<p>A novel framework based on combining the You Only Look Once-CSE (YOLO-CSE) model is implemented in this paper with Communication Visible Light (CVL) and Multiple Access non-orthogonality (MANO-CVL) for Multiple Input and Output (MIMO). The main goal of the proposed model is to decrease the detecting error in the received bits and distinguish between noise signal and correct bits. The YOLO-CSE model uses the Yolov5 model as a backbone. Two sorts of regulation are applied; position modulation (L-PPM) with different L and users, inside a Comparable Gain Combiner (CGC) at the recipient. This framework thinks about <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$n$</EquationSource> <EquationSource Format="MATHML"><math> <mi>n</mi> </math></EquationSource> </InlineEquation> and <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$m$</EquationSource> <EquationSource Format="MATHML"><math> <mi>m</mi> </math></EquationSource> </InlineEquation> clients in the ideal and non-ideal Cancellation of Successive Interferences (CSI). Because of the YOLO-CSE model, the error execution is additionally considered versus the power portion coefficient (α) for <InlineEquation ID="IEq3"> <EquationSource Format="TEX">$n$</EquationSource> <EquationSource Format="MATHML"><math> <mi>n</mi> </math></EquationSource> </InlineEquation> and <InlineEquation ID="IEq4"> <EquationSource Format="TEX">$m$</EquationSource> <EquationSource Format="MATHML"><math> <mi>m</mi> </math></EquationSource> </InlineEquation> clients switching keying (OOK) balance Single Input and Output (SISO), <InlineEquation ID="IEq5"> <EquationSource Format="TEX">$(n \times n), and \left( {m \times n} \right)$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mrow> <mo stretchy="false">(</mo> <mi>n</mi> <mo>×</mo> <mi>n</mi> <mo stretchy="false">)</mo> </mrow> <mo>,</mo> <mi>a</mi> <mi>n</mi> <mi>d</mi> <mfenced close=")" open="("> <mrow> <mi>m</mi> <mo>×</mo> <mi>n</mi> </mrow> </mfenced> </mrow> </math></EquationSource> </InlineEquation> for CVL based on utilizing the MANO and MIMO frameworks. The proposed model focuses on the significant highlights that have been removed from the dataset by utilizing the Convolutional unit (CBAU). The Fast-Pooling Spatial Pyramid (SPPF +) is likewise applied to the extricated highlights to reuse them. In that unique situation, the exponential block is coordinated to enact the capability for additional exact outcomes. The modified model, YOLO-CSE outperforms the other models in the literature by 18% outperform the other models in the literature.</p>

RETRACTED ARTICLE: Interference cancellation to enhance bit error rate using the YOLO-CSE model

期刊论文
出版模式：

开放获取
发表日期：

2025年1月22日

查看全文

Wessam M. Salama

摘要

A novel framework based on combining the You Only Look Once-CSE (YOLO-CSE) model is implemented in this paper with Communication Visible Light (CVL) and Multiple Access non-orthogonality (MANO-CVL) for Multiple Input and Output (MIMO). The main goal of the proposed model is to decrease the detecting error in the received bits and distinguish between noise signal and correct bits. The YOLO-CSE model uses the Yolov5 model as a backbone. Two sorts of regulation are applied; position modulation (L-PPM) with different L and users, inside a Comparable Gain Combiner (CGC) at the recipient. This framework thinks about $n$ $n$ and $m$ $m$ clients in the ideal and non-ideal Cancellation of Successive Interferences (CSI). Because of the YOLO-CSE model, the error execution is additionally considered versus the power portion coefficient (α) for $n$ $n$ and $m$ $m$ clients switching keying (OOK) balance Single Input and Output (SISO), $(n \times n), and \left( {m \times n} \right)$ $(n \times n), a n d (m \times n)$ for CVL based on utilizing the MANO and MIMO frameworks. The proposed model focuses on the significant highlights that have been removed from the dataset by utilizing the Convolutional unit (CBAU). The Fast-Pooling Spatial Pyramid (SPPF +) is likewise applied to the extricated highlights to reuse them. In that unique situation, the exponential block is coordinated to enact the capability for additional exact outcomes. The modified model, YOLO-CSE outperforms the other models in the literature by 18% outperform the other models in the literature.