Search

Your search keyword '"Jia, Xiangxiang"' showing total 24 results
Start Over Author "Jia, Xiangxiang"
24 results on '"Jia, Xiangxiang"'

8. Improving GAN-based feature extraction for hyperspectral images classification

Author

Jia Xiangxiang, Ding Fanchang, Wenjie Xu, Baofeng Guo, and Chi Haoyu

Subjects
Discriminator, Computer science, Generalization, business.industry, Deep learning, Feature extraction, Hyperspectral imaging, Pattern recognition, Convolutional neural network, Atomic and Molecular Physics, and Optics, Computer Science Applications, Support vector machine, Principal component analysis, Artificial intelligence, Electrical and Electronic Engineering, business
Abstract

With the recent development of machine learning theory, many deep learning based methods have been proposed to extract features from hyperspectral sensed images (HSIs) and superior performance has been achieved. Although the data of HSIs is characterized by its high volume as well as with rich spectral and spatial information, the number of the labeled samples is always very limited. But many deep learning methods, especially the supervised approaches, often require numerous labeled samples to extract the effective features, and a prolonged training procedure is inevitable. To expand the set of the labeling samples, a huge amount of manpower and material resources are required, which may make the application unaffordable. In order to alleviate the dependence on HSIs’ labeled samples, in this paper an unsupervised spatial-spectral feature extraction method is proposed. Combining the two-dimensional convolutional neural network (2DCNN) with generative adversarial networks (GANs), the requirement of the labeled samples is reduced for the training of a learning network, and the spatial-spectral characteristic of the HSIs is utilized at the same time. Moreover, the principal component analysis (PCA) is introduced as a preprocess for the high-dimensional hyperspectral data, which not only removes redundant information, but also fits the proposed feature extraction model to hyperspectral data with different dimensions. To improve the generalization capability of the proposed model, a gradient penalty term is further investigated in the objective function of the GAN’s discriminator, which can optimize the discriminator’s convergence and improve the model’s overall generalization capability. Finally, a support vector machine is applied to classify the extracted features. Experimental results on three real data sets show that the proposed method can extract features from the hyperspectral data effectively. Through the GANs-based feature extraction and the specialized regularization, the proposed method achieves a good level of generalization capability, in which a model validated on a single dataset can be extended to different datasets while a satisfactory performance still remained.

Published
2021

23. Evaluating the effect of antibiotics on aerobic granular sludge treatment of pharmaceutical wastewater.

Author

Cao Z, Sai A, Jia X, and Zhang X

Subjects
Aerobiosis, Water Pollutants, Chemical, Wastewater chemistry, Tetracycline pharmacology, Phosphorus chemistry, Bioreactors, Drug Industry, Sewage, Anti-Bacterial Agents pharmacology, Waste Disposal, Fluid methods
Abstract

Aerobic granular sludge (AGS) has been widely applied in pharmaceutical wastewater treatment due to its advantages such as high biomass and excellent settling performance. However, the influence of commonly found antibiotics in pharmaceutical wastewater on the operational efficiency of AGS has been poorly explored. This study investigated the effects of tetracycline (TE) on AGS treating pharmaceutical wastewater at room temperature and analyzed the related mechanisms. The results demonstrate a dose-dependent relationship between TE's effects on AGS. At concentrations below the threshold of 0.1 mg/L, the effects are considered trivial. In contrast, TE with more than 2.0 mg/L reduces the performance of AGS. In the 6.0 mg/L TE group, COD, TN, and TP removal efficiencies decreased to 72.6-75.5, 54.6-58.9, and 71.6-75.8%, respectively. High concentrations of TE reduced sludge concentration and the proportion of organic matter in AGS, leading to a decline in sludge settling performance. Elevated TE concentrations stimulated extracellular polymeric substance secretion, increasing polymeric nitrogen and polymeric phosphorus content. Intracellular polymer analysis revealed that high TE concentrations reduced polyhydroxyalkanoates but enhanced glycogen metabolism. Enzyme activity analysis disclosed that high TE concentrations decreased the activity of key enzymes associated with nutrient removal., Competing Interests: The authors declare there is no conflict., (© 2024 The Authors This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY 4.0), which permits copying, adaptation and redistribution, provided the original work is properly cited (http://creativecommons.org/licenses/by/4.0/).)

Published
2024
Full Text
View/download PDF

24. Synthesis of 6-O-poly(ϵ-caprolactone)-L-ascorbic acid and its controlled release from supramolecular polymer micelles.

Author

Li F, Chen B, Ping Z, Jia X, Guo X, Xiao L, and Liu L

Subjects
Chemistry Techniques, Synthetic, Drug Carriers administration & dosage, Drug Carriers chemical synthesis, HEK293 Cells, Humans, Magnetic Resonance Spectroscopy, Microscopy, Electron, Transmission, Nanospheres ultrastructure, Particle Size, Polymers pharmacokinetics, beta-Cyclodextrins administration & dosage, Ascorbic Acid chemistry, Drug Carriers chemistry, Micelles, Polyesters chemistry, Polymers chemical synthesis
Abstract

Lipophilic 6-O-poly (ϵ-caprolactone)-L-ascorbic acid (AA-6-PCL) is synthesized through ROP of ϵ-caprolactone (CL). The number of repeating CL units in the polymer chain varies from 6 to 19. AA-6-PCL loaded supramolecular polymer micelles (SMPMs) are constructed with β-cyclodextrin (β-CD) and PCL as blocks. Transmission electron microscopy images show a nanospheric morphology of the micelles with a size range of 43.3 ± 5.0 nm. The drug loading contents are 22.53-39.23% for AA-6-PCL. AA-6-PCL exhibits high radical scavenging capacity (93.96-96.73%) and efficient scavenging potency, and a cytotoxicity study proves the excellent cytocompatibility of AA-6-PCL loaded β-CD/PCL SMPMs, which altogether herald their potential application in the study of the induced pluripotent stem cells., (© 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.)

Published
2014
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results