More information can be extracted from signals, using signal transform tools. Among other tools, “wavelet transform” has an increasing fortune because of its good properties. The main issue is that choosing “different mother wavelet functions” results in diverse conclus More
More information can be extracted from signals, using signal transform tools. Among other tools, “wavelet transform” has an increasing fortune because of its good properties. The main issue is that choosing “different mother wavelet functions” results in diverse conclusions. There are various algorithms to build a suitable mother wavelet for the analyzed signal. Along with those algorithms, there are procedures too for choosing the optimum mother wavelet among existing functions. From the latter group, the “energy matching” algorithm was used in the present paper to find the optimum mother wavelet. During the use of this algorithm, its deficiency in two aspects was revealed. To solve the problem, “zero mean transform” was chose as an extendable solution to prepare data for the used energy matching algorithm. Applying this simple transform helped us not only finding the optimum mother wavelet but also a unique one.
Manuscript profile
Pattern recognition methods are able to identify the hidden relationships between exploration data, especially in the case of limited number of data. The geochemical distribution patterns of the elements are identified and generalized using these methods. Multilayer per More
Pattern recognition methods are able to identify the hidden relationships between exploration data, especially in the case of limited number of data. The geochemical distribution patterns of the elements are identified and generalized using these methods. Multilayer perceptron, MLP, is one of the pattern recognition methods which is used for the estimation of geochemical element concentrations in mineral deposit studies. In the current study, multilayer neural network was used to estimate the concentration of geochemical elements based on 1755 surface and borehole samples, analyzed by ICP. Fuzzy c-means, FCM, clustering algorithm was used to increase the neural network estimation accuracy. The optimal number of clusters in the dataset was identified by validation indices and was used to design estimator. The clustering data on average showed an increase of 13% accuracy compared to normal mode. The average accuracy was increased from 75 percent to 88 percent. Elements with the lowest estimation accuracy showed an
acceptable increase on the estimation accuracy by using clustering data. Mean squared error was 0.079 using all data and decreased to 0.025 while using hybrid developed method.
Manuscript profile