future studies are essential to fully understand the developmental origins of differences in visual attention to common oral health presentations in children. Finally, EMHMM is appropriate for assessing inter-individual differences in children’s visual attention.

Eye movements and stress during eye-tracking gaming performance in children with dyskinetic cerebral palsy.

This study aimed to explore eye movements and stress during eye-tracking gaming performance in children with dyskinetic cerebral palsy (CP) compared with typically developing children, and associations between eye-tracking performance, eye movements, stress, and participants' characteristics. This cohort study included 12 children with dyskinetic CP aged 5 to 12 years (mean age 8 years 7 months, standard deviation [SD] 2 years 3 months) and 23 typically developing children aged 5 to 13 years (mean age 9 years 0 months, SD 2 years 7 months). Participants played 10 eye-tracking games. Tobii X3-120 and Tobii Pro Lab were used to record and analyse eye movements. Stress was assessed through heart rate variability (HRV), recorded during rest, and eye-tracking performance using the Bittium Faros360° ECG Holter device. Eye-tracking performance was measured using gaming completion time. Fixation and saccade variables were used to quantify eye movements, and time- and frequency-domain variables to quantify HRV. Non-parametric statistics were used. Gaming completion time was significantly different (p< 0.001) between groups, and it was negatively correlated with experience (rs = -0.63, p= 0.029). No significant differences were found between groups in fixation and saccade variables. HRV significantly changed from rest to eye-tracking performance only in typically developing children and not in children with dyskinetic CP. Children with dyskinetic CP took longer to perform the 10 games, especially the inexperienced users, indicating the importance of the early provision of eye-tracking training opportunities. It seems that eye-tracking tasks are not a source of increased stress and effort in children with dyskinetic CP. Participants with dyskinetic cerebral palsy (CP) took twice as long to perform 10 eye-tracking games than typically developing peers. Participants with dyskinetic CP with previous eye-tracking experience performed the games faster. Fixation and saccade variables were not significantly different between children with and without dyskinetic CP. Heart rate variability showed no differences between rest and performance in participants with dyskinetic CP. Gross Motor Function Classification System, Manual Ability Classification System, and Viking Speech Scale levels were not correlated to the eye movements or stress variables.

The REM-sleep-related characteristics of narcolepsy: a nation-wide multicenter study in Turkey, the REMCON study

IntroductionNarcolepsy type 1 (NT1) is caused by hypocretin deficiency, the pathophysiology of narcolepsy type 2 (NT2) has not been delineated. Except for the hypocretin deficiency and cataplexy, all clinical and laboratory features used in the diagnosis of NT2 are identical to those used for NT1. The aim of this study was to assess the rapid eye movement (REM) sleep-related characteristics in the patients with narcolepsy; the characteristics of REM sleep in polysomnography (PSG) and multiple sleep latency test (MSLT) recordings, the quantification of REM sleep without atonia (RSWA) and atonia index, and the analysis of rapid eye movements (REMs) during REM sleep. Materials and methodsThis study was planned by the Sleep Medicine Study Group of the Turkish Neurology Society, and conducted in 11 centers in eight cities in Turkey. The analysis of RSWA was analyzed by reviewing all REM sleep periods on nocturnal PSG and MSLT recordings per standard criteria. The total duration of the increased muscle tone during REM sleep in the chin and bilateral leg electromyography (EMG) recordings was calculated as RSWA index. The REMs index was also investigated the relation to the RSWA. ResultsA total of 274 patients were involved; 147 patients (53.6%) were males and 127 patients (46.4%) were females; the mean age was 29.1 ± 12.0 years. The diagnosis of NT1 was made in 166 patients (60.6%), and 108 patients (39.4%) were diagnosed as having NT2. The mean Epworth sleepiness scale score was significantly higher in patients with NT1 than the patients with NT2 (P = 0.001). The diagnosis of REM sleep behavior disorder (RBD) was made in 19.3% of the patients with NT1 versus in 2.8% of the patients with NT2 (P < 0.001). The percentage of SOREMP in PSG recordings was significantly higher in patients with NT1 (37.1%) than those with NT2 (18.9%, P = 0.001). MSLT showed that the mean sleep latency was shorter in patients with NT1 compared to those with NT2 (P < 0.001). The total duration of REMs on electrooculography recordings was also significantly higher in patients with RSWA in comparison with the patients without RSWA (P = 0.002). Total duration of REMs was significantly and positively correlated with the duration of RSWA on chin-EMG and leg-EMG recordings (P = 0.001). ROC analyses showed an RSWA index of ≥2% for the RSWA on chin-EMG with a sensitivity of 86.7% and a specificity of 71.3% (P < 0.001). The REMs index ≥20% was associated with the presence of RSWA with a sensitivity of 70.0% and a specificity of 57.1% (P = 0.008). ConclusionsIn this nation-wide study, we identified for the first time that the increase in REMs density during REM sleep may be a major correlate of the RSWA. Significant positive correlations were demonstrated between the total duration of REMs on electrooculography recordings and the mean durations of RSWA in both chin and leg EMG recordings. A REMs index of >20% was demonstrated to have a moderate sensitivity and specificity in the diagnosis of RSWA. As observed in chin RSWA index, REMs index also showed a significantly high association with RBD, in comparison to RSWA per standard criteria.

An Eye-Movement Analysis of Overt Visual Attention During Consecutive and Simultaneous Interpreting Modes in a Remotely Interpreted Investigative Interview.

Remote interpreting via video-link is increasingly being employed in investigative interviews chiefly due to its apparent increased accessibility and efficiency. However, risks of miscommunication have been shown to be magnified in remote interpreting and empirical research specifically on video-link remote interpreting is in its infancy which greatly limits the evidence base available to inform and direct evidence-based policy and best practice, particularly in the identification of the optimal mode(s) of interpreting to be used, namely consecutive and simultaneous. Consecutive interpreting refers to a process in which the interpreter transfers short segments of speech from one language into the other as each person speaks in managed turn-taking, while simultaneous interpreting refers to the transfer of natural speech from one language into another in a concurrent manner without the need for speakers to segment their speech. This study provides novel empirical evidence by using eye tracking to compare the overt visual attention of interpreters working in a remote setting in which an English-speaking Interviewer interacts with a non-English-speaking Suspect in person, for whom interpretation is provided via video-link in real time. Using a within-subject design, we analyze eye-movement data from 28 professionally accredited interpreters who interpreted via video-link an investigative interview in which consecutive and simultaneous interpreting modes were counterbalanced. Taking interpreting performance into account, our results showed that, the consecutive mode yielded significantly less gaze time and therefore significantly less on-screen overt visual attention due to off-screen notetaking, an essential component of the consecutive interpreting mode. Relative to gaze time, the consecutive mode also resulted in significantly more and longer fixations and shifts of attention. Participants also allocated significantly more overt visual attention to the Interviewer than the Suspect, particularly in the consecutive mode. Furthermore, we found informative significant correlations between eye tracking measures and interpreting performance: accuracy, verbal rapport, and management. Finally, we found no significant differences between the three language pairs tested. We conclude with a discussion of limitations and the contributions of the study and an outline for future work on this topic of growing importance.

Oculomotor Abnormalities during Reading in the Offspring of Late-Onset Alzheimer's Disease.

Eye movement patterns during reading are well defined and documented. Each eye movement ends up in a fixation point, which allows the brain to process the incoming information and program the following saccade. In this work, we investigated whether eye movement alterations during a reading task might be already present in middle-aged, cognitively normal offspring of late-onset Alzheimer's disease (O-LOAD). 18 O-LOAD and 18 age-matched healthy individuals with no family history of LOAD participated in the study. Participants were seated in front of a 20-inch LCD monitor, and single sentences were presented on it. Eye movements were recorded with an eye tracker with a sampling rate of 1000 Hz. Analysis of eye movements during reading revealed that O-LOAD displayed more fixations, shorter saccades, and shorter fixation durations than controls. The present study shows that O-LOAD experienced alterations in their eye movements during reading. O-LOAD eye movement behavior could be considered an initial sign of oculomotor impairment. Hence, the evaluation of eye movement during reading might be a useful tool for monitoring well-defined cognitive resources.

Analysis of eye movements of workers in safe and unsafe behaviors using a video-based method

Analyzing eye movements of workers in safe and unsafe behaviors can reduce accidents. With a video-based method, the angular velocity of gaze direction (AVGD) represents micro-movements in gaze and angular velocity in saccade is used to analyze eye movements. A similar behavior simulation experiment is designed to collect operation videos, and an eye movement information extraction and processing framework is constructed to quantify and analyze eye movements. The results show that: the root mean square and movement frequency of AVGD can be used to recognize unsafe behavior; in operations with attention target fixation, compared with safe behavior, workers in unsafe behavior have higher angular velocity, movement frequency and turn frequency of eye movements; and in operations with attention target change, eye movement rules of workers in safe and unsafe behaviors depend on operation types. The results can provide features for unsafe behavior recognition and theoretical bases for safety training.

Food Captures Attention, but Not the Eyes: An Eye-Tracking Study on Mindset and BMI's Impact on Attentional Capture by High-Caloric Visual Food Stimuli.

Obesity is a worldwide pandemic and theories propose that attentional bias (AB) for food triggers craving and overeating, especially for people with obesity. However, empirical evidence is inconsistent, which may be due to methodological diversity and the double-sided nature of high-caloric palatable foods. That is, these foods simultaneously have a high hedonic and a low health value. So, depending on context and/or emotional state, people’s mindset while viewing foods may alternate between hedonic (taste) and health (calories) values, possibly affecting AB for food in opposite directions. This study tests how mindset and BMI (Body Mass Index) influences AB and food intake. We expect greater AB for food and more food intake in the hedonic compared to the health mindset, especially for people with obesity. Mindsets were induced using short video-clips in two sessions in counterbalanced order. Participants (35 with a healthy-weight-category BMI, 31 with obesity) performed a modified Additional Singleton paradigm where they searched for a neutral target among neutral fillers. On 90% of the trials, either a food or a neutral distractor appeared. Response latencies to the target and eye-movements to the distractor were recorded. Dependent variables included: response latencies, and eye-movement variables on the distractor: fixations (%), 1st fixation duration, dwell-time. Food intake was assessed in a bogus taste test. No significant effects emerged from the eye-movements analysis, whereas the analysis of response latencies showed an AB for food, not significantly moderated by BMI or mindset. Food intake was affected by mindset partly as expected, as participants ate more in the hedonic than in the health mindset when the hedonic mindset was induced in the second session. One AB measure (fixations) correlated positively with food intake. Finally, food captured attention – but not the eyes – and mindset affects food intake partly as expected.

Different saccadic profile in bulbar versus spinal-onset amyotrophic lateral sclerosis.

Two clinical phenotypes characterize the onset of amyotrophic lateral sclerosis (ALS): the spinal variant, with symptoms beginning in the limbs, and the bulbar variant, affecting firstly speech and swallowing. The two variants show some distinct features in the histopathology, localization and prognosis, but to which extent they really differ clinically and pathologically remains to be clarified. Recent neuropathological and neuroimaging studies have suggested a broader spreading of the neurodegenerative process in ALS, extending beyond the motor areas, toward other cortical and deep grey matter regions, many of which are involved in visual processing and saccadic control. Indeed, a wide range of eye movement deficits have been reported in ALS, but they have never been used to distinguish the two ALS variants. Since quantifying eye movements is a very sensitive and specific method for the study of brain networks, we compared different saccadic and visual search behaviours across spinal ALS patients (n = 12), bulbar ALS patients (n = 6) and healthy control subjects (n = 13), along with cognitive and MRI measures, with the aim to define more accurately the two patients subgroups and possibly clarify a different underlying neural impairment. We found separate profiles of visually-guided saccades between spinal (short saccades) and bulbar (slow saccades) ALS, which could result from the pathologic involvement of different pathways. We suggest an early involvement of the parieto-collicular-cerebellar network in spinal ALS and the fronto-brainstem circuit in bulbar ALS. Overall, our data confirm the diagnostic value of the eye movements analysis in ALS and add new insight on the involved neural networks.

Explicit and implicit mentalization of patients with first-episode schizophrenia: a study of self-referential gaze perception with eye movement analysis using hidden Markov models.

Mentalizing impairment is one of the core features of schizophrenia, and bias judgement of others' gaze as self-directing is common to schizophrenia patients. In this case-control study, 30 patients with first-episode schizophrenia (FES) and 30 matched healthy controls were assigned gaze perception tasks with variable stimulus presentation times (300ms and no time limit) to determine the presence of self-referential gaze perception (SRGP) bias. The eye movement pattern during the task were tracked and data were analysed using hidden Markov models (HMMs). The SRGP involves reporting of others' gaze intent and was used as a measurement of explicit mentalizing process. Eye movement measurement represents automated visual attention pattern and was considered as a measurement of implicit mentalizing process. The patients with FES had significantly more SRGP bias than the controls in the 300ms condition but not in the no-time-limit condition. Social cognitive function was related to SRGP bias in the patient group. Two distinct eye movement patterns were identified: eye-focused and nose-focused. Significant group differences in eye movement patterns in the 300ms condition were found with more controls had eye-focused pattern. Social anxiety symptoms were related to the nose-focused pattern, positive psychotic symptoms were related to the eye-focused pattern, and depressive symptoms were related to less consistent eye movement patterns. No significant relationship was found between SRGP bias and eye movement patterns. The dissociation between explicit and implicit mentalizing processes with different cognitive and symptom dimensions associated with the two processes suggests the presence of different mechanisms.

The effects of visual formats on Facebook health-related posts: evidence from eye movement analysis

PurposeThis study aimed to provide user-centered evidence for health professionals to make optimal use of images for the effective dissemination of health information on Facebook (FB).Design/methodology/approachUsing an eye-tracking experiment and a survey method, this study examined 42 participants' reading patterns as well as recall and recognition outcomes with 36 FB health information posts having various FB post features.FindingsThe findings demonstrated that FB posts with text-embedded images received more attention and resulted in the highest recall and recognition. Meanwhile, compared to text-embedded images, visual only images yielded less effective recall of information, but they caught the viewers' attention; graphics tended to attract more attention than photos. For effective communication, the text features in FB posts should align with the formats of the images.Practical implicationsThe findings of this study provide practical implications for health information disseminators by suggesting that text-embedded images should be used for effective health communication.Originality/valueThis study provided evidence of users' different viewing patterns for FB health information posts and the relationship between FB post types and recall and recognition outcomes.

Research on Flipped Classroom of University Curriculum Using Eye Movement Analysis and LSTM Neural Network

By reversing the arrangement of knowledge transfer and knowledge internalisation, FC (flipped classroom) changed the roles of teachers and students in traditional teaching and replanned the use of classroom time, realizing the innovation of traditional teaching mode. This research uses a network teaching platform to create a network platform supporting environment suitable for FC teaching in universities, allowing for the reform of university classroom teaching modes. An LSTM (Long Short-Term Memory) eye movement analysis algorithm is proposed to solve this problem. By analyzing the sequence of eye movements, this algorithm can predict students’ learning behavior and complete the current learning state detection. The research shows that the design and application of this research have achieved a good teaching effect in practice, which provides an idea for flipped classroom teaching design and curriculum resource design and development.

Eye-Tracker Study of Influence of Affective Disruptive Content on User's Visual Attention and Emotional State.

When reading interesting content or searching for information on a website, the appearance of a pop-up advertisement in the middle of the screen is perceived as irritating by a recipient. Interrupted cognitive processes are considered unwanted by the user but desired by advertising providers. Diverting visual attention away from the main content is intended to focus the user on the appeared disruptive content. Is the attempt to reach the user by any means justified? In this study, we examined the impact of pop-up emotional content on user reactions. For this purpose, a cognitive experiment was designed where a text-reading task was interrupted by two types of affective pictures: positive and negative ones. To measure the changes in user reactions, an eye-tracker (for analysis of eye movements and changes in gaze points) and an iMotion Platform (for analysis of face muscles’ movements) were used. The results confirm the impact of the type of emotional content on users’ reactions during cognitive process interruptions and indicate that the negative impact of cognitive process interruptions on the user can be reduced. The negative content evoked lower cognitive load, narrower visual attention, and lower irritation compared to positive content. These results offer insight on how to provide more efficient Internet advertising.

Analysis of Characteristics of Eye Movement While Viewing Movies and Its Application

In this article, we present the following: a background of visually induced motion sickness (VIMS), the goal of our study, and descriptions of three recent studies conducted by our group on the measurement and analysis of eye movement while viewing movies and the relationship of eye movement with VIMS. First, this study focuses on the relationship between eye movement and motion sickness susceptibility. We investigated the relationship between the motion sickness susceptibility and the frequency of optokinetic nystagmus (OKN) with peripheral viewing. It was revealed that susceptible participants showed a lower OKN frequency under conditions that strongly support the occurrence of OKN than insusceptible participants. Second, this study focuses on the relationship between visual information and postural variation such as visually evoked postural responses (VEPRs). In this study, both eye movement and the center of gravity while viewing a movie were measured. Additionally, we evaluated the difference in the transfer gain of the transfer function (vision as input and equilibrium function as output) due to the type of movie content or way of viewing. The gain for the three-dimensional movie with peripheral viewing exceeded that for the two-dimensional movie with central viewing. Third, this study focuses on eye movement and the application of deep-learning technology. In this study, we classified the eye movement as peripheral or central using a convolutional deep neural network with supervised learning. Then, cross validation was performed to test the classification accuracy. The use of >1-s eye movement data yielded an accuracy of >90%.