Comparison of decision tree based classification strategies to detect external chemical stimuli from raw and filtered plant electrical response
Abstract
Ozone, Sulfuric Acid and Sodium Chloride have been classified using the plant signals. Several statistical features have been extracted from plant electrical response. A decision tree classier is developed based on discriminant analysis. Cross validation and independent validation accuracies have been reported. Most significant features and classifier setting have been reported for classifying environmental chemical stimuli.
- Publication:
-
Sensors and Actuators B: Chemical
- Pub Date:
- October 2017
- DOI:
- 10.1016/j.snb.2017.04.071
- arXiv:
- arXiv:1707.07620
- Bibcode:
- 2017SeAcB.249..278C
- Keywords:
-
- Decision tree;
- Multiclass classification;
- Discriminant analysis;
- Mahalanobis distance classifier;
- Statistical features;
- Plant electrical signal processing;
- Time series analysis;
- Physics - Biological Physics;
- Computer Science - Machine Learning;
- Physics - Data Analysis;
- Statistics and Probability;
- Statistics - Applications;
- Statistics - Machine Learning
- E-Print:
- Sensors and Actuators B: Chemical, vol. 249, pp. 278-295, Oct. 2017