Abnormal Behavior Detection and Recognition Method Based on Improved ResNet Model

The core technology in an intelligent video surveillance system is that detecting and recognizing abnormal behaviors timely and accurately.The key breakthrough point in recognizing abnormal behaviors is how to obtain the effective features of the picture,so as to solve the problem of recognizing them.In response to this difficulty,this paper introduces an adjustable jump link coefficients model based on the residual network.The effective coefficients for each layer of the network can be set after using this model to further improving the recognition accuracy of abnormal behavior.A convolution kernel of 1×1 size is added to reduce the number of parameters for the purpose of improving the speed of the model in this paper.In order to reduce the noise of the data edge,and at the same time,improve the accuracy of the data and speed up the training,a BN(Batch Normalization)layer is added before the activation function in this network.This paper trains this network model on the public ImageNet dataset,and then uses the transfer learning method to recognize these abnormal behaviors of human in the UTI behavior dataset processed by the YOLO_v3 target detection network.Under the same experimental conditions,compared with the original ResNet-50 model,the improved model in this paper has a 2.8%higher accuracy in recognition of abnormal behaviors on the public UTI dataset.

Ruin Distributions and Their Equations

In this paper, the ruin distributions were analyzed, including the distribution of surplus immediately before ruin, the distribution of claim at the time of ruin, the distribution of deficit, and the distribution of surplus at the beginning of the claim period before ruin. Several integral equations for the ruin distributions were derived and some solutions under special conditions were obtained.

Research on Ruin Probability of Risk Model Based on AR(1)Time Series

The insurance industry typically exploits ruin theory on collected data to gain more profits.However,state-of-art approaches fail to consider the dependency of the intensity of claim numbers,resulting in the loss of accuracy.In this work,we establish a new risk model based on traditional AR(1)time series,and propose a fine-gained insurance model which has a dependent data structure.We leverage Newton iteration method to figure out the adjustment coefficient and evaluate the exponential upper bound of the ruin probability.We claim that our model significantly improves the precision of insurance model and explores an interesting direction for future research.

Study on Ecological Carrying Capacity of Land in Henan Province

In order to explore the technical methods to improve the ecological carrying capacity of regional land under the premise of limited land use area,an open ecological footprint model is established based on the traditional ecological footprint model.Using the two models,this paper evaluates the ecological carrying capacity of Henan Province in 2017.The results indicate that the ecological productive footprint of cultivated land in Henan Province is much larger than the ecological carrying capacity,but the ecological consumption footprint is lower than the ecological carrying capacity.The open ecological footprint model can clearly distinguish the internal and the external ecological consumption footprint after corrected by the consumption adjustment coefficient and the land-use structure adjustment coefficient.Based on the open ecological footprint model,the ecological carrying capacity evaluation results of Henan Province are more realistic.The comprehensive ecological carrying capacity in Henan Province has a surplus,but there are significant differences among different land use types.The cultivated land has the largest ecological carrying capacity surplus,while the fossil energy land has a larger ecological carrying capacity deficit.In the process of achieving sustainable development,Henan Province should focus on reducing energy consumption and improving the ecological carrying capacity of fossil energy land.The paper concludes that the open ecological footprint model can simulate the ecological carrying capacity under different land use structures and different consumption structures.According to the simulation results,the technical methods to improve the ecological carrying capacity under the premise of limited land use scale can be proposed.The research can provide reference for land use structure adjustment,land use planning and land protection in Henan Province.It can also provide scientific basis for ecological protection and high-quality development of the Yellow River basin.

Studying beta diversity: ecological variation partitioning by multiple regression and canonical analysis

Aims Beta diversity is the variation in species composition among sites in a geographic region.Beta diversity is a key concept for understanding the functioning of ecosystems,for the conservation of biodiversity and for ecosystem management.The present report describes how to analyse beta diversity from community composition and associated environmental and spatial data tables.Methods Beta diversity can be studied by computing diversity indices for each site and testing hypotheses about the factors that may explain the variation among sites.Alternatively,one can carry out a direct analysis of the community composition data table over the study sites,as a function of sets of environmental and spatial variables.These analyses are carried out by the statistical method of partitioning the variation of the diversity indices or the community composition data table with respect to environmental and spatial variables.Variation partitioning is briefly described herein.Important findings Variation partitioning is a method of choice for the interpretation of beta diversity using tables of environmental and spatial variables.Beta diversity is an interesting‘currency’for ecologists to compare either different sampling areas or different ecological communities cooccurring in an area.Partitioning must be based upon unbiased estimates of the variation of the community composition data table that is explained by the various tables of explanatory variables.The adjusted coefficient of determination provides such an unbiased estimate in both multiple regression and canonical redundancy analysis.After partitioning,one can test the significance of the fractions of interest and plot maps of the fitted values corresponding to these fractions.