Plants monitor their surrounding environment and control their physiological functions by producingan electrical response. We recorded electrical signals from different plants by exposing them to SodiumChloride (NaCl), Ozone (O3) and Sulfuric Acid (H2SO4) under laboratory conditions. After applying pre-processing techniques such as filtering and drift removal, we extracted few statistical features from theacquired plant electrical signals. Using these features, combined with different classification algorithms,we used a decision tree based multi-class classification strategy to identify the three different externalchemical stimuli. We here present our exploration to obtain the optimum set of ranked feature andclassifier combination that can separate a particular chemical stimulus from the incoming stream of plantelectrical signals. The paper also reports an exhaustive comparison of similar feature based classificationusing the filtered and the raw plant signals, containing the high frequency stochastic part and also thelow frequency trends present in it, as two different cases for feature extraction. The work, presentedin this paper opens up new possibilities for using plant electrical signals to monitor and detect otherenvironmental stimuli apart from NaCl, O3and H2SO4in future.

Comparison of Decision Tree Based Classification Strategies to Detect External Chemical Stimuli from Raw and Filtered Plant Electrical Response / Chatterjeea, S.K.; Das, S; Maharatna, K.; Masi, E.; Santopolo, L.; Colzi, I.; Mancuso, S.; Vitaletti, A. - In: SENSORS AND ACTUATORS. B, CHEMICAL. - ISSN 0925-4005. - ELETTRONICO. - 249:(2017), pp. 278-295. [10.1016/j.snb.2017.04.071]

Comparison of Decision Tree Based Classification Strategies to Detect External Chemical Stimuli from Raw and Filtered Plant Electrical Response

MASI, ELISA;SANTOPOLO, LUISA;COLZI, ILARIA;MANCUSO, STEFANO;
2017

Abstract

Plants monitor their surrounding environment and control their physiological functions by producingan electrical response. We recorded electrical signals from different plants by exposing them to SodiumChloride (NaCl), Ozone (O3) and Sulfuric Acid (H2SO4) under laboratory conditions. After applying pre-processing techniques such as filtering and drift removal, we extracted few statistical features from theacquired plant electrical signals. Using these features, combined with different classification algorithms,we used a decision tree based multi-class classification strategy to identify the three different externalchemical stimuli. We here present our exploration to obtain the optimum set of ranked feature andclassifier combination that can separate a particular chemical stimulus from the incoming stream of plantelectrical signals. The paper also reports an exhaustive comparison of similar feature based classificationusing the filtered and the raw plant signals, containing the high frequency stochastic part and also thelow frequency trends present in it, as two different cases for feature extraction. The work, presentedin this paper opens up new possibilities for using plant electrical signals to monitor and detect otherenvironmental stimuli apart from NaCl, O3and H2SO4in future.
2017
249
278
295
Chatterjeea, S.K.; Das, S; Maharatna, K.; Masi, E.; Santopolo, L.; Colzi, I.; Mancuso, S.; Vitaletti, A
File in questo prodotto:
File Dimensione Formato  
Chatterjee et al 2017.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 9.17 MB
Formato Adobe PDF
9.17 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1080265
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 18
social impact