Hierarchical Clustering Approach to Text Compression

摘要

A novel data compression perspective is explored in this paper and focus is given on a new text compression algorithm based on clustering technique in Data Mining. Huffman encoding is enhanced through clustering, a non-trivial phase in the field of Data Mining for lossless text compression. The seminal hierarchical clustering technique has been modified in such a way that optimal number of words (patterns which are sequence of characters with a space as suffix) are obtained. These patterns are employed in the encoding process of our algorithm instead of single character-based code assignment approach of conventional Huffman encoding. Our approach is built on an efficient cosine similarity measure, which maximizes the compression ratio. Simulation of our proposed technique over benchmark corpus clearly shows the gain in compression ratio and time of our proposed work in relation to conventional Huffman encoding.