Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2024, Vol. 58 Issue (2): 239-246    DOI: 10.3785/j.issn.1008-973X.2024.02.002
计算机技术、通信技术     
基于迁移学习的交互时序数据可视化生成方法
周姿含1(),王叙萌2,陈为1,3,*()
1. 浙江大学 CAD & CG国家重点实验室，浙江 杭州 310058
2. 南开大学 计算机科学与技术系，天津 300350
3. 教育部 浙江大学艺术与考古图像数据实验室，浙江 杭州 310058
Interactive visualization generation method for time series data based on transfer learning
Zihan ZHOU1(),Xumeng WANG2,Wei CHEN1,3,*()
1. State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou 310058, China
2. College of Computer Science, Nankai University, Tianjin 300350, China
3. Laboratory of Art and Archaeology Image, Zhejiang University, Ministry of Education, Hangzhou 310058, China
 全文: PDF(2239 KB)   HTML
摘要：

为了解决时序数据间分布不一致的问题，使模式分析更容易应用于其他数据,提出基于迁移学习的交互式时序数据可视化生成方法, 将迁移成分分析应用于时序数据提取的特征. 将用户在其中一个时序数据上的分析作为标签, 在该源域上训练分类器并应用到多个目标域, 对多个不同目标域的时序数据的模式进行批量推荐. 通过真实的天气数据和轴承信号数据的2个案例分析和专家访谈, 验证了利用该方法能够提高时序数据探索的效率，减少数据分布不一致问题带来的影响, 体现该方法的有效性和实用性.
关键词： 交互式可视化生成;  迁移学习;  时序数据可视分析;  模式推荐    
Abstract:

An interactive visualization generation method for time series data based on transfer learning was proposed in order to address the inconsistency in data distribution across time-series data and facilitate the application of pattern analysis to other data. Transfer component analysis was applied to transfer features extracted from each time series data. The user’s analysis on one of the time series data served as labels. The classifier was trained on the source domain and applied to multiple target domains in order to achieve pattern recommendations. Two case studies and expert interviews with real-world weather data and bearing signal data were conducted to verify the effectiveness and practicality of the method by improving the efficiency of temporal data exploration and reducing the impact of inconsistent data distribution.
Key words: interactive visualization generation    transfer learning    time series data visual analysis    pattern recommendation
收稿日期: 2023-06-30 出版日期: 2024-01-23
CLC:  TP 391  
基金资助: 国家自然科学基金资助项目(62132017)； 中央高校基本科研业务费专项资助项目(226-2022-00235)
通讯作者: 陈为     E-mail: zhouzihan@zju.edu.cn;chenvis@zju.edu.cn
作者简介: 周姿含（1999—），女，博士生，从事可视分析的研究. orcid.org/0000-0003-2735-4952. E-mail：zhouzihan@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
周姿含
王叙萌
陈为

引用本文:

周姿含,王叙萌,陈为. 基于迁移学习的交互时序数据可视化生成方法[J]. 浙江大学学报(工学版), 2024, 58(2): 239-246.

Zihan ZHOU,Xumeng WANG,Wei CHEN. Interactive visualization generation method for time series data based on transfer learning. Journal of ZheJiang University (Engineering Science), 2024, 58(2): 239-246.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.02.002    或    https://www.zjujournals.com/eng/CN/Y2024/V58/I2/239

图 1  迁移成分分析的示意图
图 2  所提方法的系统流程图
图 3  时序数据可视分析系统的界面概览
图 4  轴承信号数据的t-SNE投影比较
1 WONGSUPHASAWAT K, GOMEZ J A G, PLAISANT C, et al. LifeFlow: visualizing an overview of event sequences [C]//Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. Vancouver: ACM, 2011: 1747-1756.
2 TULI S, CASALE G, JENNINGS N R TranAD: deep transformer networks for anomaly detection in multivariate time series data[J]. Proceedings of Very Large Data Base, 2022, 15 (6): 1201- 1204
3 FANG Y, XU H, JIANG J. A survey of time series data visualization research [C]//Proceedings of IOP Conference Series: Materials Science and Engineering. [S. l.]: IOP, 2020: 022013.
4 WALKER J S, JONES M W, LARAMEE R S, et al TimeClassifier: a visual analytic system for the classification of multi-dimensional time series data[J]. The Visual Computer, 2015, 31 (6-8): 1067- 1078
doi: 10.1007/s00371-015-1112-0
5 HAO M C, MARWAH M, JANETZKO H, et al Visual exploration of frequent patterns in multivariate time series[J]. Information Visualization, 2012, 11 (1): 71- 83
doi: 10.1177/1473871611430769
6 WALKER J, BORGO R, JONES M W TimeNotes: a study on effective chart visualization and interaction techniques for time-series data[J]. IEEE Transactions on Visualization and Computer Graphics, 2015, 22 (1): 549- 558
7 TOMINSKI C, SCHUMANN H. Enhanced interactive spiral display [C]//Proceedings of the Annual Swedish Chapter of Eurogaphics Conference. Sweden: Linköping University Electronic Press, 2008: 53-56.
8 SOBRAL T, GALVÃO T, BORGES J Visualization of urban mobility data from intelligent transportation systems[J]. Sensors, 2019, 19 (2): 332
doi: 10.3390/s19020332
9 HAIGH K Z, FOSLIEN W, GURALNIK V. Visual query language: finding patterns in and relationships among time series data [C]//7th Workshop on Mining Scientific and Engineering Datasets. [S. l.]: Citeseer, 2004: 324-332.
10 SADAHIRO Y, KOBAYASHI T Exploratory analysis of time series data: detection of partial similarities, clustering, and visualization[J]. Computers, Environment and Urban Systems, 2014, 45: 24- 33
11 ALI M, JONES M W, XIE X, et al TimeCluster: dimension reduction applied to temporal data for visual analytics[J]. The Visual Computer, 2019, 35 (6-8): 1013- 1026
doi: 10.1007/s00371-019-01673-y
12 GHASSEMPOUR S, GIROSI F, MAEDER A Clustering multivariate time series using hidden Markov models[J]. International Journal of Environmental Research and Public Health, 2014, 11 (3): 2741- 2763
doi: 10.3390/ijerph110302741
13 AGHABOZORGI S, YING WAH T, HERAWAN T, et al A hybrid algorithm for clustering of time series data based on affinity search technique[J]. The Scientific World Journal, 2014, 2014 (1): 562194
14 LI J, ZHOU C Incorporation of human knowledge into data embeddings to improve pattern significance and interpretability[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 29 (1): 723- 733
15 YANG Q F, GAO W Y, HAN G, et al HCDC: a novel hierarchical clustering algorithm based on density-distance cores for data sets with varying density[J]. Information Systems, 2023, 114: 102159
doi: 10.1016/j.is.2022.102159
16 KEOGH E J, PAZZANI M J. An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback [C]// Knowledge Discovery and Data Mining. New York: AAAI, 1998: 239-243.
17 FAHAD S, SU F, KHAN S U, et al Implementing a novel deep learning technique for rainfall forecasting via climatic variables: an approach via hierarchical clustering analysis[J]. Science of the Total Environment, 2023, 854: 158760
doi: 10.1016/j.scitotenv.2022.158760
18 RODRIGUES P P, GAMA J, PEDROSO J Hierarchical clustering of time-series data streams[J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20 (5): 615- 627
doi: 10.1109/TKDE.2007.190727
19 MA Q, LI S, ZHUANG W, et al Self-supervised time series clustering with model-based dynamics[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32 (9): 3942- 3955
20 DEMPSTER A, PETITJEAN F, WEBB G I ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels[J]. Data Mining and Knowledge Discovery, 2020, 34 (5): 1454- 1495
doi: 10.1007/s10618-020-00701-z
21 YALÇIN M A, ELMQVIST N, BEDERSON B B Keshif: rapid and expressive tabular data exploration for novices[J]. IEEE Transactions on Visualization and Computer Graphics, 2017, 24 (8): 2339- 2352
22 WONGSUPHASAWAT K, QU Z, MORITZ D, et al. Voyager 2: augmenting visual analysis with partial view specifications [C]//Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Denver: ACM, 2017: 2648-2659.
23 REN D, LEE B, BREHMER M Charticulator: interactive construction of bespoke chart layouts[J]. IEEE Transactions on Visualization and Computer Graphics, 2018, 25 (1): 789- 799
24 PIOCH N J, EVERETT J O. Polestar: collaborative knowledge management and sensemaking tools for intelligence analysts [C]//Proceedings of the 15th ACM International Conference on Information and Knowledge Management. Virginia: ACM, 2006: 513-521.
25 SATYANARAYAN A, HEER J Lyra: an interactive visualization design environment[J]. Computer Graphics Forum, 2014, 33 (3): 351- 360
doi: 10.1111/cgf.12391
26 REN D, HÖLLERER T, YUAN X iVisDesigner: expressive interactive design of information visualizations[J]. IEEE Transactions on Visualization and Computer Graphics, 2014, 20 (12): 2092- 2101
doi: 10.1109/TVCG.2014.2346291
27 WANG Y, ZHANG H, HUANG H, et al. InfoNice: easy creation of information graphics [C]//Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Montreal: ACM, 2018: 1-12.
28 XIA H, HENRY RICHE N, CHEVALIER F, et al. DataInk: direct and creative data-oriented drawing [C]// Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Montreal: ACM, 2018: 1-13.
29 VARTAK M, RAHMAN S, MADDEN S, et al. SeeDB: efficient data-driven visualization recommendations to support visual analytics [C]//Proceedings of the VLDB Endowment International Conference on Very Large Data Bases. Hawaii: VLDB Endowment, 2015: 2182-2193.
30 WANG Y, SUN Z, ZHANG H, et al DataShot: automatic generation of fact sheets from tabular data[J]. IEEE Transactions on Visualization and Computer Graphics, 2019, 26 (1): 895- 905
31 DEMIRALP Ç, HAAS P J, PARTHASARATHY S, et al. Foresight: recommending visual insights [C]// Proceedings of the VLDB Endowment International Conference on Very Large Data Bases. Munich: VLDB Endowment, 2017: 1937-1940.
32 QIAN C, SUN S, CUI W, et al Retrieve-then-adapt: example-based automatic generation for proportion-related infographics[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27 (2): 443- 452
doi: 10.1109/TVCG.2020.3030448
33 SHI D, XU X, SUN F, et al Calliope: automatic visual data story generation from a spreadsheet[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27 (2): 453- 463
doi: 10.1109/TVCG.2020.3030403
34 BORGWARDT K M, GRETTON A, RASCH M J, et al Integrating structured biological data by kernel maximum mean discrepancy[J]. Bioinformatics, 2006, 22 (14): 49- 57
doi: 10.1093/bioinformatics/btl242
35 PAN S J, TSANG I W, KWOK J T, et al Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Networks, 2010, 22 (2): 199- 210
36 CARROLL M L, BROWN M E, WOOTEN M R, et al In situ air temperature and humidity measurements over diverse land covers in Greenbelt, Maryland, november 2013–november 2015[J]. Earth System Science Data, 2016, 8 (2): 415- 423
doi: 10.5194/essd-8-415-2016
[1] 华夏,王新晴,芮挺,邵发明,王东. 视觉感知的无人机端到端目标跟踪控制技术[J]. 浙江大学学报(工学版), 2022, 56(7): 1464-1472.
[2] 高一聪,王彦坤,费少梅,林琼. 基于迁移学习的机械制图智能评阅方法[J]. 浙江大学学报(工学版), 2022, 56(5): 856-863, 889.
[3] 付晓峰,牛力. 基于深度卷积和自编码器增强的微表情判别[J]. 浙江大学学报(工学版), 2022, 56(10): 1948-1957.
[4] 陈智超,焦海宁,杨杰,曾华福. 基于改进MobileNet v2的垃圾图像分类算法[J]. 浙江大学学报(工学版), 2021, 55(8): 1490-1499.
[5] 康庄,杨杰,郭濠奇. 基于机器视觉的垃圾自动分类系统设计[J]. 浙江大学学报(工学版), 2020, 54(7): 1272-1280.
[6] 沈宗礼,余建波. 基于迁移学习与深度森林的晶圆图缺陷识别[J]. 浙江大学学报(工学版), 2020, 54(6): 1228-1239.
[7] 付晓峰,牛力,胡卓群,李建军,吴卿. 基于过渡帧概念训练的微表情检测深度网络[J]. 浙江大学学报(工学版), 2020, 54(11): 2128-2137.