A convolutional neural network-based linguistic steganalysis for synonym substitution steganography.

In this paper, a linguistic steganalysis method based on two-level cascaded convolutional neural networks (CNNs) is proposed to improve the system's ability to detect stego texts, which are generated via synonym substitutions. The first-level network, sentence-level CNN, consists of one convolutional layer with multiple convolutional kernels in different window sizes, one pooling layer to deal with variable sentence lengths, and one fully connected layer with dropout as well as a softmax output, such that two final steganographic features are obtained for each sentence. The unmodified and modified sentences, along with their words, are represented in the form of pre-trained dense word embeddings, which serve as the input of the network. Sentence-level CNN provides the representation of a sentence, and can thus be utilized to predict whether a sentence is unmodified or has been modified by synonym substitutions. In the second level, a text-level CNN exploits the predicted representations of sentences obtained from the sentence-level CNN to determine whether the detected text is a stego text or cover text. Experimental results indicate that the proposed sentence-level CNN can effectively extract sentence features for sentence-level steganalysis tasks and reaches an average accuracy of 82.245%. Moreover, the proposed steganalysis method achieves greatly improved detection performance when distinguishing stego texts from cover texts.

Protective effect of Dl-3n-butylphthalide on learning and memory impairment induced by chronic intermittent hypoxia-hypercapnia exposure.

Cognitive impairment is a common finding in patients with chronic obstructive pulmonary disease (COPD), but little attention has been focused on therapeutic intervention for this complication. Chronic intermittent hypoxia hypercapnia (CIHH) exposure is considered to be responsible for the pathogenesis of COPD. Dl-3n-Butylphthalide (NBP), extracted from Apium graveolens Linn, has displayed a broad spectrum of neuroprotective properties. Our study aimed to investigate the potential of NBP on CIHH-induced cognitive deficits. The cognitive function of rats after CIHH exposure was evaluated by the Morris water maze, which showed that the NBP treated group performed better in the navigation test. NBP activated BDNF and phosphorylated CREB, the both are responsible for neuroprotection. Additionally, NBP decreased CIHH induced apoptosis. Moreover, NBP further induced the expression of HIF-1α, accompanied by the up-regulation of the autophagy proteins Bnip3, Beclin-1 and LC3-II. Finally, NBP also reversed the decreased expression of SIRT1 and PGC-1α, but the expression of Tfam, Cox II and mtDNA remained unchanged. These results suggested that the neuroprotective effects of NBP under CIHH condition possibly occurred through the inhibition of apoptosis, promotion of hypoxia-induced autophagy, and activation of the SIRT1/PGC-1α signalling pathway, while stimulation of mitochondrial biogenesis may not be a characteristic response.

Bacterial diversity of water and sediment in the Changjiang estuary and coastal area of the East China Sea.

The Changjiang estuary and the coastal area of the East China Sea (ECS) represent important interfaces of terrestrial and marine environments. This study included analyses of water and sediments collected during different seasons in these regions to determine the composition of microbial assemblages by means of 16S rRNA gene clone libraries. We retrieved 1946 sequences and 779 distinct operational taxonomic units from 36 clone libraries. Shannon-Weaver diversity index values and rarefaction analysis indicated that bacterial diversity in the sediment samples was much higher than in the water samples. Proteobacteria (72.9%) was the most abundant phylum, followed by Firmicutes (6.4%), Bacteroidetes (4.6%) and Actinobacteria (4.1%). In the water, clone sequences related to Alphaproteobacteria were the most abundant, whereas in the sediment samples, sequences affiliated with Gammaproteobacteria were predominant. Principal coordinate analysis showed that water samples collected from the Changjiang estuary and the ECS clustered separately. However, this spatial pattern could not be observed in sediment samples, which were mainly distinguished from one another by the season. Bacterial diversity in the Changjiang estuary was higher than that in the ECS, which may be the result of the mixing of bacterial communities from the Changjiang River, the estuary and the coastal ocean.