College of Science and Engineering
Permanent URI for this collectionhttps://hdl.handle.net/10877/17053
Browse
Browsing College of Science and Engineering by Type "Paper"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item Assessment of Shift-Invariant CNN Gaze Mappings for PS-OG Eye Movement Sensors(IEEE Computer Society, 2019-08-27) Griffith, Henry; Katrychuk, Dmytro; Komogortsev, OlegPhotosensor oculography (PS-OG) eye movement sensors offer desirable performance characteristics for integration within wireless head mounted devices (HMDs), including low power consumption and high sampling rates.To address the known performance degradation of these sensors due to HMD shifts, various machine learning techniques have been proposed for mapping sensor outputs to gaze location. This paper advances the understanding of a recently introduced convolutional neural network designed to provide shift invariant gaze mapping within a specified range of sensor translations. Performance is assessed for shift training examples which better reflect the distribution of values that would be generated through manual repositioning of the HMD. The network is shown to exhibit com-parable accuracy for this realistic shift distribution versus a previously considered rectangular grid, thereby enhancing the feasibility of in-field initialization. In addition, this work further supports the practical viability of the proposed initialization process by demonstrating robust mapping performance versus training data scale. The ability to maintain reasonable accuracy for shifts extending beyond those introduced during training is also demonstrated.Item Automatic Text Summarization with Neural Networks(2004-06-22) Kaikhah, KhosrowA novel technique for summarizing news articles using neural networks is presented. A neural network is trained to learn the relevant features cf sentences that should be included in the summary of the article. The neural network is then modified to generalize and combine the relevant fertures apparent in summary sentences. Finally, the modified neural network is used as a filter to summarize news article.Item Biometric Performance as a Function of Gallery Size(2020-01-23) Friedman, Lee; Stern, Hal; Prokopenko, Vladyslav; Djanian, Shagen; Griffith, Henry; Komogortsev, OlegMany developers of biometric systems start with modest samples before general deployment. But they are interested in how their systems will work with much larger samples. To assist them, we evaluated the effect of gallery size on biometric performance. Identification rates describe the performance of biometric identification, whereas ROC-based measures describe the performance of biometric authentication (verification). Therefore, we examined how increases in gallery size affected identification rates (i.e., Rank-1 Identification Rate, or Rank-1 IR) and ROC-based measures such as equal error rate (EER). We studied these phenomena with synthetic data as well as real data from a face recognition study. It is well known that the Rank-1 IR declines with increasing gallery size. We have provided further insight into this decline. We have shown that this relationship is linear in log(Gallery Size). We have also shown that this decline can be counteracted with the inclusion of additional information (features) for larger gallery sizes. We have also described the curves which can be used to predict how much additional information is required to stabilize the Rank-1 IR as a function of gallery size. These equations are also linear in log(gallery size). We have also shown that the entire ROC curve is not systematically affected by gallery size, and so ROC-based scalar performance metrics such as EER are also stable across gallery size. Unsurpringingly, as additional uncorrelated features are added to the model, EER decreases. We were interested in exploring what changes in similarity score distributions might accompany these declines in EERs. For this, we evaluated the effect of number of features and gallery size on key distribution characteristics (median and IQR) of the genuine and impostor similarity score distributions. We present evidence that these decreases in EER are driven primarily by decreases in the spread of the impostor similarity score distribution.Item Brief Communication: A Re-Examination of the Eye Movement Data used by Hooge et al (2018) ["Is human classification by experienced untrained observers a gold standard in fixation detection?"](2020-01) Friedman, LeeHooge et al. (2018) asked the question: ``Is human classification by experienced untrained observers a gold standard in fixation detection?'' They conclude the answer is no. If they had entitled their paper: ``Is human classification by experienced untrained observers a gold standard in fixation detection when data quality is very poor, data are error-filled, data presentation was not optimal, and the analysis was seriously flawed?'', I would have no case to make. In the present report, I will present evidence to support my view that this latter title is justified. The low-quality data assessment is based on using a relatively imprecise eye-tracker, the absence of head restraint for any subjects, and the use of infants as the majority of subjects (60 of 70 subjects). Allowing subjects with more than 50% missing data (as much as 95%) is also evidence of low-quality data. The error-filled assessment is based on evidence that a number of the ``fixations'' classified by ``experts'' have obvious saccades within them, and that, apparently, a number of fixations were classified on the basis of no signal at all. The evidence for non-optimal data presentation stems from the fact that, in a number of cases, perfectly good data was not presented to the coders. The flaws in the analysis are evidenced by the fact that entire stretches of missing data were considered classified, and that the measurement of saccade amplitude was based on many cases in which there was no saccade at all. Without general evidence to the contrary, it is correct to assume that some human classifiers under some conditions may meet the criteria for a gold standard, and classifiers under other conditions may not. This conditionality is not recognized by Hooge et al. (2018). A fair assessment would conclude that whether or not humans can be considered a gold standard is still very much an open question.Item Brief Communication: Three Errors and Two Problems in a Recent Paper: gazeNet : End-to-end Eye-movement Event Detection with Deep Neural Networks (Zemblys, Niehorster, and Holmqvist, 2019)(2020-04) Friedman, LeeA final version of this research is now published as of April 13, 2020 in Behavior Research Methods. Access to this article is through this link: Brief communication: Three errors and two problems in a recent paper: gazeNet: End-to-end eye-movement event detection with deep neural networks (Zemblys, Niehorster, and Holmqvist, 2019) https://rdcu.be/b3z4nItem Detailed Numerical Results for Paper: A Set-Partitioning-Based Model for the Stochastic Vehicle Routing Problem(2009-05) Novoa, Clara; Berger, Rosemary T.; Linderoth, Jeff; Storer, RobertFollowing are some tables with detailed results that complement the paper titled "A Set-Partitioning-Based Model for the Stochastic Vehicle Routing Problem."Item Detailed Numerical Results for Paper: An Approximate Dynamic Programming Approach for the Vehicle Routing Problem with Stochastic Demands(2008-01) Novoa, Clara; Storer, RobertThe document contains some tables and figures with detailed results that complement the paper titled: "An approximate dynamic programming approach for the vehicle routing problem with stochastic demands" submitted to the European Journal of Operations Research. As requested by referees detailed results were moved from the paper and uploaded to a permanent web repository.Item Detailed Regression Models and Complete Set of Boxplots for Validation Step for the Paper: Multiple Imputation on Design of Experiments with Multiple Responses using STATA(2015-06-23) Novoa, Clara; Asiabanpour, Bahram; Alkusari, SuleimaThe article contains the final regression models that complement the paper “Multiple Imputation on Design of Experiments with Multiple Responses using STATA” These final results are obtained after: (a) using the predictive mean matching (pmm) impute option under the command mi impute in STATA, and (b) adjusting significant linear regression models for each of the 15 response variables in the study using the command mi estimate. In this study, the mi impute pmm command was invoked to impute m=5 values for each response variable at each experimental condition with missing data. In this study, quadratic models are assumed to describe each response in terms of the 7 factors or independent variables. The initial regression models contained all the possible terms in a second order polynomial model on the factors. Quadratic terms and second order interactions were included except those involving categorical variables. The non-significant factors are iteratively removed until significant regression models are obtained for each response variable.Item Evaluating the Data Quality of Eye Tracking Signals from a Virtual Reality System: Case Study Using SMI's Eye-Tracking HTC Vive(2019-12-04) Lohr, Dillon J.; Friedman, Lee; Komogortsev, OlegThis is an unpublished article which is submitted to a journal. We evaluated the data quality of SMI's tethered eye-tracking head-mounted display based on the HTC Vive (ET-HMD) during a random saccade task. We measured spatial accuracy, spatial precision, temporal precision, linearity, and crosstalk. We proposed the use of a non-parametric spatial precision measure based on the median absolute deviation (MAD). Our linearity analysis considered both the slope and adjusted R-squared of a best-fitting line. We were the first to test for a quadratic component to crosstalk. We prepended a calibration task to the random saccade task and evaluated 2 methods to employ this user-supplied calibration. For this, we used a unique binning approach to choose samples to be included in the recalibration analyses. We compared our quality measures between the ET-HMD and our EyeLink 1000 (SR-Research, Ottawa, Ontario, CA). We found that the ET-HMD had significantly better spatial accuracy and linearity fit than our EyeLink, but both devices had similar spatial precision and linearity slope. We also found that, while the EyeLink had no significant crosstalk, the ET-HMD generally exhibited quadratic crosstalk. Fourier analysis revealed that the binocular signal was a low-pass filtered version of the monocular signal. Such filtering resulted in the binocular signal being useless for the study of high-frequency components such as saccade dynamics. Data are available [1]. [1] Lohr, Dillon; Friedman, Lee; Komogortsev, Oleg, 2019, "Data for Novel Enhancements for the Evaluation of Eye-Tracking Device Performance: Case Study using SMI’s Eye-Tracking HTC Vive", https://doi.org/10.18738/T8/N8EIVG, Texas Data Repository Dataverse, V1Item Evidence for five types of fixation during a random saccade eye tracking task: Implications for the study of oculomotor fatigue(2024-04) Friedman, Lee; Komogortsev, Oleg V.Our interest was to evaluate changes in fixation duration as a function of time-on-task (TOT) during a random saccade task. We employed a large, publicly available dataset. The frequency histogram of fixation durations was multimodal and modelled as a Gaussian mixture. We found five fixation types. The “ideal” response would be a single accurate saccade after each target movement, with a typical saccade latency of 200-250 msec, followed by a long fixation (> 800 msec) until the next target jump. We found fixations like this, but they comprised only 10% of all fixations and were the first fixation after target movement only 23.4% of the time. More frequently (57.4% of the time), the first fixation after target movement was short (117.7 msec mean) and was commonly followed by a corrective saccade. Across the entire 100 sec of the task, median total fixation duration decreased. This decrease was approximated with a power law fit with R2 = 0.94. A detailed examination of the frequency of each of our five fixation types over time on task (TOT) revealed that the three shortest duration fixation types became more and more frequent with TOT whereas the two longest fixations became less and less frequent. In all cases, the changes over TOT followed power law relationships, with R2 values between 0.73 and 0.93. We concluded that, over the 100 second duration of our task, long fixations are common in the first 15 to 22 seconds but become less common after that. Short fixations are relatively uncommon in the first 15 to 22 seconds but become more and more common as the task progressed. Apparently. the ability to produce an ideal response, although somewhat likely in the first 22 seconds, rapidly declines. This might be related to a noted decline in saccade accuracy over time.Item Rules and Guidelines for Manual Classification of Fixations, Saccades, PSEs and Other Events in High Quality Eye Movement Recordings During Reading(2021-04) Friedman, Lee; Prokopenko, Vladyslav; Djanian, Shagen; Katrychuk, Dmytro; Komogortsev, OlegWe present a set of detailed scoring rules and the design of a scoring interface for the purpose of classifying eye-movements during reading. The recordings we employed were from the EyeLink 1000 and were collected at 1000 Hz. The subjects were reading a poem during eye movement recording. The rules and interface design emerged from a series of 20 consensus discussions between 3 graduate students and 1 faculty-level person with much experience studying eye movements. The discussions lasted, on average, 2.14 hours each. From 1-5 pilot classification attempts, made by the first four authors above, were performed between discussions. The events classified included saccades, post-saccade events (PSE), various artifacts, and by default, fixation. The rules are described in detail, with many illustrations. We are not aware of any other comparably detailed publicly available set of eye movement classification rules.Item The Influence of Early STEM Career Exploration as Related to Motivation and Self-determination Theory(2018-06) Martinez Ortiz, Araceli; Warshauer, Hiroko; Rodriguez Amaya, Laura; Garcia Torres, SaraA science, technology, engineering, and mathematics (STEM) summer intervention program is the setting for a career-exploration research study with over 30 adolescent students in a low-income community. Using motivation and self-determination theory as a framework, the impact of early exposure to engineering and mathematics career opportunities is examined. In the larger study we utilized mixed methods to analyze how changes in middle school students’ affective characteristics may be linked to their future career decision-making after participating in an integrated science, technology, engineering, and mathematics academic/ career summer camp. Using a case study methodology, we examine three of the students in detail regarding their changes in self-reported future academic major choices and career goals utilizing measures of motivation, self-efficacy, and self-determination. Interview data provides qualitative evidence that participants’ experiences during camp may indeed impact their short-term outlook towards their informed decision making and motivation related to pursuing STEM careers. Repeat participants (two or more years) are highlighted as case studies and their survey and interview input is analyzed to determine to what extent, if any, students attribute changes in motivation to their summer camp experiences. Select comments that might reveal insights related to the participants’ ethnicity and/or gender are presented, given that the student participants represent a majority demographic of low income and historically underrepresented populations in STEM.