5 results on '"Peng, Pai"'
Search Results
2. Gas Classification Using Deep Convolutional Neural Networks.
- Author
-
Peng, Pai, Zhao, Xiaojin, Pan, Xiaofang, and Ye, Wenbin
- Subjects
- *
ARTIFICIAL neural networks , *ELECTRONIC noses , *COMPUTER vision , *MULTILAYER perceptrons , *SUPPORT vector machines - Abstract
In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP). [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
3. Combined Radiofrequency Ablation and Left Atrial Appendage Closure in Atrial Fibrillation and Systolic Heart Failure.
- Author
-
Sun, Jian, Zhang, Rui, Yang, Mei, Li, Wei, Zhang, Peng-Pai, Mo, Bin-Feng, Wang, Qun-Shan, Chen, Mu, and Li, Yi-Gang
- Subjects
- *
ATRIAL fibrillation , *VENTRICULAR ejection fraction , *HEART failure , *CATHETER ablation , *DISEASE risk factors - Abstract
Background: Managing patients with atrial fibrillation (AF) and comorbid heart failure (HF) with reduced (HFrEF) or mildly reduced ejection fraction (HFmrEF) is of clinical importance but a great challenge. This study aimed to evaluate the clinical benefit of the combined radiofrequency catheter ablation (RFCA) and left atrial appendage closure (LAAC) procedure in AF patients complicated with systolic HF. Methods: AF patients with HFrEF or HFmrEF who underwent the combined RFCA and LAAC procedure were prospectively enrolled in the LAACablation registry. The procedural complications and long-term outcomes were evaluated. Another cohort of AF patients with systolic HF who did not undergo either RFCA or LAAC were used for prognosis comparison. Results: Among 802 AF patients who underwent the combined procedure, 65 patients were comorbid with systolic HF (25 with HFrEF and 40 with HFmrEF). The overall procedural complication rate was 9.2%, which was mainly attributed to acute decompensated HF (6.2%). Accompanied with markedly reduced AF burden (from median [25th, 75th percentile]: 100 [100, 100] to 0 [0, 1.2]%, p < 0.001), upward trajectories of cardiac function were observed in 51 (78.4%) patients, showing improvement in New York Heart Classification (p < 0.01), natriuretic peptide levels (from 1492 [809, 3259] to 413 [163, 880] pg/mL, p < 0.001) and left ventricular EF (from 42.6 ± 5.3 to 53.8 ± 8.2%, p < 0.001). During the 27-month follow-up period, death, thromboembolism, major bleeding, and HF rehospitalization were observed in three, one, one, and four patients, respectively. The observed event rates showed a significant reduction compared with the non-procedure AF-HF cohort (n = 138; for composite endpoint: hazard ratio: 2.509, 95% confidence interval: 1.415–4.449, p = 0.002) and with the respective rates predicted by risk scores. Conclusions: Combining RFCA and LAAC achieves acceptable safety and credible long-term efficacy in AF patients with systolic HF. Further randomized studies are warranted in a larger patient cohort. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
4. Multiband Image Fusion via Regularization on a Riemannian Submanifold.
- Author
-
Pan, Han, Jing, Zhongliang, Leung, Henry, Peng, Pai, and Zhang, Hao
- Subjects
- *
IMAGE fusion , *MULTISPECTRAL imaging , *SPATIAL resolution , *LATENT variables , *GEODESICS - Abstract
Multiband image fusion aims to generate high spatial resolution hyperspectral images by combining hyperspectral, multispectral or panchromatic images. However, fusing multiband images remains a challenge due to the identifiability and tracking of the underlying subspace across varying modalities and resolutions. In this paper, an efficient multiband image fusion model is proposed to investigate the latent structures and intrinsic physical properties of a multiband image, which is characterized by the Riemannian submanifold regularization method, nonnegativity and sum-to-one constraints. An alternating minimization scheme is proposed to recover the latent structures of the subspace via the manifold alternating direction method of multipliers (MADMM). The subproblem with Riemannian submanifold regularization is tackled by the projected Riemannian trust-region method with guaranteed convergence. The effectiveness of the proposed method is demonstrated on two multiband image fusion problems: (1) hyperspectral and panchromatic image fusion and (2) hyperspectral, multispectral and panchromatic image fusion. The experimental results confirm that our method demonstrates superior fusion performance with respect to competitive state-of-the-art fusion methods. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
5. A Novel Pathway of Chlorimuron-Ethyl Biodegradation by Chenggangzhangella methanolivorans Strain CHL1 and Its Molecular Mechanisms.
- Author
-
Yu, Zhixiong, Dai, Yumeng, Li, Tingting, Gu, Wu, Yang, Yi, Li, Xiang, Peng, Pai, Yang, Lijie, Li, Xinyu, Wang, Jian, Su, Zhencheng, Li, Xu, Xu, Mingkai, and Zhang, Huiwen
- Subjects
- *
HERBICIDES , *HERBICIDE residues , *BIODEGRADATION , *SULFONYLUREAS , *TRANSCRIPTOMES - Abstract
Chlorimuron-ethyl is a widely used herbicide in agriculture. However, uncontrolled chlorimuron-ethyl application causes serious environmental problems. Chlorimuron-ethyl can be effectively degraded by microbes, but the underlying molecular mechanisms are not fully understood. In this study, we identified the possible pathways and key genes involved in chlorimuron-ethyl degradation by the Chenggangzhangella methanolivorans strain CHL1, a Methylocystaceae strain with the ability to degrade sulfonylurea herbicides. Using a metabolomics method, eight intermediate degradation products were identified, and three pathways, including a novel pyrimidine-ring-opening pathway, were found to be involved in chlorimuron-ethyl degradation by strain CHL1. Transcriptome sequencing indicated that three genes (atzF, atzD, and cysJ) are involved in chlorimuron-ethyl degradation by strain CHL1. The gene knock-out and complementation techniques allowed for the functions of the three genes to be identified, and the enzymes involved in the different steps of chlorimuron-ethyl degradation pathways were preliminary predicted. The results reveal a previously unreported pathway and the key genes of chlorimuron-ethyl degradation by strain CHL1, which have implications for attempts to enrich the biodegradation mechanism of sulfonylurea herbicides and to construct engineered bacteria in order to remove sulfonylurea herbicide residues from environmental media. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.