Distributed cooperative learning algorithms using wavelet neural network

Xie, Jin; Chen, Weisheng; Hao, Dingjun

doi:10.1007/s00521-017-3134-1

Cited by 13 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the WNN algorithm [ 21 ] was used to classify and discriminate real and fake blood because it combines the wavelet transform and the artificial neural network. It has the great capacities of strong learning, self-adaptability and fault tolerance because it avoids nonlinear optimization problems, including the blindness of structure design and local optimization of BPNN [ 22 ].…”

Section: Theoriesmentioning

confidence: 99%

Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks

Ren

Liu

2021

Photoacoustics

View full text Add to dashboard Cite

show abstract

Section: Theoriesmentioning

confidence: 99%

Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks

Ren

Liu

2021

Photoacoustics

View full text Add to dashboard Cite

show abstract

“…However, the computational resources of traditional centralized WNNs will tend to saturate with the increase of data. Notice that the distributed cooperative learning algorithm of the WNNs model [20], which uses the communication structure of graph G(υ, ε, Λ), where each non-empty node set υ i in υ jointly maintains the coefficient matrix Λ. Furthermore, the existence of the edge ε(i, j ) represents the connection of two adjacent nodes i and j , and the weight ω ij > 0 when edge exist, and ω ij = 0 in other cases.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Inspired by [7,14], the optimization function and training data can be thus formed in distributed learning structure, which is of great interest in WNNs. In response to this, a distributed cooperative learning (DCL) algorithm based on WNNs was developed in [20], which shared parameters with neighbors in calculating the estimates. However, a large amount of weight information needs to be communicated in the sharing process, and it cannot be work well in high-dimensional scenario.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, the failure of any node would paralyze the system. Different from the data communication through the weight matrix in [20], a multi-hop mesh network was utilized to optimize communication between nodes in [21], where networks are independent of each other and accomplish their tasks in a cooperative manner.…”

Section: Introductionmentioning

confidence: 99%

“…1) A subnet-independent distributed wavelet neural networks (DWNNs) is proposed, where the data are sorted and partitioned into several non-overlapping training subsets. Compared with the distributed cooperative methods in [20,22,23], the amount of weight information communication between nodes is reduced. 2) Expressing the time-frequency information as a nonlinear function, and the target signal is comprehensively characterized by DWNNs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Distributed wavelet neural networks

Yang

Chen

2021

Appl Intell

View full text Add to dashboard Cite

Utilizing the wavelet theory, the wavelet coefficients with respect to translation and scaling factors can be obtained through the iteration of neural network, which effectively solves the window immobility problem of short time Fourier transform. Notice that, the centralized wavelet neural network is weak in the representation of signal integrity as localized information is lost in the case of the signal properties are large span time-domain and high frequency. To solve this problem, the learning algorithm of distributed wavelet neural networks (DWNNs) based on domain segment is proposed in this paper, where the time frequency characteristic of objective function is set as a constraint condition, while the time width, frequency, center of time domain and band center of the wavelet are employed to determine the translation and scaling parameters. Especially, wavelet networks are distributed into several orthogonal subnet by partitioning the information of input data, and the complexity of calculating for each nodes is thus decreased. Moreover, simulations are presented to demonstrate the advantages and efficiency of the proposed DWNNs.

show abstract

Photoacoustic identification of blood authenticity based on quantum‐behaved particle swarm optimized wavelet neural network

Liu

Ren

et al. 2022

Journal of Biophotonics

View full text Add to dashboard Cite

To accurately identify the blood authenticity, a set of photoacoustic detection system was established. In experiments, five kinds of blood in total of 125 groups were used, the time‐resolved photoacoustic signals and peak‐to‐peak spectra were obtained in 700 to 1064 nm. Experimental results showed the accurate identification of blood authenticity was limited due to overlap of signals and spectra. To solve the problem, wavelet neural network (WNN) was employed to supervised train peak‐to‐peak spectra of 100 samples. The correct rate was 72% for 25 test samples. To improve correct rate, the parameters of WNN were optimized by quantum‐behaved particle swarm optimization (QPSO) algorithm. Meanwhile, the effects of neurons number, learning rate factors, iteration times and training times on correct rate were studied and compared with WNN and WNN‐PSO algorithms. Results showed the correct rate of WNN‐QPSO was increased to 96%. Then, three kinds of dynamic contraction‐expansion coefficients were used. Under the optimal dynamic coefficient, the correct rate reached 100%. Moreover, the truncated mean stabilization strategy (TMSS) was coupled to improve the convergent speed. Finally, 10 algorithms were compared. Results demonstrated that photoacoustic spectroscopy combined with WNN‐QPSO coupled with TMSS and dynamic contraction‐expansion coefficient had an excellent performance in the identification of blood authenticity.

show abstract

Distributed cooperative learning algorithms using wavelet neural network

Cited by 13 publications

References 39 publications

Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks

Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks

Distributed wavelet neural networks

Photoacoustic identification of blood authenticity based on quantum‐behaved particle swarm optimized wavelet neural network

Contact Info

Product

Resources

About