“…From our previous results [4], we know that these rocks can be correctly classified by computing the synthesized feature vector, which is the linear combination of the incoming test photocurrent with the optimal pre-computed set of weights (one for each rock type). Since the set of weights are optimally matched to the spectra of each rock type, the feature component with the maximum value is the assigned class [4]. Based on our previous results, the minimal set of bias voltages is {-3.0, -0.8, 1.0, 2.8} volts, and the three weight vectors (one for each rock type) are W1 = [15, -109, 32, 10], W2 = [24, -63, -5, -8] and W3 = [11, 3, -128, 24] [5].…”