Eye Movement Prediction Based on Adaptive BP Neural Network

Tang, Yiming; Su, Jianhuan

doi:10.1155/2021/4977620

Cited by 9 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) e input activation value s k j and the response output value z k j of each neuron in the hidden layer were calculated. Input activation value of neurons in hidden layer [23] is as follows:…”

Section: Algorithm and Steps Of Bp Model For Enterprise Comprehensive...mentioning

confidence: 99%

Application of Neural Network Sample Training Algorithm in Economic Information Management System

Wang¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

In order to make up for the shortcomings of traditional financial evaluation, this paper proposes a method of enterprise comprehensive performance evaluation system based on the balanced scorecard method and BP artificial neural network model. This method focuses on the application methods and steps of BP artificial neural network model in enterprise comprehensive performance evaluation system. In addition, it also makes a detailed study on the initial weight and threshold assignment of the BP network, the selection of training samples, the determination of hidden layer, the convergence of network, and so on. The experimental results show that this method verifies the comprehensive performance evaluation results of 15 manufacturers, and the results are 4 excellent, 5 good, 3 average, 2 poor, and 1 very poor. This method effectively reduces the limitations of enterprise comprehensive performance evaluation by introducing nonfinancial evaluation indicators.

show abstract

Section: Algorithm and Steps Of Bp Model For Enterprise Comprehensive...mentioning

confidence: 99%

Application of Neural Network Sample Training Algorithm in Economic Information Management System

Wang¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…In many cases, there are many factors affecting the results of the process, and it is necessary to analyze which indicators are more relevant or the correlation ranking of these factors, and the response results can be obtained by Grey correlation analysis. In this paper, GRA was used to determine the degree of correlation of multiple kinematic data for kinetic vGRF.Teng used GRA to optimize the construction of convolutional neural network system and the evaluation of drugs [18].Kong et al constructed a GRA-ANN to predict the effect of aggregates on the permeability of concrete [19]. Currently, GRA is more often used in engineering research, so it is hoped that this paper will open up GRA for research in sports disciplines.…”

Section: Introduction：mentioning

confidence: 99%

vGRF analysis based on GRA-BP model to predict volleyball smash landing

zhang,

Meng,

Bao

et al. 2023

Preprint

View full text Add to dashboard Cite

Vertical Ground Reaction Force (vGRF) is essential for the biomechanical analysis of volleyball players. Objective A method of constructing a coupled mathematical model of Grey Relation Analysis (GRA) and BP neural networks to predict the vGRF of volleyball players hitting the ball on the ground instead of a three-dimensional force table. method 20 second-level volleyball players from the Tianjin Institute of Physical Education were selected to demonstrate the volleyball smash action in a two-step running mode, and kinematic data and vGRF were collected synchronously using the Qualisys 8-lens infrared spot high-speed motion capture system and the Kistler three-dimensional force measuring table. Opensim was used to calculate the kinematic data of volleyball players performing a two-step running smash. GRA was used to screen kinematic indicators with a correlation of less than 0.98, root mean squared error (RMSE), mean absolute percentage error (MAPE) and mean absolute error (MAE) were used as evaluation indicators of the GRA-BP model, and Kendall's( W) coefficient evaluation was used to predict the agreement between vGRF and measured vGRF. Results The GRA results showed that the correlation degree of 13 kinematic data such as pelvic anterior tilt angle, pelvic tilt angle and pelvic rotation angle was higher than 0.98. The root mean square error (RMSE) between the predicted value and the measured value is 0.33 BW, the mean absolute percentage error (MAPE) is 4%, the mean absolute error (MAE) is 0.29 BW, and the Kendall's W coefficient is 0.945, P≤0.001. Conclusions The established GRA-BP model can significantly improve the accuracy of volleyball players in hitting the ball and vGRF and significantly reduce the measurement time. At the same time, the mathematical model provides data support for scientific training and better accompanies athletes' health training and participation. Finally, the model has good reproducibility and easy operation, and will also provide theoretical and practical reference for guiding national sports and scientific fitness.

show abstract

“…e development of big data and information technology [11][12][13][14] provides a reliable supporting tool for this research. Many studies have found that some eye movement parameters [15][16][17], such as fixation duration, fixation duration percentage, fixation frequency, regression frequency, and average pupil diameter, provided critical evidence to explore the psychological process of students. Tai [18] compared the eye movement differences in problem-solving behaviors of participants with different professional backgrounds in scientific evaluation and found that the eye movement differences were related to the participant's professional level on a specific topic.…”

Section: Introductionmentioning

confidence: 99%

Comparing Middle School Students’ Scientific Problem-Solving Behavior in Hands-On Manipulation Performance Assessment: Terms by Eye-Tracking Analysis

Zang

Lin

Chen

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

This study specifically designed an eye-tracking supported scientific problem-solving assessment: hands-on manipulation task system to explore the differences in visual attention and cognitive processes between high and low science achievement groups. Thirteen students with high science achievement and fourteen students with low science achievement participated. Students needed to complete the hands-on manipulation assessment, consisting of three modules, including selecting experimental equipment, experimental design, and building the experimental model. Behavioral and eye movement data were collected during the process. The results showed that the high science achievement group allocated more visual attention to the hands-on manipulation task, acquired more information through visual fixation, and assigned more attention to the key area. In module three of the hands-on manipulation task, the high science achievement group transformed from a visual channel to a tactile channel, and they generated more hands-on behaviors depending on the experimental area. Furthermore, the results showed a high correlation between students’ eye movement behavior and the performance of scientific problem-solving assessments. Eye movement behavior could predict students’ performance in scientific problem-solving. The average fixation duration and the average fixation duration of the interest area were two significant determining parameters. The implications of the experimental results for front-line science education, curriculum designers, and science assessment were also discussed.

show abstract

Eye Movement Prediction Based on Adaptive BP Neural Network

Cited by 9 publications

References 16 publications

Application of Neural Network Sample Training Algorithm in Economic Information Management System

Application of Neural Network Sample Training Algorithm in Economic Information Management System

vGRF analysis based on GRA-BP model to predict volleyball smash landing

Comparing Middle School Students’ Scientific Problem-Solving Behavior in Hands-On Manipulation Performance Assessment: Terms by Eye-Tracking Analysis

Contact Info

Product

Resources

About