Automatic classification of plant electrophysiological responses to environmental stimuli using machine learning and interval arithmetic

Abstract In plants, there are different types of electrical signals involving changes in membrane potentials that could encode electrical information related to physiological states when plants are stimulated by different environmental conditions. A previous study analyzing traits of the dynamics of whole plant low-voltage electrical showed, for instance, that some specific frequencies that can be observed on plants growing under undisturbed conditions disappear after stress-like environments, such as cold, low light and osmotic stimuli. In this paper, we propose to test different methods of automatic classification in order to identify when different environmental cues cause specific changes in the electrical signals of plants. In order to verify such hypothesis, we used machine learning algorithms (Artificial Neural Networks, Convolutional Neural Network, Optimum-Path Forest, k-Nearest Neighbors and Support Vector Machine) together Interval Arithmetic. The results indicated that Interval Arithmetic and supervised classifiers are more suitable than deep learning techniques, showing promising results towards such research area.

[1]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[2]  Won-Gyu Choi,et al.  Rapid, Long-Distance Electrical and Calcium Signaling in Plants. , 2016, Annual review of plant biology.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Lan Huang,et al.  Plant Electrical Signal Classification Based on Waveform Similarity , 2016, Algorithms.

[5]  D. Coomans,et al.  Alternative k-nearest neighbour rules in supervised pattern recognition : Part 1. k-Nearest neighbour classification by using alternative voting rules , 1982 .

[6]  Desire L. Massart,et al.  Alternative k-nearest neighbour rules in supervised pattern recognition : Part 2. Probabilistic classification on the basis of the kNN method modified for direct density estimation , 1982 .

[7]  João Paulo Papa,et al.  Efficient supervised optimum-path forest classification for large datasets , 2012, Pattern Recognit..

[8]  Xiangfeng Wang,et al.  Machine Learning–Based Differential Network Analysis: A Study of Stress-Responsive Transcriptomes in Arabidopsis[W] , 2014, Plant Cell.

[9]  A. Volkov,et al.  Plant Electrophysiology : Signaling and Responses , 2012 .

[10]  V. Sukhov.  Electrical signals as mechanism of photosynthesis regulation in plants , 2016, Photosynthesis Research.

[11]  B. Park,et al.  Choice of neighbor order in nearest-neighbor classification , 2008, 0810.5276.

[12]  Anthony Trewavas,et al.  Aspects of plant intelligence. , 2003, Annals of botany.

[13]  João Paulo Papa,et al.  Optimum-Path Forest based on k-connectivity: Theory and applications , 2017, Pattern Recognit. Lett..

[14]  Ulrich Lüttge,et al.  Hierarchy and Information in a System Approach to Plant Biology: Explaining the Irreducibility in Plant Ecophysiology , 2016 .

[15]  Jurandy Almeida,et al.  Phenological visual rhythms: Compact representations for fine-grained plant species identification , 2016, Pattern Recognit. Lett..

[16]  Ashutosh Kumar Singh,et al.  Machine Learning for High-Throughput Stress Phenotyping in Plants. , 2016, Trends in plant science.

[17]  B. Pogson,et al.  Systemic Photooxidative Stress Signalling , 2013 .

[18]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[19]  Vladimir Sukhov,et al.  Variation potential in higher plants: Mechanisms of generation and propagation , 2015, Plant signaling & behavior.

[20]  V. Vodeneev,et al.  Signaling role of action potential in higher plants , 2008, Russian Journal of Plant Physiology.

[21]  Andrea Vitaletti,et al.  Exploring strategies for classification of external stimuli using statistical features of the plant electrical response , 2015, Journal of The Royal Society Interface.

[22]  Jorge Stolfi,et al.  The image foresting transform: theory, algorithms, and applications , 2004 .

[23]  Marc-Williams Debono,et al.  Dynamic protoneural networks in plants , 2013, Plant signaling & behavior.

[24]  João Paulo Papa,et al.  Aquatic weed automatic classification using machine learning techniques , 2012 .

[25]  Axel Mithöfer,et al.  Before gene expression: early events in plant-insect interaction. , 2007, Trends in plant science.

[26]  U. Lüttge,et al.  Modularity and emergence: biology's challenge in understanding life. , 2012, Plant biology.

[27]  W. Ramakrishna,et al.  Machine Learning Approaches Distinguish Multiple Stress Conditions using Stress-Responsive Genes and Identify Candidate Genes for Broad Resistance in Rice[C][W][OPEN] , 2013, Plant Physiology.

[28]  Hubert H. Felle,et al.  System Potentials, a Novel Electrical Long-Distance Apoplastic Signal in Plants, Induced by Wounding1 , 2009, Plant Physiology.

[29]  Silke Lautner,et al.  Environmental stimuli and physiological responses: The current view on electrical signalling , 2015 .

[30]  Luis A Gurovich,et al.  Electrophysiological assessment of water stress in fruit-bearing woody plants. , 2014, Journal of plant physiology.

[31]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[32]  Vladimir Sukhov,et al.  Mathematical Models of Electrical Activity in Plants , 2017, The Journal of Membrane Biology.

[33]  Nobuhiro Suzuki,et al.  A tidal wave of signals: calcium and ROS at the forefront of rapid systemic signaling. , 2014, Trends in plant science.

[34]  Simone Bossi,et al.  Electrophysiology and Plant Responses to Biotic Stress , 2006 .

[35]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[36]  Lutz Plümer,et al.  A review of advanced machine learning methods for the detection of biotic stress in precision crop protection , 2014, Precision Agriculture.

[37]  Jörg Fromm,et al.  Characteristics of Action Potentials in Willow (Salix viminalis L.) , 1993 .

[38]  Stanisław Karpiński,et al.  Electrical Signaling, Photosynthesis and Systemic Acquired Acclimation , 2017, Front. Physiol..

[39]  João Paulo Papa,et al.  Supervised pattern classification based on optimum-path forest , 2009 .

[40]  Torsten Will,et al.  Spread the news: systemic dissemination and local impact of Ca²⁺ signals along the phloem pathway. , 2014, Journal of experimental botany.

[41]  Andrea Vitaletti,et al.  Forward and inverse modelling approaches for prediction of light stimulus from electrophysiological response in plants , 2014, 1410.5372.

[42]  Lyubov Katicheva,et al.  Proton cellular influx as a probable mechanism of variation potential influence on photosynthesis in pea. , 2014, Plant, cell & environment.

[43]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[44]  Xiangfeng Wang,et al.  Machine learning for Big Data analytics in plants. , 2014, Trends in plant science.

[45]  G. M. Souza,et al.  Plant “electrome” can be pushed toward a self-organized critical state by external cues: Evidences from a study with soybean seedlings subject to different environmental conditions , 2017, Plant signaling & behavior.

[46]  J. Fromm,et al.  Electrical signals and their physiological significance in plants. , 2007, Plant, cell & environment.

[47]  Annika E Huber,et al.  Long-distance plant signaling pathways in response to multiple stressors: the gap in knowledge. , 2016, Journal of experimental botany.

[48]  Vladimir Sukhov,et al.  High-Temperature Tolerance of Photosynthesis Can Be Linked to Local Electrical Responses in Leaves of Pea , 2017, Front. Physiol..

[49]  E. Davies,et al.  Electrical Signals in Plants: Facts and Hypotheses , 2006 .

[50]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[51]  A. S. Ferreira,et al.  Osmotic stress decreases complexity underlying the electrophysiological dynamic in soybean. , 2017, Plant biology.