Hardware/Software Co-design for a Neural Network Trained by Particle Swarm Optimization Algorithm

Dang, Tuan Linh; Hoshino, Yukinobu

doi:10.1007/s11063-018-9826-4

Cited by 18 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particle swarm optimization algorithms such as be used for training neural networks and for co-designing PSO training neural network software and hardware [ 17 ]. Zhang et al [ 18 ] obtained a global optimal parameter-optimized data-driven framework through the PSO algorithm and proposed a data-driven detection technology for laser welding defects based on real-time spectrometer signals.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Safety Risk Assessment of Tourism Management System Based on PSO‐BP Neural Network

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of science and technology, system management is gradually applied to tourism management. How to correctly assess the security risks of the tourism management system has become an important means to maintain passenger information. The security risk index of the travel management system is input into the PSO-BP network as a sample, and the corresponding risk value of the index is used as the network output. The results show that the error results, accuracy (96.53%), training time (216 s), number of iterations (275 times), and convergence speed are all better than traditional BP network. The relative error of PSO-BP network (0.32%) is better than that of BP network, with 300 iterations, and the error is close to 10–5. The average evaluation accuracy of S based on PSO-BP network is 99.72%, and the average time consumed is 2.512 s. It is superior to the evaluation model based on fuzzy set and entropy weight theory and the evaluation model based on gray correlation analysis and radial basis function neural network. In conclusion, the security risk assessment of the tourism management system based on PSO-BP network can effectively assess the security risk of the tourism management system.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Safety Risk Assessment of Tourism Management System Based on PSO‐BP Neural Network

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…However, the previous paper mentioned the accuracy advantage of the NN trained by PSO when compared with the NN trained by BP algorithm [6][7][8][9]. The previous paper proposed a framework for the co-design of the NN trained by PSO algorithm [15][16][17]. The original of the SPSO is from social behaviors.…”

Section: Neural Network Trained By Standard Psomentioning

confidence: 99%

“…This is co-design architecture. One part of the system is on the hardware side, another part is on software side [15][16][17]. The system can be seen in Fig.…”

Section: Hardware Implementation Of the Nn-spsomentioning

confidence: 99%

“…On the other hand, the NN is implemented in FPGA to increase the operation speed. The NN is implemented in FPGA so that the hardware speed could be maintained [15][16][17]. In the previous study, an improved version of the SPSO was proposed to solve the problem of the local minimum called the PSOd − CV algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…The wPSOd − CV is also proposed in this section. The NN-wPSOd − CV is based on the NN-PSO framework presented in the previous papers [15][16][17]. Section…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improved PSO Algorithm for Training of Neural Network in Co-design Architecture

Dang¹,

Hoshino²

2019

IJCA

Self Cite

View full text Add to dashboard Cite

This paper proposes a new version of the standard particle swarm optimization (SPSO) algorithm to train a neural network (NN). The improved PSO, called the wPSOd − CV algorithm, is the improved version of the PSOd − CV algorithm presented in a previous study. The wPSOd − CV algorithm is introduced to solve the issue of premature convergence of the SPSO algorithm. The proposed wPSOd − CV algorithm is used in a co-design architecture. Experimental results confirmed the effectiveness of the NN trained by the wPSOd − CV algorithm when compared with the NN trained by the SPSO algorithm and the PSOd − CV algorithm concerning the minimum learning error and the recognition rates.

show abstract