Remote sensing data have high spatio-temporal correlation and complex surface features， which makes the privacy protection of the data challenging. As a distributed learning method with the goal of protecting data privacy of the participants， federated learning provides an effective solution to overcome the challenges faced by remote sensing data privacy protection. However， during the training phase of federated learning models， malicious attackers may infer private information of the participants through inversion， leading to the disclosure of sensitive information. Aiming at the privacy leakage problem of remote sensing data in federated learning training， a federated learning privacy protection scheme based on local differential privacy was proposed. Firstly， the model was pre-trained， the layer importance of the model was calculated， and the privacy budget was allocated reasonably based on the layer importance. Then， local differential privacy protection was achieved by performing a crop transformation on the model update and performing adaptive random disturbance on the crop value. Finally， model correction was employed to further improve the model performance when the aggregated disturbance was updated. Theoretical analysis and simulation results show that the proposed scheme can not only provide appropriate differential privacy protection for each participant and prevent inferring privacy sensitive information through inversion effectively， but also outperform the segmentation mechanism-based disturbance scheme in accuracy on three remote sensing datasets by 3.28 to 3.93 percentage points. It can be seen that the proposed scheme guarantees model performance effectively while ensuring privacy.

The method of applying differential privacy to federated learning has been one of the key techniques for protecting the privacy of training data. Addressing the issue that most previous works do not consider the heterogeneity of parameters， resulting in pruning training parameters uniformly， leading to uniform noise addition in each round， thus affecting model convergence and the quality of training parameters， an adaptive noise addition scheme based on gradient clipping was proposed. Considering the heterogeneity of gradients， adaptive gradient clipping was executed for different clients in different rounds， thereby allowing for the adaptive adjustment of noise magnitude. At the same time， to further improve model performance， different from traditional client random sampling methods， a client sampling method that combines roulette and elite preservation was proposed. Combining the aforementioned two methods， a Client Selection and Adaptive Gradient Clipping Differential Privacy_Federated Learning （CS&AGC DP_FL） was proposed. Experimental results demonstrate that， when the privacy budget is 0.5， compared to the Federated Learning method based on Adaptive Differential Privacy （Adapt DP_FL）， the proposed method improves the final model’s classification accuracy by 4.9 percentage points under the same level of privacy constraints. Additionally， in terms of convergence speed， the proposed method requires 4 to 10 fewer rounds to reach convergence compared to the methods to be compared.

Emotion recognition based on physiological signals is affected by noise and other factors， resulting in low accuracy and weak cross-individual generalization ability. Concerning the issue， a multimodal emotion recognition method based on ElectroEncephaloGram （EEG）， ElectroCardioGram （ECG）， and eye movement signals was proposed. Firstly， physiological signals were performed multi-scale convolution to obtain higher-dimensional signal features and reduce parameter size. Secondly， self-attention was employed in the fusion of multimodal signal features to enhance the weights of key features and reduce feature interference between modalities. Finally， a Bi-directional Long Short-Term Memory （Bi-LSTM） network was used for extraction of temporal information of fused features and classification. Experimental results show that， the proposed method achieves recognition accuracies of 90.29%， 91.38%， and 83.53% for valence， arousal， and valence/arousal four-class recognition tasks， respectively， with improvements of 3.46-7.11 and 0.92-3.15 percentage points compared to the EEG single-modality and EEG+ECG bimodal methods. The proposed method can accurately recognize emotion with better recognition stability between individuals.

Due to complex structure of Three-Dimensional Stacked Integrated Circuit （3D SIC）， it is more difficult to design an efficient test structure for it to reduce test cost than for Two-Dimensional Integrated Circuit （2D IC）. For decreasing cost of 3D SIC testing， a Three-Dimensional Linear Feedback Shift Register （3D-LFSR） test structure was proposed based on Linear Feedback Shift Register （LFSR）， which can effectively adapt to different test phases of 3D SIC. The structure was able to perform tests independently in the pre-stacking tests. After the stacking， the pre-stacking test structure was reused and reconfigured into a test structure suitable for the current circuit to be tested， and the reconfigured test structure was able to further reduce test cost. Based on this structure， the corresponding test data processing method and test flow were designed， and the mixed test mode was adopted to reduce the test time. Experimental results show that compared with the dual-LFSR structure， 3D-LFSR structure has the average power consumption reduced by 40.19%， the average area overhead decreased by 21.31%， and the test data compression rate increased by 5.22 percentage points. And， using the hybrid test mode reduces the average test time by 20.49% compared to using the serial test mode.

Considering the issues of physiological signal emotion recognition， a bimodal emotion recognition method based on Graph Neural Network （GNN） and attention was proposed. Firstly， the GNN was used to classify ElectroEncephaloGram （EEG） signals. Secondly， an attention-based Bi-directional Long Short-Term Memory （Bi-LSTM） network was used to classify ElectroCardioGram （ECG） signals. Finally， the results of EEG and ECG classification were fused by Dempster-Shafer evidence theory， thus improving the comprehensive performance of the emotion recognition task. To verify the effectiveness of the proposed method， 20 subjects were invited to participate in the emotion elicitation experiment， and the EEG signals and ECG signals of the subjects were collected. Experimental results show that the binary classification accuracies of the proposed method are 91.82% and 88.24% in the valence dimension and arousal dimension， respectively， which are 2.65% and 0.40% higher than those of the single-modal EEG method respectively， and are 19.79% and 24.90% higher than those of the single-modal ECG method respectively. It can be seen that the proposed method can effectively improve the accuracy of emotion recognition and provide decision support for medical diagnosis and other fields.

In order to solve the problem of unbalanced dataset in credit assessment and the limited classification effect of single classifier on unbalanced data, a Majority Weighted Minority Oversampling TEchnique-Random Forest (MWMOTE-RF) credit assessment method was proposed. Firstly, MWMOTE technology was applied to increase the samples of minority classes in the preprocessing stage. Then, on the preprocessed balanced dataset, random forest algorithm, one of supervised machine learning algorithms, was used to classify and predict the data. With Area Under the Carve (AUC) used to evaluate the performance of classifier, experiments were conducted on German credict card dataset from UCI database and a company's car default loan dataset. The results show that the AUC value of MWMOTE-RF method increases by 18% and 20% respectively compared with random forest method and Naive Bayes method on the same data set. At the same time, random forest method was combined with Synthetic Minority Over-sampling TEchnique (SMOTE) and ADAptive SYNthetic over-sampling (ADASYN), respectively, and the AUC value of MWMOTE-RF method increases by 1.47% and 2.34% respectively compared with them. The results prove the effectiveness and the optimization of classifier performance of the proposed method.