Gender classification system from offline survey data using neural networks

Gender classification is becoming more important with the increasing demand of automated applications especially interactive applications. It can be used to increase the user friendliness of the interactive systems and also to improve the performance of systems like, targeted advertisement, automatic vending machines, security and surveillance systems etc. This work focuses on implementing a gender classification system using Back Propagation Neural Network (BPNN). It is well known that there are some nuances between men and women in their behavior, psychology and lifestyle. Based on these differences we firstly selected four relevant questions. Then we collected the answers from a large number of candidates and fed them to a back propagation neural network to test the system and found that the accuracy of our system is 73.4%.