Early Detection of Fire Blight Disease of Pome Fruit Trees Using Visible-NIR Spectrometry and Dimensionality Reduction Methods

Journal Title: Journal of Agricultural Machinery - Year 2020, Vol 10, Issue 1

Abstract

Fire Blight (FB) is the most destructive bacterial disease of pome fruit trees around the world. In recent years, spectrometry has been shown to be an accurate and real-time sensing technology for plant disease detection. So, the main objective of this research is early detecting FB of pear trees by using Visible-Near-infrared spectrometry. To get this goal, the reflectance spectra of healthy leaves (ND), non-symptomatic (NS), and symptomatic diseased leaves (SY) were captured in the visible–NIR spectral regions. In order to keep the important information of spectra and reduce the dimension of data, three linear and non-linear manifold-based learning techniques were applied such as, Principal Component Analysis (PCA), Sammon mapping and Multilayer auto-encoder (MAE). The output of manifold-based learning techniques was used as an input of the SIMCA (Soft independent modeling by class analogy) classification model to discriminate NS and ND leaves. Based on the results, the best classification accuracy obtained by using PCA on the 1st derivative spectra, with accuracy of 95.8%, 89.3%, and 91.6% for ND, NS, and SY samples, respectively. These results support the capability of manifold-based learning techniques for early detection of FB via spectrometry method.

Authors and Affiliations

N. Bagheri,H. Mohamadi-Monavar,

Keywords

Related Articles

Study of Ammonia Gas Emission from Broiler Houses and the Effects of Temperature, Humidity and Age on It

IntroductionIran as one of the largest producers of poultry in Asia and plays major role in feeding the world's population, particularly in the poultry industry. Research about this industry will help to improve the qual...

Energy and Exergy Analysis of a Greenhouse Heating System Equipped with a Parabolic Trough Concentrator and a Flat -Plate Solar Collector

Introduction Greenhouse cultivation has been increased in response to population growth, reduction in available supplies and arable lands and raising the standards of living. The quality and quantity of the products are...

Determination of the optimal amount of nitrous oxide injected into the engine in order to reduce emissions

Introduction: Nowadays the number of motor vehicles in large and small cities is growing. Increasing the number of motor vehicles leads to serious increase of the amount of environmental pollution and daily fuel consumpt...

Investigation the Rototiller Blade Operational Factors on the Soil Tillage of Orchard and Paddy Fields

In recent years using rototillers in orchards and small fields especially in northern areas of Iran has been increased. In this study, a multi-function rototiller was developed and its performance was analyzed and evalua...

Investigation of Compost Fertilizer Granulation Parameters Using Response Surface Methodology

Nowadays compost fertilizers are suitable alternative to chemical fertilizers, due to the threats for human health and agriculture products. The most important problems for applying the compost fertilizer in the farm are...

Download PDF file
  • EP ID EP717946
  • DOI https://doi.org/10.22067/jam.v10i1.71911
  • Views 33
  • Downloads 0

How To Cite

N. Bagheri, H. Mohamadi-Monavar, (2020). Early Detection of Fire Blight Disease of Pome Fruit Trees Using Visible-NIR Spectrometry and Dimensionality Reduction Methods. Journal of Agricultural Machinery, 10(1), -. https://europub.co.uk/articles/-A-717946