Automatically Generated Neural Networks for Human Condition Detection Using Non-Contact Vital Sensing

This study is focused on the application of the automatically generated neural networks for complex system operators’ condition detection. The neural networks were generated by two modifications of the Differential Evolution algorithm based on the NSGA and MOEA/D schemes, developed for solving multi-objective optimization problems. Databases for problems described in this study were obtained by using non-contact Doppler sensors. Experimental results demonstrated that automatically generated neural networks can properly determine the human condition and reaction. Besides, they outperformed alternative data mining tools. Thus, more complex problems related to the automated condition detection can be solved in the same manner.