Detection of Water Stress in Khasi Mandarin Orange Plants from Volatile Organic Compound Emission Profile Implementing Electronic Nose
Rajdeep Choudhury1, Sudipta Hazarika2, Utpal Sarma3
1Rajdeep Choudhury*, Instrumentation & USIC, Gauhati University, Gauhati, Assam, India.
2Sudipta Hazarika, Instrumentation & USIC, Gauhati University, Gauhati, Assam, India.
3Utpal Sarma, Instrumentation & USIC, Gauhati University, Gauhati, Assam, India.
Manuscript received on September 27, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 133-137 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1086109119/2019©BEIESP | DOI: 10.35940/ijeat.A1086.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Plants in the absence of an innate immune system like animals and being immobile are regularly exposed to a host of stresses, ranging from biotic to abiotic stresses. In response to these, plants have developed a complicated response system like reprogramming gene expressions and emission of secondary metabolites as volatile organic compounds (VOCs) by its various tissues like roots, stems, leaves etc. These VOCs can be used as biomarkers for inspecting plants’ in situ health status. This paper address the usefulness of electronic nose (e-nose) system to sense the VOCs emitted by plants’ leaves to detect the stresses in it. Standard commercial electronic nose (e-nose) system Alfa Mos Fox 3000 has been used here to identify the stressed and non-stressed plants. Fifteen Mandarin orange plants were considered for the study and were subdivided into three categories. Each one was subjected to a different level of water stress. Leaf samples were collected for e-nose analyses from each plant of all three categories on the 15th day and 30th day of induction of water stresses. Dimensionality reduction techniques like kernel Principal Component Analysis (kPCA), Linear Discriminant Analysis (LDA) and classification algorithms like Support Vector Machines (SVC) and Multi-Layer Perceptron Classifier (MLPC) have been used to classify the three categories of plants. The scores obtained from these analyses reveals the feasibility of using an e nose system in discriminating plants based on the status of water stress in them. This paper analyses the applicability of e nose system in stress diagnosis of agricultural and horticultural crops, which would significantly help in controlling the irrigation regime.
Keywords: About four key words or phrases in alphabetical order, Separated by commas.