Research On Application Of Deep Learning In Data Compression

How to store and transfer data efficiently is always an important research subject in computer science with the advent of the information age,and the most common solution to the problem is data compression.Data compression is a technique which can reduce the storage space and improve the efficiency of transmission,storage and processing without losing the information or keeping the most important information.Two factors make compression technology become very important:(1)Because of the capacity constraints,the researchers have developed a variety of compression algorithms to compress the data so that more data can be stored in a limited space.(2)Due to the limit of the transmission speed,the faster the data is,the faster the transmission speed is.So in order to get faster transmission speed and higher processing efficiency,the smaller the amount of data is the better.With the advent of the era of big data,data storage and transmission is facing more and more problems.Traditional data compression algorithms are facing severe challenges as the volume of data is explosive growth and the structure of the data becomes more and more complex and so on.Under this background,this paper proposes a combination of deep learning model and clustering algorithm for data compression.The experimental results show the hybrid model can obtain high compression ratio but also contain a large amount of important information,which makes the reconstruction data can better represent the original data and is very suitable for complex data compression.This paper also applies data completion and data correction techniques for data preprocessing,which are conducive to improving the ability of deep learning model for data mining and increasing the compression ratio of the model.Finally,the cross validation technique is used to verify the performance of the model,and results show that the model is reliable,stable and efficient.