Automatic Classification of Herbal Substances Enhanced with an Entropy Criterion

Abstract

This paper presents a novel automatic pattern recognition system for the classification of herbal substances, which comprises the analysis of chemical data obtained from three analytical techniques such as Thin Layer Chromatography (TLC), Gas Chromatography (GC) and Ultraviolet Spectrometry (UV), composed of the following stages. First, a preprocessing stage takes place that ranges from the TLC plate image conversion into a spectrum to the normalization and alignment of spectral data for all techniques. Then, a hierarchical clustering procedure is applied for each technique with the goal of discovering groups or classes that provide evidence concerning the different existing types. Next, an entropy-based template selection step for each group was introduced to exclude the less significant samples, thus allowing to improve the quality of the training set for each technique. In this manner, each class is now described by a set of key prototypes that allows the field expert to have a more accurate characterization and understanding of the phenomenon. Moreover, an improvement of the computational complexity for training and prediction tasks of the Support Vector Machines (SVM) is also achieved. Finally, a SVM classifier is trained for each technique. The experiments conducted show the validity of the proposal, showing an improvement of the classification results on each technique.

Bio-Chemical Data Classification by Dissimilarity Representation and Template Selection

“…The data sets used in this study come from different analytical techniques and sources, thus allowing for representativeness. Some data sets such as IR Fuel (Infrared spectroscopy of fuel) [13], GC Cannabis (Gas Chromatography of cannabis) [10], and UV Cannabis (Ultraviolet spectroscopy of cannabis) [10] VECTORIAL REPRESENTATION were obtained from our laboratory. MVDA Alcohol (Alcohols in medical applications) [8], NIR Tablets (NIR spectroscopy of tablets) [1], NIR Tecator (NIR spectroscopy of meat) [16], Raman Porkfat (Raman spectroscopy of porcine tissue) [2] and Raman Tablets (Raman spectroscopy of tablets) [1]; come from known sources.…”

“…In previous works [4,10], the information gain has been used to select the best templates for improving classification accuracy. In analytic chemistry, the analysis performed on a substance is usually replicated, yielding almost identical replicated samples.…”

“…After performing sample ordering according, a top-percentage criterion [10] was used to select templates that guarantee a suitable representativeness of the gallery. In this work, the classification behavior for different training sets yielded by the top-percentage criterion was analyzed.…”

“…Another factor to take into account is the representation chosen for building the dissimilarity space [12]. Recent works [4,10] have addressed this problem by selecting templates based on an entropy criterion. A suitable combination of these two factors is key for the improvement of the classification process.…”