A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2025  > In Press, Accepted Manuscript
J. Li, Y. Cao, Z. Xie, and L. Jin, “A k-winners-take-all (kWTA) network with noise characteristics captured,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 4, pp. 1–11, Apr. 2025.
Citation: J. Li, Y. Cao, Z. Xie, and L. Jin, “A k-winners-take-all (kWTA) network with noise characteristics captured,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 4, pp. 1–11, Apr. 2025.
shu

A k-Winners-Take-All (kWTA) Network With Noise Characteristics Captured

Funds:  This work was supported in part by the National Natural Science Foundation of China (62176109, 62476115), in part by the Fundamental Research Funds for the Central Universities (lzuibky-2023-ey07), in part by the Youth and Middle-aged Scientific Research Foundation of Qinghai Normal University (2020QZR012), and in part by the Supercomputing Center of Lanzhou University
More Information
    Abstract
  • Competition-based $ k $-winners-take-all ($ k $WTA) networks play a crucial role in multi-agent systems. However, existing $ k $WTA networks either neglect the impact of noise or only consider simple forms, such as constant noise. In practice, noises often exhibit time-varying and nonlinear characteristics, which can be modeled using nonlinear functions and approximated by high-order polynomials. Such noises pose significant challenges for current $ k $WTA networks, limiting their practical applications. To address this, a $ k $WTA network with noise characteristics captured ($ k $WTA-NCC) is proposed in this article. Theoretical analyses demonstrate that the residual error of the proposed $ k $WTA-NCC network converges to zero globally, while simulation results confirm its robustness against polynomial noises. Additionally, a $ k $WTA coordination model is constructed by integrating the proposed network with a consensus estimator to achieve multi-agent tracking tasks. Finally, simulations and physical experiments are conducted further to demonstrate the validity and practicality of the $ k $WTA coordination model.

     

    • FullText(HTML)
  • loading
    • References(41)
  • [1]
    C.-M. Chen and J.-F. Yang, “Layer winner-take-all neural networks based on existing competitive structures,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 30, no. 1, pp. 25–30, Feb. 2000. doi: 10.1109/3477.826944
    [2]
    K. M. Cherry and L. Qian, “Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks,” Nature, vol. 559, pp. 370–376, Jul. 2018. doi: 10.1038/s41586-018-0289-6
    [3]
    R. Zarei-Sabzevar, K. Ghiasi-Shirazi, and A. Harati, “Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 11, pp. 9016–9028, Nov. 2023. doi: 10.1109/TNNLS.2022.3155174
    [4]
    J. Wang, “Analysis and design of a k-winners-take-all model with a single state variable and the Heaviside step activation function,” IEEE Trans. Neural Netw., vol. 21, no. 9, pp. 1496–1506, Sept. 2010. doi: 10.1109/TNN.2010.2052631
    [5]
    P. Tien, “A new discrete-time multi-constrained k-winner-take-all recurrent network and its application to prioritized scheduling,” IEEE Trans. Neural Netw. Learn. Syst., vol. 28, no. 11, pp. 2674–2685, Nov. 2017. doi: 10.1109/TNNLS.2016.2600410
    [6]
    C. A. Marinov and J. J. Hopfield, “Stable computational dynamics for a class of circuits with O(n) interconnections capable of kWTA and rank extractions,” IEEE Trans. Circuits Syst. I, Reg. Papers., vol. 52, no. 5, pp. 949–959, May 2005. doi: 10.1109/TCSI.2005.846662
    [7]
    W. Lu, C.-S. Leung, J. Sum, and Y. Xiao, “DNN-kWTA with bounded random offset voltage drifts in threshold logic units,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 7, pp. 3184–3192, Jul. 2022. doi: 10.1109/TNNLS.2021.3050493
    [8]
    S. Liu and J. Wang, “A simplified dual neural network for quadratic programming with its kWTA application,” IEEE Trans. Neural Netw., vol. 17, no. 6, pp. 1500–1510, Nov. 2006. doi: 10.1109/TNN.2006.881046
    [9]
    M. Liu and M. Shang, “On RNN-based k-WTA models with time-dependent inputs,” IEEE/CAA J. Autom. Sinica., vol. 9, no. 11, pp. 2034–2036, Nov. 2022. doi: 10.1109/JAS.2022.105932
    [10]
    A. Nazemi and M. Nazemi, “A gradient-based neural network method for solving strictly convex quadratic programming problems,” Cognit. Comput., vol. 6, no. 3, pp. 484–495, Feb. 2014. doi: 10.1007/s12559-014-9249-0
    [11]
    Z. Sun, S. Tang, J. Zhang, and J. Yu, “Nonconvex noise-tolerant neural model for repetitive motion of omnidirectional mobile manipulators,” IEEE/CAA J. Autom. Sinica., vol. 10, no. 8, pp. 1766–1768, Aug. 2023. doi: 10.1109/JAS.2023.123273
    [12]
    Z. Zeng, J. Wang, and X. Liao, “Global exponential stability of a general class of recurrent neural networks with time-varying delays,” IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 50, no. 10, pp. 1353–1358, Oct. 2003. doi: 10.1109/TCSI.2003.817760
    [13]
    S. Li, Y. Li, and Z. Wang, “A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application,” IEEE Trans. Neural Netw., vol. 39, pp. 27–39, Mar. 2013. doi: 10.1016/j.neunet.2012.12.009
    [14]
    Y. Zhang, S. Li, and J. Weng, “Distributed k-winners-take-all network: An optimization perspective,” IEEE Trans. Cybern., vol. 53, no. 8, pp. 5069–5081, Aug. 2023. doi: 10.1109/TCYB.2022.3170236
    [15]
    Y. Zhang, S. Li, and G. Geng, “Initialization-based k-winners-take-all neural network model using modified gradient descent,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 8, pp. 4130–4138, Aug. 2023. doi: 10.1109/TNNLS.2021.3123240
    [16]
    P. S. Stanimirović and M. D. Petković, “Gradient neural dynamics for solving matrix equations and their applications,” Neurocomputing, vol. 306, pp. 200–212, Sept. 2018. doi: 10.1016/j.neucom.2018.03.058
    [17]
    M. Liu, X. Zhang, M. Shang, and L. Jin, “Gradient-based differential kWTA network with application to competitive coordination of multiple robots,” IEEE/CAA J. Autom. Sinica., vol. 9, no. 8, pp. 1452–1463, Aug. 2022. doi: 10.1109/JAS.2022.105731
    [18]
    R. Feng, C.-S. Leung, and J. Sum, “Robustness analysis on dual neural network-based k-WTA with input noise,” IEEE Trans. Neural Netw. Learn. Syst., vol. 29, no. 4, pp. 1082–1094, Apr. 2018. doi: 10.1109/TNNLS.2016.2645602
    [19]
    W. Lu, C.-S. Leung, and J. Sum, “Influence of imperfections on the operational correctness of DNN-kWTA model,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 10, pp. 15021–15029, Oct. 2024. doi: 10.1109/TNNLS.2023.3281523
    [20]
    Y. Qi, L. Jin, X. Luo, Y. Shi, and M. Liu, “Robust k-WTA network generation, analysis, and applications to multiagent coordination,” IEEE Trans. Cybern., vol. 52, no. 8, pp. 8515–8527, Aug. 2022. doi: 10.1109/TCYB.2021.3079457
    [21]
    L. Jin, S. Liang, X. Luo, and M. Zhou, “Distributed and time-delayed k-winner-take-all network for competitive coordination of multiple robots,” IEEE Trans. Cybern., vol. 53, no. 1, pp. 641–652, Jan. 2023. doi: 10.1109/TCYB.2022.3159367
    [22]
    X. Zhao, Q. Zong, B. Tian, and M. You, “Finite-time dynamic allocation and control in multiagent coordination for target tracking,” IEEE Trans. Cybern., vol. 52, no. 3, pp. 1872–1880, Mar. 2022. doi: 10.1109/TCYB.2020.2998152
    [23]
    K. Ogata, Modern Control Engineering, 5th ed. Upper Saddle River, NJ: Prentice Hall, 2010.
    [24]
    J. Liu, X. Du, and L. Jin, “A localization algorithm for underwater acoustic sensor networks with improved Newton iteration and simplified Kalman filter,” IEEE Trans. Mobile Comput., vol. 23, no. 12, pp. 14459−14470, Dec. 2024.
    [25]
    H. Jian, S. Zheng, P. Shi, Y. Xie, and H. Li, “Consensus for multiple random mechanical systems with applications on robot manipulator,” IEEE Trans. Ind. Electron., vol. 71, no. 1, pp. 846–856, Jan. 2024. doi: 10.1109/TIE.2023.3241397
    [26]
    Z. Qiu, Z. Zhu, and X. Liu, “An investigation of aerodynamic performance of aeroengine fan and booster under non-uniform inlet conditions,” Aerospace Systems, vol. 7, pp. 465–479, 2024. doi: 10.1007/s42401-023-00229-2
    [27]
    L. Jin, L. Wei, and S. Li, “Gradient-based differential neural-solution to time-dependent nonlinear optimization,” IEEE Trans. Autom. Control, vol. 68, no. 1, pp. 620–627, Jan. 2023. doi: 10.1109/TAC.2022.3144135
    [28]
    E. Javanfar and M. Rahmani, “Data-based filters for non-Gaussian dynamic systems with unknown output noise covariance,” IEEE/CAA J. Autom. Sinica., vol. 11, no. 4, pp. 866–877, Apr. 2024. doi: 10.1109/JAS.2023.124164
    [29]
    X. Chen, M. Liu, and S. Li, “Echo state network with probabilistic regularization for time series prediction,” IEEE/CAA J. Autom. Sinica., vol. 10, no. 8, pp. 1743–1753, Aug. 2023. doi: 10.1109/JAS.2023.123489
    [30]
    A. Quarteroni and A. Valli, Numerical Approximation of Partial Differential Equations, Heidelberg, Berlin, GER.: Springer, 1994.
    [31]
    I. Djurovic and M. Simeunović, “Estimation of higher order polynomial phase signals in an impulsive noise,” IEEE Trans. Aerosp. Electron. Syst., vol. 54, no. 4, pp. 1790–1798, Aug. 2018. doi: 10.1109/TAES.2018.2801558
    [32]
    S. Li, H. Wang, and M. U. Rafique, “A novel recurrent neural network for manipulator control with improved noise tolerance,” IEEE Trans. Neural Netw. Learn. Syst., vol. 29, no. 5, pp. 1908–1918, May 2018. doi: 10.1109/TNNLS.2017.2672989
    [33]
    M. Liu, J. Li, S. Li, and N. Zeng, “Recurrent-neural-network-based polynomial noise resistance model for computing dynamic nonlinear equations applied to robotics,” IEEE Trans. Cogn. Devel. Syst., vol. 15, no. 2, pp. 518–529, Jun. 2023. doi: 10.1109/TCDS.2022.3159852
    [34]
    H. Wang and Q.-L. Han, “Designing proportional-integral consensus protocols for second-order multi-agent systems using delayed and memorized state information,” IEEE/CAA J. Autom. Sinica., vol. 11, no. 4, pp. 878–892, Apr. 2024. doi: 10.1109/JAS.2024.124308
    [35]
    M. Doostmohammadian, U. A. Khan, M. Pirani, and T. Charalambous, “Consensus-based distributed estimation in the presence of heterogeneous, time-invariant delays,” IEEE Control Syst. Lett., vol. 6, pp. 1598–1603, Nov. 2021.
    [36]
    M. Doostmohammadian, A. Taghieh, and H. Zarrabi, “Distributed estimation approach for tracking a mobile target via formation of UAVs,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 4, pp. 3765–3776, Oct. 2022. doi: 10.1109/TASE.2021.3135834
    [37]
    L. Jin, Y. Li, X. Zhang, and X. Luo, “Fuzzy k-winner-take-all network for competitive coordination in multirobot systems,” IEEE Trans. Fuzzy Syst., vol. 32, no. 4, pp. 2005–2016, Apr. 2024. doi: 10.1109/TFUZZ.2023.3339654
    [38]
    F. Bi, X. Luo, B. Shen, H. Dong, and Z. Wang, “Proximal alternating-direction-method-of-multipliers-incorporated nonnegative latent factor analysis,” IEEE/CAA J. Autom. Sinica., vol. 10, no. 6, pp. 1388–1406, Jun. 2023. doi: 10.1109/JAS.2023.123474
    [39]
    S. Effati and A. Nazemi, “Neural network models and its application for solving linear and quadratic programming problems,” Appl. Math. Comput., vol. 172, no. 1, pp. 305–331, Jan. 2006.
    [40]
    Z. Zeng, J. Wang, and X. Liao, “Stability analysis of delayed cellular neural networks described using cloning templates,” IEEE Trans. Circuits Syst. I, Reg. Papers, vol. 51, no. 11, pp. 2313–2324, Nov. 2004. doi: 10.1109/TCSI.2004.836855
    [41]
    L. Jin, S. Li, H. M. La, X. Zhang, and B. Hu, “Dynamic task allocation in multi-robot coordination for moving target tracking: A distributed approach,” Automatica, vol. 100, pp. 75–81, Feb. 2019. doi: 10.1016/j.automatica.2018.11.001
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(9)  / Tables(1)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (11) PDF downloads(4) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return