In-depth basic data detection device based on Internet of Things technology

Abstract Due to the limited computing power of perception layer Internet Things (IoT), ability analyse and process collected complex object information data is insufficient, it also difficult complete storage a large amount data. Through convolutional neural network-simple recurrent unit (CNN-SRU) deep learning, we preprocess in layer. The by are first transmitted CNN for simple category screening analysis, then they reach SRU link, which updated optimised again, improve integrity accuracy IoT collection. results show that gated (GRU), long–short-term memory (LSTM) algorithms shows downward trend under three error evaluation standards root mean squared (RMSE), absolute (MAE) relative (RE), from 0.034 0.015, 0.028 0.012 0.024 0.013, respectively; terms training time. algorithm increased 54.52%; maximum 33.22%; reduction mining energy consumption 11.45%. This meets requirements applications big mining.