Drug-target prediction method can effectively reduce costs and accelerate research process compared with traditional drug discovery. However， there are various challenges such as low balance of datasets and low precision of prediction in practical applications. Therefore， a drug-target interaction prediction method based on self-adaptive spherical evolution was proposed， namely ASE-KELM （self-Adaptive Spherical Evolution based on Kernel Extreme Learning Machine）. By the method， negative samples with high confidence were selected based on the principle that drugs with similar structures are likely to interact with targets. And to solve the problem that spherical evolution algorithm tends to fall into local optima， the feedback mechanism of historical memory of search factors and Linear Population Size Reduction （LPSR） were used to balance global and local search， which improved the optimization ability of the algorithm. Then the parameters of Kernel Extreme Learning Machine （KELM） were optimized by the self-adaptive spherical evolution algorithm. ASE-KELM was compared with algorithms such as NetLapRLS （Network Laplacian Regularized Least Square） and BLM-NII （Bipartite Local Model with Neighbor-based Interaction profile Inferring） on gold standard based datasets to verify the performance of the algorithms. Experimental results show that ASE-KELM outperforms comparison algorithms in AUC （Area Under the receiver operating Characteristic curve） and AUPR （Area Under the Precision-Recall curve） for the Enzyme （E）， G-Protein-Coupled Receptor （GPCR）， Ion Channel （IC）， and Nuclear Receptor （NR） datasets. And the effectiveness of ASE-KELM in predicting new drug-target pairs was validated on databases such as DrugBank.

How to allocate spectra to users efficiently and improve the revenue of providers are popular research topics recently. To address the problem of low revenue of providers in spectrum combinatorial auctions， Random Walk for Spectrum Combinatorial Auctions （RWSCA） mechanism was designed to maximize the revenue of spectrum providers by combining the characteristics of asymmetric distribution of user valuations. First， the idea of virtual valuation was introduced， the random walk algorithm was used to search for a set of optimal parameters in the parameter space， and the valuations of buyers were linearly mapped according to the parameters. Then， VCG （Vickrey-Clarke-Groves） mechanism based on virtual valuation was run to determine the users who won the auction and calculate the corresponding payments. Theoretical analysis proves that the proposed mechanism is incentive compatible and individually rational. In spectrum combinatorial auction simulation experiments， the RWSCA mechanism increases the provider’s revenue by at least 16.84%.

To solve the long training time and slow convergence problems when applying SAC （Soft Actor-Critic） algorithm to the local path planning of mobile robots， a PER-SAC algorithm was proposed by introducing the Prioritized Experience Replay （PER） technique. Firstly， to improve the convergence speed and stability of the robot training process， a priority strategy was applied to extract samples from the experience pool instead of the traditional random sampling and the network prioritized the training of samples with larger errors. Then， the calculation of Temporal-Difference （TD） error was optimized， and the training deviation was reduced. Next， the transfer learning was used to train the robot from a simple environment to a complex one gradually in order to improve the training speed. In addition， an improved reward function was designed to increase the intrinsic reward of robots， and therefore， the sparsity problem of environmental reward was solved. Finally， the simulation was carried out on the ROS （Robot Operating System） platform， and the simulation results show that PER-SAC algorithm outperforms the original algorithm in terms of convergence speed and length of the planned path in different obstacle environments. Moreover， the PER-SAC algorithm can reduce the training time and is significantly better than the original algorithm on path planning performance.

As a multi-task meta learning algorithm， Model Agnostic Meta Learning （MAML） can use different models and adapt quickly to different tasks， but it still needs to be improved in terms of training speed and accuracy. The principle of MAML was analyzed from the perspective of Gaussian stochastic process， and a new Model Agnostic Meta Learning algorithm based on Bayesian Weight function （BW-MAML） was proposed， in which the weight was assigned by Bayesian analysis. In the training process of BW-MAML， each sampling task was regarded as following a Gaussian distribution， and the importance of the task was determined according to the probability of the task in the distribution， and then the weight was assigned according to the importance， thus improving the utilization of information in each gradient descent. The small sample image learning experimental results on Omniglot and Mini-ImageNet datasets show that by adding Bayesian weight function， for training effect of BW-MAML after 2500 step with 6 tasks， the accuracy of BW-MAML is at most 1.9 percentage points higher than that of MAML， and the final accuracy is 0.907 percentage points higher than that of MAML on Mini-ImageNet averagely； the accuracy of BW-MAML on Omniglot is also improved by up to 0.199 percentage points averagely.

Concerning the problems that the parameters of the state of the aluminum reduction cells are multivariate and with strong coupling, the calculation of established diagnosis model is large and the precision of diagnosis is limited, this paper proposed Optimized Relative Principal Component Analysis (ORPCA) method to diagnose the status of aluminum reduction cells. An effective principle of determining the relative weight was put forward, which took advantage of Relative Principal Component Analysis (RPCA) in reducing dimensions. In the method, Genetic Algorithm (GA) was used to optimize the fitness function about false alarm rate. The diversification of the sample project in principal component space and residual space was observed to acquire the best relative transforming matrix, so the false alarm rate of Hotelling's T2 test and Squared Prediction Error (SPE) were reduced to the least. By using a group data of 170kA operating aluminum smelter from a factory, the experimental results show that, when the confidence coefficients are 95% and 97.5%, the false alarm rates of T2 test are 16.79% and 9.77% respectively, meanwhile, the false alarm rates of SPE test are 4.01% and 1.75% respectively. Compared with other similar algorithms, the proposed method can test the abnormal condition of aluminum reduction cells and obviously reduce the false alarm rate of Hotelling's T2 test and SPE test.

Based on time-frequency analysis, the theory of estimating a modulation scale representation was discussed, and a new method of features extraction for speech recognition was proposed. Considering specialty of human auditory perception and disturbances, wavelet analysis was used instead of Fourier analysis for modulation frequency transform, and wavelet modulation scales was acquired as speech features for recognition. For further attenuating the effects of disturbances, subband normalization was introduced with the wavelet modulation scales. Experiments for the Chinese syllables recognition show extracting the wavelet modulation scales as the dynamic features outperform the frequency differences both in noise environments and in time misalignment cases.