Stimulus classification with electrical potential and impedance of living plants : comparing discriminant analysis and deep-learning methods

Abstract

The physiology of living organisms, such as living plants, is complex and particularly difficult to understand on a macroscopic, organism-holistic level. Among the many options for studying plant physiology, electrical potential and tissue impedance are arguably simple measurement techniques that can be used to gather plant-level information. Despite the many possible uses, our research is exclusively driven by the idea of phytosensing, that is, interpreting living plants’ signals to gather information about surrounding environmental conditions. As ready-to-use plant-level physiological models are not available, we consider the plant as a blackbox and apply statistics and machine learning to automatically interpret measured signals. In simple plant experiments, we expose Zamioculcas zamiifolia and Solanum lycopersicum (tomato) to four different stimuli: wind, heat, red light and blue light. We measure electrical potential and tissue impedance signals. Given these signals, we evaluate a large variety of methods from statistical discriminant analysis and from deep learning, for the classification problem of determining the stimulus to which the plant was exposed. We identify a set of methods that successfully classify stimuli with good accuracy, without a clear winner. The statistical approach is competitive, partially depending on data availability for the machine learning approach. Our extensive results show the feasibility of the blackbox approach and can be used in future research to select appropriate classifier techniques for a given use case. In our own future research, we will exploit these methods to derive a phytosensing approach to monitoring air pollution in urban areas. Contents of this repository:

mu_interface: Code for our data collection plant experiments, based on Raspberry Pis and the Cybertronica phytosensing and phytoactuating system. SupplementaryCode: Includes the discriminant analysis classifier, raw datasets, calculated features, test-train split and the corresponding code. dl-4-tsc: Deep learning framework developed by Fawaz et. al (Deep learning for time series classification: a review) and adapted to our use case. DeepClassifier: Trained deep learning time series classifier. classification_results.xlsx: Overview of the results from the deep learning framework (accuracy, precision, recall, training time, confusion matrix) and the achieved accuracies using discriminant analysis with sequential forward section (further evaluation metrics of the discriminant analysis can be found in SupplementaryCode.