Application of genetic algorithm for optimization of NQR signal detection

The globalization of terrorism has become a reality that cannot be challenged, a threat to domestic and international security and, implicitly, a phenomenon under the responsibility of the entire international community. Terrorist threats, theaters of operations with explosive traps everywhere, explosive substances with the possibility of explosions, drugs, etc. represent a permanent threat to the civilian population, the victim of any kind of interest. It is a permanent concern of many laboratories in the world to detect of the explosive substances in order to mitigate the risks they generate. This paper presents concerns about detecting explosives using the NQR principle. This is a multiple and selective detection method without being invasive. Instead, it has the disadvantage of the very poor signal response from the substance under detection and further research is being done to improve it. To obtain the best result, the detection method that we approached uses 6 algorithms for determining the presence of an illegal substance is used. In order to reduce the number of false alarms, the algorithms' results are fused and the decision is taken by applying specific weights to each result. This study proposes a genetic algorithm for finding the optimal weights, that is based on a dataset composed of 8000 acquisitions in different conditions. Sodium nitrite is used as the test substance, because it has a piezoelectric response which makes the detection process more difficult in particular situations.