The paper proposes using a fuzzy controller in telecommunication networks for improving the scheduling process. A structure of the fuzzy controller was developed. Linguistic variables, terms and membership functions for input and output values were defined. A rules base was developed. An Adaptive Neuro-fuzzy Inference System (ANFIS) on the base of the fuzzy-controller was developed. A genetic algorithm to improve the rule base was proposed. The operation of ANFIS was simulated and trained.
The paper deals with a problem of insufficient productivity of existing computer means for large image processing, which do not meet modern requirements posed by resource-intensive computing tasks of laser beam profiling. The research concentrated on one of the profiling problems, namely, real-time processing of spot images of the laser beam profile. Development of a theory of parallel-hierarchic transformation allowed to produce models for high-performance parallel-hierarchical processes, as well as algorithms and software for their implementation based on the GPU-oriented architecture using GPGPU technologies. The analyzed performance of suggested computerized tools for processing and classification of laser beam profile images allows to perform real-time processing of dynamic images of various sizes.
This paper describes a double compression method (DCM) of biomedical images. A comparison of image compression factors in size JPEG, PNG and developed DCM was carried out. The main purpose of the DCM - compression of medical images while maintaining the key points that carry diagnostic information. To estimate the minimum compression factor an analysis of the coding of random noise image is presented.