The frequency distribution of International Classification of Diseases （ICD） codes is long tail， resulting in it is challenging to perform multi-label text classification for few-shot code. An MNIC （Meta Network-based automatic ICD Coding model） was proposed to solve the problem of insufficient training data in few-shot code classification. Firstly， instances in the feature space and features in the semantic space were fitted to the same space for mapping， and the feature representations of many-shot codes were mapped to their classifier weights， thus learning meta-knowledge through meta-network. Secondly， the learned meta-knowledge was transferred from data-abundant many-shot codes to data-poor few-shot codes. Finally， a reasonable explanation was provided for the transferability and generality of meta-knowledge. Experimental results on MIMIC-Ⅲ dataset show that MNIC improves the Micro-F1 and Micro Area Under Curve （Micro-AUC） of few-shot codes by 3.77 and 3.82 percentage points respectively compared to the suboptimal AGM-HT （Adversarial Generative Model conditioned on code descriptions with Hierarchical Tree structure） model， indicating that the proposed model improves the performance of few-shot code classification significantly.

Infrared small targets occupy few pixels and lack features such as color， texture and shape， so it is difficult to track them effectively. To solve this problem， an infrared small target tracking method based on state information was proposed. Firstly， the target， background and distractors in the local area of the small target to be detected were encoded to obtain dense local state information between consecutive frames. Secondly， feature information of the current and the previous frames were input into the classifier to obtain the classification score. Thirdly， the state information and the classification score were fused to obtain the final degree of confidence and determine the center position of the small target to be detected. Finally， the state information was updated and propagated between the consecutive frames. After that， the propagated state information was used to track the infrared small target in the entire sequences. The proposed method was validated on an open dataset DIRST （Dataset for Infrared detection and tRacking of dim-Small aircrafT）. Experimental results show that for infrared small target tracking， the recall of the proposed method reaches 96.2%， and the precision of the method reaches 97.3%， which are 3.7% and 3.7% higher than those of the current best tracking method KeepTrack. It proves that the proposed method can effectively complete the tracking of small infrared targets under complex background and interference.

With the deepening of the network in the Medical Named Entity Recognition （MNER） problem， the recognition accuracy and computing power requirements of the deep learning-based recognition models are unbalanced. Aiming at this problem， a medical named entity recognition model CasSAttMNER （Cascade Self-Attention Medical Named Entity Recognition） based on deep auto-encoding was proposed. Firstly， a depth difference balance strategy between encoding and decoding was used in the model， and the distilled Transformer language model RBT6 was used as the encoder to reduce the encoding depth and the computing power requirements for training and application. Then， Bidirectional Long Short-Term Memory （BiLSTM） network and Conditional Random Field （CRF） were used to propose a cascaded multi-task dual decoder to complete entity mention sequence labeling and entity class determination. Finally， based on the self-attention mechanism， the model design was optimized by effectively representing the implicit decoding information between the entity classes and the entity mentions. Experimental results show that the F value measurements of CasSAttMNER on two Chinese medical entity datasets can reach 0.943 9 and 0.945 7， which are 3 percentage points and 8 percentage points higher than those of the baseline model， respectively， verifying that this model further improves the decoder performance.

Resource load prediction with high accuracy can provide a basis for real-time task scheduling， thus reducing energy consumption. However， most prediction models for time series of resource load make short-term or long-term prediction by extracting the long-time series dependence characteristics of time series and neglecting the short-time series dependence characteristics of time series. In order to make a better long-term prediction of resource load， a new edge computing resource load prediction model based on long-short time series feature fusion was proposed. Firstly， the Gram Angle Field （GAF） was used to transform time series into image format data， so as to extract features by Convolutional Neural Network （CNN）. Then， the CNN was used to extract spatial features and short-term data features， the Long Short-Term Memory （LSTM） network was used to extract the long-term time series dependent features of time series. Finally， the extracted long-term and short-term time series dependent features were fused through dual-channel to realize long-term resource load prediction. Experimental results show that， the Mean Absolute Error （MAE）， Root Mean Square Error （RMSE） and R-squared（R²） of the proposed model for CPU resource load prediction in Alibaba cloud clustering tracking dataset are 3.823， 5.274， and 0.815 8 respectively. Compared with the single-channel CNN and LSTM models， dual-channel CNN+LSTM and ConvLSTM+LSTM models， and resource load prediction models such as LSTM Encoder-Decoder （LSTM-ED） and XGBoost， the proposed model can provide higher prediction accuracy.