改进DBA算法的眼动模式分析

doi:10.3778/j.issn.1002-8331.2103-0567

摘要/Abstract

摘要： 随着眼动追踪技术的进步和设备成本的降低，眼动追踪技术已广泛应用于智能教育领域，分析眼动数据以评估学习状态成为智能教育中一个十分重要的环节。眼动扫描路径可以直接或间接地反映思维模式及心理状态的变化，通过分析扫描路径探索学习者眼动行为的共性和差异性，为改善视觉内容和给出指导性意见提供重要参考。首先研究在同一任务情况下学习者扫描路径的时间序列表示和聚类，通过聚类结果评估专注、走神及信息迷航等三种学习状态。进而对重心平均动态时间规整（DTW?barycenter averaging，DBA）算法进行改进，并用于提取群体眼动模式，结合动态时间规整（dynamic time warping，DTW）算法计算扫描路径的相似度和确定聚类种子，采用距离密度聚类（distance density clustering，DDC）算法进行聚类。实验表明，基于时间序列的眼动模式挖掘能够识别群体观看行为。而聚类揭示了不同的阅读策略，并提供了评估学习状态的能力。

关键词: 扫描路径, 眼动模式, 学习状态, 重心平均动态时间规整（DBA）, 距离密度聚类（DDC）

Abstract: With the advancement of eye tracking technology and the reduction of equipment costs, eye tracking technology has been widely applied in the field of intelligent education. Therefore, analyzing eye tracking data to evaluate learning status has become a very important part of intelligent education. Eye movement scanpath can reflect thinking pattern and mental state changes directly or indirectly. In this paper, scanpath is analyzed to explore the commonalities and differences of learners’ eye movement behaviors, so as to provide reference for improving visual stimulus and giving guidance. The time series representation and clustering of learners’ scanpath under the same task are studied, and the learning states are evaluated by clustering results, which are divided into three states：concentration, mind-wandering and information wandering. Based on the improved DBA（DTW barycenter averaging） algorithm to extract group eye movement patterns, combined with the DTW（dynamic time warping） algorithm to calculate the similarity and clustering seed of scanpaths, DDC （distance density clustering） algorithm is used to cluster the scanpaths. Experimental results show that eye movement pattern mining based on time series can identify group viewing behavior. Clustering reveals different reading strategies and provides the ability to assess learning status.

Key words: scanpath, eye movement pattern, learning?state, DTW barycenter averaging（DBA）, distance density clustering（DDC）

陈子麟, 战荫伟, 杨卓. 改进DBA算法的眼动模式分析[J]. 计算机工程与应用, 2022, 58(22): 254-261.

CHEN Zilin, ZHAN Yinwei, YANG Zhuo. Eye Movement Pattern Analysis of Improved DBA Algorithm[J]. Computer Engineering and Applications, 2022, 58(22): 254-261.

参考文献

[1] BLASCHECK T，BURCH M，RASCHKE M，et al.Challenges and perspectives in big eye-movement data visual analytics[C]//2015 Big Data Visual Analytics，2015：1-8.
[2] RANDALL J G，OSWALD F L，BEIER M E.Mind-wandering，cognition，and performance：a theory-driven meta-analysis of attention regulation[J].Psychological Bulletin，2014，140（6）：1411-1431.
[3] 程时伟，孙煜杰.面向阅读教学的眼动数据可视化批注方法[J].浙江工业大学学报，2017，45（6）：610-614.
CHENG S，SUN Y.Eye movement data visualization based annotation for reading teaching[J].Journal of Zhejiang University of Technology，2017，45（6）：610-614.
[4] 安璐，李子运.教学PPT背景颜色的眼动实验研究[J].电化教育研究，2012（1）：77-82.
AN L，LI Z Y.Experimental study on eye movement of teaching PPT background color[J].E-education Research，2012（1）：77-82.
[5] MASON L，PLUCHINO P，TORNATORA M C.Using eye-tracking technology as an indirect instruction tool to improve text and picture processing and learning[J].British Journal of Educational Technology，2016，47（6）：1083-1095.
[6] RAHMAN Y，ASISH S M，FISHER N P，et al.Exploring eye gaze visualization techniques for identifying distracted students in educational VR[C]//2020 IEEE Conference on Virtual Reality and 3D User Interfaces，2020.
[7] CONATI C，MERTEN C.Eye-tracking for user modeling in exploratory learning environments：an empirical evaluation[J].Knowledge-Based Systems，2007，20（6）：557-574.
[8] FRAME M E，WARREN R，MARESCA A M.Scanpath comparisons for complex visual search in a naturalistic environment[J].Behavior Research Methods，2019，51：1454-1470.
[9] TABLATIN C L，MA M R.Identifying common code reading patterns using scanpath trend analysis with a tolerance[Z].2018.
[10] ERASLAN S，YESILADA Y.Patterns in eye tracking scanpaths and the affecting factors[J].Journal of Web Engineering，2015，14（5/6）：363-385.
[11] MING J，BOIX X，ROIG G，et al.Learning to predict sequences of human visual fixations[J].IEEE Transactions on Neural Networks & Learning Systems，2016，27（6）：1241-1252.
[12] KURZHALS K，HLAWATSCH M，HEIMERL F，et al.Gaze stripes：image-based visualization of eye tracking data[J].IEEE Transactions on Visualization & Computer Graphics，2016，22（1）：1005-1014.
[13] KUMAR A，TIMMERMANS N，BURCH M，et al.Clustered eye movement similarity matrices[C]//11th ACM Symposium on Eye Tracking Research & Applications，2019.
[14] KUMAR A，NETZEL R，BURCH M，et al.Multi-similarity matrices of eye movement data[C]//2016 IEEE 2nd Workshop on Eye Tracking and Visualization Eye Tracking & Visualization，2016：26-30.
[15] BEHRISCH M，BACH B，RICHE N H，et al.Matrix reordering methods for table and network visualization[J].Computer Graphics Forum，2016，35（3）：693-716.
[16] HOLMQVIST K，NYSTR?M M，ANDERSSON R，et al.Eye tracking：a comprehensive guide to methods and measures[M].Oxford：OUP，2011.
[17] SANTELLA A，DECARLO D.Robust clustering of eye movement recordings for quantification of visual interest[C]//2004 Symposium on Eye Tracking Research & Applications，2004：27-34.
[18] BERNDT D J，CLIFFORD J.Using dynamic time warping to find patterns in time series[C]//KDD Workshop，1994：359-370.
[19] GUPTA L，MOLFESE D L，TAMMANA R，et al.Nonlinear alignment and averaging for estimating the evoked potential[J].IEEE Transactions on Bio-medical Engineering，1996，43（4）：348-356.
[20] NIENNATTRAKUL V，RATANAMAHATANA C A.Shape averaging under time warping[C]//2009 International Conference on Electrical Engineering/Electronics，2009.
[21] PETITJEAN F，KETTERLIN A，GANARSKI P.A global averaging method for dynamic time warping，with applications to clustering[J].Pattern Recognition，2011，44（3）：678-693.
[22] MA R，ANGRYK R A，RILEY P，et al.Coronal mass ejection data clustering and visualization of decision trees[J].The Astrophysical Journal Supplement Series，2018，236（1）：14.
[23] NETZEL R，OHLHAUSEN B，KURZHALS K，et al.User performance and reading strategies for metro maps：an eye tracking study[J].Spatial Cognition and Computation，2016，17（1/2）：39-64.
[24] NEEDLEMAN S B.A general method applicable to the search for similarities in the amino acid sequence of two proteins[J].Journal of Molecular Biology，1970，48（3）：443-453.