کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Performance Evaluation of a Deep Neural Network Joint Equalizer-Decoder in AWGN-ISI Channels

نویسندگان :

Zahra Joleini¹ Ali Jamshidi²

1- دانشگاه شیراز 2- دانشگاه شیراز

کلمات کلیدی :

Deep learning techniques،deep neural network decoder،equalizer،polar codes،channel estimation error

چکیده :

We propose a novel joint equalizer and decoder system based on deep neural networks for linear time invariant multipath channels. We use polar codes as the channel code and train two neural networks to perform blind joint equalization and decoding without requiring channel state information or encoder parameters. The first deep neural network recovers the signal from channel distortion, and the second deep neural network decodes the polar code. We demonstrate the superior performance of our system over both conventional and deep convolutional neural network methods, especially under large channel estimation errors.

لیست مقالات

لیست مقالات بایگانی شده

A novel CMRR Enhancement technique in fully-differential Class-AB OTAs

Amirhossein Sabour - Mahsa Ramezan Pour - Mohammad Yavari

Optimal Receiver Placement in Distributed Passive Sensor Networks: A DRL Approach

Hossein Nikaein - Mohammad Reza Jabbari - Maedeh Kadkhodaie Elyaderani - Saeed Gazor

تدوین استراتژی تعمیرات و نگهداری مبتنی بر قابلیت اطمینان در شبکه ی انتقال قدرت

سید سینا طاهری اطاقسرا - مسعود اصغری قراخیلی

Positioning a Moving Target Using Range and Doppler-Rate Measurements with Bi-static Radar

MohammadAmin Latifi - Fereidoon Behnia

Agglomerative Hierarchical Clustering Based on Q-learning for D2D Communication in Public Safety Communication Networks

Sahel Alipour - Mohammad Mansour Kesargheh - Abdulhamid Zahedi - Ghasem Mirjalily - Jamshid Abouei

A Novel HVDC Transmission System Based on Z-Source Converter

Mehdi Zareian Jahromi - Mohammadreza Mousavikhademi - Ebrahim Kazemi

Non-Line-of-Sight imaging using raster scanning at NIR wavelength

Mohammad Roueinfar - Mahdi Salmanian

Improving CycleGAN-VC2 Voice Conversion by Learning MCD-Based Evaluation and Optimization

Majid Behdad - Davood Gharavian

Recurrence Quantification and Machine Learning: A Novel Approach for Parkinson’s Disease Diagnosis from EEG Signals

Asghar Zarei - Alireza Talesh Jafadideh

A Single-Fed Circularly-Polarized Elliptical Slot Antenna for S-Band applications

Sina Rezaee - Mahdi Janforooz - Behnam Rasoulpour

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0