Daily behavior prediction of college students on campus based on multifragment semantic spatiotemporal graph convolutional network

YU Hongwei; ZHOU Dongbo; XU Wenhui; YU Yaying; WANG Xiaomei; TU Yue

doi:10.16511/j.cnki.qhdxxb.2021.21.041

PDF(6020 KB)

Journal of Tsinghua University(Science and Technology) ›› 2022, Vol. 62 ›› Issue (1) : 105-115. DOI: 10.16511/j.cnki.qhdxxb.2021.21.041

SPECIAL SECTION:SOCIAL MEDIA PROCESSING

Daily behavior prediction of college students on campus based on multifragment semantic spatiotemporal graph convolutional network

{{article.zuoZhe_EN}}

Author information +

History +

Abstract

Shallow algorithms of mining and learning such as statistics, clustering, and association relationships are generally used in current research on the prediction and mining of college students' daily behaviors on campus, and there is a lack of in-depth and high-level analysis of the applications in time series, spatial location, and correlation of students' behaviors on campus. Based on the network structure of spatio-temporal graphs, this paper proposes a multifragment semantic spatiotemporal graph convolutional network (MFSTGCN) model that considers the time series of campus activities and the correlation between hierarchy and spatial semantic features. By constructing a data set of college students' campus behaviors and conducting experiments, the model in this paper achieves 90.4% behavior prediction accuracy, which is better than typical prediction models. Finally, we provide students with early warning of abnormal daily behaviors to monitor students' individual growth and excavate high-level information such as student's behaviors and habits to provide a meaningful reference for the construction of personalized education.

Key words

campus activity data / graph convolutional network / spatiotemporal data mining / behavior prediction / abnormal behavior / behavior habit

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

YU Hongwei, ZHOU Dongbo, XU Wenhui, YU Yaying, WANG Xiaomei, TU Yue. Daily behavior prediction of college students on campus based on multifragment semantic spatiotemporal graph convolutional network[J]. Journal of Tsinghua University(Science and Technology). 2022, 62(1): 105-115 https://doi.org/10.16511/j.cnki.qhdxxb.2021.21.041

References

[1] 李有增, 曾浩. 基于学生行为分析模型的高校智慧校园教育大数据应用研究[J]. 中国电化教育, 2018(7):33-38. LI Y Z, ZENG H. Smart campus big data education application based on students' behavior analysis model[J]. China Educational Technology, 2018(7):33-38.(in Chinese)
[2] 杨倍倍, 曲英杰, 王金鑫. 基于移动数据和时间地理学的大学生行为模式构建与分析[J]. 地理信息世界, 2018, 25(1):77-81. YANG B B, QU Y J, WANG J X. Construction and analysis of college students' behavior patterns based on mobile data and time geography[J]. Geomatics World, 2018, 25(1):77-81. (in Chinese)
[3] 崔聪, 涂庆华, 束乾倩, 等. 基于大数据的高校安全与维稳系统设计与实践[J]. 中国教育信息化, 2020(3):61-65. CUI C, TU Q H, SHU Q Q, et al. Design and practice of university security and stability system based on big data[J]. The Chinese Journal of ICT in Education, 2020(3):61-65. (in Chinese)
[4] 郑庆华, 董博, 钱步月, 等. 智慧教育研究现状与发展趋势[J]. 计算机研究与发展, 2019, 56(1):209-224. ZHENG Q H, DONG B, QIAN B Y, et al. The state of the art and future tendency of smart education[J]. Journal of Computer Research and Development, 2019, 56(1):209-224. (in Chinese)
[5] 武法提, 黄石华. 基于多源数据融合的共享教育数据模型研究[J]. 电化教育研究, 2020, 41(5):59-65. WU F T, HUANG S H. Research on shared education data model based on multi-source data fusion[J]. e-Education Research, 2020, 41(5):59-65. (in Chinese)
[6] 李宇帆, 张会福, 刘上力, 等. 教育数据挖掘研究进展[J]. 计算机工程与应用, 2019, 55(14):15-23. LI Y F, ZHANG H F, LIU S L, et al. Research progress on educational data mining[J]. Computer Engineering and Applications, 2019, 55(14):15-23. (in Chinese)
[7] ALYAHYAN E, DüŞTEGöR D. Predicting academic success in higher education:Literature review and best practices[J]. International Journal of Educational Technology in Higher Education, 2020, 17(1):3.
[8] 朱天宇, 黄振亚, 陈恩红, 等. 基于认知诊断的个性化试题推荐方法[J]. 计算机学报, 2017, 40(1):176-191. ZHU T Y, HUANG Z Y, CHEN E H, et al. Cognitive diagnosis based personalized question recommendation[J]. Chinese Journal of Computers, 2017, 40(1):176-191. (in Chinese)
[9] TOMASEVIC N, GVOZDENOVIC N, VRANES S. An overview and comparison of supervised data mining techniques for student exam performance prediction[J]. Computers & Education, 2020, 143:103676.
[10] 孔啸, 刘乃嘉, 张梦豪, 等. COVID-19疫情前后高校在线教学数据分析[J]. 清华大学学报(自然科学版), 2021, 61(2):104-116. KONG X, LIU N J, ZHANG M H, et al. Analysis of online college teaching data before and after the COVID-19 epidemic[J]. Journal of Tsinghua University (Science and Technology), 2021, 61(2):104-116. (in Chinese)
[11] MENGASH H A. Using data mining techniques to predict student performance to support decision making in university admission systems[J]. IEEE Access, 2020, 8:55462-55470.
[12] YE H J, ZHAN D C, LI X L, et al. College student scholarships and subsidies granting:A multi-modal multi-label approach[C]//Proceedings of the 16th International Conference on Data Mining. Barcelona, Spain:IEEE Press, 2016:559-568.
[13] HANG M, PYTLARZ I, NEVILLE J. Exploring student check-in behavior for improved point-of-interest prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY, USA:ACM, 2018:321-330.
[14] 王德, 谢栋灿, 王灿, 等. 个体时空行为的规律性与可预测性研究——以上海市居民工作日活动为例[J]. 地理科学进展, 2021, 40(3):433-440. WANG D, XIE D C, WANG C, et al. Regularity and predictability of individual spatiotemporal behavior:A case study ofresidents working day activities in Shanghai[J]. Progress in Geography, 2021, 40(3):433-440. (in Chinese)
[15] SONG C M, QU Z H, BLUMM N, et al. Limits of predictability in human mobility[J]. Science, 2010, 327(5968):1018-1021.
[16] ABIDINE M B, FERGANI B. Evaluating C-SVM, CRF and LDA classification for daily activity recognition[C]//Proceedings of the 2012 International Conference on Multimedia Computing and Systems. Tangiers, Morocco:IEEE Press, 2012:272-277.
[17] TRABELSI D, MOHAMMED S, CHAMROUKHI F, et al. An unsupervised approach for automatic activity recognition based on hidden markov model regression[J]. IEEE Transactions on Automation Science and Engineering, 2013, 10(3):829-835.
[18] RONAO C A, CHO S B. Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models[C]//Proceedings of the 10th International Conference on Natural Computation. Xiamen, China:IEEE Press, 2014:681-686.
[19] RONAO C A, CHO S B. Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models[J]. International Journal of Distributed Sensor Networks, 2017, 13(1):1-16.
[20] ZHANG J B, ZHENG Y, QI D K, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018, 259:147-166.
[21] NIEPERT M, AHMED M, KUTZKOV K. Learning convolutional neural networks for graphs[C]//Proceedings of the 33rd International Conference on Machine Learning. New York, NY, USA:JMLR, 2016:2014-2023.
[22] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and locally connected networks on graphs[C]//Proceedings of the 2nd International Conference on Learning Representations. Banff, AB, Canada:IEEE Press, 2014:1-14.
[23] YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks:A deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden:Morgan Kaufmann, 2018:3634-3640.
[24] GUO S N, LIN Y F, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting forecasting[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA:AAAI, 2019:922-929.
[25] SONG C, LIN Y F, GUO S N, et al. Spatial-temporal synchronous graph convolutional networks:A new framework for spatial-temporal network data forecasting[C]//Proceedings of the 34rd AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA:AAAI, 2020:914-921.
[26] 骆歆远, 陈欣, 寿黎但, 等. 面向室内空间的语义轨迹提取框架[J]. 清华大学学报(自然科学版), 2019, 59(3):186-193. LUO X Y, CHEN X, SHOU L D, et al. Semantic trajectory extraction framework for indoor space[J]. Journal of Tsinghua University(Science and Technology), 2019, 59(3):186-193. (in Chinese)
[27] 周涛, 韩筱璞, 闫小勇, 等. 人类行为时空特性的统计力学[J]. 电子科技大学学报, 2013, 42(4):481-540. ZHOU T, HAN X P, YAN X Y, et al. Statistical mechanics on temporal and spatial activities of human[J]. Journal of University of Electronic Science and Technology of China, 2013, 42(4):481-540. (in Chinese)
[28] DE MONTJOYE Y A, RADAELLI L, SINGH V K, et al. Unique in the shopping mall:On the reidentifiability of credit card metadata[J]. Science, 2015, 347(6221):536-539.
[29] LALLY P, VAN JAARSVELD C H M, POTTS H W W, et al. How are habits formed:Modelling habit formation in the real world[J]. European Journal of Social Psychology, 2010, 40(6):998-1009.
[30] NEAL D T, WOOD W, QUINN J M. Habits-A repeat performance[J]. Current Directions in Psychological Science, 2006, 15(4):198-202.