Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
Add more filters











Database
Language
Publication year range
2.
Bioengineering (Basel) ; 10(8)2023 Aug 03.
Article in English | MEDLINE | ID: mdl-37627804

ABSTRACT

Computer vision (CV) technology and convolutional neural networks (CNNs) demonstrate superior feature extraction capabilities in the field of bioengineering. However, during the capturing process of finger-vein images, translation can cause a decline in the accuracy rate of the model, making it challenging to apply CNNs to real-time and highly accurate finger-vein recognition in various real-world environments. Moreover, despite CNNs' high accuracy, CNNs require many parameters, and existing research has confirmed their lack of shift-invariant features. Based on these considerations, this study introduces an improved lightweight convolutional neural network (ILCNN) for finger vein recognition. The proposed model incorporates a diverse branch block (DBB), adaptive polyphase sampling (APS), and coordinate attention mechanism (CoAM) with the aim of improving the model's performance in accurately identifying finger vein features. To evaluate the effectiveness of the model in finger vein recognition, we employed the finger-vein by university sains malaysia (FV-USM) and PLUSVein dorsal-palmar finger-vein (PLUSVein-FV3) public database for analysis and comparative evaluation with recent research methodologies. The experimental results indicate that the finger vein recognition model proposed in this study achieves an impressive recognition accuracy rate of 99.82% and 95.90% on the FV-USM and PLUSVein-FV3 public databases, respectively, while utilizing just 1.23 million parameters. Moreover, compared to the finger vein recognition approaches proposed in previous studies, the ILCNN introduced in this work demonstrated superior performance.

3.
Pediatr Cardiol ; 41(1): 206-208, 2020 Jan.
Article in English | MEDLINE | ID: mdl-31482238

ABSTRACT

Ascending aortic aneurysm following aortico-left ventricular tunnel (ALVT) repair is an uncommon but life-threatening complication. A 27-year-old man had received patch closure for ALVT at infancy. Eighteen years later, aortic valve replacement for severe aortic regurgitation and direct suture for recurrent slit tunnel were performed. Another 9 years later, ascending aortic replacement was performed because of ascending aortic aneurysm. Thus we report an uncommon case of ascending aortic aneurysm 27 years after the repair of an ALVT.


Subject(s)
Aorta, Thoracic/surgery , Aortic Aneurysm/etiology , Heart Ventricles/surgery , Adult , Aorta, Thoracic/abnormalities , Aortic Aneurysm/diagnostic imaging , Aortic Aneurysm/surgery , Aortic Valve , Aortic Valve Insufficiency/etiology , Aortic Valve Insufficiency/surgery , Computed Tomography Angiography , Heart Defects, Congenital/surgery , Humans , Male
6.
Virus Res ; 147(2): 247-57, 2010 Feb.
Article in English | MEDLINE | ID: mdl-19941916

ABSTRACT

To elucidate the epidemiological relationships between ND outbreaks and genetic lineages, a portion of the F gene (535 bp) and the full-length HN gene (1922 bp) of recent Taiwanese NDVs isolated in 2002-2008 was amplified by reverse transcription (RT)-polymerase chain reaction (PCR) and sequenced. Only a portion of above amplified PCR products of the F and HN genes (374 and 1713 bp) and their deduced amino acid residues were compared with the other 60 NDVs retrieved from GenBank. Most (29/30) of the recent Taiwanese isolates were clustered in subgenotype VIIe while only one isolate was classified as subgenotype VIIc. All the 29 isolates of subgenotype VIIe were further subclassified and termed provisionally as sub-subgenotypes VIIe2 (13 isolates), VIIe3 (5 isolates), and VIIe4 (11 isolates). The sub-subgenotype VIIe2 isolates possessing the motif (112)R-R-Q-K-R-F(117) and amino acid residue substitutions at positions 23 (L to F) and 90 (T to A) were collected during 2002-2005. The sub-subgenotype VIIe3 isolates possessing the motif (112)R-R-K-K-R-F(117) and amino acid residue substitutions at positions 74 (E to G) and 75 (A to G) within epitopes and 114 (Q to K) within cleavage site of F protein were collected during 2003-2006. The sub-subgenotype VIIe4 isolates possessing the motif (112)R-R-Q-K-R-F(117) and amino acid residue substitutions at positions 23 (L to F), 26 (I to T), and 90 (T to A) were collected during 2007-2008. All the NDV isolates in this study exhibited a high intra-cerebral pathogenicity index (ICPI), they were all classified as velogenic type of NDVs. The sub-subgenotype VIIe2 and VIIe4 viruses are now dominant and have been implicated in most of the recent ND outbreaks in Taiwan. Phylogenetic analysis of these isolates revealed that they may have evolved from previously reported local strains (VIIe1). This finding is essential for improving the disease control strategies and development of vaccines for ND.


Subject(s)
Newcastle Disease/epidemiology , Newcastle Disease/virology , Newcastle disease virus/classification , Newcastle disease virus/isolation & purification , Amino Acid Motifs , Amino Acid Substitution/genetics , Animals , Chickens , Cluster Analysis , Genotype , HN Protein/genetics , Molecular Sequence Data , Mutation, Missense , Newcastle disease virus/genetics , Phylogeny , RNA, Viral/genetics , Sequence Analysis, DNA , Sequence Homology , Taiwan/epidemiology , Viral Fusion Proteins/genetics
SELECTION OF CITATIONS
SEARCH DETAIL