Identity determination of hashish samples quantified by means of ICP-AES and NAA and data handling with neural networks Part 2: Separation of sample signatures with neural networks

Twenty different hashish samples, which were confiscated in Irak, Iran, Bulgaria, Switzerland, Great Britain and Germany were analysed by means of NAA and ICP-AES. We used modified ANNs to identify a repeated analysed sample out of that data pool. The ANNs are described. Especially the learning rule, a modified backpropagation method, is presented. It is obvious, that neural networks can solve the described classification tasks. There is no significant difference in the power of the applied analytical methods.