In recent years, with the development of social economy and technology, the brain-computer interface based on motor imagery(MI-BCI) has gradually become the focus content of many re-searchers. However, the motor imagery EEG signal (MI-EEG) itself has the characteristics of non-linearity and low signal-to-noise ratio, and because the characteristics of different domains of MI-EEG cannot be effectively combined, the recognition rate of MI-EEG is unsatisfactory. To overcome the above problems, this paper proposes a Transformer-based one-dimensional convolutional neural network model(CNN-Transformer) for the classification and recognition of four types of motor imagery EEG signals. Firstly, the artifacts of the original EEG are removed and new time-space-frequency features are constructed by preprocessing such as bandpass filtering and PCA dimensionality; then, the local features in the temporal dimension are extracted through the convolution and pooling operations of 1D-CNN, while reducing the dimension of the time feature; next, the Transformer based on the attention mechanism is used to extract more abstract and high-level temporal features from multiple perspectives; finally, the classification results are integrated and output through the fully connected layer. The performance of the CNN-Transformer model is evaluated using the competition dataset 2008 BCI-Competition 2A. The results show that the average accuracy and kappa value of the CNN-Transformer model are as high as 99.29%(±0.07%) and 98.43%(±0.21), respectively, which are 3.72% and 7.68% higher than the classical architecture (CNN-LSTM). This model provides a design idea for improving the accuracy of MI-EEG classification and recognition, and also lays a foundation for the wide application of MI-BCI.

To solve the problems of large number of notifications, low relevance and no relevant knowledge base in the field of discipline inspection, a method of constructing a knowledge map of discipline inspection and supervision based on the BERT-BiLSTM-CRF model is proposed. Firstly, the unstructured data is collected from the content of the disciplinary inspection and supervision report. Through the bottom-up method the notification concept layer is constructed. By using deep learning models to extract entities. Then the entities and semantic relations are stored in the graph database Neo4j and displayed in the form of a knowledge graph. This method realizes the whole process from unstructured data to knowledge graph, and provides technical reference for the construction of domain-based knowledge graph. Simultaneously, the knowledge map of discipline inspection field established through the example can find the hidden association between those who break the law and discipline, prevent criminal facts in advance, and provide support and help for discipline inspection personnel to implement the spirit of the eight-point regulation of the Central Committee and continue to fight against the “four winds” and other actions.

To realize the prognostics and health management (PHM) of the mechanical system, it is the key to accurately predict the remaining useful life (RUL) of the equipment. The network captured features at different time steps will contribute to the final RUL prediction to varying degrees. Therefore, a deep learning network based on the attention mechanism is proposed. Firstly, the raw sensor data is passed to the Bi-LSTM network to capture the long-term dependence of features. Secondly, the features extracted by Bi-LSTM are passed to the attention mechanism for feature weighting, thereby giving greater weight to important features. Finally, the weighted features are input into the fully connected network to predict the RUL of the turbofan engine. Using the data set C-MAPSS to explore the feasibility of this method. The results show that this method is more accurate than other RUL prediction methods.

This paper propose a new method to extract ontology concepts from multiple text of the same type. This method uses mutual information and document frequency. According to the mutual information tend to choose the low frequency words, combining mutual information and document frequency to avoid this problem. In this paper, a number of financial and economic reports are reported as the corpus. First of all, do the text preprocessing, and then based on the N-gram algorithm to generate a set of candidate phrases, and finally use the statistics and the rules to screen for the concept of ontology from candidate phrases.

The e-map is the most important part in vehicle navigation system. Functional requirements for the road map database vary in different navigation phases. Though there are various road network models, their traditional road network structures, unfortunately, do not solve the problem well. Therefore this paper proposes a feature-based data model with two level structures. The level-one is a feature-oriented geometry network used for map showing the level-two is a node-link based logical network for route planning. Further, a two-layer network topological structure in logical network is presented, which accords with the practical driving habit better than traditional way treating the entire road network as one graph.

Dynamic navigation is the advanced level of navigation service. The construction for an efficient and effective navigation data model to meet the requirements of dynamic navigation is the key point of the study. It first introduces the system requirements of dynamic navigation for navigation data. Then it briefly discusses several current navigation data models, such as KIWI, SDAL and ISO-GDF. The study found that current navigation data models have limits in their design for dynamic navigation and more work should be done in the research of real time navigation data models. In the paper, it discusses the content of real time navigation data and gets that the content mainly contains data of traffic events and data of traffic flow. Both of them are different feature classes of real-time navigation data based on ISO-GDF model. The descriptions of them include definition, properties and relations. In the model construction, the relations among events, the executants of events and target statuses are given consideration. The model which is got by the study can be used with a certain physical data models in dynamic navigation applications.