4-Ch &amp;#x00D7; 10-Gb/s chip-to-chip optical interconnections with optoelectronic packages and optical waveguide separated from PCB

Takagi, Yutaka; Suzuki, Atsushi; Horio, Toshikazu; Ohno, Takeshi; Kojima, Toshifumi; Takada, Toshikatsu; Iio, Satoshi; Obayashi, Kazushige; Okuyama, Masahiko

doi:10.1109/cpmtsympj.2010.5680206

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ey proved that Auto-VRS could reduce the false alarm rate of pseudo defects. In addition, Takagi et al [15] proposed an approach for PCB defect detection and classification by extracting features from standard board images using CNN layers and then using an SVM classifier for classification.…”

Section: Related Workmentioning

confidence: 99%

Cost‐Sensitive Siamese Network for PCB Defect Classification

Miao

Liu

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

After the production of printed circuit boards (PCB), PCB manufacturers need to remove defected boards by conducting rigorous testing, while manual inspection is time-consuming and laborious. Many PCB factories employ automatic optical inspection (AOI), but this pixel-based comparison method has a high false alarm rate, thus requiring intensive human inspection to determine whether alarms raised from it resemble true or pseudo defects. In this paper, we propose a new cost-sensitive deep learning model: cost-sensitive siamese network (CSS-Net) based on siamese network, transfer learning and threshold moving methods to distinguish between true and pseudo PCB defects as a cost-sensitive classification problem. We use optimization algorithms such as NSGA-II to determine the optimal cost-sensitive threshold. Results show that our model improves true defects prediction accuracy to 97.60%, and it maintains relatively high pseudo defect prediction accuracy, 61.24% in real-production scenario. Furthermore, our model also outperforms its state-of-the-art competitor models in other comprehensive cost-sensitive metrics, with an average of 33.32% shorter training time.

show abstract

Section: Related Workmentioning

confidence: 99%

Cost‐Sensitive Siamese Network for PCB Defect Classification

Miao

Liu

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Many people believe that replacing electrical cables with optical fibres will solve many of the problems associated with the transmission of signals with GHz frequencies. This is reflected in the number of articles [1][2][3][4] and books concerning the introduction of optical interconnects into VLSI circuits [5][6][7][8]. The optical connections found in Integrated Systems (IS) divide into two groups: on-chip and off-chip.…”

Section: Introductionmentioning

confidence: 99%

The integration of optical interconnections on ceramic substrates

Guzowski

Rosowski

Lisik

et al. 2016

Microelectronic Engineering

View full text Add to dashboard Cite

show abstract

“…This is reflected in a number of articles [1][2][3][4][5] and books related to the introduction of optical interconnectors for very-large-scale integration (VLSI) circuits [6][7][8][9]. A printed circuit board (PCB) makes use of optical systems communicating with each other in free space [10].…”

Section: Optical Connections In Chip-to-chip Systemsmentioning

confidence: 99%