Convolutional Neural Network(CNN) and Recurrent Neural Network(RNN) have been widely used in the field of text sentiment analysis and have achieved good results. However, there is an anteroposterior dependency between texts, although CNN can extract local information between consecutive words of a sentence, it ignores the contextual semantic information between words. Bidirectional GRU can make up for the shortcomings that CNN can't extract contextual semantic information of long text, but it can't extract the local features of the text as well as CNN. Therefore, we propose a multi-channel model that combines the CNN and the bidirectional gated recurrent unit network with attention mechanism (MC-AttCNN-AttBiGRU). The model can pay attention to the words that are important to the sentiment polarity classification in the sentence through the attention mechanism and combine the advantages of CNN to extract local features of text and bidirectional GRU to extract contextual semantic information of long text, which improves the text feature extraction ability of the model. The experimental results on the IMDB dataset and Yelp 2015 dataset show that the proposed model can extract more rich text features than other baseline models, and can achieve better results than other baseline models. INDEX TERMS Convolutional Neural Network, Bidirectional gated recurrent unit network, attention mechanism, text sentiment orientation analysis.

Gastrointestinal nematodes (GIN) are a crucial restraint to grazing sheep production worldwide. This study was conducted to determine the infections and anthelmintic resistance (AR) of GIN in pasture-based sheep in the Eastern Inner Mongolia, China. GIN eggs were tested from 600 grazing sheep feces of 10 farms using saturated saline flotation method and McMaster's method. The egg hatch test (EHT) and the faecal egg count reduction test (FECRT) were used to evaluate resistance of GIN to anthelmintics. We found that the average infection rate was 79.2% (range: 45%-100%). The grand mean faecal egg count (FEC) was 1813.2 eggs per gram (EPG) (range: 0-32400 EPG). There were significant differences in GIN infection among different breeds of sheep. The sequence of infection intensity and infection rate were Small fat tail > Ujimqin > Ju Ud (p<0.05). The 50% effective doses (ED50) of albendazole(ABZ) and levamisole (LMS) for expelling were 5.670 µg/mL and 0.302 µg/mL, respectively. The percentage reductions of avermectin (AVM), ivermectin (IVM), ABZ and LMS were 81.28%, 86.49%, 76.21% and 96.59%, respectively. The most predominant parasite genus in all four anthelmintics was Haemonchus. In these tested areas, mixed infections of GIN in grazing sheep were very common. AR, especially in Haemonchus, was a serious problem in these sheep flocks. Thus, actions are urgently required to taken to mitigate the worsening situation.

No abstract

No abstract

No abstract