Advanced flexible wavelength routing based on Bragg trans-reflectance in 1550 nm VCSEL

Isoe, G. M.; Cherutoi, H. C.; Waswa, D. W.; Gibbon, T. B.

doi:10.1080/09500340.2020.1858200

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study proposes a shallow All-optical Neuron-based SNN (AoN-SNN) approach, uses the Northeast University (NEU)-CLS example as its application and enables end-to-end steel surface defect identification tasks. We used vertical-cavity surface-emitting laser (VCSEL)-SA-based AoN (Hurtado et al , 2010; Isoe et al , 2020) and vertical-cavity semiconductor optical amplifier (VCSOA)-based STDP rule-based photonic synaptic connections (Fok et al , 2013) to form an AoN-SNN network structure. We propose a hybrid attention mechanism (AM) based on convolutional pooling forward-hopping connection mixed with AoN-SNN to overcome the shallow AoN-SNN architecture’s inability to convey complicated visual information.…”

Section: Introductionmentioning

confidence: 99%

Steel surface defect classification approach using an All-optical Neuron-based SNN with attention mechanism

Gong

Dong

Cheng

et al. 2023

IJICC

View full text Add to dashboard Cite

PurposeThe purpose of this study is to propose a new method for the end-to-end classification of steel surface defects.Design/methodology/approachThis study proposes an AM-AoN-SNN algorithm, which combines an attention mechanism (AM) with an All-optical Neuron-based spiking neural network (AoN-SNN). The AM enhances network learning and extracts defective features, while the AoN-SNN predicts both the labels of the defects and the final labels of the images. Compared to the conventional Leaky-Integrated and Fire SNN, the AoN-SNN has improved the activation of neurons.FindingsThe experimental findings on Northeast University (NEU)-CLS demonstrate that the proposed neural network detection approach outperforms other methods. Furthermore, the network’s effectiveness was tested, and the results indicate that the proposed method can achieve high detection accuracy and strong anti-interference capabilities while maintaining a basic structure.Originality/valueThis study introduces a novel approach to classifying steel surface defects using a combination of a shallow AoN-SNN and a hybrid AM with different network architectures. The proposed method is the first study of SNN networks applied to this task.

show abstract

Section: Introductionmentioning

confidence: 99%