The traditional reinforcement learning algorithm has limitations in convergence speed and solution accuracy when solving the taxi path planning problem and the traffic signal control problem in traffic scenarios. Therefore， an improved reinforcement learning algorithm was proposed to solve this kind of problems. Firstly， by applying the optimized Bellman equation and Speedy Q-Learning （SQL） mechanism， and introducing experience pool technology and direct strategy， an improved reinforcement learning algorithm， namely Generalized Speedy Q-Learning with Direct Strategy and Experience Pool （GSQL-DSEP）， was proposed. Then， GSQL-DSEP algorithm was applied to optimize the path length in the taxi path planning decision problem and the total waiting time of vehicles in the traffic signal control problem. The error of GSQL-DSEP algorithm was reduced at least 18.7% than those of the algorithms such as Q-learning， SQL， Generalized Speedy Q-Learning （GSQL） and Dyna-Q， the decision path length determined by GSQL-DSEP algorithm was reduced at least 17.4% than those determined by the compared algorithms， and the total waiting time of vehicles determined by GSQL-DSEP algorithm was reduced at most 51.5% than those determined by compared algorithms for the traffic signal control problem. Experimental results show that， GSQL-DSEP algorithm has advantages in solving traffic scenario problems over the compared algorithms.

To solve the problems of low recognition rate and poor adaptability of single feature， a feature extraction method named Hilbert-CSP-Huang Transform （HCHT） was proposed based on Hilbert-Huang Transform （HHT） and Common Spatial Pattern （CSP）. Firstly， the Intrinsic Mode Function （IMF） was obtained by the Empirical Mode Decomposition （EMD） of original ElectroEncephaloGram （EEG） signals， and the IMF components were merged into a new signal matrix. Secondly， the time-frequency domain features were obtained by Hilbert spectrum analysis. Thirdly， the time-frequency domain features were extended into time-frequency-space features by further CSP decomposition of the constructed signal matrix. Finally， the feature set was classified by Support Vector Machine （SVM）. Experiments on the BCI Competition II dataset show that compared with methods based on HHT time-frequency and CSP spatial domain features， the proposed method has the recognition accuracy increased by 7.5， 10.3 and 9.2 percentage points respectively with smaller standard deviation. The online experimental results on the intelligent wheelchair platform show that HCHT can effectively improve the recognition accuracy and robustness.

Concerning the problem that it is difficult for the users in cloud computing to obtain the high-quality and personalized cloud services provided by a large number of cloud providers, a trust model based on user types and privacy protection for the personalized cloud services was proposed. Firstly, the users were divided into familiar users, strange users and normal users according to the transaction history. Secondly, a fair and reasonable trust evaluation Agent was introduced to protect users' privacy, which could evaluate the trust relationship between requesters and providers based on the user types. Lastly, in view of the dynamics of trust, a new updating mechanism combined with the transaction time and transaction amount was provided based on Quality of Service (QoS). The simulation results show that the proposed model has higher transaction success rate than AARep and PeerTrust. The transaction success rate can be increased by 10% and 16% in the harsh environment where the malicious user ratio reaches 70%. This method can improve transaction success rate, and has a strong ability to withstand harsh environments.

In order to solve the distortion of wool geometric dimension, resulting from image binarization with weak contour, an automatic binarization algorithm for Charge-Coupled Device （CCD） wool image was proposed with reference to a ramp-width-reduction approach based on intensity and gradient indices, using a classical global threshold method and a local one. In that algorithm, edge-pixel-seeking step was added and gray-adjusting factor was improved, with sobel operator and ramp edge model introduced, to increase processing efficiency and avoid human intervention. Besides, every sub image was processed by the mixed global and local threshold based on the analysis of Otsus and Bernsens methods to intensify edge details and decrease distortion. Compared with the traditional ways, the experimental results show that the new algorithm has good performance in automatic binarization with weak contour.