Multiclass classification of environmental chemical stimuli from unbalanced plant electrophysiological data.

Plant electrophysiological response contains useful signature of its environment and health which can be utilized using suitable statistical analysis for developing an inverse model to classify the stimulus applied to the plant. In this paper, we have presented a statistical analysis pipeline to tackle a multiclass environmental stimuli classification problem with unbalanced plant electrophysiological data. The objective here is to classify three different environmental chemical stimuli, using fifteen statistical features, extracted from the plant electrical signals and compare the performance of eight different classification algorithms. A comparison using reduced dimensional projection of the high dimensional features via principal component analysis (PCA) has also been presented. Since the experimental data is highly unbalanced due to varying length of the experiments, we employ a random under-sampling approach for the two majority classes to create an ensemble of confusion matrices to compare the classification performances. Along with this, three other multi-classification performance metrics commonly used for unbalanced data viz. balanced accuracy, F1-score and Matthews correlation coefficient have also been analyzed. From the stacked confusion matrices and the derived performance metrics, we choose the best feature-classifier setting in terms of the classification performances carried out in the original high dimensional vs. the reduced feature space, for this highly unbalanced multiclass problem of plant signal classification due to different chemical stress. Difference in the classification performances in the high vs. reduced dimensions are also quantified using the multivariate analysis of variance (MANOVA) hypothesis testing. Our findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly unbalanced datasets, employing a combination of existing machine learning algorithms. This work also advances existing studies on environmental pollution level monitoring using plant electrophysiological data.

Chemical Sensing Employing Plant Electrical Signal Response-Classification of Stimuli Using Curve Fitting Coefficients as Features.

In order to exploit plants as environmental biosensors, previous researches have been focused on the electrical signal response of the plants to different environmental stimuli. One of the important outcomes of those researches has been the extraction of meaningful features from the electrical signals and the use of such features for the classification of the stimuli which affected the plants. The classification results are dependent on the classifier algorithm used, features extracted and the quality of data. This paper presents an innovative way of extracting features from raw plant electrical signal response to classify the external stimuli which caused the plant to produce such a signal. A curve fitting approach in extracting features from the raw signal for classification of the applied stimuli has been adopted in this work, thereby evaluating whether the shape of the raw signal is dependent on the stimuli applied. Four types of curve fitting models-Polynomial, Gaussian, Fourier and Exponential, have been explored. The fitting accuracy (i.e., fitting of curve to the actual raw signal) depicted through R-squared values has allowed exploration of which curve fitting model performs best. The coefficients of the curve fit models were then used as features. Thereafter, using simple classification algorithms such as Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) etc. within the curve fit coefficient space, we have verified that within the available data, above 90% classification accuracy can be achieved. The successful hypothesis taken in this work will allow further research in implementing plants as environmental biosensors.

Exploring strategies for classification of external stimuli using statistical features of the plant electrical response.

Plants sense their environment by producing electrical signals which in essence represent changes in underlying physiological processes. These electrical signals, when monitored, show both stochastic and deterministic dynamics. In this paper, we compute 11 statistical features from the raw non-stationary plant electrical signal time series to classify the stimulus applied (causing the electrical signal). By using different discriminant analysis-based classification techniques, we successfully establish that there is enough information in the raw electrical signal to classify the stimuli. In the process, we also propose two standard features which consistently give good classification results for three types of stimuli--sodium chloride (NaCl), sulfuric acid (H2SO4) and ozone (O3). This may facilitate reduction in the complexity involved in computing all the features for online classification of similar external stimuli in future.