For various features of heterogeneous network access, combined with multi-master multiple slave Stackelberg game model, network pricing and resource allocation scheme of a heterogeneous IOT is proposed. A mobile end-user utility function based on income and spending is designed. After the operator's price is determined, the utility function satisfies the concave conditions to ensure the existence of mobile user's non-cooperative Nash equilibrium point, resulting in multiple resource participants in the joint optimal objective.

In company with medical instruments ' development, the corresponding software plays more and more role in the application. And medical image processing software has become an important component of the medical ultrasonic instruments. Image segmentation plays an important role in both qualitative and quantitative analysis of medical ultrasound images. But state-of-arts methods in the aspect of segmentation can not get satisfactory results. We propose an intelligent image segmentation method for medical ultrasonic images. The algorithm improved active contour model with relevance vector machine, where the advantages of supervised learning classification and the global region distribution information can be exploited to enhance the performance. In order to improve the segmentation speed and get precise initial contour, relevance vector machine also is used to obtain initial contour firstly. A large amount of experimental results have proved that our method outperforms many state-of-arts methods in the aspect of segmentation, and the method can be used in ultrasonic instruments effectively.