Introduction of Neural Networks in the Decentralized Detection Problems 1993 IEEE Systems, Man, and Cybernetics Conference Proceedings
Emmanuel Duflos, Y. Coquard, Philippe Vanheeghe, Boulevard Vauban · 1993
The problem of decentralized detection appears Then various sensors are used simultaneously to collect obser- vations from multiple points apart from each other. In this case, mne difficulties such as transmission errors, very high trans- mission rates or memory requirement may occur when a cen- tralized detection is used. To override these limitations detection structu~es involving two processing levels have been introduced the decentralized detection. Unfortunately the solu- tions proposed to the decentralized problem require many cal- culations. Basing their approach on the similarity between detection problems and neural networks the authors propose a neural approach to solve the decentralized detection problem with fewer calculations.