scholarly journals Is the low-cost EyeTribe eye tracker any good for research?

Author(s):  
Edwin Dalmaijer

Eye-tracking technology is becoming increasingly cheaper, both on the hardware and on the software front. Currently, the EyeTribe tracker is the most inexpensive commercial eye tracker in the world, at a price of $99. The low costs make it a potentially interesting resource for research, but no objective testing of its quality has been performed yet. Here the EyeTribe tracker is compared with an EyeLink 1000, a high-quality video eye tracker. Results indicate that the spatial precision and accuracy are good enough for fixation checking, point-of-regard analyses, and pupilometry. However, the low sampling rate renders the device unsuitable for testing high-accuracy saccade metrics. Additionally, open-source toolboxes for Matlab and Python, and a plug-in for OpenSesame are presented, which can be used to interface with the EyeTribe tracker.

Author(s):  
Edwin Dalmaijer

Eye-tracking technology is becoming increasingly cheaper, both on the hardware and on the software front. Currently, the EyeTribe tracker is the most inexpensive commercial eye tracker in the world, at a price of $99. The low costs make it a potentially interesting resource for research, but no objective testing of its quality has been performed yet. Here the EyeTribe tracker is compared with an EyeLink 1000, a high-quality video eye tracker. Results indicate that the spatial precision and accuracy are good enough for fixation checking, point-of-regard analyses, and pupilometry. However, the low sampling rate renders the device unsuitable for testing high-accuracy saccade metrics. Additionally, open-source toolboxes for Matlab and Python, and a plug-in for OpenSesame are presented, which can be used to interface with the EyeTribe tracker.


2015 ◽  
Vol 8 (1) ◽  
Author(s):  
Kristien Ooms ◽  
Lien Dupont ◽  
Lieselot Lapon ◽  
Stanislav Popelka

This article compares the accuracy and precision of the low-cost Eye Tribe tracker and a well-established comparable eye tracker: SMI RED 250. Participants were instructed to fixate on predefined point locations on a screen. The accuracy is measured by the distance between the recorded fixation locations and the actual location. Precision is represented by the standard deviation of these measurements. Furthermore, the temporal precision of both eye tracking devices (sampling rate) is evaluated as well. The obtained results illustrate that a correct set-up and selection of software to record and process the data are of utmost importance to obtain acceptable results with the low-cost device. Nevertheless, with careful selections in each of these steps, the quality (accuracy and precision) of the recorded data can be considered comparable.


2021 ◽  
Author(s):  
Kalyan Kumar Jena ◽  
Sourav Kumar Bhoi ◽  
Satyajeet Behera ◽  
Raghvendra Kumar ◽  
Hoang Viet Long ◽  
...  

Abstract Understanding human emotions is one of the crucial aspects when we are to take action. Our emotions dictate our apparent behaviors. In simple words, what we feel inside can predict things about what we would do. This creates a huge opportunity for government and businesses industry to understand and predict people's behaviors. There has been some really great research done on this with high accuracy. Recently, Covid-19 vaccination process is a challenging task going on all over the world and it is necessary to explore people’s reaction over this for more effective vaccination process spread. In this paper, wetried to understand an event (Covid-19 vaccination) with a relatively simple model with decent accuracy compared to other sophisticated models. We use simple machine learning models to train and deploy it over the network. We have used KNIME Analytical Platform to design and implement our model as it provides end-to-end analytics. We have managed to get 88.67% accuracy and Cohen’s kappa 0.789 with SVM model by tuning some parameters. The model is deployed on Twitter data. This paper shows our efforts trying to make a simple model to analyze an event (Covid-19 vaccination) and understand people's emotions towards the event. The methodology involves identifying important topics (terms) and finding out the sentiment (positive, negative, neutral). This paper tries to find a low-cost solution to analyze an event and provide data-driven insights from it without involving sophisticated algorithms.


Author(s):  
Hélio Clemente Cuve ◽  
Jelka Stojanov ◽  
Xavier Roberts-Gaal ◽  
Caroline Catmur ◽  
Geoffrey Bird

AbstractEye-tracking and recording of physiological signals are increasingly used in research within cognitive science and human–computer interaction. For example, gaze position and measures of autonomic arousal, including pupil dilation, skin conductance (SC), and heart rate (HR), provide an indicator of cognitive and physiological processes. The growing popularity of these techniques is partially driven by the emergence of low-cost recording equipment and the proliferation of open-source software for data collection and analysis of such signals. However, the use of new technology requires investigation of its reliability and validation with respect to real-world usage and against established technologies. Accordingly, in two experiments (total N = 69), we assessed the Gazepoint GP3-HD eye-tracker and Gazepoint Biometrics (GPB) system from Gazepoint. We show that the accuracy, precision, and robustness of the eye-tracker are comparable to competing systems. While fixation and saccade events can be reliably extracted, the study of saccade kinematics is affected by the low sampling rate. The GP3-HD is also able to capture psychological effects on pupil dilation in addition to the well-defined pupillary light reflex. Finally, moderate-to-strong correlations between physiological recordings and derived metrics of SC and HR between the GPB and the well-established BIOPAC MP160 support its validity. However, low amplitude of the SC signal obtained from the GPB may reduce sensitivity when separating phasic and tonic components. Similarly, data loss in pulse monitoring may pose difficulties for certain HR variability analyses.


2021 ◽  
Vol 38 (2) ◽  
pp. 369-377
Author(s):  
Güneş Ekim ◽  
Ayten Atasoy ◽  
Nuri İkizler

Motor neuron patients such as paralysis, locking syndrome, and amyotrophic lateral sclerosis can see and hear what is happening in their environment, but cannot communicate with their environment. It is very important for these patients, who do not have any physical function other than eye movements, to be able to express their needs, feelings and thoughts. Therefore, to express the thoughts, needs and feelings of these patients, a system that converts eye-blink signals to speech was developed in this study. The main purpose of the designed system is high accuracy, low cost, high speed and independence from environmental factors. Undoubtedly, it is also very important that it causes as little discomfort to the patient as possible. Morse-coded signals generated by voluntary eye-blinks and the single-channel wireless NeuroSky MindWave Mobile device eliminates the need for cost-increasing equipment such as a camera or eye tracker and environmental factors such as light. With the use of Dynamic Time Warping (DTW), an algorithm which works at high speed and high accuracy at the time domain and does not require any training process has been implemented. In this way, the recorded speech was performed with a quite impressive accuracy.


Author(s):  
Jonathan Reades ◽  
Martin Crookston

Face-to-Face: The Persistent Power of Cities In a Post-Pandemic Era, is about the way that people and firms are adapting to the world of always-on and everywhere digital access, and what that means for cities and regions. Twenty years after The Death of Distance—and in the midst of a pandemic that has led some to question the future of cities—many people still think that we are on track for ‘business anywhere’. The book shows why that's not the case, and provides a structure for thinking about the next twenty years of social and economic upheaval. It shows how the changing fortunes of cities are tied to the ongoing importance of face-to-face contact to our most valuable industries, and thus why the ‘human touch’ will continue to be crucial in the cities of tomorrow. Drawing on interviews with artists and advertisers, bankers and bakers, software devs and property developers, across some forty interviews we home in on what people actually do and why. ‘Contact’, in all its forms, is shown to still matter hugely to companies and individuals, even in a world with high-quality video conferencing and free online calling. And when the pandemic hit, a further digital survey explored interviewees’ experiences of an ‘e-only’ world, gaining ‘front-line’ insights into the short- and long-terms. The book seeks to provide guidance for city leaders, businesses, policymakers and students of urban and regional planning on how to think about 21st Century urban change.


Author(s):  
Michaël Canu ◽  
◽  
Boris Gálvis ◽  
Malika Madelin

Deteriorating air quality is of great concern around the world. Recently, citizen scientists, researchers, and many others have used low-cost devices such as the Shinyei PPD42NS dust sensor to measure particulate matter pollution in both developed and under-developed countries. However, few articles exist specifically on the features and performance of these sensors. Some have shown mixed results in terms of precision, accuracy, and repeatability, especially for portable applications. Frequently, users assemble the electronics and the sensors applying simple guidelines, using electric schematics, and coding extraneous algorithms to get questionable data. There is a need to better understand how it works exactly, its limitations and the effect of the program used to interpret the outputs of this sensor. This article provides a short electronic analysis of the Shinyei PPD42NS dust sensor and shows that the internal sensor electronic design (filters and detection stage) as well as the used data processing algorithm, limit its precision and accuracy by generating nonlinearities and biases. These issues avoid some applications like moving ones and imply that the algorithm used to process the sensor signals must be clearly presented in future articles.


2021 ◽  
Author(s):  
Helio Clemente Cuve ◽  
Jelka Stojanov ◽  
Miklos Roberts-Gaal ◽  
Caroline Catmur ◽  
Geoff Bird

Eye-tracking and recording of physiological signals are increasingly used in research within cognitive science and human-computer interaction. For example, gaze position and measures of autonomic arousal, including pupil dilation, skin conductance (SC) and heart rate (HR), provide an indicator of cognitive and physiological processes. The growing popularity of these techniques is partially driven by the emergence of low-cost recording equipment and the proliferation of open-source software for data collection and analysis of such signals. The use of new technology requires investigation of its reliability and reproducibility, however, and validation with respect to real-world usage and against established technologies. Accordingly, in two experiments (total N = 69) we assessed the Gazepoint GP3-HD eye-tracker and Gazepoint Biometrics (GPB) system from Gazepoint. We show that accuracy, precision and robustness of the eye-tracker are comparable to competing systems. While fixation and saccade events can be reliably extracted, the study of saccade kinematics is affected by the low sampling rate. The GP3-HD is also able to capture psychological effects on pupil dilation in addition to the well-defined pupillary light reflex. Finally, moderate-to-strong correlations between physiological recordings and derived metrics of SC and HR between the GPB and the well-established BIOPAC MP160 support its validity. However, low amplitude of the SC signal obtained from the GPB may reduce sensitivity when separating phasic and tonic components. Similarly, data loss in pulse monitoring may pose difficulties for certain HR variability analyses.


Sign in / Sign up

Export Citation Format

Share Document