Analysis and feasibility study of plant disease using e-nose

Abstract

Agriculture is one of the main sources that contribute to the economic development in the country. However, diseases that attack the crops have given a little impact to the agricultural production. Generally, plant pathologist has the difficulties to detect the symptoms that relate to the plant disease. The plant usually gets infected that are caused by different plant pathogens such as bacteria, fungus and virus that attack the plant.Therefore, some method of solution needs to be uncounted in order to provide faster solution in detecting this disease. In order to overcome this problem, the current study proposes detection of plant disease using an electronic nose (e-nose) called PEN3 e nose. This type of e-nose will detect the volatile organic compounds that are produced by two types of plants which are chilies and papaya. The data that have been collected from PEN3 e-nose are processed using principal component analysis (PCA) and linear discriminant analysis (LDA) methods. In order to validate the detection result, the bacteria sample will be stained based on Gram staining procedure in order to observe the structure and colony of the bacteria cells using a digital microscope. Thus, this study shows that the PEN3 e-nose is able to detect the presence of plant pathogenic bacteria on both chilli and papaya plants.Index Terms-Plant disease, pathogenic bacteria, e-nose, principal component analysis, linear discriminant analysis.

Advanced biosensing technologies for monitoring of agriculture pests and diseases: A review

“…The rationale for e-nose is to detect the variation of VOC compositions when crops have been attacked. E-noses have already been applied for early detection of stored grain insects [30,31] or storage diseases [32] , fungus [33] , bacterial diseases [34] and viruses [35] , as well as to distinguish different disease levels [36] , showing promising discrimination to monitor rapidly, noninvasively, and cost-effectively. The chemical emissions are released to the surrounding gas phase from host plants, from which one can detect damage information from the pest-induced specific volatiles (i.e., volatile fingerprints) (Fig.…”

Plant Leaf Disease Detection and Simultaneous Pesticide Distribution Using Mobilenet CNN Architecture and Raspberry Pi

“…The authors have used the concept of Convolutional Neural Network along with Learning Vector Quantization (LVQ) algorithm to classify various diseases occurring in tomato plant in paper [3] and have achieved an average accuracy of 86%. In paper [4], the authors have used the concept of e-nose to detect foul smell coming from plants in order to detect disease using principal component analysis algorithm from machine learning. The paper [5] describes the internal and complex working components of deep learning in context with convolutional neural network.…”

“…The use of modern technology greatly reduces the human effort and save a lot of time. The authors in this study have investigated about different plant diseases and have use deep learning technology to build a model which will instantly detect the type of disease and will auto recommend the treatment of such diseases [4].…”

Electronic tool coupled with machine learning algorithms for the detection of deltamethrin residues in Mentha Spicata L.

“…The electronic nose is a new technology that has recently been widely utilized to check agricultural crops. Known for its construction low price, accuracy and utilization simplicity, in addition to being portable, this instrument has been used in various applications like environmental monitoring (Capelli et al, 2014), biochemical processing (Gu et al, 2017), pathology plants (Chang et al, 2014), pesticide detection (Amkor and El Barbri, 2022a) and cultivar selection (Trirongjitmoah et al, 2015). For our present case, which is interested in the detection of pesticides in food, the electronic nose was used for apples (Tang et al, 2021), black tea (Banerjee et al, 2019), and potatoes (Amkor and El Barbri, 2022b, 2023a, 2023b.…”