Abstract
The moisture content of stored rice is dependent on the surrounding and environmental factors which in turn affect the quality and economic value of the grains. Therefore, the moisture content of grains needs to be measured frequently to ensure that optimum conditions that preserve their quality are maintained. The current state of the art for moisture measurement of rice in a silo is based on grab sampling or relies on single rod sensors placed randomly into the grain. The sensors that are currently used are very localized and are, therefore, unable to provide continuous measurement of the moisture distribution in the silo. To the authors’ knowledge, there is no commercially available 3D volumetric measurement system for rice moisture content in a silo. Hence, this paper presents results of work carried out using low-cost wireless devices that can be placed around the silo to measure changes in the moisture content of rice. This paper proposes a novel technique based on radio frequency tomographic imaging using low-cost wireless devices and regression-based machine learning to provide contactless non-destructive 3D volumetric moisture content distribution in stored rice grain. This proposed technique can detect multiple levels of localized moisture distributions in the silo with accuracies greater than or equal to 83.7%, depending on the size and shape of the sample under test. Unlike other approaches proposed in open literature or employed in the sector, the proposed system can be deployed to provide continuous monitoring of the moisture distribution in silos.
Highlights
Rice storage is a part of the post-harvest activities and contributes up to 6% losses of harvest [1]
This paper proposes a new technique that uses radio tomography based on Wi-Fi signals at a frequency of 2.4 GHz
This paper proposes a novel non-destructive method to determine the moisture content of rice grain using 3D Radio Tomography Imaging (RTI) based on low-cost Wi-Fi signal transmissions and regression-based machine learning approaches
Summary
Rice storage is a part of the post-harvest activities and contributes up to 6% losses of harvest [1]. To ensure that the quality of the grain is maintained, thereby reducing losses, it is essential to know the distribution of moisture content in the bulk of the stored grain continually and in real-time, if possible. To the best of the authors’ knowledge, none of the techniques proposes a real-time 3D moisture content measurement of stored rice. Under the framework of Bayesian statistics, Bayesian Compressive Sensing (BCS) [15] exploits a priori distribution knowledge of attenuation images to improve the recovery accuracy. This paper proposes a novel non-destructive method to determine the moisture content of rice grain using 3D Radio Tomography Imaging (RTI) based on low-cost Wi-Fi signal transmissions and regression-based machine learning approaches. This paper is organized as follows: Section 2 describes the methodology and the experimental setup to measure the moisture contents of rice grain; Section 3 describes the signal processing and the algorithms used to estimate the moisture contents, and Section 4 discusses the results obtained and the conclusions are drawn
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
