Gaussian mixture model (GMM) is easily affected by noise, and Markov random field (MRF) model can well describe the spatial characteristics. The combination of the two is suitable for image segmentation with noise, but MRF model is prone to over segmentation. To solve this problem, an improved image segmentation algorithm based on adaptive weight coefficient was proposed, which can segment cerebrospinal fluid, gray matter and white matter from magnetic resonance imaging (MRI). Firstly, the K?means algorithm was used to obtain the initial segmentation results, and the Expectation?Maximization (EM) algorithm was used to estimate the parameters of GMM, and then the joint probability energy function of the pixel gray level of the image was obtained. Then, the adaptive weight coefficient was obtained by using the gray value, posterior probability and Euclidean distance of the center pixel and the neighboring pixels of the MRF neighborhood system, and the prior probability energy function was obtained by MRF. Finally, the final image segmentation results were obtained by Bayesian criterion. Experimental results show that the algorithm has strong adaptability, can better overcome the impact of noise on image segmentation. Compared with similar algorithms, the proposed algorithm has higher segmentation accuracy for brain MR images with noise, and obtains better segmentation results.

Aiming at the problem that the existing online life prediction of lithium?ion batteries based on the correlation vector machine has a single consideration factor, which results in unsatisfactory prediction accuracy, a method based on principal component analysis (PCA) for weighted construction of characteristic factor variables was proposed. In this method, a variety of characteristic factor variables are taken as the research object to find the matrix of the score vector after the linear transformation. The feature coverage degree of different score vectors to the original variable data matrix is analyzed, and the corresponding feature vectors are constructed by weighted fusion. Using the vector as input, a prediction model is established by the relevance vector machine and the online prediction of lithium?ion battery life is performed, and the prediction results are finally obtained. International public battery data was used as the research object, and MATLAB experiments were used to verify that the method has the feasibility of multivariate prediction of battery life, and the prediction effect is better.

Logging while drilling (LWD) technology can obtain more real formation data information than traditional logging, so it is more suitable for practical applications. What follows is how to quickly and accurately determine whether the mixture contains crude oil in the process of testing while drilling, that is, to achieve qualitative analysis of the mixture. Laser Raman spectroscopy analysis technology, as a relatively complete molecular spectroscopy technology currently developed, has been widely used in the field of many kinds of material analysis. In this paper, according to the characteristics of crude oil drilling fluid mixture, based on laser Raman spectrum analysis technology, a qualitative analysis algorithm based on partial least squares analysis was proposed. At the same time, the known Raman spectra are smoothed and denoised, baseline correction based on the fitting polynomial method, normalization and other pre?processing operations. On this basis, the feature extraction process with singular value decomposition as the main method was completed, thus attained the aim of qualitative analysis of mixture, and completed the quantitative calculation within a certain precision.

The existing image segmentation algorithms based on Markov random field are prone to over segmentation and the segmentation results are not ideal. This paper presents an improved image segmentation algorithm based on Markov random field and region merging. First, the algorithm uses the image segmentation algorithm based on the theory of Markov random field and Gaussian mixture model to get the initial segmentation results; second, the region distance between each region is given by using the adjacent relationship, color relationship and boundary condition of each region; finally, the initial segmentation is performed according to the distance between regions and the change rate of color divergence after region merging. The final image segmentation results are output by region merging. In this paper, Berkeley standard image library is used for experimental simulation, and the Dice and Jaccard coefficients are used as the evaluation index of this paper. The experimental simulation shows that the proposed algorithm has better segmentation effect than the existing algorithm based on MRF theory.