scholarly journals EVM Loss: A Loss Function for Training Neural Networks in Communication Systems

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1094
Author(s):  
Scott Stainton ◽  
Martin Johnston ◽  
Satnam Dlay ◽  
Paul Anthony Haigh
Keyword(s):  
Neural Networks ◽  
Loss Function ◽  
Communication Systems ◽  
Orthogonal Frequency Division Multiplexing ◽  
Frequency Division Multiplexing ◽  
Efficiency Gain ◽  
Frequency Division ◽  
Error Vector Magnitude ◽  
Modulation Formats ◽  
Complex Approach

Neural networks and their application in communication systems are receiving growing attention from both academia and industry. The authors note that there is a disconnect between the typical objective functions of these neural networks with regards to the context in which the neural network will eventually be deployed and evaluated. To this end, a new loss function is proposed and shown to increase the performance of neural networks when implemented in a communication system compared to previous methods. It is further shown that a ‘split complex’ approach used by many implementations can be improved via formalisation of the ‘concatenated complex’ approach described herein. Experimental results using the orthogonal frequency division multiplexing (OFDM) and spectrally efficient frequency division multiplexing (SEFDM) modulation formats with varying bandwidth compression factors over a wireless visible light communication (VLC) link validate the efficacy of the proposed method in a real system, achieving the lowest error vector magnitude (EVM), and thus bit error rate (BER), across all experiments, with a 5 dB to 10 dB improvement in the received symbols EVM overall compared to the baseline implementation, with bandwidth compressions down to 40% compared to OFDM, resulting in a spectral efficiency gain of 67%.

scholarly journals Channel estimation of OFDM in C-band communication systems under different distribution conditions

2021 ◽  
Vol 23 (3) ◽  
pp. 1778
Author(s):  
Heba Abdul-Jaleel Al-Asady ◽  
Hassan Falah Fakhruldeen ◽  
Mustafa Qahtan Alsudani
Keyword(s):  
Fourier Transform ◽  
Channel Estimation ◽  
Fast Fourier Transform ◽  
Communication Systems ◽  
Orthogonal Frequency Division Multiplexing ◽  
Frequency Division Multiplexing ◽  
Frequency Division ◽  
Ofdm System ◽  
High Data ◽  
High Efficient

<p>Orthogonal frequency division multiplexing (OFDM) is a transmission system that uses multiple orthogonal carriers that are sent out at the same time. OFDM is a technique for mobile and wireless communication that has high-efficient frequency utilization, high data-rate transmission, simple and efficient implementation using the fast Fourier transform (FFT) and the inverse fast Fourier transform (IFFT), and reduces inter symbol interference (ISI) by inserting cyclic prefix (CP). One of the most important approaches in an OFDM system is channel estimation. In this paper, the orthogonal frequency division multiplexing system with the Rayleigh channel module is analyzed for different areas. The proposed approach used large numbers of subcarriers to transmit the signals over 64-QAM modulation with pilot add channel estimation. The accuracy of the OFDM system is shown in the measuring of the relationships of peak power to the noise ratio and bit error rate.</p>

scholarly journals Research of the Influence of the Quadrature Components Mismatch on the Noise Immunity of OFDM and UFMC Signals

2021 ◽  
Vol 24 (1) ◽  
pp. 71
Author(s):  
A. Yu. Belousov ◽  
V. V. Khvorenkov
Keyword(s):  
Bit Error Rate ◽  
Error Rate ◽  
Orthogonal Frequency Division Multiplexing ◽  
Noise Immunity ◽  
Frequency Division Multiplexing ◽  
Frequency Division ◽  
Error Vector Magnitude ◽  
Error Vector ◽  
Vector Magnitude

Метод непосредственной модуляции с использованием комплексных сигналов применяется при реализации сигнальных трактов передатчиков в базовых станциях систем сотовой связи. В процессе модуляции возникают рассогласования коэффициента усиления и фазы квадратурных составляющих сигнала. Рассогласование ухудшает модуль вектора ошибки (Error Vector Magnitude, EVM) в приемнике, что, в свою очередь, приводит к повышению частоты появления ошибочных битов (Bit Error Rate, BER). Качество принимаемого сигнала выражается в частоте появления битовых ошибок. Рассогласование амплитуды и фазы квадратурных составляющих является одним из важнейших факторов, вносящих наибольший вклад в амплитуду вектора ошибки, который необходимо исследовать.В статье приведено исследование влияния рассогласования квадратурных составляющих сигналов технологий OFDM (Orthogonal frequency-division multiplexing) и UFMC (universal filtered multi-carrier). Разработана модель передатчика, канала связи и приемника для сигналов OFDM и UFMC. Модель построена в програм­мной среде MatLab при помощи языка MatLab и представляет собой программную модель m-script.В ходе работы путем исследования имитационной модели изучена зависимость помехоустойчивости технологий путем изменения параметров канала связи, таких как амплитудное и фазовое рассогласование квадратурных составляющих сигнала, а также отношение сигнал/шум. Проведен сравнительный анализ таких параметров сигналов, как занимаемая полоса частот, пик-фактор, частота появления битов с ошибкой. По результатам исследования получены графики зависимости вероятности ошибки и пик-фактора сигнала от рассогласования квадратурных составляющих для двух технологий – OFDM и UFMC. Проведенное исследование позволяет выделить преимущества технологии UFMC, которые выражаются в спектральной эффективности, помехоустойчивости и уровне пик-фактора сигнала.

scholarly journals Number of subcarrier filter coefficients in GFDM system: effect on performance

Ingenius ◽  
2019 ◽  
pp. 53-61
Author(s):  
Randy Verdecia Peña ◽  
Humberto Millán Vega
Keyword(s):  
Communication Systems ◽  
Orthogonal Frequency Division Multiplexing ◽  
Modulation Scheme ◽  
Frequency Division Multiplexing ◽  
Frequency Division ◽  
Transmission Scheme ◽  
System Effect ◽  
Simple Method ◽  
Multicarrier Transmission ◽  
Prototype Filter

Generalized Frequency Division Multiplexing (GFDM) is a non-orthogonal multicarrier transmission scheme proposed for fifth (5G) and future generation wireless networks. Due to its attractive properties, it has been recently discussed as a candidate waveform for the future wireless communication systems. GFDM is introduced as a generalized form of the widely used Orthogonal Frequency Division Multiplexing (OFDM) modulation scheme and it uses only one cyclic prefix (CP) for a group of symbols. The main focus of this work is to present like impact on the system performance the coefficient quantity of the subcarrier filter. A simple method for the computation of the coefficients of the prototype filter is employed. Besides, it is presented a structure for the GFDM by taking advantage of the arrangement in the modulation matrix. We evaluated the Bit Error Rate (BER) using the receiver models presented in this work. The results showed that the BER is affected according to the coefficients quantity of the prototype filter. Based on the obtained results, the coefficients quantity has a relation with the number of time slots of the GFDM system.

scholarly journals An identification of the tolerable time-interleaved analog-to-digital converter timing mismatch level in high-speed orthogonal frequency division multiplexing systems

2022 ◽  
Vol 12 (2) ◽  
pp. 1667
Author(s):  
Vo Trung Dung Huynh ◽  
Linh Mai ◽  
Hung Ngoc Do ◽  
Minh Ngoc Truong Nguyen ◽  
Trung Kien Pham
Keyword(s):  
Bit Error Rate ◽  
Error Rate ◽  
Communication Systems ◽  
Orthogonal Frequency Division Multiplexing ◽  
High Speed ◽  
Performance Degradation ◽  
Frequency Division Multiplexing ◽  
Frequency Division ◽  
Analog To Digital ◽  
Time Interleaved

<span>High-speed Terahertz communication systems has recently employed orthogonal frequency division multiplexing approach as it provides high spectral efficiency and avoids inter-symbol interference caused by dispersive channels. Such high-speed systems require extremely high-sampling <br /> time-interleaved analog-to-digital converters at the receiver. However, timing mismatch of time-interleaved analog-to-digital converters significantly causes system performance degradation. In this paper, to avoid such performance degradation induced by timing mismatch, we theoretically determine maximum tolerable mismatch levels for orthogonal frequency division multiplexing communication systems. To obtain these levels, we first propose an analytical method to derive the bit error rate formula for quadrature and pulse amplitude modulations in Rayleigh fading channels, assuming binary reflected gray code (BRGC) mapping. Further, from the derived bit error rate (BER) expressions, we reveal a threshold of timing mismatch level for which error floors produced by the mismatch will be smaller than a given BER. Simulation results demonstrate that if we preserve mismatch level smaller than 25% of this obtained threshold, the BER performance degradation is smaller than 0.5 dB as compared to the case without timing mismatch.</span>

Sign in / Sign up

Export Citation Format

Share Document