Investigation of Golay Code (8, 12, 24) Structure ‎ in Improving Search Techniques

This paper presents a new technique for hash searching that is designed for approximate matching problem of multi-attribute ‎objects. The suggested technique can be used for improving the search operation when the multi-attribute objects are partially ‎distorted or when the searching criterion is not specified properly. The suggested approach is based upon reversing the ‎conventional scheme of Golay code (8, 12, 24), which maps 24-bit vectors into 12-bit message words. In this technique, a ‎multi-dimensional space is used to represent objects, where each object is given by a 24-bit vector. The closeness of the objects ‎is determined by partitioning a 24-dimensional cube. In addition, the possibility of 1-bit distortions is considered through bit ‎modifications of the 24-bit vectors. Thus, we proposed a hash table of 4096 entries that is fault-tolerant in the sense that the ‎index is the same for any two different 24-bit vectors that share the same sphere. This allows organizing a direct retrieval of a ‎neighborhood of 24-bit vectors with two or possibly more mismatches. The simulation experiments measured the retrieval ‎capabilities of the proposed system and the expected hash distribution