Fast-Fading Channel Environment Estimation Using Linear Minimum Mean Squares Error-Support Vector Regression

Charrada, Anis; Samet, Abdelaziz

doi:10.1007/s11277-018-5728-z

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x i denotes the input vector, ∥.∥ is the Euclidean norm, and σ is a scaling factor determined by crossvalidation methods or using previous information. References [8][9][10][11] have used the standard SVR for channel estimation in two steps, that is, learning and estimation. First, the channel response of the pilot symbols is determined using the LS and MMSE estimators, and the necessary coefficients are obtained by solving the QP problem.…”

Section: Support Vector Regression (Svr) Channel Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Least squares support vector regression-based channel estimation for OFDM systems in the presence of impulsive noise

Mirsalari,

Haghbin,

Khatir

et al. 2024

Preprint

View full text Add to dashboard Cite

This work aimed to investigate a multipath channel estimation technique for orthogonal frequency division multiplexing (OFDM) systems based on least squares support vector regression (LSSVR) in the presence of Gaussian and impulse noise. Since impulsive noise can considerably affect the performance of communication systems and also due to the time-varying and frequency selectivity of wireless channels, it is unavoidable to have a proper channel estimation and interpolation technique. Therefore, in this contribution, an autoregressive modeled multipath channel was estimated using LSSVR in the presence of impulsive and Gaussian noises. Considering that the proposed method does not need to solve a quadratic programming (QP) problem, it is less complex than standard support vector regression (SVR). The simulation results indicate that the proposed method outperforms standard SVR and the cubic-spline interpolated LS in terms of bit error rate (BER) and mean square error (MSE) criteria.

show abstract

Section: Support Vector Regression (Svr) Channel Estimationmentioning

confidence: 99%

“…Then, the data symbol channel response was interpolated using the SVR interpolator. SVR was used to estimate the channel by [10] and [11] where MMSE was used during the learning phase. SVM for detection was provided by [12].…”

Section: Introductionmentioning

confidence: 99%

Least squares support vector regression-based channel estimation for OFDM systems in the presence of impulsive noise

Mirsalari,

Haghbin,

Khatir

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…To minimize approximation errors e 1 and e 2 , we exploited the ε-Huber loss function presented in [22]. For purposes of convenience, we symbolize by (t 1 n ) the T(n, 1) value corresponding to the rst reference symbol location at the n th line.…”

Section: Normalized Mean Squares Error (Nmse) and Root Mean Squares Errormentioning

confidence: 99%

Robust and sparse Dual Tree Complex Wavelet Transform-based Twin Support Vector regression for dense 5G InH Communications

Charrada

Samet

2021

Preprint

Self Cite

View full text Add to dashboard Cite

A robust and sparse Twin Support Vector Regression based on Dual Tree Discrete Wavelet Transform algorithm is conceived in this paper and applied to 28, 38, 60 and 73-GHz LOS (Line-of-Sight) wireless multipath transmission system in 5G Indoor Hotspot (InH) settings (simple, semi-complex and complex conference rooms) under small receiver sensitivity threshold. The algorithm establishes a denoising process in the learning phase based on Dual Tree Discrete Wavelet Transform (DT-CWT) which is suitable for time-series data. Additionally, the Close-In (CI) free space reference distance path loss model is analyzed and the large-scale propagation and probability distribution functions are investigated by determining the PLE (Path Loss Exponent) and the standard deviation of Shadow Factor (SF) for each InH scenario under consideration. Performance are evaluated under twelve (12) configuration scenarios, according to three criteria: mobility (0/3mps), receiver sensitivity threshold (-80/-120 dBm) and type of the InH area (simple, semi-complex and complex conference room). Experimental results confirm the effectiveness of the proposed approach compared to other standard techniques.

show abstract

Machine Learning Based Illuminance Estimation from RGB Sensor in a Wireless Network

Ghosh¹,

Satvaya

Kundu

et al. 2022

Wireless Pers Commun

View full text Add to dashboard Cite

Fast-Fading Channel Environment Estimation Using Linear Minimum Mean Squares Error-Support Vector Regression

Cited by 6 publications

References 9 publications

Least squares support vector regression-based channel estimation for OFDM systems in the presence of impulsive noise

Least squares support vector regression-based channel estimation for OFDM systems in the presence of impulsive noise

Robust and sparse Dual Tree Complex Wavelet Transform-based Twin Support Vector regression for dense 5G InH Communications

Machine Learning Based Illuminance Estimation from RGB Sensor in a Wireless Network

Contact Info

Product

Resources

About