scholarly journals An Improved Capsule Network (WaferCaps) for Wafer Bin Map Classification Based on DCGAN Data Upsampling

Author(s):  
Abd Al Rahman M. Abu Ebayyeh ◽  
Sebelan Danishvar ◽  
Alireza Mousavi
Keyword(s):  

2020 ◽  
Vol 21 (4) ◽  
pp. 1284 ◽  
Author(s):  
Shukun Jiang ◽  
Chao Yang ◽  
Quan Xu ◽  
Lizhi Wang ◽  
Xianli Yang ◽  
...  

Among all cereals, rice is highly sensitive to cold stress, especially at the germination stage, which adversely impacts its germination ability, seed vigor, crop stand establishment, and, ultimately, grain yield. The dissection of novel quantitative trait loci (QTLs) or genes conferring a low-temperature germination (LTG) ability can significantly accelerate cold-tolerant rice breeding to ensure the wide application of rice cultivation through the direct seeding method. In this study, we identified 11 QTLs for LTG using 144 recombinant inbred lines (RILs) derived from a cross between a cold-tolerant variety, Lijiangxintuanheigu (LTH), and a cold-sensitive variety, Shennong265 (SN265). By resequencing two parents and RIL lines, a high-density bin map, including 2,828 bin markers, was constructed using 123,859 single-nucleotide polymorphisms (SNPs) between two parents. The total genetic distance corresponding to all 12 chromosome linkage maps was 2,840.12 cm. Adjacent markers were marked by an average genetic distance of 1.01 cm, corresponding to a 128.80 kb physical distance. Eight and three QTL alleles had positive effects inherited from LTH and SN265, respectively. Moreover, a pleiotropic QTL was identified for a higher number of erected panicles and a higher grain number on Chr-9 near the previously cloned DEP1 gene. Among the LTG QTLs, qLTG3 and qLTG7b were also located at relatively small genetic intervals that define two known LTG genes, qLTG3-1 and OsSAP16. Sequencing comparisons between the two parents demonstrated that LTH possesses qLTG3-1 and OsSAP16 genes, and SN-265 owns the DEP1 gene. These comparison results strengthen the accuracy and mapping resolution power of the bin map and population. Later, fine mapping was done for qLTG6 at 45.80 kb through four key homozygous recombinant lines derived from a population with 1569 segregating plants. Finally, LOC_Os06g01320 was identified as the most possible candidate gene for qLTG6, which contains a missense mutation and a 32-bp deletion/insertion at the promoter between the two parents. LTH was observed to have lower expression levels in comparison with SN265 and was commonly detected at low temperatures. In conclusion, these results strengthen our understanding of the impacts of cold temperature stress on seed vigor and germination abilities and help improve the mechanisms of rice breeding programs to breed cold-tolerant varieties.



2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Chia-Yu Hsu

Wafer bin map (WBM) represents specific defect pattern that provides information for diagnosing root causes of low yield in semiconductor manufacturing. In practice, most semiconductor engineers use subjective and time-consuming eyeball analysis to assess WBM patterns. Given shrinking feature sizes and increasing wafer sizes, various types of WBMs occur; thus, relying on human vision to judge defect patterns is complex, inconsistent, and unreliable. In this study, a clustering ensemble approach is proposed to bridge the gap, facilitating WBM pattern extraction and assisting engineer to recognize systematic defect patterns efficiently. The clustering ensemble approach not only generates diverse clusters in data space, but also integrates them in label space. First, the mountain function is used to transform data by using pattern density. Subsequently,k-means and particle swarm optimization (PSO) clustering algorithms are used to generate diversity partitions and various label results. Finally, the adaptive response theory (ART) neural network is used to attain consensus partitions and integration. An experiment was conducted to evaluate the effectiveness of proposed WBMs clustering ensemble approach. Several criterions in terms of sum of squared error, precision, recall, andF-measure were used for evaluating clustering results. The numerical results showed that the proposed approach outperforms the other individual clustering algorithm.



2019 ◽  
Vol 67 (44) ◽  
pp. 12313-12321
Author(s):  
Yujie Ma ◽  
Weiyu Ma ◽  
Dezhou Hu ◽  
Xinnan Zhang ◽  
Wenjie Yuan ◽  
...  


2020 ◽  
Vol 46 (3) ◽  
pp. 326-337
Author(s):  
Seung Ho Baek ◽  
Chang Hyun Lee ◽  
Seoung Bum Kim




Author(s):  
Qiang He ◽  
Hui Zhi ◽  
Sha Tang ◽  
Lu Xing ◽  
Suying Wang ◽  
...  




Genetics ◽  
2004 ◽  
Vol 168 (2) ◽  
pp. 701-712 ◽  
Author(s):  
L. L. Qi ◽  
B. Echalier ◽  
S. Chao ◽  
G. R. Lazo ◽  
G. E. Butler ◽  
...  


2002 ◽  
Vol 40 (10) ◽  
pp. 2207-2223 ◽  
Author(s):  
S. F. Liu ◽  
F. L. Chen ◽  
W. B. Lu


Sign in / Sign up

Export Citation Format

Share Document