Improving rural living environment and realizing its sustainable development is a key task for China's new rural construction, vital for implementation of a rural revitalization strategy.This paper, based on sustainable development theory of rural living environment, uses factor breakdown structure and subjective/objective weighing to establish an evaluation index system for sustainable development of rural living environment from the perspective of natural and social resources, and applies development level (sustainable development potential), coordination index (sustainable development trend) to set up a measurement model, which is employed to comprehensively evaluate their sustainable development level and spatial pattern of 11 provinces' rural living environment in Yangtze River Economic Zone with an attempt to improve the sustainable development level of rural living environment and to increase regional balanced development. ArcGIS is used to classify development level into four categories, high, relatively high, relatively low and low, and development coordination degree into three, high, moderate and low. Clustering features are analyzed at overall and local levels from auto-correlation perspective with causes explained from resource allocation and development. Results show a regional imbalance, with sustainable development level of rural living environment, high in the east and low in the west, and development coordination, high in the central and low in the west. Sustainable development level of rural living environment is of outstanding global and local clustering/dispersing features with eco-environment and economy systems of strongest spatial clustering, and social culture system of strongest dispersing. High-level hot spots of sustainable development are concentrating on Yangtze River Delta and low-level cold spots on Yunnan and Guizhou. This paper presents suggestions on orderly conducting economic activities, enhancing environmental and cultural construction, overall planning regional development in order to optimize rural living environment.

Crude oil price is influenced not only by the traditional demand-supply factor, but also readily by non-conventional factors such as wars, financial crisis, natural disasters and political events. This paper, aiming at forecasting the crude oil price and improving oil price forecasting theory, uses sentiment analysis (SA) to process the non-conventional text data and to estimate the market trend, which is input into wavelet neural network (WNN) to establish a SA-WNN forecasting model. Compared with the traditional BP neural network model and ICA-WNN model, SA-WNN model can forecast the general trend of oil price precisely, making it an excellent forecasting model.