地图线状要素眼动识别的朴素贝叶斯方法

doi:10.11947/j.AGCS.2021.20210048

测绘学报 ›› 2021, Vol. 50 ›› Issue (6): 749-756.doi: 10.11947/j.AGCS.2021.20210048

地图线状要素眼动识别的朴素贝叶斯方法

董卫华^1,2, 王圣凯^1,2, 王雪元^1,2, 杨天宇^1,2

1. 北京师范大学地理科学学部, 北京 100875;
2. 北京师范大学地理空间认知与可视分析实验室, 北京 100875

收稿日期:2021-01-22 修回日期:2021-01-25 发布日期:2021-06-28
通讯作者: 王圣凯 E-mail:wangsk@mail.bnu.edu.cn
作者简介:董卫华(1976—),男,教授,研究方向为地理空间认知、地图可视化。E-mail:dongweihua@bnu.edu.cn
基金资助:
国家自然科学基金（41871366）

A naive Bayesian method for eye movement recognition of map linear elements

DONG Weihua^1,2, WANG Shengkai^1,2, WANG Xueyuan^1,2, YANG Tianyu^1,2

1. Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;
2. Research Center of Geospatial Cognition and Visual Analytics, Beijing Normal University, Beijing 100875, China

Received:2021-01-22 Revised:2021-01-25 Published:2021-06-28
Supported by:
The National Natural Science Foundation of China(No. 41871366)

摘要/Abstract

摘要： 眼动追踪技术在人机交互、用户行为识别、预测等方面得到了广泛应用，但是如何自动识别用户的地图阅读行为，眼动行为仍具有一定的挑战性。本文提出了一种基于朴素贝叶斯分类模型的方法识别用户阅读地图线状要素时的眼动行为。本试验首先通过25名被试者阅读地图过程中的眼动行为进行数据采集，然后提取了250个眼动特征并对其进行离散化处理，采用最小冗余最大相关方法进行特征选择排序。结果显示，当采用信息熵法，特征数量为m=5时分类准确率最大为78.27%；而采用信息差法，特征数量为m=4时分类准确率达到最大值为77.01%。本文提出的基于朴素贝叶斯的方法在准确率方面优于已有研究方法。此外，由于特征数量的减少，大幅提高了算法的执行效率。本文提出的地图阅读行为眼动识别方法，为未来眼控交互式地图研究奠定基础。

关键词: 眼动识别, 地图读图行为, 朴素贝叶斯分类器, 特征选择, 最小冗余最大相关

Abstract: At present, eye tracking technology has been widely used in human-computer interaction, user behavior recognition and prediction, but how to automatically identify user’s eye movement behavior in map reading is still a challenge. This paper proposed a method based on the naive Bayesian classification model to identify the users’ behavior when performing linear feature recognition. We first conducted an eye tracking experiment to acquire users’ eye movement dataset of map reading. Then we extracted and discretized 250 eye movement features involved in the algorithm, and used minimum redundancy maximum relevance algorithm to further select the features. The results show that when the attribute selection method is m=5 using mutual information quotient, the classification accuracy is 78.27%. And when using mutual information difference and m=4, the classification accuracy is 77.01%.We suggested that the proposed method can effectively identify the first elements in the map using eye movement data. This study explores the interaction technology by combining the eye tracking, laying the foundation for the future of designing gaze-controlled interactive map. The proposed method based on naive Bayesian model in this paper is comparable to the existing methods. In addition, the execution efficiency of the model is greatly improved due to the reduction in the number of features. The eye-track recognition algorithm of map reading behavior proposed in this study lays a foundation for future gaze-controlled interactive map research.

Key words: eye movement recognition, map reading behavior, naive Bayesian classifier, feature selection, minimum redundancy maximum relevance

中图分类号:

P208

董卫华, 王圣凯, 王雪元, 杨天宇. 地图线状要素眼动识别的朴素贝叶斯方法[J]. 测绘学报, 2021, 50(6): 749-756.

DONG Weihua, WANG Shengkai, WANG Xueyuan, YANG Tianyu. A naive Bayesian method for eye movement recognition of map linear elements[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(6): 749-756.

参考文献

[1] 董卫华, 廖华, 詹智成, 等. 2008年以来地图学眼动与视觉认知研究新进展[J]. 地理学报, 2019, 74(3): 599-614. DONG Weihua, LIAO Hua, ZHAN Zhicheng, et al. New research progress of eye tracking-based map cognition in cartography since 2008[J]. Acta Geographica Sinica, 2019, 74(3): 599-614.
[2] OOMS K, DE MAEYER P, FACK V. Analyzing eye movement patterns to improve map design[C]//Proceedings of the 18th International Research Symposium on Computer-based Cartography and GIScience (AutoCarto 2010). Orlando, FL: Cartography and Geographic Information Society, 2010.
[3] KIEFER P, GIANNOPOULOS I, RAUBAL M. Using eye movements to recognize activities on cartographic maps[C]//Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando, FL: Association for Computing Machinery, 2013: 488-491.
[4] TATEOSIAN L G, GLATZ M, SHUKUNOBE M, et al. GazeGIS: a gaze-based reading and dynamic geographic information system[C]//Proceedings of Workshop on Eye Tracking and Visualization. Chicago, USA: Springer, 2015: 129-147.
[5] GÖBEL F, BAKOGIANNIS N, HENGGELER K, et al. A public Gaze-controlled campus map[M]. Zurich: ETH Zurich, 2018.
[6] MANSON S M, KNE L, DYKE K R, et al. Using eye-tracking and mouse metrics to test usability of web mapping navigation[J]. Cartography and Geographic Information Science, 2012, 39(1): 48-60.
[7] DONG Weihua, LIAO Hua, XU Fang, et al. Using eye tracking to evaluate the usability of animated maps[J]. Science China Earth Sciences, 2014, 57(3): 512-522.
[8] 高俊. 图到用时方恨少, 重绘河山待后生——《测绘学报》60年纪念与前瞻[J]. 测绘学报, 2017, 46(10): 1219-1225. DOI: 10.11947/j.AGCS.2017.20170503. GAO Jun. The 60 anniversary and prospect of Acta Geodaetica et Cartographica Sinica[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1219-1225. DOI: 10.11947/j.AGCS.2017.20170503.
[9] 王家耀. 时空大数据时代的地图学[J]. 测绘学报, 2017, 46(10): 1226-1237. DOI: 10.11947/j.AGCS.2017.20170308. WANG Jiayao. Cartography in the age of spatio-temporal big data[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1226-1237. DOI: 10.11947/j.AGCS.2017.20170308.
[10] EPPLER M J, MENGIS J. The concept of information overload: a review of literature from organization science, accounting, marketing, MIS, and related disciplines[J]. The Information Society, 2004, 20(5): 325-344.
[11] BUNCH R L, LLOYD R E. The cognitive load of geographic information[J]. The Professional Geographer, 2006, 58(2): 209-220.
[12] HARROWER M. The cognitive limits of animated maps[J]. Cartographica: The International Journal for Geographic Information and Geovisualization, 2007, 42(4): 349-357.
[13] JACOB R J K, KARN K S. Eye tracking in human-computer interaction and usability research: ready to deliver the promises[M]//The Mind’s Eye. Amsterdam: Elsevier, 2003: 573-605.
[14] ÇÖLTEKIN A, HEIL B, GARLANDINI S, et al. Evaluating the effectiveness of interactive map interface designs: a case study integrating usability metrics with eye-movement analysis[J]. Cartography and Geographic Information Science, 2009, 36(1): 5-17.
[15] DONG Weihua, WANG Shengkai, CHEN Yizhuou, et al. Using eye tracking to evaluate the usability of flow maps[J]. ISPRS International Journal of Geo-Information, 2018, 7(7): 281.
[16] KIEFER P, GIANNOPOULOS I. Gaze map matching: mapping eye tracking data to geographic vector features[C]//Proceedings of the 20th International Conference on Advances in Geographic Information Systems. Redondo Beach, California: Association for Computing Machinery, 2012: 359-368.
[17] QVARFORDT P, ZHAI Shumin. Conversing with the user based on eye-gaze patterns[C]//Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. Portland, Oregon, USA: Association for Computing Machinery, 2005: 221-230.
[18] LOBBEN A K. Tasks, strategies, and cognitive processes associated with navigational map reading: a review perspective[J]. The Professional Geographer, 2004, 56(2): 270-281.
[19] BULLING A, WARD J A, GELLERSEN H, et al. Eye movement analysis for activity recognition using electrooculography[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 741-753.
[20] PENG Hanchuan, LONG Fuhui, DING C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238.
[21] SALVUCCI D D, GOLDBERG J H. Identifying fixations and saccades in eye-tracking protocols[C]//Proceedings of 2000 Symposium on Eye Tracking Research & Applications. Palm Beach Gardens, Florida, USA: Association for Computing Machinery, 2000: 71-78.
[22] GOLDBERG J H, KOTVAL X P. Computer interface evaluation using eye movements: methods and constructs[J]. International Journal of Industrial Ergonomics, 1999, 24(6): 631-645.
[23] HOLMQVIST K, NYSTRÖM M, ANDERSSON R, et al. Eye tracking: a comprehensive guide to methods and measures[M]. Oxford: Oxford University Press, 2011.
[24] OOMS K, DE MAEYER P, FACK V, et al. Investigating the effectiveness of an efficient label placement method using eye movement data[J]. The Cartographic Journal, 2012, 49(3): 234-246.
[25] LIAO Hua, WANG Xueyuan, DONG Weihua, et al. Measuring the influence of map label density on perceived complexity: a user study using eye tracking[J]. Cartography and Geographic Information Science, 2019, 46(3): 210-227.
[26] ZANGEMEISTER W H, SHERMAN K, STARK L. Evidence for a global scanpath strategy in viewing abstract compared with realistic images[J]. Neuropsychologia, 1995, 33(8): 1009-1025.

地图线状要素眼动识别的朴素贝叶斯方法

A naive Bayesian method for eye movement recognition of map linear elements

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	赵生银, 安如, 朱美如. 联合像元-深度-对象特征的遥感图像城市变化检测[J]. 测绘学报, 2019, 48(11): 1452-1463.
[2]	熊艳, 高仁强, 徐战亚. 机载LiDAR点云数据降维与分类的随机森林方法[J]. 测绘学报, 2018, 47(4): 508-518.
[3]	左志权,张祖勋,张剑清. 一种基于多分辨率拓扑网络的高质量初始图斑对象生成方法[J]. 测绘学报, 2012, 41(1): 65-0.
[4]	虞欣. 贝叶斯网络在航空影像纹理分类中的应用研究[J]. 测绘学报, 2009, 38(4): 0-310.