Abiotic stress classification through spectral analysis of enhanced electrophysiological signals of plants.

Electrical activity in plants undergoes potential changes in interpreting the plant's physiological state. These electrical signals show arbitrary and probabilistic dynamics in which stress can be detected and analysed in the early stages of symptom appearance in plants. Evaluation of uncertainty in plant signals by signal strength enhancement is stress-specific. In this paper, we considered physiological signals from 15 days old soybean plants that endured three types of stress (cold, osmotic and lowlight). A novel enhancement methodology is proposed to pre-process the stress information present in the electrical signals. Sixteen spectral features were computed from spectrograms of enhanced signals to attain a better hypothesis. To verify the performance metrics of pre and post-enhancement methods, classification is done in two levels (Multi-class, Binary-class) using machine learning algorithms (Decision Trees (DT), K- Nearest Neighbors (KNN), Support Vector Machines (SVM), Ensemble Boosted Tree (EBT), Ensemble Bagged Tree (EBGT), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA)). Superlative feature pairs showing classification accuracy greater than 95% after 5-fold cross-validation were nominated. The results obtained by the SVM classifier in cold stress and KNN in lowlight stress are accurate to 98% after enhancement. The successful premises taken from this work assure early-stage detection and classification of plant stress, thereby suggesting future requirements to develop enhancement & classification techniques according to the type of stress. • Plant electrical signals play a significant role in comprehending plant stresses. • Accuracies improved after processing signals by enhancement methods. • Spectral feature extraction and feature pairing structured the classification model. • Classification performance is greatly improved after enhancement. • Various ML classifiers obtained results greater than 95% in classifying abiotic stress. [ABSTRACT FROM AUTHOR]