Aiming at the problem that the target regions of rectal cancer show different sizes， shapes， textures， and boundary clarity on Magnetic Resonance Imaging （MRI） images， to overcome the individual variability among patients and improve the segmentation accuracy， an Adjacent Slice Attention Fusion Network for rectal cancer segmentation （ASAF-Net） was proposed. Firstly， using High Resolution Network （HRNet） as the backbone network， the high-resolution feature representation was maintained during the feature extraction process， thereby reducing the loss of semantic information and spatial location information. Secondly， the multi-scale contextual semantic information between adjacent slices was fused and enhanced by the Adjacent Slice Attention Fusion （ASAF） module， so that the network was able to learn the spatial features between adjacent slices. Finally， in the decoder， the co-training of Fully Convolutional Network （FCN） and Atrous Spatial Pyramid Pooling （ASPP） segmentation heads was carried out， and the large differences between adjacent slices during training was reduced by adding consistency constraints between adjacent slices as an auxiliary loss. Experimental results show that compared with HRNet， ASAF-Net improves the mean Intersection over Union （IoU） and mean Dice Similarity Coefficient （DSC） by 1.68 and 1.26 percentage points， respectively， and reduces the 95% mean Hausdorff Distance （HD） by 0.91 mm. At the same time， ASAF-Net can achieve better segmentation results in both internal filling and edge prediction of multi-objective target regions in rectal cancer MRI image， and helps to improve physician efficiency in clinical auxiliary diagnosis.

In actual industrial production， Informer model will lose a large number of temporal characteristics during feature extraction due to its probabilistic sparsity mechanism. To address this shortcoming of Informer model and meet the demands for prediction speed and efficiency in industrial production， a Convolutional Neural Network （CNN）-enhanced Informer model was proposed. Short-Time Fourier Transform （STFT） was introduced to process sequence to obtain frequency-domain features of the data， thereby further reducing feature loss caused by probabilistic sparse attention mechanism and improving prediction accuracy. On public datasets， ETT （Electricity Transformer Temperature）， ECL （Electricity Consumption Load）， as well as one private dataset， comparative experiments were conducted between the proposed model and four models widely used in the industrial field， including Long Short-Term Memory （LSTM） and AutoRegressive Integrated Moving Average （ARIMA） model. Experimental results show that both Mean Squared Error （MSE） and Mean Absolute Error （MAE） of the proposed model are decreased.