Abstract File management archives are important records formed by enterprises and government departments in business processing and decision-making, which are of great significance for business continuity, decision-making, and risk management. However, due to various factors such as human error, ageing and damage to archives, the accuracy and reliability of document management archives are often challenged. Therefore, how to effectively test and... File management archives are important records formed by enterprises and government departments in business processing and decision-making, which are of great significance for business continuity, decision-making, and risk management. However, due to various factors such as human error, ageing and damage to archives, the accuracy and reliability of document management archives are often challenged. Therefore, how to effectively test and adjust file management archives has become an important research issue. This article studies a method for testing and adjusting file management archives based on multiple neural feedback models. This method utilizes a multi-neural feedback model to test and regulate file management archives, aiming to improve the accuracy and reliability of file management archives and provide new ideas and methods for research and application in related fields. Read More Read Less

Abstract Witnessing the rapid growth in technology development in recent years, there is a need to store the huge amounts of data generated and stored. Cloud storage is widely used for storing large, structured, unstructured data. Cloud computing services are provided by third-party authorities to store all the data in a distributed framework. Data stored in the cloud has to be... Witnessing the rapid growth in technology development in recent years, there is a need to store the huge amounts of data generated and stored. Cloud storage is widely used for storing large, structured, unstructured data. Cloud computing services are provided by third-party authorities to store all the data in a distributed framework. Data stored in the cloud has to be protected to guarantee the security of its clients. However, Cloud Service Providers (CSP) control the data stored by the users, thus separating ownership and management of data. The current schema uses traditional encryption technology, which is not effective in handling the user’s data without privacy leakage. Hence, we propose a three-layer framework based on fog computing, an extension of cloud computing that carries out a substantial amount of computation, storage, and communication locally and routed over the internet. In this framework, we implement the Hash-Solomon code algorithm to isolate the data into several parts stored in a local machine, fog server and cloud server. This can ensure security from internal attackers. Moreover, Computational Intelligence computes the distribution proportion in each server. The plausibility has been validated through experimental analysis, a ground-breaking supplement to existing distributed storage conspire. Read More Read Less

Abstract This article studies the analysis of the sports industry development value chain using the fuzzy GMDH network algorithm model. The sports industry is an important component of the modern service industry, and its development is of great significance for promoting economic growth, improving people’s health levels, and promoting social progress. Value chain analysis is an important means to understand the... This article studies the analysis of the sports industry development value chain using the fuzzy GMDH network algorithm model. The sports industry is an important component of the modern service industry, and its development is of great significance for promoting economic growth, improving people’s health levels, and promoting social progress. Value chain analysis is an important means to understand the development status of industries and optimize resource allocation. The fuzzy GMDH network algorithm model is based on data mining and machine learning technology, which can extract valuable information by processing and analyzing a large amount of data. Read More Read Less