Search

The influencing factors of coal and gas outburst are complex, and now the accuracy and efficiency of outburst prediction are not high. In order to obtain the effective features from influencing factors and realize the accurate and fast dynamic prediction of coal and gas outburst, this article proposes an outburst prediction model based on the coupling of feature selection and intelligent optimization classifier. Firstly, in view of the redundancy and irrelevance of the influencing factors of coal and gas outburst, we use Boruta feature selection method to obtain the optimal feature subset from influencing factors of coal and gas outburst. Secondly, based on Apriori association rules mining method, the internal association relationship between coal and gas outburst influencing factors is mined, and the strong association rules existing in the influencing factors and samples that affect the classification of coal and gas outburst are extracted. Finally, svm is used to classify coal and gas outburst based on the above obtained optimal feature subset and sample data, and Bayesian optimization algorithm is used to optimize the kernel parameters of svm, and the coal and gas outburst pattern recognition prediction model is established, which is compared with the existing coal and gas outburst prediction model in literatures. Compared with the method of feature selection and association rules mining alone, the proposed model achieves the highest prediction accuracy of 93% when the feature dimension is 3, which is higher than that of Apriori association rules and Boruta feature selection, and the classification accuracy is significantly improved. However, the feature dimension decreased significantly, the results show that the proposed model is better than other prediction models, which further verifies the accuracy and applicability of the coupling prediction model.

The development of network technology provides people with a convenient means of searching information, but to search agricultural information from the network need rapid and accurate assistance. The information searching tool that is designed theoretically by ontology is proposed, and the establishment and application of distributed data acuisition model in the web is used to collect related topics on the extraction of knowledge, through the establishment of searching and reasoning model, the extracted knowledge is classified by the intended users, then achieve the semantic searching, and is classified automatically by neural network. Result has shown that the technique can improve greatly the accuracy and reliability of agriculture information searching.

How to quickly and accurately identify the quality of grain seed, grain type and other basic indicators and improve the efficiency of breeding quality, wheat production and quality in the work of selection or breeding have become a serious problem. The project developed the necessary software and hardware detection device platform, carried out research on the segmentation and counting algorithms of particle images for the system, and designed and implemented image processing techniques based on particle quality grain seed of the determination system. The result of the research has broad application prospects.

Cloud computing is low-cost, high-performance network application model, is gradually affecting study, work and life of people. This article introduces cloud computing and function of cloud computing, then analyzes the exiting problems of campus network resource management, the cloud computing technology and methods are applied in the construction of college information sharing platform, which can not only improve the utilization of college information resource and college information resources management, but also achieve efficient application and centralized management of college information resource with the help of efficient cloud computing capabilities and unlimited storage capacity.

Virtual plant plays an import part in growth process of plant, precision agriculture and remote sensing monitoring. The paper presents key technologies for the growth of plant growth model visualization based on neural network, and implements the simulation of plant growth process. The result shows that visual simulation of virtual plant growth can achieve the result that the traditional way can not reach, providing decision for growth management of plant.

Agricultural products information on the internet is constructed repeatedly, the content is haphazard and sharing resources can not be used, then a classification of improved neural network which is based on the adjustment and optimization of the weight is presented. The adjustment of weight, optimization of network structure and reasonable adjustment of parameters of BP neural network are discussed, a forecasting model is constructed to classify agricultural products information. Experimental results show that this method can be applied in classification of agricultural information. Comparing with traditional methods, the model has greatly improved the accuracy of the classification and obtained good stability and fault tolerance, providing the base for intelligent search and agricultural information.

To forecast quickly the operation condition of loom, optimizing operation parameters of loom, and improve the production efficiency of loom. The paper studied operation prediction of loom production based on neural network. Because traditional network method had the defects of slow convergence velocity and low prediction accuracy, BP algorithm was improved by combined algorithms by the merging of impulse item and adaptation of learning rate, network structure and parameters adjustment were used to optimize neural network, and to predict the operation condition of the loom. Research showed that improved BP network has good rate of convergence, the number of training was less and improved the reliability of the algorithm.

Textile industry requires automatic operation, then a long distance control and data gathering system has been developed. The system consists of three main parts: master control computer, which distributes in the office, the loom and the loom gathering, which distributes in the textile factory. In the office, administrative personnel can carry out long distance monitoring and gather movement parameters of the loom which distributes in a far factory district, establishes corresponding production management database, then provides powerful decision-making support for the enterprise management. The system provides a simple and practical method of computerized data gathering.