Search

Carrying out investigations into the relationships between the satisfaction in old-age security and its influence factors is of great significance for safeguarding social fairness and justice. As powerful statistical tools in machine learning, the support vector machine (SVM) and back-propagation neural network (BPNN) algorithms are used to develop nonlinear estimation models for satisfaction in the old-age security in China. Five influence factors (educational background, educational satisfaction, satisfaction with family's financial situation, overall life satisfaction, society overall evaluation) were used as the input features. A SVM model obtained in this paper has prediction accuracies of 78.0% for the training set and 77.5% for the test, and a BPNN model possesses prediction accuracies of 77.8% and 77.0% for the two tests. Obviously, the SVM is superior to the BPNN in predicting satisfaction of old-age security in China. [ABSTRACT FROM AUTHOR]

• A novel vector field-based SVR for building energy consumption prediction (ECP) is proposed. • Nonlinearity of the ECP models is transformed into linearity via vector field-based SVR. • Two high precision, generalization capability, and robustness energy consumption prediction models are established. • A real case study demonstrates the superiority of this study compared with previous studies. Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Data-driven approaches, such as artificial neural networks, support vector regression, gradient boosting regression and extreme learning machine are the most advanced methods for building energy prediction. However, owing to the high nonlinearity between inputs and outputs of building energy consumption prediction models, the aforementioned approaches require improvement with regard to the prediction accuracy, robustness, and generalization ability. To counter these shortcomings, a novel vector field-based support vector regression method is proposed in this paper. Through multi-distortions in the sample data space or high-dimensional feature space mapped by a vector field, the optimal feature space is found, in which the high nonlinearity between inputs and outputs is approximated by linearity. Hence, the proposed method ensures a high accuracy, a generalization ability, and robustness for building energy consumption prediction. A large office building in a coastal town of China is used for a case study, and its summer hourly cooling load data are used as energy consumption data. The results indicate that the proposed method achieves better performance than commonly used methods with regard to the accuracy, robustness, and generalization ability. [ABSTRACT FROM AUTHOR]

The geological and metallogenic process is a typical non-stationary multifactor and multi-scale random process. Multiple measurement data assess the performance of the integrated process, and the combined data set is usually large and complex, among other characteristics. When different metallogenic prediction targets exist, the data must be decomposed on different scales in space. The study of the scale interval in which the object features are located can eliminate useless information and retrieve useful scale data that are needed for metallogenic prediction. Thus, the model that the specific deposit presents will be rapidly and accurately identified to enhance the efficiency of the prediction and analysis models. This paper employs an improved bidimensional empirical decomposition method to decompose aeromagnetic survey data and expresses and decomposes the spatial distribution of deposits with a mixed Gaussian model. By comparing the decomposition results on various sampling data scales with the distribution function for the deposit, the characteristic scale interval that contains the measurement information that exhibits the greatest similarity to the distribution of the deposits can be identified. This method was employed to analyse a Yunnan Gejiu tin–copper polymetallic deposit using aeromagnetic sampling data to calculate suitable decomposition-scale parameters. This approach provides valuable parameters for metallogenic prediction in other areas with aeromagnetic data. [ABSTRACT FROM AUTHOR]

The coordinated actions of the central and the provincial governments are important in improving China's energy efficiency. This paper uses a three-dimensional decomposition model to measure the contribution of each province in improving the country's energy efficiency and a small-sample hybrid model to forecast this contribution. Empirical analysis draws the following conclusions which are useful for the central government to adjust its provincial energy-related policies. (a) There are two important areas for the Chinese government to improve its energy efficiency: adjusting the provincial economic structure and controlling the number of the small-scale private industrial enterprises; (b) Except for a few outliers, the energy efficiency growth rates of the northern provinces are higher than those of the southern provinces; provinces with high growth rates tend to converge geographically; (c) With regard to the energy sustainable development level, Beijing, Tianjin, Jiangxi, and Shaanxi are the best performers and Heilongjiang, Shanxi, Shanghai, and Guizhou are the worst performers; (d) By 2020, China's energy efficiency may reach 24.75 thousand yuan per ton of standard coal; as well as (e) Three development scenarios are designed to forecast China's energy consumption in 2012–2020. [ABSTRACT FROM AUTHOR]