Abstract:
The purpose of this research is to analyze the importance of network security in
today's society where the internet has become essential in everyday life. With the increasing
global concerns about cybersecurity, it is crucial to use big data analysis technologies and
machine learning techniques to examine and forecast the state of network security. The
existing models for network security monitoring have challenges such as being resource intensive, inaccurate analysis results, low processing efficiency, and unsuitability for real time and large-scale scenarios. To overcome these challenges, the study proposes a new BP
neural network-based model that incorporates the blocked fuzzy C-means clustering
approach to enhance the input data's characteristics and improve the model's accuracy. The
model's methodology is comprehensively explained, and testing is conducted to verify its
accuracy and usefulness in perceiving network security scenarios. The proposed model has
the potential to overcome the challenges faced by current network security monitoring
models and provide a viable solution for network security analysis and prediction.