Weisong Mu

A new privacy-preserving proximal support vector machine for classification of vertically partitioned data

A new privacy-preserving proximal support vector machine (P3SVM) is formulated for classification of vertically partitioned data. Our classifier is based on the concept of global random reduced kernel which is composed of local reduced kernels. Each of them is computed using local reduced matrix with Gaussian perturbation, which is privately generated by only one of the parties, and never made public. This formulation leads to an extremely simple and fast privacy-preserving algorithm, for generating a linear or nonlinear classifier that merely requires the solution of a single system of linear equations. Comprehensive experiments are conducted on multiple publicly available benchmark datasets to evaluate the performance of the proposed algorithms and the results indicate that: (a) Our P3SVM achieves better performance than the recently proposed privacy-preserving SVM via random kernels in terms of both classification accuracy and computational time. (b) A significant improvement of accuracy is attained by our P3SVM when compared to classifiers generated only using each party’s own data. (c) The generated classifier has comparable accuracy to an ordinary PSVM classifier trained on the entire dataset, without releasing any private data.

FARMERS' INFORMATION USAGE INTENTION IN CHINA BASED ON THE TECHNOLOGY ACCEPTANCE MODEL

Information technology acceptance has received much attention, but little research has been conducted to assess farmers’ information adoption. Despite the importance of information, its value will not be realized if farmers are reluctant to accept it. This research aims to study farmers’ information adoption in China, in order to provide some decision-making advice for the people and organization who supply the agriculture information. The model of information usage intention has been established based on the Technology Acceptance Model (TAM). A sample of 231 farmers participated in this study. The results show that the factors which influence the usage willingness for information are perceived usefulness, perceived ease of use, learning intention, risk preference and experience in information before. In addition, income and education may also affect the decision.

Analysing levels of China's agricultural domestic support with an optimising model

Abstract The paper analyses the impacts of alteration of agricultural domestic supports on state welfare adopting partial equilibrium theory. In order to find out the appropriate levels of agricultural domestic supports in China, a nonlinear programming approach was utilised, based on constraints of the annual financial budget and the Uruguay Round Agreement on Agriculture, to build an optimisation model for levels of China agricultural domestic support was built to aim at the maximum welfare. The result shows that the maximum levels of China “amber box” support are 50 billion dollars from welfare maximisation in the international agricultural product trade. The amber box support is about 174 billion RMB yuan according to the de minimis levels of China with 8.5%. The national annual budgetary expenditure for agriculture was 175.445 billion RMB yuan approximately in 2003, the amber box support of which was only 55.143 billion RMB yuan.

Estimating technical efficiency of Chinese table grape wholesalers

Purpose – The purpose of this paper is to estimate the technical efficiency of Chinese table grape wholesalers and subsequently to examine the degree to which the calculated efficiency correlates with a set of explanatory variables. Design/methodology/approach – A two-stage procedure is applied in this paper. First, a non-parametric data envelopment analysis (DEA) technique is applied to investigate the degree of technical efficiency for Chinese table grape wholesalers. Second, Tobit regression is used to analyze the factors influencing technical efficiency. Findings – Research results reveal that the mean technical efficiency of the sample is 0.544 and 0.860 under constant returns scale (CRS) and VRS assumptions, respectively, and the scale efficiency (SE) is 0.620. The variables of experiences, number of grape varieties on sale, daily selling volumes and fixed sale ratio have a significant effect on technical efficiency, while the other exogenous variables do not affect the efficiency in any significant...

Daily Sales Forecasting for Grapes by Support Vector Machine

In this article, the quantity of grapes sold in one fruit shop of an interlocking fruit supermarket is forecasted by the method of support vector machine (SVM) based on deficient data. Since SVMs have a lot advantages such as great generalization performance and guarantying global minimum for given training data, it is believed that support vector regression will perform well for forecasting sales of grapes. In order to improve forecasting precision (FP), this article quantifies the factors affecting the sales forecast of grapes such as weather and weekend or weekday, results are suitable for real situations. In this article, we apply e-SVR and LS-SVR to forecast sales of three varieties of grapes. Moreover, the artificial neural network (ANN) and decision tree (DT) are used as contrast and numerical experiments show that forecasting systems with SVMs is better than ANN and DT to forecast the daily sales of grapes overall.

Using Protégé to Construct Vegetable SCM Knowledge Ontology *

Ontology is gradually used for knowledge representation recently. It helps computer understand human knowledge more intelligently in intelligent control, knowledge searching etc. In this paper, after given vegetable supply chain model based on our investigation, we proposed the process of constructing vegetable supply chain ontology. The concepts and their relationships of vegetable supply chain are described in the ontology framework. Then we formalized the ontology framework using protege. Classes and properties of vegetable supply chain are all represented using protege. This makes the knowledge of vegetable supply chain express clearly. These methods can also be used to construct other fields ontology

A hybrid model for forecasting aquatic products short-term price integrated wavelet neural network with genetic algorithm

The technological advances in the production and storage of fishery products have exceeded the development of effective market demand over the past one-decade. As a result, participants within the fishery industry have frequently found themselves facing increased variable and declining prices negatively affected the fishery industry and need to be pro-active instead of reactive to market changes. In this paper, a hybrid model is described, which integrate the Wavelet Neural Network with Genetic Algorithm and can predict the short-term aquatic products price. Then the theory framework and algorithms of the model are discussed. Then an empirical example is described. It shows that the proposed model can predict the short-term aquatic product price with the scale of one day, one week and ten days and the precision of prediction is not the decline trend when the forecasting scale is extended.

A Decision Support System (Dss) for Price Risk Management in Vegetable, China

Vegetable industry plays a very important role in adjusting Agricultural structure and increasing farmers’ income. But vegetable industry is characterized by a strong exposure to price risk, due to the increasingly volatility of vegetable price. Price volatility in vegetable markets has been wreaked havoc on the financial performance of producers and their customers. So it is important to develop decision aids that help manage the risks of the price fluctuate to vegetable growers and vegetable companies. A vegetable price risk management decision support system (DSS_PRM) was developed by China agricultural University. Based on questionnaire and interviews, we analyze the decision problems and user needs. Then the architecture and development of DSS_PRM were described. At last we discussed on problems we had encountered during development and promotion.