scholarly journals Quick Models for Saccade Amplitude Prediction

2009 ◽  
Vol 3 (1) ◽  
Author(s):  
Oleg V. Komogortsev ◽  
Young Sam Ryu ◽  
Do H. Koh
Keyword(s):  
Eye Gaze ◽  
Prediction Performance ◽  
Eye Position ◽  
Saccade Amplitude ◽  
Theoretical Evaluation ◽  
The Gaze ◽  
Proposed Model ◽  
Two Samples ◽  
Network Delays ◽  
Short Network

This paper presents a new saccade amplitude prediction model. The model is based on a Kalman filter and regression analysis. The aim of the model is to predict a saccade’s am-plitude extremely quickly, i.e., within two eye position samples at the onset of a saccade. Specifically, the paper explores saccade amplitude prediction considering one or two sam-ples at the onset of a saccade. The models’ prediction performance was tested with 35 subjects. The amplitude accuracy results yielded approximately 5.26° prediction error, while the error for direction prediction was 5.3% for the first sample model and 1.5% for the two samples model. The practical use of the proposed model lays in the area of real-time gaze-contingent compression and extreme eye-gaze aware interaction applications. The paper provides theoretical evaluation of the benefits of saccade amplitude prediction to the gaze-contingent multimedia compression, estimating a 21% improvement in com-pression for short network delays.

scholarly journals Influence of soundtrack on eye movements during video exploration

2012 ◽  
Vol 5 (4) ◽  
Author(s):  
Antoine Coutrot ◽  
Nathalie Guyader ◽  
Gelu Ionescu ◽  
Alice Caplier
Keyword(s):  
Eye Movements ◽  
Visual Attention ◽  
Fixation Duration ◽  
Visual Features ◽  
Eye Position ◽  
Saccade Amplitude ◽  
The Gaze ◽  
Spatial Sound ◽  
Complex Scenes ◽  
The Impact

Models of visual attention rely on visual features such as orientation, intensity or motion to predict which regions of complex scenes attract the gaze of observers. So far, sound has never been considered as a possible feature that might influence eye movements. Here, we evaluate the impact of non-spatial sound on the eye movements of observers watching videos. We recorded eye movements of 40 participants watching assorted videos with and without their related soundtracks. We found that sound impacts on eye position, fixation duration and saccade amplitude. The effect of sound is not constant across time but becomes significant around one second after the beginning of video shots.

scholarly journals Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis

2021 ◽  
Vol 3 (4) ◽  
Author(s):  
Jianlei Zhang ◽  
Yukun Zeng ◽  
Binil Starly
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Machine Tool ◽  
Recurrent Neural Network ◽  
Machine Tools ◽  
Prediction Performance ◽  
Sequential Data ◽  
Diagnosis And Prognosis ◽  
Proposed Model

AbstractData-driven approaches for machine tool wear diagnosis and prognosis are gaining attention in the past few years. The goal of our study is to advance the adaptability, flexibility, prediction performance, and prediction horizon for online monitoring and prediction. This paper proposes the use of a recent deep learning method, based on Gated Recurrent Neural Network architecture, including Long Short Term Memory (LSTM), which try to captures long-term dependencies than regular Recurrent Neural Network method for modeling sequential data, and also the mechanism to realize the online diagnosis and prognosis and remaining useful life (RUL) prediction with indirect measurement collected during the manufacturing process. Existing models are usually tool-specific and can hardly be generalized to other scenarios such as for different tools or operating environments. Different from current methods, the proposed model requires no prior knowledge about the system and thus can be generalized to different scenarios and machine tools. With inherent memory units, the proposed model can also capture long-term dependencies while learning from sequential data such as those collected by condition monitoring sensors, which means it can be accommodated to machine tools with varying life and increase the prediction performance. To prove the validity of the proposed approach, we conducted multiple experiments on a milling machine cutting tool and applied the model for online diagnosis and RUL prediction. Without loss of generality, we incorporate a system transition function and system observation function into the neural net and trained it with signal data from a minimally intrusive vibration sensor. The experiment results showed that our LSTM-based model achieved the best overall accuracy among other methods, with a minimal Mean Square Error (MSE) for tool wear prediction and RUL prediction respectively.

scholarly journals Saccades and smooth pursuit eye movements trigger equivalent gaze-cued orienting effects

2018 ◽  
Vol 71 (9) ◽  
pp. 1860-1872 ◽  
Author(s):  
Stephen RH Langton ◽  
Alex H McIntyre ◽  
Peter JB Hancock ◽  
Helmut Leder
Keyword(s):  
Eye Movements ◽  
Smooth Pursuit ◽  
Target Location ◽  
Eye Gaze ◽  
Saccadic Eye Movements ◽  
Gaze Shift ◽  
The Gaze ◽  
Orienting Effect ◽  
Motion Speed ◽  
Uncued Target

Research has established that a perceived eye gaze produces a concomitant shift in a viewer’s spatial attention in the direction of that gaze. The two experiments reported here investigate the extent to which the nature of the eye movement made by the gazer contributes to this orienting effect. On each trial in these experiments, participants were asked to make a speeded response to a target that could appear in a location toward which a centrally presented face had just gazed (a cued target) or in a location that was not the recipient of a gaze (an uncued target). The gaze cues consisted of either fast saccadic eye movements or slower smooth pursuit movements. Cued targets were responded to faster than uncued targets, and this gaze-cued orienting effect was found to be equivalent for each type of gaze shift both when the gazes were un-predictive of target location (Experiment 1) and counterpredictive of target location (Experiment 2). The results offer no support for the hypothesis that motion speed modulates gaze-cued orienting. However, they do suggest that motion of the eyes per se, regardless of the type of movement, may be sufficient to trigger an orienting effect.

scholarly journals What is unique about the human eye? Comparative image analysis on the external eye morphology of human and nonhuman great apes

2021 ◽  
Author(s):  
Fumihiro Kano ◽  
Takeshi Furuichi ◽  
Chie Hashimoto ◽  
Christopher Krupenye ◽  
Jesse G Leinwand ◽  
...  
Keyword(s):  
Image Analysis ◽  
Eye Gaze ◽  
Great Apes ◽  
Gaze Direction ◽  
Human Eye ◽  
The Gaze ◽  
Eye Morphology ◽  
New Findings ◽  
Heated Debate ◽  
Signaling Hypothesis

The gaze-signaling hypothesis and the related cooperative-eye hypothesis posit that humans have evolved special external eye morphology, including exposed white sclera (the white of the eye), to enhance the visibility of eye-gaze direction and thereby facilitate conspecific communication through joint-attentional interaction and ostensive communication. However, recent quantitative studies questioned these hypotheses based on new findings that humans are not necessarily unique in certain eye features compared to other great ape species. Therefore, there is currently a heated debate on whether external eye features of humans are distinguished from those of other apes and how such distinguished features contribute to the visibility of eye-gaze direction. This study leveraged updated image analysis techniques to test the uniqueness of human eye features in facial images of great apes. Although many eye features were similar between humans and other species, a key difference was that humans have uniformly white sclera which creates clear visibility of both eye outline and iris; the two essential features contributing to the visibility of eye-gaze direction. We then tested the robustness of the visibility of these features against visual noises such as darkening and distancing and found that both eye features remain detectable in the human eye, while eye outline becomes barely detectable in other species under these visually challenging conditions. Overall, we identified that humans have distinguished external eye morphology among other great apes, which ensures robustness of eye-gaze signal against various visual conditions. Our results support and also critically update the central premises of the gaze-signaling hypothesis.

A quality system’s impact on the service experience

2017 ◽  
Vol 37 (12) ◽  
pp. 1817-1839 ◽  
Author(s):  
Jeffery Smith ◽  
Sidney Anderson ◽  
Gavin Fox
Keyword(s):  
Service Quality ◽  
Social Systems ◽  
Theory And Practice ◽  
Service Experience ◽  
Content Type ◽  
Proposed Model ◽  
The Social ◽  
Two Samples ◽  
The Impact ◽  
Integrated Service

Purpose The purpose of this paper is to examine the interplay between technical and social systems within an organization that potentially affect the service experience, as perceived by end customers. Design/methodology/approach The paper explores the potential impact of an integrated service quality system on the service experience. A conceptual model is presented, accompanied by a detailed development of the hypotheses. Two samples (Study 1: n=474, Study 2: n=225) of consumers are used to empirically test the proposed model. Findings The analysis reveals the impact a technical system has on employees’ inherent abilities (i.e. the social system), which, in turn, affect the overall assessment by customers. Additionally, the situation in which an employee works (i.e. operating environmental conditions) results in differences in the model. Research limitations/implications This paper’s main implication is this paper employs established theory to develop a model that is empirically tested to show that implementing and maintaining a quality-oriented service system can positively influence the overall customer experience. The limitations are based primarily on the methodology in which individual employees assessed all aspects of both the social and technical systems. Practical implications Managers should be diligent in their design and implementation of the quality components as these affect the work setting in which employees operate. Originality/value Prior research has neither explored an integrated service quality system’s impact on the service experience nor employed an established theoretical framework. This work accomplishes both with the results providing contributions to both theory and practice.

A novel fractional discrete nonlinear grey Bernoulli model for forecasting the wind turbine capacity of China

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Wen-ze Wu ◽  
Wanli Xie ◽  
Chong Liu ◽  
Tao Zhang
Keyword(s):  
Wind Turbine ◽  
Nonlinear Coefficient ◽  
Predictive Performance ◽  
Prediction Performance ◽  
New Method ◽  
Grey Model ◽  
Content Type ◽  
Proposed Model ◽  
Whale Optimization ◽  
Turbine Capacity

PurposeA new method for forecasting wind turbine capacity of China is proposed through grey modelling technique.Design/methodology/approachFirst of all, the concepts of discrete grey model are introduced into the NGBM(1,1) model to reduce the discretization error from the differential equation to its discrete forms. Then incorporating the conformable fractional accumulation into the discrete NGBM(1,1) model is carried out to further improve the predictive performance. Finally, in order to effectively seek the emerging coefficients, namely, fractional order and nonlinear coefficient, the whale optimization algorithm (WOA) is employed to determine the emerging coefficients.FindingsThe empirical results show that the newly proposed model has a better prediction performance compared to benchmark models; the wind turbine capacity from 2019 to 2021 is expected to reach 275954.42 Megawatts in 2021. According to the forecasts, policy suggestions are provided for policy-makers.Originality/valueBy combing the fractional accumulation and the concepts of discrete grey model, a new method to improve the prediction performance of the NGBM(1,1) model is proposed. The newly proposed model is firstly applied to predict wind turbine capacity of China.

scholarly journals A Novel Discrete Grey Model and Its Application

2019 ◽  
Vol 2019 ◽  
pp. 1-6 ◽  
Author(s):  
Wen-Ze Wu ◽  
Jianming Jiang ◽  
Qi Li
Keyword(s):  
Tensile Strength ◽  
Arbitrary Number ◽  
Prediction Accuracy ◽  
Historical Data ◽  
Prediction Performance ◽  
Grey Model ◽  
Original Series ◽  
Proposed Model ◽  
Grey Models ◽  
Future Data

This paper aims to further increase the prediction accuracy of the grey model based on the existing discrete grey model, DGM(1,1). Herein, we begin by studying the connection between forecasts and the first entry of the original series. The results comprehensively show that the forecasts are independent of the first entry in the original series. On this basis, an effective method of inserting an arbitrary number in front of the first item of the original series to extract messages is applied to produce a novel grey model, which is abbreviated as FDGM(1,1) for simplicity. Incidentally, the proposed model can even forecast future data using only three historical data. To demonstrate the effectiveness of the proposed model, two classical examples of the tensile strength and life of the product are employed in this paper. The numerical results indicate that FDGM(1,1) has a better prediction performance than most commonly used grey models.

The Power of Attention: Using Eye Gaze to Predict Other-Regarding and Moral Choices

2018 ◽  
Vol 29 (11) ◽  
pp. 1878-1889 ◽  
Author(s):  
Minou Ghaffari ◽  
Susann Fiedler
Keyword(s):  
Eye Gaze ◽  
Decision Makers ◽  
Sequential Presentation ◽  
Top Down ◽  
Bottom Up ◽  
The Gaze ◽  
Autonomous Decision ◽  
Gaze Patterns ◽  
Moral Choices ◽  
Other Regarding

According to research studying the processes underlying decisions, a two-channel mechanism connects attention and choices: top-down and bottom-up processes. To identify the magnitude of each channel, we exogenously varied information intake by systematically interrupting participants’ decision processes in Study 1 ( N = 116). Results showed that participants were more likely to choose a predetermined target option. Because selection effects limited the interpretation of the results, we used a sequential-presentation paradigm in Study 2 (preregistered, N = 100). To partial out bottom-up effects of attention on choices, in particular, we presented alternatives by mirroring the gaze patterns of autonomous decision makers. Results revealed that final fixations successfully predicted choices when experimentally manipulated (bottom up). Specifically, up to 11.32% of the link between attention and choices is driven by exogenously guided attention (1.19% change in choices overall), while the remaining variance is explained by top-down preference formation.

Exploring the effect of eye gaze cues on novel L2 morphosyntactic pattern learning

2020 ◽  
pp. 026765831989682
Author(s):  
Dato Abashidze ◽  
Kim McDonough ◽  
Yang Gao
Keyword(s):  
Visual Cues ◽  
Eye Gaze ◽  
Generalization Test ◽  
Pattern Learning ◽  
The Gaze ◽  
Movement Data ◽  
Visual Events ◽  
Static Images ◽  
Post Hoc ◽  
Gaze Cues

Recent research that explored how input exposure and learner characteristics influence novel L2 morphosyntactic pattern learning has exposed participants to either text or static images rather than dynamic visual events. Furthermore, it is not known whether incorporating eye gaze cues into dynamic visual events enhances dual pattern learning. Therefore, this exploratory eye-tracking study examined whether eye gaze cues during dynamic visual events facilitate novel L2 pattern learning. University students ( n = 72) were exposed to 36 training videos with two dual novel morphosyntactic patterns in pseudo-Georgian: completed events ( bich-ma kocn-ul gogoit, ‘boy kissed girl’) and ongoing actions ( bich-su kocn-ar gogoit, ‘boy is kissing girl’). They then carried out an immediate test with 24 items using the same vocabulary words, followed by a generalization test with 24 items created from new vocabulary words. Results indicated that learners who received the eye gaze cues scored significantly higher on the immediate test and relied on the verb cues more than on the noun cues. A post-hoc analysis of eye-movement data indicated that the gaze cues elicited longer looks to the correct images. Findings are discussed in relation to visual cues and novel morphosyntactic pattern learning.

scholarly journals Bayesian multi-trait kernel methods improve multi-environment genome based prediction

2021 ◽  
Author(s):  
Osval Antonio Montesinos-López ◽  
José Cricelio Montesinos-López ◽  
Abelardo Montesinos-Lopez ◽  
Juan Manuel Ramírez-Alcaraz ◽  
Jesse Poland ◽  
...  
Keyword(s):  
Kernel Methods ◽  
Genomic Prediction ◽  
Linear Models ◽  
Kernel Method ◽  
Prediction Performance ◽  
Gaussian Kernel ◽  
Phenotypic Traits ◽  
Proposed Model ◽  
The Mean ◽  
Gaussian Polynomial

Abstract When multi-trait data are available, the preferred models are those that are able to account for correlations between phenotypic traits because when the degree of correlation is moderate or large, this increases the genomic prediction accuracy. For this reason, in this paper we explore Bayesian multi-trait kernel methods for genomic prediction and we illustrate the power of these models with three real datasets. The kernels under study were the linear, Gaussian, polynomial and sigmoid kernels; they were compared with the conventional Ridge regression and GBLUP multi-trait models. The results show that, in general, the Gaussian kernel method outperformed conventional Bayesian Ridge and GBLUP multi-trait linear models by 2.2 to 17.45% (datasets 1 to 3) in terms of prediction performance based on the mean square error of prediction. This improvement in terms of prediction performance of the Bayesian multi-trait kernel method can be attributed to the fact that the proposed model is able to capture non-linear patterns more efficiently than linear multi-trait models. However, not all kernels perform well in the datasets used for evaluation, which is why more than one kernel should be evaluated to be able to choose the best kernel.

Sign in / Sign up

Export Citation Format

Share Document