Review: A review of advanced techniques for detecting plant diseases

https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=3087&context=usdaarsfacpub

Review: Development of soft computing and applications in agricultural and biological engineering

Early detection of toxigenic fungi on maize by hyperspectral imaging analysis

Aflatoxins produced by the Aspergillus species are highly toxic, carcinogenic, and cause severe contamination to food sources, leading to serious health consequences. Contaminations by aflatoxins have been reported in food and feed, such as groundnuts, millet, sesame seeds, maize, wheat, rice, fig, spices and cocoa due to fungal infection during pre- and post-harvest conditions. Besides these food products, commercial products like peanut butter, cooking oil and cosmetics have also been reported to be contaminated by aflatoxins. Even a low concentration of aflatoxins is hazardous for human and livestock. The identification and quantification of aflatoxins in food and feed is a major challenge to guarantee food safety. Therefore, developing feasible, sensitive and robust analytical methods is paramount for the identification and quantification of aflatoxins present in low concentrations in food and feed. There are various chromatographic and sensor-based methods used for the detection of aflatoxins. The current review provides insight into the sources of contamination, occurrence, detection techniques, and masked mycotoxin, in addition to management strategies of aflatoxins to ensure food safety and security.

/pdf/aflatoxins-in-food-and-feed-an-overview-on-prevalence-1sh8oa6frc.pdf

Aflatoxins in Food and Feed: An Overview on Prevalence, Detection and Control Strategies.

In recent years, intelligent sensor techniques have achieved significant attention in agriculture. It is applied in agriculture to plan the several activities and missions properly by utilising limited resources with minor human interference. Currently, plant cultivation using new agriculture methods is very popular among the growers. However, the aeroponics is one of the methods of modern agriculture, which is commonly practiced around the world. In the system, plant cultivates under complete control conditions in the growth chamber by providing a small mist of the nutrient solution in replacement of the soil. The nutrient mist is ejected through atomization nozzles on a periodical basis. During the plant cultivation, several steps including temperature, humidity, light intensity, water nutrient solution level, pH and EC value, CO2 concentration, atomization time, and atomization interval time require proper attention for flourishing plant growth. Therefore, the object of this review study was to provide significant knowledge about early fault detection and diagnosis in aeroponics using intelligent techniques (wireless sensors). So, the farmer could monitor several paraments without using laboratory instruments, and the farmer could control the entire system remotely. Moreover, the technique also provides a wide range of information which could be essential for plant researchers and provides a greater understanding of how the key parameters of aeroponics correlate with plant growth in the system. It offers full control of the system, not by constant manual attention from the operator but to a large extent by wireless sensors. Furthermore, the adoption of the intelligent techniques in the aeroponic system could reduce the concept of the usefulness of the system due to complicated manually monitoring and controlling process.

/pdf/monitoring-and-control-systems-in-agriculture-using-376f2duta5.pdf

Monitoring and Control Systems in Agriculture Using Intelligent Sensor Techniques: A Review of the Aeroponic System

Single-kernel reflectance spectra (550 to 1700 nm), visible color reflectance images, x-ray images, multi-spectral transmittance images (visible and NIR), and physical properties (mass, length, width, thickness, and cross-sectional area) were analyzed to determine if they could be used to detect fungal-infected corn kernels Kernels were collected from corn ears inoculated with one of several different common fungi several weeks before harvest, and then collected at harvest time It was found that two NIR reflectance spectral bands centered at 715 nm and 965 nm could correctly identify 981% of asymptomatic kernels and 966% of kernels showing extensive discoloration and infected with Aspergillus flavus, Aspergillus niger, Diplodia maydis, Fusarium graminearum, Fusarium verticillioides, or Trichoderma viride These two spectral bands can easily be implemented on high-speed sorting machines for removal of fungal-damaged grain Histogram features from three transmittance images (blue and red components of color images and another at 960 nm) can distinguish 919% of infected kernels with extensive discoloration from 962% of asymptomatic kernels Similar classification accuracies were achieved using x-ray images and physical properties (kernel thickness, weight, length) A neural network was trained to identify infecting fungal species on single kernels using principle components of the reflectance spectra as input features

D. T. Wicklow

Papers

Detection of corn kernels infected by fungi