کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

A Novel CNN-Based FSK Demodulator With Efficient FPGA Implementation

نویسندگان :

AmirHossein Sadough¹ Sina Rezaeeahvanouee²

1- Department of Electrical Engineering, Shahid Rajaee Teacher Training University 2- Department of Electrical and Computer Engineering, University of Minnesota

کلمات کلیدی :

FSK،CNN،Demodulator،CFD،FPGA،BER،Implementation

چکیده :

Abstract— Nowadays, neural networks have become a new approach to achieving the destinations of researchers due to their accuracy. Neural networks are widely used in machine vision, image classification, and sound detection, but in the field of signal processing, it still has no content of the extent in the field of image processing. This is not due to the inability of deep learning to meet the needs of signal processing, but because that is an ultra-modern solution. This paper proposed a novel CNN-Based FSK demodulator (CFD) that uses a compact convolutional neural network as a special method to demodulate the FSK signal. The proposed CNN network has a minimal computational load and is optimized in terms of hardware implementation complexity. The designed CNN Network has three layers: a convolutional Layer, a Max-Pooling layer, and a fully connected Layer. The CFD is designed to demodulate an FSK signal of 20±1MHz with a bitrate of 1Mbps. The BER of lower than 10-6 has been achieved at Eb/N0=15dB. The resource utilization of implemented proposed demodulator on FPGA only shows 970 and 751, for LUT and FF respectively, which is minimal and indicates the efficiency of our method.

لیست مقالات

لیست مقالات بایگانی شده

Design and Determing Two Separate Rotor Axial Flux Permanent Magnet Motor Load and Efficinecy

Siamak Omrani - Ahmad Darabi

A New Optimal Design of a Solar Power Plant On The Rooftop of Bovisa Train Station in Milan

Omid Nasirkhani - Mohsen Tamaddon

Millimeter-Wave Imaging System: A Brief Study on System Performance

Behnam Ghandi - Sobhan Dabidian - Sina Zeraatkar - Zahra Kavehvash

Multinomial Emoji Prediction Using Deep Bidirectional Transformers and Topic Modeling

Zahra Ebrahimian - Ramin Toosi - Mohammad Ali Akhaee

Design and Simulation of Nano-Second Pulsed Power Generator for Cancer Treatment and Considering Load Effect

Reza PirNia - Maryam A.Hejazi - Nasrin Deldadeh

Design and fabrication tip tapered fiber optic dopamine sensor based on LSPR

Roksana Esmaeilpour - Mohammad Ismail zibaii - Masoumeh Barkand - Marzieh Pajouhandeh - Soroush Rostami - Mehdi Banihashemi - Mohammad-Mahdi Babakhani-fard

Image steganography Based on Chaos permutation, authentication and wiener deconvolution

Ali Sheidaee - Mohammad Asadpour - Leili Farzinvash

Design and Implementation of a Flexible CNN Accelerator for Fast Real-Time Object Detection on FPGA

Emadodin Sakhaee - Mahdi Kalbasi

Forecasting Crude Oil Prices using improved deep belief network (IDBN) and long-term short-term memory network (LSTM)

Mohammad Mahdi Lotfi Heravi - Mahsa Khorrampanah - Monireh Houshmand

Network-based functional connectivity in MDD with suicide ideation before and after TMS: An fMRI case study

Moslem Khafi - Morteza Fattahi - Hamid Soltanian-Zadeh - Reza Rostami

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2