Probability estimation based on grey system theory for simulation evaluation

In the evaluation of some simulation systems, only small samples data are gotten due to the limited conditions. In allusion to the evaluation problem of small sample data, an interval estimation approach with the improved grey confidence degree is proposed.On the basis of the definition of grey distance, three kinds of definition of the grey weight for every sample element in grey estimated value are put forward, and then the improved grey confidence degree is designed. In accordance with the new concept, the grey interval estimation for small sample data is deduced. Furthermore,the bootstrap method is applied for more accurate grey confidence interval. Through resampling of the bootstrap, numerous small samples with the corresponding confidence intervals can be obtained. Then the final confidence interval is calculated from the union of these grey confidence intervals. In the end, the simulation system evaluation using the proposed method is conducted. The simulation results show that the reasonable confidence interval is acquired, which demonstrates the feasibility and effectiveness of the proposed method.

Human Motion Recognition Based on Incremental Learning and Smartphone Sensors

Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical data must be gathered for retraining. This consumes a huge amount of storage space, and the new training process will be more complicated. In this paper, we use an incremental learning method to model the motion classifier. A weighted decision tree is proposed to help illustrate the process, and the probability sampling method is also used. The resuhs show that with continuous learning, the motion classifier is more precise. The average classification precision for the weighted decision tree was 88.43% in a typical test. Incremental learning consumes much less time than the batch processing mode when the input training data comes continuously.

Study on a soil erosion sampling survey in the Pan-Third Pole region based on higher-resolution images

Soil erosion is one of the most severe global environmental problems,and soil erosion surveys are the scientific basis for planning soil conservation and ecological development.To improve soil erosion sampling survey methods and accurately and rapidly estimate the actual rates of soil erosion,a Pan-Third Pole region was taken as an example to study a methodology of soil erosion sampling survey based on high-spatial-resolution remote sensing images.The sampling units were designed using a stratified variable probability systematic sampling method.The spatiotemporal characteristics of soil erosion and conservation were taken into account,and finer-resolution freely available and accessible images in Google Earth were used.Through the visual interpretation of the free high-resolution remote sensing images,detailed information on land use and soil conservation measures was obtained.Then,combined with the regional soil erosion factor data products,such as rainfall-runoff erosivity factor(R),soil erodibility factor(K),and slope length and steepness factor(LS),the soil loss rates of some sampling units were calculated.The results show that,based on these high-resolution remote sensing images,the land use and soil conservation measures of the sampling units can be quickly and accurately extracted.The interpretation accuracy in 4 typical cross sections was more than 80%,and sampling accuracy,described by histogram similarity in 11 large sampling sites,show that the landuse of sampling uints can represent the structural characteristics of regional land use.Based on the interpretation of data from the sample survey and the regional soil erosion factor data products,the calculation of the soil erosion rate can be completed quickly.The calculation results can reflect the actual conditions of soil erosion better than the potential soil erosion rates calculated by using the coarse-resolution remote sensing method.