Aiming at the problems of high power consumption and complex scene for scene perception in universal transportation modes, a new transportation mode detection algorithm combining Residual Network (ResNet) and dilated convolution was proposed. Firstly, the 1D sensor data was converted into the 2D spectral image by using Fast Fourier Transform (FFT). Then, the Principal Component Analysis (PCA) algorithm was used to realize the downsampling of the spectral image. Finally, the ResNet was used to mine the local features of transportation modes, and the global features of transportation modes were mined with dilated convolution, so as to detect eight transportation modes. Experimental evaluation results show that, compared with 8 algorithms including decision tree, random forest and AlexNet, the transportation mode recognition algorithm combining ResNet and dilated convolution has the highest accuracy in eight traffic patterns including static, walking and running, and the proposed algorithm has good identification accuracy and robustness.

Traffic mode recognition is an important branch of user behavior recognition, the purpose of which is to identify the user's current traffic mode. Aiming at the demand of the modern intelligent urban transportation system to accurately perceive the user's traffic mode in the mobile device environment, a traffic mode recognition algorithm based on the residual temporal attention neural network was proposed. Firstly, the local features in the sensor time sequence were extracted through the residual network with strong local feature extraction ability. Then, the channel-based attention mechanism was used to recalibrate the different sensor features, and the attention recalibration was performed by focusing on the data heterogeneity of different sensors. Finally, the Temporal Convolutional Network (TCN) with a wider receptive field was used to extract the global features in the sensor time sequence. The data-rich High Technology Computer (HTC) traffic mode recognition dataset was used to evaluate the existing traffic mode recognition algorithms and the residual temporal attention model. Experimental results show that the proposed residual temporal attention model has the accuracy as high as 96.07% with friendly computational overhead for mobile devices, and has the precision and recall for any single class reached or exceeded 90%, which verify the accuracy and robustness of the proposed model. The proposed model can be applied to intelligent transportation, smart city and other domains as a kind of traffic mode detection for supporting mobile intelligent terminal operation.

Entity relation extraction is a critical basic step of question answering, knowledge graph construction and information extraction in the medical field. In view of the fact that there is no open dataset available in the process of building knowledge graph specialized for cardiovascular disease, a professional training set for entity relation extraction of specialized cardiovascular disease knowledge graph was constructed by collecting some medical guidelines for cardiovascular disease and performing the corresponding professional labeling of the categories of entities and relations. Based on this dataset, firstly, Bidirectional Encoder Representation from Transformers and Convolutional Neural Network (BERT-CNN) model was proposed to realize the relation extraction in Chinese corpus. Then, the improved Bidirectional Encoder Representation from Transformers and Convolutional Neural Networks based on whole word mask (BERT(wwm)-CNN) model was proposed to improve the performance of relation extraction in Chinese corpus, according to the fact that word instead of character is the fundamental unit in Chinese. Experimental results show that, the improved BERT(wwm)-CNN model has the accuracy of 0.85, the recall of 0.80 and the F ₁ value of 0.83 on the constructed relation extraction dataset, which are better than those of the comparison models, Bidirectional Encoder Representation from Transformers and Long Short Term Memory (BERT-LSTM) and BERT-CNN, verifying the superiority of the improved BERT(wwm)-CNN.

Time series data of gas station contains multi-dimensional information of fueling behavior, but the data of specific gas station are sparse. The existing abnormal data detection algorithms are not suitable for gas station time series data, because many pseudo outliers are mined and many real abnormal points are missed. To solve the problems, an abnormal detection method based on deep learning was proposed to detect vehicles with abnormal fueling. Firstly, feature extraction was performed on data collected from the gas station through an automatic encoder. Then, a deep learning model Seq2Seq with embedding Bidirectional Long Short-Term Memory (Bi-LSTM) was used to predict the fueling behavior. Finally, the threshold of outliers was defined by comparing the predicted value and the original value. The experiments on a fueling dataset and a credit card fraud dataset verify the effectiveness of the proposed method. Compared with the existing methods, the Root Mean Squared Error (RMSE) of the proposed method is decreased by 21.1% on the fueling dataset, and abnormal detection accuracy of the proposed method is improved by 1.4% on the credit card fraud dataset. Therefore, the proposed method can be applied to detect vehicles with abnormal fueling behavior, improving the management and operational efficiency of gas station.

Traditional data cleaning approaches usually implement cleaning rules specified by business requirements through hard-coding mechanism, which leads to well-known issues in terms of reusability, scalability and flexibility. In order to address these issues, a new Dynamic Rule-based Data Cleaning Method (DRDCM) was proposed, which supports the complex logic operation between various types of rules and three kinds of dirty data repair behavior. It integrates data detection, error correction and data transformation in one system and contributes several unique characteristics, including domain-independence, reusability and configurability. Besides, the formal concepts and terms regarding data detection and correction were defined, while necessary procedures and algorithms were also introduced. Specially, the supported multiple rule types and rule configurations in DRDCM were presented in detail. At last, the DRDCM approach was implemented. Experimental results show that the implemented system provides a high accuracy on the discarded behavior of dirty data repair with real-life data sets. Especially for the attribute required to comply with the statutory coding rules (such as ID card number), whose accuracy can reach 100%. Moreover, these results also indicate that this reference implementation of DRDCM can successfully support multiple data sources in cross-domain scenarios, and its performance does not sharply decrease with the increase of the number of rules. These results further validate that the proposed DRDCM is practical in real-world scenarios.

Automatic Number Plate Recognition (ANPR) data is easier to obtain than private Global Positioning System (GPS) data, and it contains more useful information, but the relatively mature GPS track data mining with vehicle group method did not apply to ANPR data, the existing accompanying vehicle group mining algorithm pays attention to the similarity of the trajectory and ignores the time factor when dealing with small amount of ANPR data. A clustering method based on trajectory feature to excavate the accompanying vehicle group was proposed. Aiming at the fact that the sampling points are fixed and the sampling time is uncertain in the ANPR data, whether two objects were accompanied was determined by the number of co-occurrence in the trajectory. The co-occurrence definition introduced the Hausdorff distance, taking into account the location, direction and time characteristics of the trajectory. The accompanying vehicle group with different but adjacent sampling points and similar trajectories was minned to improve the mining efficiency. The experimental results show that the proposed method is more effective than the existing method to excavate the vehicle group, and improves the efficiency by nearly two times when identifying the non-accompanying mode data.

Aiming at the problem of channel insecurity caused by wireless transmission in mobile Radio Frequency IDentification (RFID) system, a low-cost mobile mutual authentication protocol based on the Hash function was proposed by considering the complexity of the protocol and the implementation cost of the tag. In the protocol, the square operation was used to dynamically update the tag identifier. And the reader identifier, the pseudo random function and Hash function were used to enhance the identity authentication between the reader and the back-end server, which can improve the mobility of the system. Compared with the typical authentication protocols based on the Hash function and the tag ownership transfer protocol, this proposed protocol can resist tracking, impersonation, replay, man-in-the-middle, Denial of Service (DoS) attacks, etc., which can ensure the security of tag ownership transfer. The efficiency of calculation and storage was analyzed, and the results show that the calculation of the tag is reduced and the storage capacity is lower.