Yuheng Guo
ABSTRACT
This paper performs a comprehensive evaluation of Smartwatch in-air signature classification based on multiple deep learning models. We leverage the Shapley value in dimension-wise feature selection to provide the in-air signature community with the most and least dominant dimension regarding the accuracy of in-air signature classification. Our experiment results highlight InceptionTime as the top-performing model, achieving an accuracy of 97.73%. Through our Shapley Value analysis, among all the sensors embedded in the Smartwatch, we find that the y dimension of the gyroscope and the z dimension of the gyroscope contribute the most to classification accuracy with 12.57% and 12.51% respectively, while the x dimension of the accelerometer produces the least contribution with 8.71%.
- Abien Fred Agarap. 2018. Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375 (2018).Google Scholar
- Gonzalo Bailador, Carmen Sanchez-Avila, Javier Guerra-Casanova, and Alberto de Santos Sierra. 2011. Analysis of pattern recognition techniques for in-air signature biometrics. Pattern Recognition 44, 10-11 (2011), 2468–2478.Google ScholarDigital Library
- Mustafa Gokce Baydogan and George Runger. 2016. Time series representation and similarity based on local autopatterns. Data Mining and Knowledge Discovery 30 (2016), 476–509.Google ScholarDigital Library
- Donald J Berndt and James Clifford. 1994. Using dynamic time warping to find patterns in time series. In Proceedings of the 3rd international conference on knowledge discovery and data mining. 359–370.Google ScholarDigital Library
- Attaullah Buriro, Bruno Crispo, Filippo Delfrari, and Konrad Wrona. 2016. Hold and sign: A novel behavioral biometrics for smartphone user authentication. In 2016 IEEE security and privacy workshops (SPW). IEEE, 276–285.Google Scholar
- Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine learning 20 (1995), 273–297.Google Scholar
- Hoang Anh Dau, Eamonn Keogh, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, Yanping, Bing Hu, Nurjahan Begum, Anthony Bagnall, Abdullah Mueen, Gustavo Batista, and Hexagon-ML. 2018. The UCR Time Series Classification Archive. https://www.cs.ucr.edu/ eamonn/time_series_data_2018/.Google Scholar
- Evelyn Fix and Joseph Lawson Hodges. 1989. Discriminatory analysis. Nonparametric discrimination: Consistency properties. International Statistical Review/Revue Internationale de Statistique 57, 3 (1989), 238–247.Google ScholarCross Ref
- Claudio Gallicchio and Simone Scardapane. 2020. Deep Randomized Neural Networks. CoRR abs/2002.12287 (2020). arXiv:2002.12287https://arxiv.org/abs/2002.12287Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision. 1026–1034.Google ScholarDigital Library
- Tin Kam Ho. 1995. Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition, Vol. 1. IEEE, 278–282.Google Scholar
- Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arxiv:1502.03167 [cs.LG]Google Scholar
- Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, and Pierre-Alain Muller. 2019. Deep learning for time series classification: a review. Data mining and knowledge discovery 33, 4 (2019), 917–963.Google ScholarDigital Library
- Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier, Charlotte Pelletier, Daniel F Schmidt, Jonathan Weber, Geoffrey I Webb, Lhassane Idoumghar, Pierre-Alain Muller, and François Petitjean. 2020. Inceptiontime: Finding alexnet for time series classification. Data Mining and Knowledge Discovery 34, 6 (2020), 1936–1962.Google ScholarDigital Library
- Gen Li and Hiroyuki Sato. 2022. Sensing In-Air Signature Motions Using Smartwatch: A High-Precision Approach of Behavioral Authentication. IEEE Access 10 (2022), 57865–57879. https://doi.org/10.1109/ACCESS.2022.3177905Google ScholarCross Ref
- Jameel Malik, Ahmed Elhayek, Suparna Guha, Sheraz Ahmed, Amna Gillani, and Didier Stricker. 2020. DeepAirSig: End-to-End Deep Learning Based in-Air Signature Verification. IEEE Access 8 (2020), 195832–195843. https://doi.org/10.1109/ACCESS.2020.3033848Google ScholarCross Ref
- Abdulhalık Oğuz and Ömer Faruk Ertuğrul. 2022. Human identification based on accelerometer sensors obtained by mobile phone data. Biomedical signal processing and control 77 (2022), 103847.Google Scholar
- L. Rabiner and B. Juang. 1986. An introduction to hidden Markov models. IEEE ASSP Magazine 3, 1 (1986), 4–16. https://doi.org/10.1109/MASSP.1986.1165342Google ScholarCross Ref
- Frank Rosenblatt. 1957. The perceptron, a perceiving and recognizing automaton Project Para. Cornell Aeronautical Laboratory.Google Scholar
- Benedek Rozemberczki, Lauren Watson, Péter Bayer, Hao-Tsung Yang, Olivér Kiss, Sebastian Nilsson, and Rik Sarkar. 2022. The Shapley Value in Machine Learning. arxiv:2202.05594 [cs.LG]Google Scholar
- Baljit Singh Saini, Parminder Singh, Anand Nayyar, Navdeep Kaur, Kamaljit Singh Bhatia, Shaker El-Sappagh, and Jong-Wan Hu. 2020. A three-step authentication model for mobile phone user using keystroke dynamics. IEEE Access 8 (2020), 125909–125922.Google ScholarCross Ref
- Mohammad Saleem and B Kovari. 2019. Survey of signature verification databases. In International Multidisciplinary Scientific Conference.Google ScholarCross Ref
- Joan Serra, Santiago Pascual, and Alexandros Karatzoglou. 2018. Towards a Universal Neural Network Encoder for Time Series.. In CCIA. 120–129.Google Scholar
- Lloyd S Shapley 1953. A value for n-person games. (1953).Google Scholar
- Erik Strumbelj and Igor Kononenko. 2010. An efficient explanation of individual classifications using game theory. The Journal of Machine Learning Research 11 (2010), 1–18.Google ScholarDigital Library
- Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2017. Instance Normalization: The Missing Ingredient for Fast Stylization. arxiv:1607.08022 [cs.CV]Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. arxiv:1706.03762 [cs.CL]Google Scholar
- Shixuan Wang, Jiabin Yuan, and Jing Wen. 2019. Adaptive phone orientation method for continuous authentication based on mobile motion sensors. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 1623–1627.Google ScholarCross Ref
- Zhiguang Wang, Weizhong Yan, and Tim Oates. 2017. Time series classification from scratch with deep neural networks: A strong baseline. In 2017 International joint conference on neural networks (IJCNN). IEEE, 1578–1585.Google Scholar
- Kevin Yeo, Ooi Shih Yin, Pang Ying Han, and Wee Kuok Kwee. 2015. Real time mobile application of in-air signature with Fast Dynamic Time Warping (FastDTW). In 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). IEEE, 315–320.Google ScholarCross Ref
- Bendong Zhao, Huanzhang Lu, Shangfeng Chen, Junliang Liu, and Dongya Wu. 2017. Convolutional neural networks for time series classification. Journal of Systems Engineering and Electronics 28, 1 (2017), 162–169.Google ScholarCross Ref
- Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, and J Leon Zhao. 2014. Time series classification using multi-channels deep convolutional neural networks. In International conference on web-age information management. Springer, 298–310.Google ScholarCross Ref
- Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, and J Leon Zhao. 2016. Exploiting multi-channels deep convolutional neural networks for multivariate time series classification. Frontiers of Computer Science 10 (2016), 96–112.Google ScholarDigital Library
- Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2921–2929.Google ScholarCross Ref
Index Terms
- Dimension-Wise Feature Selection of Deep Learning Models for In-Air Signature Time Series Analysis Based on Shapley Values
Recommendations
On connections between individual values and coalition values for games in characteristic function form
This paper investigates some connections between individual values, such as the Shapley value and the Banzhaf value, and coalition values, such as blockability value, viability value and profitability value, for games in characteristic function form. It ...
Shapley Values with Uncertain Value Functions
Advances in Intelligent Data Analysis XXIAbstractWe propose a novel definition of Shapley values with uncertain value functions based on first principles using probability theory. Such uncertain value functions can arise in the context of explainable machine learning as a result of non-...
Towards interpretable and maintainable supervised learning using shapley values in arrhythmia
CASCON '20: Proceedings of the 30th Annual International Conference on Computer Science and Software EngineeringThis paper investigates the application of a model-agnostic interpretability technique, Shapley Additive Explanations (SHAP), to understand and hence, enhance machine learning classification models using Shapley values in the prediction of arrhythmias1. ...
Comments