Extreme learning machine-based receiver for MIMO LED communications

Gao, Dawei; Guo, Qinghua

doi:10.1016/j.dsp.2019.102594

Cited by 13 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ELM RECEIVER BORROWED FROM [7] In [7], we proposed an ELM based receiver to handle both the LED nonlinearity and cross-LED interference in MIMO LED communications. Here, we borrow the ELM receiver in [7]. As shown in Fig.…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…It can be seen in ( 10) that, intensive calculations are involved in the product of the input weight matrix Ω and the input data vector r [m], leading to a quadratic complexity O(LN). As we proposed in [7], we can put a constrain on the structure of Ω, i.e., it is a (partial) circulant input weight matrix, enabling an implementation using the fast Fourier transform (FFT) with significantly reduced complexity. Refer to [7] for details.…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…As we proposed in [7], we can put a constrain on the structure of Ω, i.e., it is a (partial) circulant input weight matrix, enabling an implementation using the fast Fourier transform (FFT) with significantly reduced complexity. Refer to [7] for details.…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…The parameters to be learned in ELM are the output weights, which boils down to solving a linear system, making ELM fast in learning. ELM has been investigated for light emitting diode (LED) communications in our previous works [7], [8] to tackle LED nonlinearity and/or cross-LED interference. We have designed ELM based non-iterative and iterative receivers [8], and our investigations demonstrate that ELM is very effective to handle nonlinearity, delivering much better performance than polynomial based techniques [9], [10].…”

Section: Introductionmentioning

confidence: 99%

“…ELM is briefly introduced in Section III. In Section IV, an ELM receiver is borrowed from [7] for massive MIMO detection. In Section V, the new ELM based receiver is proposed, where the massive MIMO itself is treated as part of the ELM.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Massive MIMO as an Extreme Learning Machine

Gao

Guo

Eldar

2021

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

This work shows that massive multiple-input multiple-output (MIMO) with low-resolution analog-to-digital converters (ADCs) forms a natural extreme learning machine (ELM), where the massive number of receive antennas act as hidden nodes of the ELM, and the low-resolution ADCs serve as the activation function of the ELM. It is demonstrated that by adding biases to received signals and optimizing the ELM output weights, the system can effectively tackle hardware impairments, e.g., the power amplifier nonlinearity at transmitter side. It is interesting that the low-resolution ADCs can bring benefit to the receiver in handling nonlinear impairments, and the most computation-intensive part of the ELM is naturally accomplished by signal transmission and reception.

show abstract

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Extreme Learning Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Massive MIMO as an Extreme Learning Machine

Gao

Guo

Eldar

2021

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

Machine learning‐based predictive modeling for failure management of optical spatial mode division multiplexing system

Kaur

Parasher²,

Srivastava

et al. 2022

Int J Communication

View full text Add to dashboard Cite

The bit error rate (BER) in optical communication systems is often get degraded due to various factors like launch power, dispersion, modal noise, and so on. Finding the most optimal launch power for a signal to provide acceptable BER is usually difficult on an installed link. Therefore, in this paper, an attempt has been made to use machine learning-based linear regression technique for predicting the optimal signal quality for spatial division multiplexed (SDM)-based fiber optical transmission system for a fixed distance. This technique helps in predicting the optimal value of continuous launch power. Therefore, to demonstrate the given concept in this research work, the generic setup of an SDM optical long-haul system of 20 km in length has been designed and simulated in Optisystem-14.0. The light sources in our experiments are two spatial optical transmitters with an emission wavelength of around 1550 nm. Abiding to the first step for the regression analysis, that is the data preparation, normality and correlation checks were performed. After this, a linear regression model is developed which was validated through a summary report, coefficients and diagnostic plots. Furthermore, the accuracy of the model is improved by employing Cook's distance. These tests help in dealing with the influence points that hinders the prediction ability of the proposed model. The results show that the R-squared value is 0.9366, and value of adjusted R 2 comes out to be around 0.9344; we therefore came to infer that the model explains nearly 94% variations in the dependent variables. K E Y W O R D Sbit error rate (BER), launch power (LP), linear regression, optical transmission systems, spatial division multiplex (SDM)

show abstract