Abstract
When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogorov complexity, the compression performances of the algorithms implemented in the available compression programs in the system differ. Thus, it is impossible to deliberately select the best compression program before we try the compression operation. From this background, this paper proposes a method with a principal component analysis (PCA) and a deep neural network (DNN) to predict the entropy of data to be compressed. The method infers an appropriate compression program in the system for each data block of the input data and achieves a good compression ratio without trying to compress the entire amount of data at once. This paper especially focuses on lossless compression for image data, focusing on the image blocks. Through experimental evaluation, this paper shows the reasonable compression performance when the proposed method is applied rather than when a compression program randomly selected is applied to the entire dataset.
Highlights
Various algorithms of lossless data compression are widely applied to the fields such as medical storage [1], industrial manufacturing [2], IoT [3], database [4], cloud computing [5], and communication networks [6]
It is hard to find the best algorithm to compress the data dedicated to the target application because a conventional algorithm of lossless data compression has not been designed for a particular data pattern
Applying a deep neural network (DNN) that infers a data compression algorithm from a data pattern of a data block divided from the original data, we have developed a novel method for lossless data compression that achieves a better compression ratio than the worst case of available data compression programs
Summary
Various algorithms of lossless data compression are widely applied to the fields such as medical storage [1], industrial manufacturing [2], IoT [3], database [4], cloud computing [5], and communication networks [6]. This paper proposes a novel method that selects the best algorithm of lossless data compression without trial and error. Applying a DNN that infers a data compression algorithm from a data pattern of a data block divided from the original data, we have developed a novel method for lossless data compression that achieves a better compression ratio than the worst case of available data compression programs. The third section will explain the proposed method that performs adaptive lossless data compression for image data applying entropy prediction by using DNN. Even if we can find an algorithm that achieves the maximum entropy, it is known that we are not able to decode the compressed data to the original This means that the compressed data must include some redundancy for the decoding process. The algorithms do not promise to achieve maximum entropy
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call