ADPCM environment with a neural network predictor engine

Author

Groza, Voicu ; Abielmona, Rami ; Petriu, Emil M.

Author_Institution

Sch. of Inf. Technol. Eng., Ottawa Univ., Ont., Canada

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

541

Abstract

Presented in this paper is an innovative technique to improve analog-to-digital converters (ADCs). The methodology utilizes a built-in neural network engine to first learn, and then predict, the quantization step size. This produces a completely adaptable ADC, consisting of ADPCM samples fed back with the output of the neural network, which is capable of generating a better quantized output. The algorithmic solution, simulation methodology and results are also presented in this writing.

Keywords

adaptive modulation; backpropagation; differential pulse code modulation; linear predictive coding; multilayer perceptrons; quantisation (signal); ADPCM environment; PCB realization; algorithmic solution; analog-digital converters; built-in neural network engine; completely adaptable ADC; dynamic instruction; forward linear prediction; learned network output; linear predictive coefficients; neural network predictor engine; opcode modulation; quantisation step size; real-time signal tracking; simulation methodology; Costing; Engines; Equations; Information technology; Modulation coding; Neural networks; Phase change materials; Pulse modulation; Pulse width modulation converters; Quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2002. IMTC/2002. Proceedings of the 19th IEEE

ISSN

1091-5281

Print_ISBN

0-7803-7218-2

Type

conf

DOI

10.1109/IMTC.2002.1006900

Filename

1006900