Review of neural network technique for modeling PA memory effect

Yan, Shuxia; Shi, Weiguang; Wen, Jia

doi:10.1109/nemo.2016.7561675

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, Volterra model is also not ideal for characterizing PAs with light nonlinearity and/or weak memory effect, due to a likelihood overfitting. Several complexity reduced (CR) Volterra models have been proposed in previous literature including the Memory Polynomial (MP) and the Generalized Memory Polynomial (GMP) [6], [8], [9], [10], [11]. These models are relatively compact but often employ coefficients of insignificant contribution.…”

Section: Introductionmentioning

confidence: 99%

A Complexity Reduced Non-Uniform Generalized Memory Polynomial Model for Nonlinear Power Amplifier Behavioural Modeling

Byrne

Farrell

et al. 2019

2019 30th Irish Signals and Systems Conference (ISSC)

View full text Add to dashboard Cite

Power amplifiers are widely employed electronic devices in various fields such as mobile networks and radio frequency (RF) transceivers. To achieve efficient operations, power amplifiers can often suffer from nonlinearity problems. This problem can be mitigated through the use of linearization techniques, such as digital predistortion, regarded as the most promising solution to power amplifier linearization. Behavioural modeling is a substantial part of the digital predistortion, responsible for acquiring the coefficients that are necessary to linearize the power amplifier. A Complex Reduced Non-Uniform Generalized Memory Polynomial model was proposed to reach comparable performance of accuracy as Memory Polynomial Model with reduced complexities. The proposed model was tested with a 5MHz LTE signal measured at the input and output of a Doherty PA under different conditions of nonlinearities, memory effects and attenuations as well as PA working powers. It can be observed that the proposed model shows superior accuracy at low complexities, when the PA has higher levels of nonlinearity and memory depth while still maintaining low complexities. Over 60% of coefficients reduction could be reached at the same level of accuracy compared to the MP model.

show abstract

Section: Introductionmentioning

confidence: 99%

A Complexity Reduced Non-Uniform Generalized Memory Polynomial Model for Nonlinear Power Amplifier Behavioural Modeling

Byrne

Farrell

et al. 2019

2019 30th Irish Signals and Systems Conference (ISSC)

View full text Add to dashboard Cite

show abstract

Theoretical analysis of neuronal network’s response under different stimulus

Xue,

Lu,

Lan

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Neuromodulation plays a critical role in the normal physiological functions of organisms. With advancements in science and technology, neuromodulation has expanded into various fields. For instance, in the field of engineering, in vitro-cultured neural networks are utilized to perform closed-loop control for achieving complex functionalities. Conducting pioneering theoretical research using mathematical models is particularly essential for enhancing efficiency and reducing costs. This study focuses on examining the relationship between input and output in order to establish a groundwork for more advanced closed-loop regulation applications in engineering. Using a constructed neural network model, Poisson, square wave and direct current (DC) stimulation are applied. The results show that the network’s firing rate increases with the frequency or amplitude of these stimulations. And the network’s firing rate could reach to a stable state after the stimulation is applied for 0.8s and return to initial states when the stimulus is removed for 1s. To ascertain if the system exhibits a memory effect from the previous stimulus, we conduct independent and continuous stimulation schemes. Comparing the firing rate of neuronal networks under these two stimulation schemes reveals a memory effect of the system on the previous stimulus, which is independent of network properties and stimulus types. Finally, by applying square wave stimulation to the in vitro cultured neural network, we have confirmed that cultured neural network actually can reach to a steady state and have memory effects on the previous stimulus. Our research results have important theoretical significance and reference value for designing the closed-loop regulation strategy of in vitro cultured neuronal networks.

show abstract

Review of neural network technique for modeling PA memory effect

Cited by 2 publications

References 3 publications

A Complexity Reduced Non-Uniform Generalized Memory Polynomial Model for Nonlinear Power Amplifier Behavioural Modeling

A Complexity Reduced Non-Uniform Generalized Memory Polynomial Model for Nonlinear Power Amplifier Behavioural Modeling

Theoretical analysis of neuronal network’s response under different stimulus

Contact Info

Product

Resources

About