Search

Your search keyword '"Xie, Shouyu"' showing total 10 results
Start Over Author "Xie, Shouyu"
10 results on '"Xie, Shouyu"'

2. An FPGA Implementation of Convolutional Spiking Neural Networks for Radioisotope Identification

Author

Huang, Xiaoyu, Jones, Edward, Zhang, Siru, Xie, Shouyu, Furber, Steve, Goulermas, Yannis, Marsden, Edward, Baistow, Ian, Mitra, Srinjoy, and Hamilton, Alister

Subjects
Electrical Engineering and Systems Science - Signal Processing
Abstract

This paper details the FPGA implementation methodology for Convolutional Spiking Neural Networks (CSNN) and applies this methodology to low-power radioisotope identification using high-resolution data. Power consumption of 75 mW has been achieved on an FPGA implementation of a CSNN, with an inference accuracy of 90.62% on a synthetic dataset. The chip validation method is presented. Prototyping was accelerated by evaluating SNN parameters using SpiNNaker neuromorphic platform., Comment: 5 pages, 10 FIGURES, IEEE ISCAS 2021

Published
2021

3. Spiking Neural Network Based Low-Power Radioisotope Identification using FPGA

Author

Huang, Xiaoyu, Jones, Edward, Zhang, Siru, Xie, Shouyu, Furber, Steve, Goulermas, Yannis, Marsden, Edward, Baistow, Ian, Mitra, Srinjoy, and Hamilton, Alister

Subjects
Electrical Engineering and Systems Science - Signal Processing
Abstract

this paper presents a detailed methodology of a Spiking Neural Network (SNN) based low-power design for radioisotope identification. A low power cost of 72 mW has been achieved on FPGA with the inference accuracy of 100% at 10 cm test distance and 97% at 25 cm. The design verification and chip validation methods are presented. It also discusses SNN simulation on SpiNNaker for rapid prototyping and various considerations specific to the application such as test distance, integration time, and SNN hyperparameter selections., Comment: 4 pages, 10 figures, 27th IEEE International Conference on Electronics Circuits and Systems (ICECS) 2020

Published
2020

9. Evolution and genetic diversity of atypical porcine pestivirus (APPV) from piglets with congenital tremor in Guangxi Province, Southern China.

Author

Shi, Kaichuang, Xie, Shouyu, Sun, Wenchao, Liu, Huixin, Zhao, Jing, Yin, Yanwen, Si, Hongbin, Qu, Sujie, and Lu, Wenjun

Subjects
*GENETIC variation, *TREMOR, *PROVINCES, *SEQUENCE analysis, *AMINO acids, *PIGLETS, *COMPARATIVE genomics, *CATTLE genetics
Abstract

Atypical porcine pestivirus (APPV) was identified and associated with congenital tremor (CT) type A‐II in new born piglets and has been reported in many countries. In China, the first APPV identification in swine herds was reported in Guangdong province in 2016. To investigate the genetic characteristics of APPV in Guangxi province, 53 tissue samples from neonatal piglets with CT were collected and detected from October 2017 to May 2019. Five APPV strains which were named as GX04/2017, GX01‐2018, GX02‐2018, GX01‐2019 and GX02‐2019 were obtained. Sequence analysis revealed that all six APPV strains from Guangxi province, including five strains from this study and one from a previous report, shared 83.3%‐97.5% nucleotide identity of complete genome and 91.7%‐99.1% amino acid identity of the open reading frame (ORF), and shared 77.7%‐97.7% nucleotide identity of complete genome and 90.6%‐99.3% amino acid identity of ORF with reference strains. Phylogenetic analysis indicated that all APPV strains could be divided into three clades based on the complete genome, Npro, Erns and E2 gene sequences, respectively; and the APPV strains from Guangxi province distributed in two clades (clades I and II). No sign of recombination was observed from Guangxi strains. Evolution analysis performed on the complete genome of 58 APPV strains showed that America, Europe and Asia strains during 2006–2019 evolved at a mean rate of 1.37 × 10–4 substitutions/site/year, and the most recent common ancestor (tMRCA) of them was estimated as 1,700.5 years ago. The findings of this study indicated that there existed a high degree of genetic diversity of APPV from Guangxi province, Southern China, which provided important information on the epidemiological features and evolutionary relationships of APPV. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results