Jiangxi University of Finance and Economics

About: Jiangxi University of Finance and Economics is a education organization based out in Nanchang, China. It is known for research contribution in the topics: Fuzzy logic & China. The organization has 2865 authors who have published 3556 publications receiving 41567 citations.

Definition of Management Zones for Enhancing Cultivated Land Conservation Using Combined Spatial Data

Abstract: The loss of cultivated land has increasingly become an issue of regional and national concern in China. Definition of management zones is an important measure to protect limited cultivated land resource. In this study, combined spatial data were applied to define management zones in Fuyang city, China. The yield of cultivated land was first calculated and evaluated and the spatial distribution pattern mapped; the limiting factors affecting the yield were then explored; and their maps of the spatial variability were presented using geostatistics analysis. Data were jointly analyzed for management zone definition using a combination of principal component analysis with a fuzzy clustering method, two cluster validity functions were used to determine the optimal number of cluster. Finally one-way variance analysis was performed on 3,620 soil sampling points to assess how well the defined management zones reflected the soil properties and productivity level. It was shown that there existed great potential for increasing grain production, and the amount of cultivated land played a key role in maintaining security in grain production. Organic matter, total nitrogen, available phosphorus, elevation, thickness of the plow layer, and probability of irrigation guarantee were the main limiting factors affecting the yield. The optimal number of management zones was three, and there existed significantly statistical differences between the crop yield and field parameters in each defined management zone. Management zone I presented the highest potential crop yield, fertility level, and best agricultural production condition, whereas management zone III lowest. The study showed that the procedures used may be effective in automatically defining management zones; by the development of different management zones, different strategies of cultivated land management and practice in each zone could be determined, which is of great importance to enhance cultivated land conservation, stabilize agricultural production, promote sustainable use of cultivated land and guarantee food security.

Time Series Prediction Based on Recurrent LS-SVM with Mixed Kernel

Abstract: Time series prediction is a main research content in time series analysis, and has become a hot research field with great theoretical value and application value. As an extension type of Least Square Support Vector Machine (LS-SVM), recurrent LS-SVM is proposed and applied to chaotic time series prediction. Aimed at the key and difficult research problem on LS-SVM — the selection and construction of kernel functions, a mixed kernel function used to recurrent LS-SVM is constructed through analyzing the existed kernel functions of LS-SVM. Based on Rossler chaotic time series prediction, the parameters of recurrent LS-SVM with mixed kernel are optimized by Genetic Algorithms (GA), and the prediction results are compared with that of recurrent LS-SVM with RBF kernel. The results show that, the prediction accuracy based on recurrent LS-SVM with mixed kernel is apparently higher than that based on recurrent LS-SVM with RBF kernel under the same condition. Compared with recurrent LS-SVM with RBF kernel, recurrent LS-SVM with mixed kernel possesses the better long-time predictive ability by absorbing the advantages of RBF kernel and polynomial kernel function.

Integrated production planning and scheduling under uncertainty: A fuzzy bi-level decision-making approach

Abstract: Production planning and scheduling are two core decision layers, constrained and affected by one another in manufacturing systems. Owing to different time scales and objectives, planning and scheduling are often separately handled in a sequential way, which frequently results in infeasible or suboptimal solutions. Moreover, uncertain issues, e.g. the fuzzy startup time of a machine and the fuzzy processing time for a task, are inherent to manufacturing systems due to mechanized and/or man-made factors. Motivated by these challenges, this paper aims to develop fuzzy bi-level decision-making techniques to handle integrated planning and scheduling problems in the fuzzy manufacturing system. First, the integrated problem is formulated into a fuzzy bi-level decision model in which solving the higher-level planning problem has to take into account lower-level implicit scheduling reactions in advance. Second, a hybrid solution method is developed to solve the resulting bi-level decision model, in which a particle swarm optimization (PSO) algorithm is applied to update planning decisions, and then, in view of each given planning decision, a heuristic algorithm is presented to find an optimal schedule under fuzzy manufacturing conditions. Lastly, a set of computational study is constructed to demonstrate the effectiveness of the proposed fuzzy bi-level decision-making techniques. Compared with existing works, they can find better planning decisions fulfilled by schedules and perform much better in terms of computational efficiency.