Deep convolutional adversarial graph autoencoder using positive pointwise mutual information for graph embedding

Graph embedding aims to map the high-dimensional nodes to a low-dimensional space and learns the graph relationship from its latent representations.Most existing graph embedding methods focus on the topological structure of graph data,but ignore the semantic information of graph data,which results in the unsatisfied performance in practical applications.To overcome the problem,this paper proposes a novel deep convolutional adversarial graph autoencoder(GAE)model.To embed the semantic information between nodes in the graph data,the random walk strategy is first used to construct the positive pointwise mutual information(PPMI)matrix,then,graph convolutional net-work(GCN)is employed to encode the PPMI matrix and node content into the latent representation.Finally,the learned latent representation is used to reconstruct the topological structure of the graph data by decoder.Furthermore,the deep convolutional adversarial training algorithm is introduced to make the learned latent representation conform to the prior distribution better.The state-of-the-art experimental results on the graph data validate the effectiveness of the proposed model in the link prediction,node clustering and graph visualization tasks for three standard datasets,Cora,Citeseer and Pubmed.

Aspect-Based Sentiment Classification Using Deep Learning and Hybrid of Word Embedding and Contextual Position

Aspect-based sentiment analysis aims to detect and classify the sentiment polarities as negative,positive,or neutral while associating them with their identified aspects from the corresponding context.In this regard,prior methodologies widely utilize either word embedding or tree-based rep-resentations.Meanwhile,the separate use of those deep features such as word embedding and tree-based dependencies has become a significant cause of information loss.Generally,word embedding preserves the syntactic and semantic relations between a couple of terms lying in a sentence.Besides,the tree-based structure conserves the grammatical and logical dependencies of context.In addition,the sentence-oriented word position describes a critical factor that influences the contextual information of a targeted sentence.Therefore,knowledge of the position-oriented information of words in a sentence has been considered significant.In this study,we propose to use word embedding,tree-based representation,and contextual position information in combination to evaluate whether their combination will improve the result’s effectiveness or not.In the meantime,their joint utilization enhances the accurate identification and extraction of targeted aspect terms,which also influences their classification process.In this research paper,we propose a method named Attention Based Multi-Channel Convolutional Neural Net-work(Att-MC-CNN)that jointly utilizes these three deep features such as word embedding with tree-based structure and contextual position informa-tion.These three parameters deliver to Multi-Channel Convolutional Neural Network(MC-CNN)that identifies and extracts the potential terms and classifies their polarities.In addition,these terms have been further filtered with the attention mechanism,which determines the most significant words.The empirical analysis proves the proposed approach’s effectiveness compared to existing techniques when evaluated on standard datasets.The experimental results represent our approach outperforms in the F1 measure with an overall achievement of 94%in identifying aspects and 92%in the task of sentiment classification.

Spatial signalling mediated by the transforming growth factor-β signalling pathway during tooth formation

Tooth development relies on sequential and reciprocal interactions between the epithelial and mesenchymal tissues, and it is continuously regulated by a variety of conserved and specific temporal-spatial signalling pathways. It is well known that suspensions of tooth germ cells can form tooth-like structures after losing the positional information provided by the epithelial and mesenchymal tissues. However, the particular stage in which the tooth germ cells start to form tooth-like structures after losing their positional information remains unclear. In this study, we investigated the reassociation of tooth germ cells suspension from different morphological stages during tooth development and the phosphorylation of Smad2/3 in this process. Four tooth morphological stages were designed in this study. The results showed that tooth germ cells formed odontogenic tissue at embryonic day （E） 14.5, which is referred to as the cap stage, and they formed tooth-like structures at E16.5, which is referred to as the early bell stage, and E18.5, which is referred to as the late bell stage. Moreover, the transforming growth factor-β signalling pathway might play a role in this process.

An Autonomous Overtaking Maneuver Based on Relative Position Information

Reliable and efficient overtaking maneuvers are important and challenging for autonomous vehicles.Higher precision position information is thus required,rather than that traditional global navigation satellite systems can provide.In this paper,we try to perform reliable autonomous overtaking controls of vehicles,mainly based on the“relative”position information,including the distance,angle and velocity between vehicles,which can be achieved by on-board radars.To reduce the complexity of maneuvers,a fuzzy inference system is applied to analyze the driving behavior of the preceding vehicle based on the obtained consecutive relative position information.An output of“safe”or“dangerous”will be sent to the decision part based on reinforcement learning frameworks.Various overtaking maneuvers including“conservative”and“aggressive”can be obtained accordingly.Furthermore,we propose another overtaking strategy that vehicles can share their maneuver information during overtaking process via wireless links.Numeric results validate our analysis,and can provide meaningful performance benchmarks for practical system implementations.

Study of Human Action Recognition Based on Improved Spatio-temporal Features

Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combining local spatio-temporal feature and global positional distribution information(PDI) of interest points, a novel motion descriptor is proposed in this paper. The proposed method detects interest points by using an improved interest point detection method. Then, 3-dimensional scale-invariant feature transform(3D SIFT) descriptors are extracted for every interest point. In order to obtain a compact description and efficient computation, the principal component analysis(PCA) method is utilized twice on the 3D SIFT descriptors of single frame and multiple frames. Simultaneously, the PDI of the interest points are computed and combined with the above features. The combined features are quantified and selected and finally tested by using the support vector machine(SVM) recognition algorithm on the public KTH dataset. The testing results have showed that the recognition rate has been significantly improved and the proposed features can more accurately describe human motion with high adaptability to scenarios.