A Massively Parallel Algorithm for Fuzzy Vector Quantization
0
조회
0
다운로드
12
인용
0
참고문헌
키워드
초록
Vector quantization algorithm based on fuzzy clustering has been widely used in the field of data compression since the use of fuzzy clustering analysis in the early stages of a vector quantization process can make this process less sensitive to its initialization. However, the process of fuzzy clustering is computationally very intensive because of its complex framework for the quantitative formulation of the uncertainty involved in the training vector space. To overcome the computational burden of the process, this paper introduces an array architecture for the implementation of fuzzy vector quantization (FVQ). The arrayarchitecture, which consists of 4,096 processing elements (PEs), provides a computationally efficient solution by employing an effective vector assignment strategy during the clustering process. Experimental results indicatethat the proposed parallel implementation providessignificantly greater performance and efficiency than appropriately scaled alternative array systems. In addition, the proposed parallel implementation provides 1000x greater performance and 100x higher energy efficiency than other implementations using today’s ARMand TI DSP processors in the same 130nm technology. These results demonstrate that the proposed parallel implementation shows the potential for improved performance and energy efficiency.
Abstract
Vector quantization algorithm based on fuzzy clustering has been widely used in the field of data compression since the use of fuzzy clustering analysis in the early stages of a vector quantization process can make this process less sensitive to its initialization. However, the process of fuzzy clustering is computationally very intensive because of its complex framework for the quantitative formulation of the uncertainty involved in the training vector space. To overcome the computational burden of the process, this paper introduces an array architecture for the implementation of fuzzy vector quantization (FVQ). The arrayarchitecture, which consists of 4,096 processing elements (PEs), provides a computationally efficient solution by employing an effective vector assignment strategy during the clustering process. Experimental results indicatethat the proposed parallel implementation providessignificantly greater performance and efficiency than appropriately scaled alternative array systems. In addition, the proposed parallel implementation provides 1000x greater performance and 100x higher energy efficiency than other implementations using today’s ARMand TI DSP processors in the same 130nm technology. These results demonstrate that the proposed parallel implementation shows the potential for improved performance and energy efficiency.
참고문헌 (14)
- N. B. Karayiannis, "Fuzzy Vector Quantization Algorithms and Their Application in Image Compression", IEEE Trans. on Image Processing, 4(9), pp.1193~1201 (1995)
- N. Gkalelis, "Combining Fuzzy Vector Quantization with Linear Discriminant Analysis for Continuous Human Movement Recognition", IEEE Trans. On Circuits and Systems for Video Technology, 18(11) (2008)
- G. E. Tsekouras, "A Fuzzy Vector Quantization Approach to Image Compression", Applied Mathematics and Computation, pp.539~560 (2005), Elsevier
- F. Masulli, "Fuzzy Concepts in Vector Quantization Training", LNAI, 2955, pp.279~288 (2006)
- H. S. Jayanna, "Fuzzy Vector Quantization for Speaker Recognition under Limited Data Conditions", IEEE Conference on TENCON 2008, pp.1~4 (2008)
- W. Pedrycz, "A Development of Fuzzy Encoding and Decoding Through Fuzzy Clustering", IEEE Trans. on Instrumentation and Measurement, 57(4), pp.829~837 (2008)
- N. B. Karayiannis, "An Integrated Approach to Fuzzy Learning Vector Quantization and Fuzzy c-Means Clustering", IEEE Trans. on Fuzzy Systems, 5(4), pp.622~628 (1997)
- S. M. Chai, "Heterogeneous Architecture Models for Interconnect- motivated System Design", IEEE Trans. VLSI Systems, special issue on system level interconnect prediction, 8(6), pp.660~670 (2000)
- J. C. Eble, "A Generic System Simulator (GENESYS) for ASIC Technology and Architecture Beyond 2001", Proc. of the Ninth Ann. IEEE Intl. ASIC Conf, pp.193~196 (1996)
- H. J. Lee, "A Parallel Vector Quantization Algorithm for Single-Instruction- Multiple-Data (SIMD) Multiprocessor Systems", Proc. of the 5th Data Compression Conference, pp.479~ (1995)
- K. S. Prashant, "A Massively Parallel Algorithm for Vector Quantization", Proc. of the 1995 NASA Space and Earth Sciences Workshop (1995)
- Implementation of VQ Algorithms on a Reconfigurable Array Processor, "T. B. Henderson", Naval Ocean Systems, ~, pp.Professional Paper No. AD-A236 483 (1991), 4[DOI]