Aiming at the problems of network flow monitoring (classification) in complex network environment, a stochastic artificial neural network learning method was proposed to realize the direct classification of multiple classes and improve the training speed of learning methods. Using Plane-Gaussian (PG) artificial neural network model, the idea of stochastic projection was introduced, and the network connection matrix was obtained by calculating the pseudo-inverse analysis. Theoretically, it can be proved that the network has global approximation ability. The artificial simulation was carried out on artificial data and standard network flow monitoring data. Compared with the Extreme Learning Machine (ELM) and PG network using the random method, the analysis and experimental results show that: 1)the proposed method inherits the geometric characteristics of the PG network and is more effective for the planar distributed data; 2)it has comparable training speed to ELM, but significantly faster than PG network; 3)among the three methods, the proposed method is more suitable for solving the problem of network flow monitoring.

The shortcomings about these days clustering algorithm considering the condition of planar adjacency relationship are analysised.The clustering algorithm considering the condition of planar adjacency relationship is defined again newly from the general clustering.In order to dealing with the clustering considering the condition of planar adjacency relationship,the concept adjacency matrix is defined.The genetic-clustering algorithm considering the condition of planar adjacency relationship is put forward,partitioning samples on the best-close distance and adjacency matrix,calculating cluster aim function on within-group sum of squares(WGSS) error,importing genetic algorithm.The algorithm is validated and compared with the FCM clustering outcome by examples.Algorithm testing show: the genetic-clustering algorithm considering the condition of planar adjacency relationship is completely feasible and availability.

In accordance with the present situation and some problems in the area of 3D modeling, the technology of 3D modeling based on discrete algorithm was proposed. From the view of engineering application, this paper mainly discussed the data pre-processing of the 3D model face, the discretization of the 3D model face, topological relation based on the discretization meshwork model and mutual division algorithm of 3D model. Finally combining OpenGL,the Object ARX and Oriented Object Programming(OOP) technology, a simulation system of mineral deposit 3D model has been developed. The result shows that the 3D modeling method is much simple and practical, and has a wide area of application.