Suggesting a New Approach on Identifying Degree of Separability in Signal Detection, for Using in Channel Estimation

Detecting Signals Noise reduction is a critical issue in channel estimation and signal translation performance in cognitive networks. As a result, a criterion for measuring the degree of correctness and reliability of the signals is required. Nowadays, neural networks play an essential role in computations, and when paired with statistical approaches, they produce ideal results in the identification of separability. The separability degree was employed as a criterion for separating and identifying noise from the main signal in this work. To make the signal more suitable by boosting noise detection quality, we utilise statistical hypotheses and declare specific statistical criteria for signal validity. For our signal, this technique assumes two states: incorrect identification of a weak signal and proper detection of the primary signal. All of this will be accomplished using statistical neural approaches.

Author(S) Details

Hadi Alipour
Education Department, Payame Noor, Tehran, Shiraz, Iran.

Saeed Ayat
University of Payame Noor, Najaf Abad, Iran.

View Book:- https://stm.bookpi.org/RAMRCS-V5/article/view/4976

Leave a Reply

Your email address will not be published.

Previous post Study on Dense Matrix Multiplication Algorithms and Performance Evaluation of HPCC in 81 Nodes IBM Power 8 Architecture
Next post A Study on Optimization of Truck-Drone Parcel Delivery Using Metaheuristics