Scalable and Parameterized Architecture for Efficient Stream Mining

Li ZHANG; Dawei LI; Xuecheng ZOU; Yu HU; Xiaowei XU

doi:10.1587/transfun.E101.A.219

Scalable and Parameterized Architecture for Efficient Stream Mining

Li ZHANG, Dawei LI, Xuecheng ZOU, Yu HU, Xiaowei XU

Full Text Views

0

Share
Cite this

Summary :

With an annual growth of billions of sensor-based devices, it is an urgent need to do stream mining for the massive data streams produced by these devices. Cloud computing is a competitive choice for this, with powerful computational capabilities. However, it sacrifices real-time feature and energy efficiency. Application-specific integrated circuit (ASIC) is with high performance and efficiency, which is not cost-effective for diverse applications. The general-purpose microcontroller is of low performance. Therefore, it is a challenge to do stream mining on these low-cost devices with scalability and efficiency. In this paper, we introduce an FPGA-based scalable and parameterized architecture for stream mining.Particularly, Dynamic Time Warping (DTW) based k-Nearest Neighbor (kNN) is adopted in the architecture. Two processing element (PE) rings for DTW and kNN are designed to achieve parameterization and scalability with high performance. We implement the proposed architecture on an FPGA and perform a comprehensive performance evaluation. The experimental results indicate thatcompared to the multi-core CPU-based implementation, our approach demonstrates over one order of magnitude on speedup and three orders of magnitude on energy-efficiency.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E101-A No.1 pp.219-231

Publication Date: 2018/01/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E101.A.219

Type of Manuscript: PAPER

Category: Systems and Control

Authors

Li ZHANG
  Huazhong University of Science and Technology
Dawei LI
  Huazhong University of Science and Technology
Xuecheng ZOU
  Huazhong University of Science and Technology
Yu HU
  Huazhong University of Science and Technology
Xiaowei XU
  Huazhong University of Science and Technology

Keyword

stream mining architecture, parameterization, dynamic time warping, k-nearest neighbor

Cite this

Copy

Li ZHANG, Dawei LI, Xuecheng ZOU, Yu HU, Xiaowei XU, "Scalable and Parameterized Architecture for Efficient Stream Mining" in IEICE TRANSACTIONS on Fundamentals, vol. E101-A, no. 1, pp. 219-231, January 2018, doi: 10.1587/transfun.E101.A.219.
Abstract: With an annual growth of billions of sensor-based devices, it is an urgent need to do stream mining for the massive data streams produced by these devices. Cloud computing is a competitive choice for this, with powerful computational capabilities. However, it sacrifices real-time feature and energy efficiency. Application-specific integrated circuit (ASIC) is with high performance and efficiency, which is not cost-effective for diverse applications. The general-purpose microcontroller is of low performance. Therefore, it is a challenge to do stream mining on these low-cost devices with scalability and efficiency. In this paper, we introduce an FPGA-based scalable and parameterized architecture for stream mining.Particularly, Dynamic Time Warping (DTW) based k-Nearest Neighbor (kNN) is adopted in the architecture. Two processing element (PE) rings for DTW and kNN are designed to achieve parameterization and scalability with high performance. We implement the proposed architecture on an FPGA and perform a comprehensive performance evaluation. The experimental results indicate thatcompared to the multi-core CPU-based implementation, our approach demonstrates over one order of magnitude on speedup and three orders of magnitude on energy-efficiency.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.219/_p

Copy

@ARTICLE{e101-a_1_219,
author={Li ZHANG, Dawei LI, Xuecheng ZOU, Yu HU, Xiaowei XU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Scalable and Parameterized Architecture for Efficient Stream Mining},
year={2018},
volume={E101-A},
number={1},
pages={219-231},
abstract={With an annual growth of billions of sensor-based devices, it is an urgent need to do stream mining for the massive data streams produced by these devices. Cloud computing is a competitive choice for this, with powerful computational capabilities. However, it sacrifices real-time feature and energy efficiency. Application-specific integrated circuit (ASIC) is with high performance and efficiency, which is not cost-effective for diverse applications. The general-purpose microcontroller is of low performance. Therefore, it is a challenge to do stream mining on these low-cost devices with scalability and efficiency. In this paper, we introduce an FPGA-based scalable and parameterized architecture for stream mining.Particularly, Dynamic Time Warping (DTW) based k-Nearest Neighbor (kNN) is adopted in the architecture. Two processing element (PE) rings for DTW and kNN are designed to achieve parameterization and scalability with high performance. We implement the proposed architecture on an FPGA and perform a comprehensive performance evaluation. The experimental results indicate thatcompared to the multi-core CPU-based implementation, our approach demonstrates over one order of magnitude on speedup and three orders of magnitude on energy-efficiency.},
keywords={},
doi={10.1587/transfun.E101.A.219},
ISSN={1745-1337},
month={January},}

Copy

TY - JOUR
TI - Scalable and Parameterized Architecture for Efficient Stream Mining
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 219
EP - 231
AU - Li ZHANG
AU - Dawei LI
AU - Xuecheng ZOU
AU - Yu HU
AU - Xiaowei XU
PY - 2018
DO - 10.1587/transfun.E101.A.219
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2018
AB - With an annual growth of billions of sensor-based devices, it is an urgent need to do stream mining for the massive data streams produced by these devices. Cloud computing is a competitive choice for this, with powerful computational capabilities. However, it sacrifices real-time feature and energy efficiency. Application-specific integrated circuit (ASIC) is with high performance and efficiency, which is not cost-effective for diverse applications. The general-purpose microcontroller is of low performance. Therefore, it is a challenge to do stream mining on these low-cost devices with scalability and efficiency. In this paper, we introduce an FPGA-based scalable and parameterized architecture for stream mining.Particularly, Dynamic Time Warping (DTW) based k-Nearest Neighbor (kNN) is adopted in the architecture. Two processing element (PE) rings for DTW and kNN are designed to achieve parameterization and scalability with high performance. We implement the proposed architecture on an FPGA and perform a comprehensive performance evaluation. The experimental results indicate thatcompared to the multi-core CPU-based implementation, our approach demonstrates over one order of magnitude on speedup and three orders of magnitude on energy-efficiency.
ER -