• Mr. Gaurav

The use of repeat neural networks with high iterating values to identify and avoid packet losses is expected to result in a more successful WSN test randomization technique, which will further reduce packet losses. According to the planned research results, it was discovered in the first seven GUI tests and recommended seven times as a result of the findings. Given that only a small number of packets were lost in a single packet, it is clear that a certain number of packets were initially sent when specific packets were sent. As a result, when it comes to digital data, the results of the necessary effort are immediately visible. It nearly doubled when compared to the previous year. It is thus clear that when a repeating neural network employs large iteration values, the use of very active pattern recognition methods ensures that the network also repartees packet loss issues, thereby reducing packet loss. As a result of this change, overall latency and performance are only marginally improved. As a result, the proposed approach performs admirably in terms of packet drop during transmission and estimation of packet loss.

Throughput, E2Edelay and PDR, WSN, Packet Drop, MATLAB-2013.

"QoS Analysis of Customized WSN through Recurrent Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 9, page no.b640-b648, September-2021, Available :http://www.jetir.org/papers/JETIR2109178.pdf

"QoS Analysis of Customized WSN through Recurrent Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 9, page no. ppb640-b648, September-2021, Available at : http://www.jetir.org/papers/JETIR2109178.pdf