Abstract: A method for assessing test adequacy of deep neural networks based on element decomposition is provided. The network testing is divided into black box testing and white box testing, of which key elements are decomposed and defined. Network parameters including a weight matrix and a bias vector are extracted. Importance values of neurons in individual layers of the deep neural network are calculated and clustered, and an importance value hot map of neurons in each layer is generated based on clustering results. Mutation testing, and index calculation and evaluation are performed.

Abstract: The present invention discloses a signal anti-noise-based indoor localization method and system. The method includes receiving a signal and a data packet broadcast by a signal base station laid indoors; determining a noisy distance from the signal base station to a to-be-localized terminal according to an RSSI value from the signal base station to the to-be-localized terminal; and localizing the to-be-localized terminal by using an indoor localization algorithm according to a distance value from the to-be-localized terminal to different signal base stations, a noisy distance from different signal base stations to the to-be-localized terminal, and location information of the signal base station laid indoors. The present invention can improve the noise resistance and accuracy of indoor localization.