Quantitative Method of Classification and Discrimination of a Porous Carbonate Reservoir Integrating K-means Clustering and Bayesian Theory

Reservoir classification is a key link in reservoir evaluation.However,traditional manual means are inefficient,subjective,and classification standards are not uniform.Therefore,taking the Mishrif Formation of the Western Iraq as an example,a new reservoir classification and discrimination method is established by using the K-means clustering method and the Bayesian discrimination method.These methods are applied to non-cored wells to calculate the discrimination accuracy of the reservoir type,and thus the main reasons for low accuracy of reservoir discrimination are clarified.The results show that the discrimination accuracy of reservoir type based on K-means clustering and Bayesian stepwise discrimination is strongly related to the accuracy of the core data.The discrimination accuracy rate of TypeⅠ,TypeⅡ,and TypeⅤreservoirs is found to be significantly higher than that of TypeⅢand TypeⅣreservoirs using the method of combining K-means clustering and Bayesian theory based on logging data.Although the recognition accuracy of the new methodology for the TypeⅣreservoir is low,with average accuracy the new method has reached more than 82%in the entire study area,which lays a good foundation for rapid and accurate discrimination of reservoir types and the fine evaluation of a reservoir.

Probabilistic Methods in Multi-Class Brain-Computer Interface

Abstract-Two probabilistic methods are extended to research multi-class motor imagery of brain-computer interface （BCI）： support vector machine （SVM） with posteriori probability （PSVM） and Bayesian linear discriminant analysis with probabilistic output （PBLDA）. A comparative evaluation of these two methods is conducted. The results shows that： 1） probabilistie information can improve the performance of BCI for subjects with high kappa coefficient, and 2） PSVM usually results in a stable kappa coefficient whereas PBLDA is more efficient in estimating the model parameters.

A model for discrimination and prediction of mental workload of aircraft cockpit display interface

With respect to the ergonomic evaluation and optimization in the mental task design of the aircraft cockpit display interface, the experimental measurement and theoretical modeling of mental workload were carried out under flight simulation task conditions using the performance evaluation, subjective evaluation and physiological measurement methods. The experimental results show that with an increased mental workload, the detection accuracy of flight operation significantly reduced and the reaction time was significantly prolonged; the standard deviation of R-R intervals（SDNN） significantly decreased, while the mean heart rate exhibited little change; the score of NASA_TLX scale significantly increased. On this basis, the indexes sensitive to mental workload were screened, and an integrated model for the discrimination and prediction of mental workload of aircraft cockpit display interface was established based on the Bayesian Fisher discrimination and classification method. The original validation and cross-validation methods were employed to test the accuracy of the results of discrimination and prediction of the integrated model, and the average prediction accuracies determined by these two methods are both higher than 85%. Meanwhile, the integrated model shows a higher accuracy in discrimination and prediction of mental workload compared with single indexes. The model proposed in this paper exhibits a satisfactory coincidence with the measured data and could accurately reflect the variation characteristics of the mental workload of aircraft cockpit display interface, thus providing a basis for the ergonomic evaluation and optimization design of the aircraft cockpit display interface in the future.