Improved perception-based spiking neuron learning rule for real-time user authentication

被引:18
|
作者
Qu, Hong [1 ]
Xie, Xiurui [1 ]
Liu, Yongshuai [1 ]
Zhang, Malu [1 ]
Lu, Li [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China
基金
美国国家科学基金会;
关键词
Spiking neural networks; Perception-based spiking neuron learning rule; User authentication; Spatiotemporal pattern recognition; NETWORKS; MODEL;
D O I
10.1016/j.neucom.2014.09.034
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Spiking neural networks (SNNs) have been highly successful in spatiotemporal pattern recognition. As one of the most efficient supervised learning algorithms in spike sequences learning, the perceptron-based spiking neuron learning rule (PBSNLR) still has a relatively high computational complexity, which is difficult to use in a real-time system. In this paper, a novel method is presented to improve PBSNLR's efficiency without reducing its accuracy, and this method is applied to solve user authentication problem in real time. In our method, a user's behavioral biometric of sliding dynamic and finger pressure are selected as spatiotemporal features to recognize the user's identity. The temporal feature is obtained by the time coding of SNNs and the spatial feature is represented by the neurons' relative positions. Comprehensive experimental results demonstrate that our improved algorithm outperforms the traditional PBSNLR in terms of efficiency and exhibits excellent performance when identifying users of touch screen devices. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:310 / 318
页数:9
相关论文
共 50 条
  • [21] Learning from User Feedback for Machine Translation in Real-Time
    Huang, Guoping
    Zhang, Jiajun
    Zhou, Yu
    Zong, Chengqing
    NATURAL LANGUAGE UNDERSTANDING AND INTELLIGENT APPLICATIONS (NLPCC 2016), 2016, 10102 : 595 - 607
  • [22] A Framework for an Adaptive Human-Robot Collaboration approach through Perception-based Real-Time adjustments of robot behavior in industry
    Kumar, Shitij
    Sahin, Ferat
    2017 12TH SYSTEM OF SYSTEMS ENGINEERING CONFERENCE (SOSE), 2017,
  • [23] Spectral Analysis of Keystroke Streams: Towards Effective Real-time Continuous User Authentication
    Alshehri, Abdullah
    Coenen, Frans
    Bollegala, Danushka
    ICISSP: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS SECURITY AND PRIVACY, 2018, : 62 - 73
  • [24] Real-Time Human Authentication System Based on Iris Recognition
    Hafeez, Huma
    Zafar, Muhammad Naeem
    Abbas, Ch Asad
    Elahi, Hassan
    Ali, Muhammad Osama
    ENG, 2022, 3 (04): : 693 - 708
  • [25] A Real-time Silicon Cerebellum Spiking Neural Model based on FPGA
    Luo, Junwen
    Coapes, Graeme
    Degenaar, Patrick
    Mak, Terrence
    Yamazaki, Tadashi
    Tin, Chung
    2014 14TH INTERNATIONAL SYMPOSIUM ON INTEGRATED CIRCUITS (ISIC), 2014, : 276 - 279
  • [26] Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception
    Ghosh, Anurag
    Balloli, Vaibhav
    Nambi, Akshay
    Singh, Aditya
    Ganu, Tanuja
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [27] Zero-Stop Authentication: Sensor-based real-time authentication system
    Matsumiya, K
    Aoki, S
    Murase, M
    Tokuda, H
    REAL-TIME AND EMBEDDED COMPUTING SYSTEMS AND APPLICATIONS, 2003, 2968 : 296 - 311
  • [28] Real-Time Facial Expression Recognition Based on the Improved Brain Emotional Learning Model
    Mei, Ying
    Yang, Xin
    Liu, Zhentao
    Wu, He
    Guo, Junyu
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 9624 - 9628
  • [29] Optimizing real-time equational rule-based systems
    Lee, YH
    Cheng, AMK
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2004, 30 (02) : 112 - 125
  • [30] A RULE-BASED PROGRAMMING LANGUAGE FOR REAL-TIME APPLICATIONS
    DELRIO, A
    MARINO, P
    MICROPROCESSING AND MICROPROGRAMMING, 1993, 39 (2-5): : 139 - 142