With the advancement of mobile and embedded devices, many applications such as data mining have found their\nway into these devices. These devices consist of various design constraints including stringent area and power\nlimitations, high speed-performance, reduced cost, and time-to-market requirements. Also, applications running on\nmobile devices are becoming more complex requiring significant processing power. Our previous analysis illustrated\nthat FPGA-based dynamic reconfigurable systems are currently the best avenue to overcome these challenges. In this\nresearch work, we introduce efficient reconfigurable hardware architecture for principal component analysis (PCA), a\nwidely used dimensionality reduction technique in data mining. For mobile applications such as signature verification\nand handwritten analysis, PCA is applied initially to reduce the dimensionality of the data, followed by similarity\nmeasure. Experiments are performed, using a handwritten analysis application together with a benchmark dataset, to\nevaluate and illustrate the feasibility, efficiency, and flexibility of reconfigurable hardware for data mining applications.\nOur hardware designs are generic, parameterized, and scalable. Furthermore, our partial and dynamic reconfigurable\nhardware design achieved 79 times speedup compared to its software counterpart, and 71% space saving compared\nto its static reconfigurable hardware design.
Loading....