首页|Researchers from University of Sciences and Technology of Oran Describe Research in Machine Learning (LLR estimation using machine learning)
Researchers from University of Sciences and Technology of Oran Describe Research in Machine Learning (LLR estimation using machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on artificial intell igence have been published. According to news reporting out of the University of Sciences and Technology of Oran by NewsRx editors, research stated, "Many decod ers of error-correcting codes use the Log-Likelihood Ratio (LLR) as an input, wh ich involves the probability density function (pdf) of the noise. In impulsive n oise, the pdf of the noise is not accessible in closed form and is only availabl e through very complex numerical computation." Our news correspondents obtained a quote from the research from University of Sc iences and Technology of Oran: "Therefore, the LLR calculation for Binary Phase Shift Keying (BPSK) is too complex. It becomes even more complex for high-order modulations. Moreover, the LLR computational complexity grows as the modulation order increases. The main contribution of our work lies in the LLR approximation for high-order modulations and its estimation using supervised machine learning , without requiring prior knowledge of the noise distribution model. To this end , we propose two approaches to approximate the LLR values using supervised machi ne learning, for high-order modulated symbols. The first approach can also be us ed for BPSK modulated symbols. The second approach aims to approximate the LLR f or high-order modulated symbols in a more simplified manner compared to the firs t approach. For both approaches, we estimate the parameters of the approximate L LR under known noise channel conditions using the linear regression algorithm. T o estimate these parameters without prior knowledge of the noise distribution mo del, we use a binary logistic regression algorithm. Our simulations focus on the second proposed approach to estimate the LLR with unknown noise distributions."
University of Sciences and Technology of OranCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
