Aiming at the complicated and time-consuming problems of brushed Direct-Current （DC） motor Proportion Integral Differential （PID） parameter tuning， a PID parameter tuning method based on improved Genetic Algorithm （GA） was proposed. Firstly， a fitness enhanced elimination through selection rule was proposed， which improved the selection process of traditional GA. Then， a gene infection crossover method was proposed to ensure the increase of the average fitness value in the evolution process. Finally， the unnecessary copy operation in traditional GA was deleted to improve the running speed of the algorithm. Modeling and simulation analysis were carried out through the motor transfer function. Experimental results show that， compared with conventional tuning methods， the proposed improved GA can significantly improve the PID parameter tuning effect. At the same time， compared with the traditional GA， the improved GA reduces the evolutionary generation number required to achieve the same evolutionary effect by 79%， and increases the running speed of the algorithm by 4.1%. The proposed improved GA improves GA from the two key operation steps of selection and crossover， and is applied to PID parameter tuning to make the rise time less， the stability time shorter， and the overshoot smaller.

Aiming at the problem of low clinical practicability and accuracy in the clinical diagnosis of myocardial infarction， an auxiliary diagnosis method of myocardial infarction based on 12-lead ElectroCardioGram （ECG） signal was proposed. Firstly， denoising and data enhancement were performed on the 12-lead ECG signals. Secondly， aiming at the ECG signals of each lead， the statistical features including standard deviation， kurtosis coefficient and skewness coefficient were extracted respectively to reflect the morphological characteristics of ECG signals， meanwhile the entropy features including Shannon entropy， sample entropy， fuzzy entropy， approximate entropy and permutation entropy were extracted to characterize the time and frequency spectrum complexity， the new mode generation probability， the regularity and the unpredictability of the ECG signal time series as well as detect the small changes of ECG signals. Thirdly， the statistical features and entropy features of ECG signals were fused. Finally， based on the random forest algorithm， the performance of algorithm was analyzed and verified in both intra-patient and inter-patient modes， and the cross-validation technology was used to avoid over-fitting. Experimental results show that， the accuracy and F1 value of the proposed method in the intra-patient modes are 99.98% and 99.99% respectively， the accuracy and F1 value of the proposed method in the inter-patient mode are 94.56% and 97.05% respectively； and compared with the detection method based on single-lead ECG， the detection of myocardial infarction with 12-lead ECG is more logical for doctors’ clinical diagnosis.

The classical regression systems modeling methods suppose that the training data are sufficient, but partial information missing may weaken the generalization abilities of the regression systems constructed based on this dataset. In order to solve this problem, a regression system with the transfer learning abilities, i.e. Transfer learning Support Vector Regression (T-SVR for brevity) was proposed based on support vector regression. T-SVR could use the current data information sufficiently, and learn from the existing useful historical knowledge effectively, so that remedy the information lack in the current scene. Reinforced current model was obtained through controlling the similarity between current model and history model in the object function and current model can benefit from history scene when information is missing or insufficient. The experiments on simulation data and real data show that T-SVR has better adaptability than the traditional regression modeling method in the scene with information missing.

To study the effect of meteorological conditions on Unmanned Aerial Vehicle (UAV), an algorithm of multi-level fuzzy comprehensive evaluation method based on threat value was proposed. This algorithm improved a two-level weight value determination and the comprehensive evaluation model, which can get the comprehensive threat index after being calculated. The simulation results show that this algorithm can assess the degree of weather threat accurately and have faster operation speed, smaller error and lower complexity. The efficiency and validity have also been improved.

Abstract：To the blemish of PERT in the project plan management, this thesis introduces a kind of optimization arithmetic which is called PSO and offers an advanced technique to PERT on PSO. This technique using the method of treating with the time of the tasks in project and the theory of PSO made a advantage to the traditional PERT. The experimental results show that the technique show a more advantage, more exact ration controlling standard, can get better controlling and regulating ability to the whole project process compared with the traditional PERT.

Concerning the inefficient problem of traditional signature-based virus filtering algorithm in practice, a novel virus filtering algorithm based on Matrix Bloom Filter (MBF) was proposed. Based on the analysis of the space efficiency, time efficiency and the potential effects of false positives, the mathematical model of the algorithm was studied and the design scheme of virus filters in high-speech engine was given. Finally, the simulation experimental results demonstrate the effectiveness and practicability of the proposed algorithm.

To improve the performance of embedded graphic midware, this paper analyzed the time and space complexity of clip region which is a key technique used in the multiwindow system, and proposed an optimal switching algorithm according to the characteristics of multiwindow operation and embedded system. Application and simulation test have proved that the algorithm works well and runs faster.