Focusing on the issues that the relationships between the stations are affected by the sparse distribution of surface meteorological stations and it is difficult to infer the strengths of relationships between the stations， a Deep learning Model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data was proposed， namely GDM， which included Spatio-Temporal Attention （TSA） ， Double Graph neural Long Short-Term Memory （DG-LSTM） network encoding and Edge-Node transform Gated Recurrent Unit （EN-GRU） decoding modules. Firstly， TSA module was utilized to extract MOD11A1 image features and form the temperature time series of multiple virtual meteorological stations， so as to alleviate the impact of sparse distribution of surface meteorological stations on the relationships between the stations. Secondly， DG-LSTM encoder was used to calculate the strengths of the relationships among surface meteorological stations and virtual meteorological stations via fusing two sets of temperature time series. Finally， EN-GRU decoder was adopted to model the temperature time series relationships between surface meteorological stations through combining the inter-station relationship strengths. Experimental results show that compared with 2-Dimensional Convolutional Neural Network （2D-CNN）， Long Short-Term Memory-Fully Connected network （LSTM-FC）， Long Short-Term Memory neural network Extended （LSTME） and Long Short-Term Memory and AdaBoost network （LSTM-AdaBoost）， GDM has the Average Absolute Error （MAE） of temperature prediction in 24 hours at 10 surface meteorological stations reduced by 0.383 ℃， 0.184 ℃， 0.178 ℃ and 0.164 ℃ respectively. It can be seen that GDM can improve the prediction accuracy of the temperature for meteorological stations in the next 24 hours.

In order to solve the problems of high computing cost and over-fitting of the model caused by complicated network structure in pulmonary nodule detection method, an improved residual network structure combining deep separable convolution and pre-activation was proposed. And the proposed network structure was applied to a pulmonary nodule detection model. Based on the target detection network Faster R-CNN, with U-Net coder-decoder structure adopted, the deep separable convolution and pre-activation operations were used by the model to improve the 3D residual network structure. Firstly, with the use of deep separable convolution, the complexity and computing cost of the model were reduced. Then, the regularization of the model was improved by introducing the pre-activation operation, and the phenomenon of overfitting was alleviated. Finally, the rectangular convolution kernel was used to expand the receptive field of the convolution operation on the premise that the computing cost of the model was slightly increased, so as to effectively take into account both the global and local characteristics of the pulmonary nodules. On the LUNA16 dataset, the proposed method has the sensitivity of 96.04%, and the Free-response area under the Receiver Operating Characteristic curve (FROC) score of 83.23%. The experimental results show that the method improves the sensitivity of pulmonary nodule detection, effectively reduces the average number of false positives in the detection results, and improves the detection efficiency. This proposed method can effectively assist radiologists in detecting pulmonary nodules.

Because the existing trajectory clustering algorithms in the similarity measurement usually used the spatial characteristics as the standards the characteristics lacking the consideration of temporal, a trajectory data clustering algorithm based on spatial-temporal pattern was proposed. The proposed algorithm was based on partition-and-group framework. Firstly, the trajectory feature points were extracted by using the curve edge detection method. Then the sub-trajectory segments were divided according to the trajectory feature points. Finally, the clustering algorithm based on density was used according to the spatio-temporal similarity between sub-trajectory segments. The experimental results show that the trajectory feature points extracted using the proposed algorithm are more accurate to describe the trajectory structure under the premise that the feature points have better simplicity. At the same time, the similarity measurement based on spatio-temporal feature obtains better clustering result by taking into account both spatial and temporal characteristics of trajectory.