Improvement of Echo State Network Generalization by Selective Ensemble Learning Based on BPSO
Xiaodong Zhang,
Xuefeng Yan
Issue:
Volume 4, Issue 6, December 2016
Pages:
84-88
Received:
Nov. 29, 2016
Accepted:
Published:
Dec. 01, 2016
Abstract: The Echo State Network (ESN) is a novel and special type of recurrent neural network that has become increasingly popular in machine learning domains such as time series forecasting, data clustering, and nonlinear system identification. This network is characterized by large randomly constructed recurrent neural networks (RNN) called “reservoir”, in which the neurons are sparsely connected and the weights remain unchanged during training, leaving the simple training of the output layer. However, the reservoir is criticized for its randomness and instability because of the random initialization of the connectivity and weights. In this article, we introduced the selective ensemble learning based on BPSO to improve the generalization performance of ESN. Two widely studied tasks are used to prove the feasibility and priority of the selective ESN ensemble based on BPSO(SESNE-BPSO) model. And the results indicate that the SESNE-BPSO model performs better than the general ESN ensemble, the single standard ESN and several other improved ESN models.
Abstract: The Echo State Network (ESN) is a novel and special type of recurrent neural network that has become increasingly popular in machine learning domains such as time series forecasting, data clustering, and nonlinear system identification. This network is characterized by large randomly constructed recurrent neural networks (RNN) called “reservoir”, i...
Show More
Barcode Recognizable System Implementing Based on AM5728
Xicai Li,
Junsheng Shi,
Xiaoqiao Huang,
Yonghang Tai,
Chongde Zi,
Huan Yang,
Xingyu Yang,
Zhiwei Deng,
Feiyan Li
Issue:
Volume 4, Issue 6, December 2016
Pages:
89-94
Received:
Nov. 29, 2016
Accepted:
Published:
Dec. 01, 2016
Abstract: To refine the implementation of industrial camera requirements in terms of barcode identification, speeding the barcode image acquisition and processing challenges, as well as the defect of low accuracy. We proposed a barcode recognition framework based on AM5728 embedded system, which employed industrial CCD to scan the barcode image, moreover, integrated with AM5728 visual development platform to manipulate the collected images. After that, decoding information is yielded from series of algorithms refer to convolution filtering, barcode positioning as well as recognition facilitated by AM5728 visual development platform. Experimental outcomes validated that the accuracy of our system recognition rate can reach up to satisfied 100% in the threshold condition, with 20 frames per second barcode images recognition rate.
Abstract: To refine the implementation of industrial camera requirements in terms of barcode identification, speeding the barcode image acquisition and processing challenges, as well as the defect of low accuracy. We proposed a barcode recognition framework based on AM5728 embedded system, which employed industrial CCD to scan the barcode image, moreover, in...
Show More