Multi-source sensor information fusion mainly collects various types of information from multiple independent decentralized sensors. Due to the different types of information, specific combinations of time and events are required to make the collected information more advanced and useful information. From the level of fusion, it will be merged from the three levels of data set, feature level and decision-making level. For different practical problems, it is necessary to use a certain level of fusion or a certain two levels of fusion according to the situation, so as to obtain the most optimal integration scheme.

No abstract

No abstract

No abstract

This paper researches and analyzes the evaluation of the competitiveness of ice and snow tourism, uses the improved fuzzy neural network algorithm to process the system flow diagram of ice and snow tourism development through the function and characteristics of the power system of ice and snow tourism, and finally selects more than 40 indicators of the three subsystems of resources, economy, and culture. Based on the construction of cloud fuzzy neural network model, the above method is used for experimental comparison analysis, and experiments are conducted through University of California Irvine (UCI) dataset and engineering examples to compare with the traditional cloud model, fuzzy neural network, and BP neural network to analyze the operation efficiency, accuracy rate, and several rules of the algorithm. Through the experimental comparative analysis, the cloud fuzzy neural network can fully take into account the randomness and fuzziness of the data, optimize the generation of cloud rules, avoid multidimensional rule disasters, and ensure the operational efficiency of the algorithm; the accuracy rate of the algorithm is improved relative to that of the traditional technology, and it applies to a variety of datasets. And the software is used to test the ice and snow tourism industry system dynamics model to realize the correctness and robustness testing of the model. After the constructed model can reflect the real situation within the error range, the final policy simulation of the model is carried out.