In this paper, we address a challenging problem of aesthetic image classification, which is to label an input image as high or low aesthetic quality. We take both the local and global features of images into consideration. A novel deep convolutional neural network named ILGNet is proposed, which combines both the Inception modules and an connected layer of both Local and Global features. The ILGnet is based on GoogLeNet. Thus, it is easy to use a pre-trained GoogLeNet for large-scale image classification problem and fine tune our connected layers on an large scale database of aesthetic related images: AVA, i.e. domain adaptation. The experiments reveal that our model achieves the state of the arts in AVA database. Both the training and testing speeds of our model are higher than those of the original GoogLeNet.

Activated sludge is a highly changeable colloidal system. In this study, the dynamic variation in physicochemical characteristics, especially distribution and abundance of extracellular polymeric substances (EPS) of activated sludges from different WWTPs was investigated in order to establish the relationships between floc properties and the sludge dewatering property. Firstly, it was observed that the total EPS content of the activated sludge was significantly decreased with the rise in temperature.Three-dimensional fluorescence excitation-emission matrix (3D-EEM) spectroscopy analysis indicated that each sludge fraction (soluble EPS, loosely-bound EPS (LB-EPS), tightly bound EPS (TB-EPS) and pellet) from different WWTPs had a similar fluorescence fingerprint in the same time period. In addition, protein-like substances were found to be the dominant components in TB-EPS and pellets regardless of operating time for each WWTP sludge. At low temperatures, soluble EPS and LB-EPS also mainly contained protein-like compounds, while the amount of humic acids of them was increased significantly in the summer. According to Pearson's correlation analysis, normalized CST correlated well with the composition and content of soluble EPS, indicating that the change in soluble EPS properties caused fluctuation of sludge dewatering behavior. Finally, we proposed some operating strategies for improving the dewatering performance of activated sludge in full-scale WWTPs by regulating the soluble EPS properties.Correlation is signicant at the 0.05 level (2-tailed). bCorrelation is signicant at the 0.01 level (2-tailed). c SEPS-soluble EPS, LB-LB-EPS, TB-TB-EPS, S1-region I of soluble EPS, S2-region II of soluble EPS, S3-region III of soluble EPS, S4-region IV of soluble EPS,.This journal is

No abstract

No abstract

Aesthetic quality prediction is a challenging task in the computer vision community because of the complex interplay with semantic contents and photographic technologies. Recent studies on the powerful deep learning based aesthetic quality assessment usually use a binary high-low label or a numerical score to represent the aesthetic quality. However the scalar representation cannot describe well the underlying varieties of the human perception of aesthetics. In this work, we propose to predict the aesthetic score distribution (i.e., a score distribution vector of the ordinal basic human ratings) using Deep Convolutional Neural Network (DCNN). Conventional DCNNs which aim to minimize the difference between the predicted scalar numbers or vectors and the ground truth cannot be directly used for the ordinal basic rating distribution. Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization). Experimental results on large scale aesthetic dataset demonstrate the effectiveness of our introduced CJS-CNN in this task.

No abstract

The root of Polygala tenuifolia Willd. or Polygala sibirica L. exhibits protective effects on the central nervous system and is frequently used to treat insomnia, amnesia, and other cognitive dysfunction. In our study, we studied nine bioactive compounds spanning oligosaccharide esters, saponins, and xanthones by using a sensitive, efficient, and validated method established on ultra-performance liquid chromatography coupled with triple quadrupole mass spectrometry. The quantified result of interesting compounds proved that accumulation of those compounds were found in phloem rather than in xylem. By taking the standardized result of nine compound contents into account, the “Spider-web” analytical result of xylem and phloem from Radix polygalae (RP) unveiled the rationality of RP’s classical use in clinic including discarding the xylem and reserving the phloem. Moreover, the remarkable variation was also revealed from the quantitative result of 45 samples with different diameters from the different origins, which did not significantly correlate with the variation of RP’s diameter. Our study could shed the light on the quality assessment of RP for further research and illustrate the scientific connotation of the processing method of “discarding the xylem and reserving the phloem”.

No abstract