More Web Proxy on the site http://driver.im/

research-article

DeepVix: Explaining Long Short-Term Memory Network With High Dimensional Time Series Data

Authors:

Rattikorn HewettAuthors Info & Claims

IAIT '20: Proceedings of the 11th International Conference on Advances in Information Technology

Article No.: 38, Pages 1 - 10

https://doi.org/10.1145/3406601.3406643

Published: 03 July 2020 Publication History

Abstract

Machine learning automates the process of analytical model building by means of the computing power of machines. Visual analytics couples interactive visual representations and underlying analysis, putting the human at the center of the analytics and decisionmaking process. This paper aims to combine the strengths of both data science fields into a unified system, called DeepVix, which focuses on the visual explainability of the multivariate time-series predictions using neural networks. Within our DeepVix system, a visual presentation of the neural network explains the intermediate steps, as well as the temporal weights of various gates of the entire learning process. The relationships between input variables and the target variable can also be inferred automatically from the trained model. Interactive operations allow users to explore the neural network, to gain understandings of the model and essential features with layers and nodes, and finally to customize the neural network configurations to fit their needs. We demonstrate our approach with Recurrent Deep Learning on various real-world time series datasets, including the multivariate measurements of a medium-size High-Performance Computing Center, the S&P500 stock data over the past 39 years, and the US employment data retrieved from the Bureau of Labor and Statistics.

References

[1]

Rakesh Agrawal, Johannes Gehrke, Dimitrios Gunopulos, and Prabhakar Raghavan. 1998. Automatic subspace clustering of high dimensional data for data mining applications. In Proceedings of the 1998 ACM SIGMOD international conference on Management of data (Seattle, Washington, USA) (SIGMOD '98). ACM, New York, NY, USA, 94--105. https://doi.org/10.1145/276304.276314

Digital Library

[2]

Nesreen K Ahmed, Amir F Atiya, Neamat El Gayar, and Hisham El-Shishiny. 2010. An empirical comparison of machine learning models for time series forecasting. Econometric Reviews 29, 5-6 (2010), 594--621.

[3]

Sefi Akerman, Edan Habler, and Asaf Shabtai. 2019. VizADS-B: Analyzing Sequences of ADS-B Images Using Explainable Convolutional LSTM Encoder-Decoder to Detect Cyber Attacks. arXiv preprint arXiv:1906.07921 (2019).

[4]

Moustafa Alzantot, Bharathan Balaji, and Mani Srivastava. 2018. Did you hear that? adversarial examples against automatic speech recognition. arXiv preprint arXiv:1801.00554 (2018).

[5]

Jacob Andreas, Marcus Rohrbach, Trevor Darrell, and Dan Klein. 2016. Neural module networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 39--48.

[6]

Roy Assaf and Anika Schumann. 2019. Explainable deep neural networks for multivariate time series predictions. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press, 6488--6490.

[7]

Vahid Behzadan and Arslan Munir. 2017. Vulnerability of deep reinforcement learning to policy induction attacks. In International Conference on Machine Learning and Data Mining in Pattern Recognition. Springer, 262--275.

[8]

Enrico Bertini, Alessio Di Girolamo, and Giuseppe Santucci. 2007. See What You Know: Analyzing Data Distribution to Improve Density Map Visualization. In Eurographics/ IEEE-VGTC Symposium on Visualization, K. Museth, T. Moeller, and A. Ynnerman (Eds.). The Eurographics Association. https://doi.org/10.2312/VisSym/EuroVis07/163-170

[9]

Michael Bostock, Vadim Ogievetsky, and Jeffrey Heer. 2011. D3 Data-Driven Documents. IEEE Trans. Vis. Comput. Graph. 17, 12 (2011), 2301--2309.

Digital Library

[10]

Ines Farber, Andrada Tatu, Daniel Keim, Thomas Seidl, Fabian Maas, Tobias Schreck, and Enrico Bertini. 2012. Subspace Search and Visualization to Make Sense of Alternative Clusterings in High-dimensional Data. In Proceedings of the 2012 IEEE Conference on Visual Analytics Science and Technology (VAST) (VAST '12). IEEE Computer Society, Washington, DC, USA, 63--72. https://doi.org/10.1109/VAST.2012.6400488

Digital Library

[11]

Rui Fu, Zuo Zhang, and Li Li. 2016. Using LSTM and GRU neural network methods for traffic flow prediction. In 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC). IEEE, 324--328.

[12]

Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014).

[13]

Klaus Greff, Rupesh K Srivastava, Jan Koutník, Bas R Steunebrink, and Jürgen Schmidhuber. 2016. LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems 28, 10 (2016), 2222--2232.

[14]

David Gunning. 2017. Explainable artificial intelligence (xai). Defense Advanced Research Projects Agency (DARPA), nd Web 2 (2017).

[15]

Tian Guo, Tao Lin, and Nino Antulov-Fantulin. 2019. Exploring Interpretable LSTM Neural Networks over Multi-Variable Data. arXiv preprint arXiv:1905.12034 (2019).

[16]

Junfeng He, Shih-Fu Chang, Regunathan Radhakrishnan, and Claus Bauer. 2011. Compact hashing with joint optimization of search accuracy and time. In CVPR 2011. IEEE, 753--760.

Digital Library

[17]

Timothy Heeren and Ralph D'Agostino. 1987. Robustness of the two independent samples t-test when applied to ordinal scaled data. Statistics in medicine 6, 1 (1987), 79--90.

[18]

Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.

Digital Library

[19]

Fred Hohman, Haekyu Park, Caleb Robinson, and Duen Horng Chau. 2020. Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations. IEEE Transactions on Visualization and Computer Graphics (TVCG) (2020). https://fredhohman.com/summit/

[20]

Enguerrand Horel and Kay Giesecke. 2019. Towards explainable ai: Significance tests for neural networks. arXiv preprint arXiv:1902.06021 (2019).

[21]

Ronghang Hu, Jacob Andreas, Trevor Darrell, and Kate Saenko. 2018. Explainable neural computation via stack neural module networks. In Proceedings of the European conference on computer vision (ECCV). 53--69.

Digital Library

[22]

Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, and Pieter Abbeel. 2017. Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017).

[23]

E. Isufi, A. Loukas, N. Perraudin, and G. Leus. 2019. Forecasting Time Series With VARMA Recursions on Graphs. IEEE Transactions on Signal Processing 67, 18 (Sep. 2019), 4870--4885. https://doi.org/10.1109/TSP.2019.2929930

Digital Library

[24]

Lahiru Jayasinghe, Tharaka Samarasinghe, Chau Yuen, Jenny Chen Ni Low, and Shuzhi Sam Ge. 2018. Temporal convolutional memory networks for remaining useful life estimation of industrial machinery. arXiv preprint arXiv:1810.05644 (2018).

[25]

Dayhoff J.E. and DeLeo J.M. 2001. Artificial Neural Networks Opening the Black Box. Cancer 91, S8 (2001), 1615--1635. https://doi.org/10.1016/S0967-067X(01)00020-4

[26]

Jobiya John and Sreeja Ashok. 2019. Process Framework for Modeling Multivariate Time Series Data. In Advances in Intelligent Systems and Computing. 577--588. https://doi.org/10.1007/978-981-13-0514-6_56

[27]

Fazle Karim, Somshubra Majumdar, Houshang Darabi, and Shun Chen. 2017. LSTM fully convolutional networks for time series classification. IEEE Access 6 (2017), 1662--1669.

[28]

Keras. 2019. Core Layers - Keras Documentation. https://keras.io/layers/core/.

[29]

Dy D. Le, Vung Pham, Huyen N. Nguyen, and Tommy Dang. 2019. Visualization and Explainable Machine Learning for Efficient Manufacturing and System Operations. Smart and Sustainable Manufacturing Systems 3, 2 (Feb. 2019), 20190029. https://doi.org/10.1520/ssms20190029

[30]

S. Liu, B. Wang, J. J. Thiagarajan, P.-T. Bremer, and V. Pascucci. 2015. Visual Exploration of High-Dimensional Data Through Subspace Analysis and Dynamic Projections. Comput. Graph. Forum 34, 3 (June 2015), 271--280. https://doi.org/10.1111/cgf.12639

[31]

Weibo Liu, Zidong Wang, Xiaohui Liu, Nianyin Zeng, Yurong Liu, and Fuad E Al-saadi.2017. A survey of deep neural network architectures and their applications. Neurocomputing 234 (2017), 11--26.

[32]

Alberto Luceño and Daniel Peña. 2008. Autoregressive Integrated Moving Average (ARIMA) Modeling. American Cancer Society. https://doi.org/10.1002/9780470061572.eqr276 arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/9780470061572.eqr276

[33]

Sheng Ma and J Hellerstein. 1999. Ordering categorical data to improve visualization. INFOVIS-99 (1999).

[34]

Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, and Puneet Agarwal. 2015. Long short term memory networks for anomaly detection in time series. In Proceedings. Presses universitaires de Louvain, 89.

[35]

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard. 2016. Deepfool: a simple and accurate method to fool deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2574--2582.

[36]

Anh Nguyen, Jason Yosinski, and Jeff Clune. 2015. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE conference on computer vision and pattern recognition. 427--436.

[37]

Minh Nguyen, Sanjay Purushotham, Hien To, and Cyrus Shahabi. 2017. m-tsne: A framework for visualizing high-dimensional multivariate time series. arXiv preprint arXiv:1708.07942 (2017).

[38]

Ngan Nguyen and Tommy Dang. 2019. HiperViz: Interactive Visualization of CPU Temperatures in High Performance Computing Centers. In Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (Learning) (Chicago, IL, USA) (PEARC '19). ACM, New York, NY, USA, Article 129, 4 pages. https://doi.org/10.1145/3332186.3337959

Digital Library

[39]

Chris Nicholson. 2019. A Beginner's Guide to LSTMs and Recurrent Neural Networks. Skymind. Saatavissa: https://skymind. ai/wiki/lstm. Hakupäivä 6 (2019), 2019.

[40]

Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z Berkay Celik, and Ananthram Swami. 2016. The limitations of deep learning in adversarial settings. In 2016 IEEE European Symposium on Security and Privacy (EuroS&P). IEEE, 372--387.

[41]

Lance Parsons, Ehtesham Haque, and Huan Liu. 2004. Subspace clustering for high dimensional data: a review. SIGKDD Explor. Newsl. 6, 1 (June 2004), 90--105. https://doi.org/10.1145/1007730.1007731

Digital Library

[42]

Vung Pham and Tommy Dang. 2019. SOAViz: Visualization for Portable X-ray Fluorescence Soil Profiles. In Workshop on Visualisation in Environmental Sciences (EnvirVis), Roxana Bujack, Kathrin Feige, Karsten Rink, and Dirk Zeckzer (Eds.). The Eurographics Association. https://doi.org/10.2312/envirvis.20191102

[43]

V. V. Pham and T. Dang. 2018. MTDES: Multi-dimensional Temporal Data Exploration System; Strong Support for Exploratory Analysis Award in VAST 2018, Mini-Challenge 2. In 2018 IEEE Conference on Visual Analytics Science and Technology (VAST). 100--101. https://doi.org/10.1109/VAST.2018.8802440

[44]

Vasili Ramanishka, Abir Das, Jianming Zhang, and Kate Saenko. 2017. Top-down visual saliency guided by captions. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 2017-January (2017), 3135--3144. https://doi.org/10.1109/CVPR.2017.334

[45]

Mahdi Soltanolkotabi, Ehsan Elhamifar, and Emmanuel J. Candès. 2013. Robust Subspace Clustering. CoRR abs/1301.2603 (2013). http://arxiv.org/abs/1301.2603

[46]

Daniel Soutner and Luděk Müller. 2013. Application of LSTM neural networks in language modelling. In International Conference on Text, Speech and Dialogue. Springer, 105--112.

[47]

Jiawei Su, Danilo Vasconcellos Vargas, and Kouichi Sakurai. 2019. One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation (2019).

[48]

Daniel Svozil, Vladimir Kvasnicka, and Jiri Pospichal. 1997. Introduction to multilayer feed-forward neural networks. Chemometrics and intelligent laboratory systems 39, 1 (1997), 43--62.

[49]

Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013).

[50]

Tensorflow Playground. 2017. A Neural Network Playground. https://playground.tensorflow.org/.

[51]

Dan Tsafrir, Ilan Tsafrir, Liat Ein-Dor, Or Zuk, Daniel A Notterman, and Eytan Domany. 2005. Sorting points into neighborhoods (SPIN): data analysis and visualization by ordering distance matrices. Bioinformatics 21, 10 (2005), 2301--2308.

Digital Library

[52]

Joel Vaughan, Agus Sudjianto, Erind Brahimi, Jie Chen, and Vijayan N Nair. 2018. Explainable neural networks based on additive index models. arXiv preprint arXiv:1806.01933 (2018).

[53]

X. Wang, A. Wirth, and L. Wang. 2007. Structure-Based Statistical Features and Multivariate Time Series Clustering. In Seventh IEEE International Conference on Data Mining (ICDM 2007). 351--360. https://doi.org/10.1109/ICDM.2007.103

Digital Library

[54]

Peter R. Winters. 1960. Forecasting Sales by Exponentially Weighted Moving Averages. Management Science (1960). https://doi.org/10.1287/mnsc.6.3.324

Digital Library

[55]

Svante Wold, Kim Esbensen, and Paul Geladi. 1987. Principal component analysis. Chemometrics and intelligent laboratory systems 2, 1-3 (1987), 37--52.

[56]

Yahoo Finance. 2019. S&P 500 (GSPC). https://finance.yahoo.com/quote/%5EGSPC.

[57]

Chao-Lung Yang, Chen-yi Yang, Zhi-xuan Chen, and Nai-wei Lo. 2019. Multivariate Time Series Data Transformation for Convolutional Neural Network. In 2019 IEEE/SICE International Symposium on System Integration (SII). IEEE, 188--192. https://doi.org/10.1109/SII.2019.8700425

[58]

Jianfeng Zhang, Yan Zhu, Xiaoping Zhang, Ming Ye, and Jinzhong Yang. 2018. Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas. Journal of hydrology 561 (2018), 918--929.

Cited By

Alicioglu GSun B(2024)Visual Analytics in Explaining Neural Networks with Neuron ClusteringAI10.3390/ai50200235:2(465-481)Online publication date: 5-Apr-2024
https://doi.org/10.3390/ai5020023
Das Antar AMolaei SChen YLee MBanovic N(2024)VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-MakingProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology10.1145/3654777.3676323(1-21)Online publication date: 13-Oct-2024
https://dl.acm.org/doi/10.1145/3654777.3676323
Adebisi OAfolayan AAyoade IAdejumobi PAdejumobi I(2024)Integration of Deep Learning Techniques in Mechatronic Devices and Systems: Advancement, Challenges, and Opportunities2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG)10.1109/SEB4SDG60871.2024.10630414(1-6)Online publication date: 2-Apr-2024
https://doi.org/10.1109/SEB4SDG60871.2024.10630414
Show More Cited By

Index Terms

DeepVix: Explaining Long Short-Term Memory Network With High Dimensional Time Series Data
1. Human-centered computing
  1. Visualization
    1. Visualization application domains
      1. Information visualization

Recommendations

Weather analysis using ensemble of connectionist learning paradigms

This paper presents a comparative analysis of different connectionist and statistical models for forecasting the weather of Vancouver, Canada. For developing the models, one year's data comprising of daily temperature and wind speed were used. A multi-...
Intelligent weather monitoring systems using connectionist models

This paper presents a comparative study of different neural network models for forecasting the weather of Vancouver, British Columbia, Canada. For developing the models, we used one years data comprising of daily maximum and minimum temperature, and ...
Performance comparison of artificial neural network models for daily rainfall prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network (BPN), cascade-forward back propagation neural network (CBPN), distributed time delay neural ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

IAIT '20: Proceedings of the 11th International Conference on Advances in Information Technology

July 2020

370 pages

ISBN:9781450377591

DOI:10.1145/3406601

General Chair:
K. Porkaew,
Program Chairs:
M. Chignell,
S. Fong,
B. Watanapa

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Microsoft Corporation: Microsoft Corporation
NECTEC: National Electronics and Computer Technology Center
KMUTT: King Mongkut's University of Technology Thonburi

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 03 July 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article
Research
Refereed limited

Conference

IAIT2020

IAIT2020: The 11th International Conference on Advances in Information Technology

July 1 - 3, 2020

Bangkok, Thailand

Acceptance Rates

Overall Acceptance Rate 20 of 47 submissions, 43%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
279
Total Downloads

Downloads (Last 12 months)57
Downloads (Last 6 weeks)4

Reflects downloads up to 20 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Alicioglu GSun B(2024)Visual Analytics in Explaining Neural Networks with Neuron ClusteringAI10.3390/ai50200235:2(465-481)Online publication date: 5-Apr-2024
https://doi.org/10.3390/ai5020023
Das Antar AMolaei SChen YLee MBanovic N(2024)VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-MakingProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology10.1145/3654777.3676323(1-21)Online publication date: 13-Oct-2024
https://dl.acm.org/doi/10.1145/3654777.3676323
Adebisi OAfolayan AAyoade IAdejumobi PAdejumobi I(2024)Integration of Deep Learning Techniques in Mechatronic Devices and Systems: Advancement, Challenges, and Opportunities2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG)10.1109/SEB4SDG60871.2024.10630414(1-6)Online publication date: 2-Apr-2024
https://doi.org/10.1109/SEB4SDG60871.2024.10630414
Hussain STeni AHussain IHussain ZPallonetto FEichman JIrshad RAlwayle IAlharby MHussain MZia MKim Y(2024)Enhancing electric vehicle charging efficiency at the aggregator level: A deep-weighted ensemble model for wholesale electricity price forecastingEnergy10.1016/j.energy.2024.132823(132823)Online publication date: Aug-2024
https://doi.org/10.1016/j.energy.2024.132823
Nguyen HAbri FPham VChatterjee MNamin ADang T(2022)MalView: Interactive Visual Analytics for Comprehending Malware BehaviorIEEE Access10.1109/ACCESS.2022.320778210(99909-99930)Online publication date: 2022
https://doi.org/10.1109/ACCESS.2022.3207782
Theissler ASpinnato FSchlegel UGuidotti R(2022)Explainable AI for Time Series Classification: A Review, Taxonomy and Research DirectionsIEEE Access10.1109/ACCESS.2022.320776510(100700-100724)Online publication date: 2022
https://doi.org/10.1109/ACCESS.2022.3207765
Alicioglu GSun B(2022)A survey of visual analytics for Explainable Artificial Intelligence methodsComputers and Graphics10.1016/j.cag.2021.09.002102:C(502-520)Online publication date: 1-Feb-2022
https://dl.acm.org/doi/10.1016/j.cag.2021.09.002
Musleh MChatzimparmpas AJusufi I(2022)Visual analysis of blow molding machine multivariate time series dataJournal of Visualization10.1007/s12650-022-00857-425:6(1329-1342)Online publication date: 1-Dec-2022
https://dl.acm.org/doi/10.1007/s12650-022-00857-4
Narkhede PWalambe RPoddar SKotecha K(2021)Incremental learning of LSTM framework for sensor fusion in attitude estimationPeerJ Computer Science10.7717/peerj-cs.6627(e662)Online publication date: 4-Aug-2021
https://doi.org/10.7717/peerj-cs.662
Dang TNguyen HNguyen N(2021)VixLSTM: Visual Explainable LSTM for Multivariate Time SeriesProceedings of the 12th International Conference on Advances in Information Technology10.1145/3468784.3471603(1-5)Online publication date: 29-Jun-2021
https://dl.acm.org/doi/10.1145/3468784.3471603
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents