Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation

Henry José Block Saldaña; Carlos Silva Cárdenas

doi:10.1109/ANDESCON.2010.5633065

Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation

Henry José Block Saldaña, Carlos Silva Cárdenas

Sección de Ingeniería de Telecomunicaciones

Pontifical Catholic Univ. of Peru

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

This paper presents a digital system architecture for a two-input one-output zero order ANFIS (Adaptive Neuro-Fuzzy Inference System) and its implementation on an FPGA (Field Programmable Gate Array) using VHDL (VHSIC Hardware Description Language). The designed system is used for nonlinear function generation. First, a nonlinear function is chosen and off-line training is carried out using MATLAB ANFIS to obtain the premise and consequence parameters of the fuzzy rules. Then, these parameters are converted to a binary fixed-point representation and are stored in read-only memories of the VHDL code. Finally, simulations are performed to verify the system operation and to evaluate the system response time for given input data.

Original language	English
Title of host publication	2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010
DOIs	https://doi.org/10.1109/ANDESCON.2010.5633065
State	Published - 2010
Event	2010 IEEE ANDESCON Conference, ANDESCON 2010 - Bogota, Colombia Duration: 14 Sep 2010 → 17 Sep 2010

Publication series

Name	2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010

Conference

Conference	2010 IEEE ANDESCON Conference, ANDESCON 2010
Country/Territory	Colombia
City	Bogota
Period	14/09/10 → 17/09/10

Keywords

ANFIS
Digital system
FPGA
Neuro-fuzzy system
VHDL

Access to Document

10.1109/ANDESCON.2010.5633065

Cite this

@inproceedings{3fc696921a2946bc9c43ca056720c1af,

title = "Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation",

abstract = "This paper presents a digital system architecture for a two-input one-output zero order ANFIS (Adaptive Neuro-Fuzzy Inference System) and its implementation on an FPGA (Field Programmable Gate Array) using VHDL (VHSIC Hardware Description Language). The designed system is used for nonlinear function generation. First, a nonlinear function is chosen and off-line training is carried out using MATLAB ANFIS to obtain the premise and consequence parameters of the fuzzy rules. Then, these parameters are converted to a binary fixed-point representation and are stored in read-only memories of the VHDL code. Finally, simulations are performed to verify the system operation and to evaluate the system response time for given input data.",

keywords = "ANFIS, Digital system, FPGA, Neuro-fuzzy system, VHDL",

author = "Salda{\~n}a, {Henry Jos{\'e} Block} and C{\'a}rdenas, {Carlos Silva}",

year = "2010",

doi = "10.1109/ANDESCON.2010.5633065",

language = "English",

isbn = "9781424467419",

series = "2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010",

booktitle = "2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010",

note = "2010 IEEE ANDESCON Conference, ANDESCON 2010 ; Conference date: 14-09-2010 Through 17-09-2010",

}

Saldaña, HJB & Cárdenas, CS 2010, Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation. in 2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010., 5633065, 2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010, 2010 IEEE ANDESCON Conference, ANDESCON 2010, Bogota, Colombia, 14/09/10. https://doi.org/10.1109/ANDESCON.2010.5633065

Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation. / Saldaña, Henry José Block; Cárdenas, Carlos Silva.
2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010. 2010. 5633065 (2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation

AU - Saldaña, Henry José Block

AU - Cárdenas, Carlos Silva

PY - 2010

Y1 - 2010

N2 - This paper presents a digital system architecture for a two-input one-output zero order ANFIS (Adaptive Neuro-Fuzzy Inference System) and its implementation on an FPGA (Field Programmable Gate Array) using VHDL (VHSIC Hardware Description Language). The designed system is used for nonlinear function generation. First, a nonlinear function is chosen and off-line training is carried out using MATLAB ANFIS to obtain the premise and consequence parameters of the fuzzy rules. Then, these parameters are converted to a binary fixed-point representation and are stored in read-only memories of the VHDL code. Finally, simulations are performed to verify the system operation and to evaluate the system response time for given input data.

AB - This paper presents a digital system architecture for a two-input one-output zero order ANFIS (Adaptive Neuro-Fuzzy Inference System) and its implementation on an FPGA (Field Programmable Gate Array) using VHDL (VHSIC Hardware Description Language). The designed system is used for nonlinear function generation. First, a nonlinear function is chosen and off-line training is carried out using MATLAB ANFIS to obtain the premise and consequence parameters of the fuzzy rules. Then, these parameters are converted to a binary fixed-point representation and are stored in read-only memories of the VHDL code. Finally, simulations are performed to verify the system operation and to evaluate the system response time for given input data.

KW - ANFIS

KW - Digital system

KW - FPGA

KW - Neuro-fuzzy system

KW - VHDL

UR - http://www.scopus.com/inward/record.url?scp=79952081746&partnerID=8YFLogxK

U2 - 10.1109/ANDESCON.2010.5633065

DO - 10.1109/ANDESCON.2010.5633065

M3 - Conference contribution

AN - SCOPUS:79952081746

SN - 9781424467419

T3 - 2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010

BT - 2010 IEEE ANDESCON Conference Proceedings, ANDESCON 2010

T2 - 2010 IEEE ANDESCON Conference, ANDESCON 2010

Y2 - 14 September 2010 through 17 September 2010

ER -

Design and implementation of an adaptive neuro-fuzzy inference system on an FPGA used for nonlinear function generation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this