Application and Optimization of Micro/Nano Electronic Sensors Based on Deep Learning in Human-Computer Interaction

The exponential growth of population and the use of electronic and electrical equipment have increased the requirement for energy production management, thereby increasing the need for precise energy management systems that can predict consumer use for future policy formulation. MEMS/NEMS technology, as a mature microstructure manufacturing technology, can form micro sensors and testing systems with small volume, light weight, and high performance. To improve the human-machine interaction experience of smart grids, this article applies micro/nano sensor technology to human-machine interaction optimization and proposes a data fusion model based on deep learning (DL). Based on the principle structure and training method of Deep Neural Network (DNN), a multi-source data system for power grid technical renovation projects has been constructed, which includes technical factors, economic factors, and environmental factors. This system can effectively analyze energy usage and combine multi-source data fusion technology to achieve intelligent evaluation of power grid projects. The experimental results show that the model designed in this paper is effective and superior, and has reference significance for improving the data fusion algorithm of micro and nano sensors in big data environments.