Artículos - Ingeniería Electrónica y de Telecomunicaciones

Permanent URI for this collection

https://hdl.handle.net/20.500.12590/18070

Browse

Browsing Artículos - Ingeniería Electrónica y de Telecomunicaciones by Subject "Agriculture"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A nonlinear model to estimate nitrogen level in agricultural soil using Gaussian kernels
    (Institute of Electrical and Electronics Engineers Inc., 2017) Sánchez Mora, Katty; Zuñiga Gutierrez, María; Mayhua López, Efraín Tito
    Nitrogen fertilizers are commonly used to improve agricultural productivity. However, its excessive use may cause or lead to environmental problems. Therefore, technologies capable of monitoring and measure levels of nitrogen in agricultural soil in-situ and in real time are required in order to make efficient the use of fertilizers. Nitrogen levels are usually measured by direct and indirect methods. Direct methods can be conducted in-situ or in laboratory, but they are really expensive and/or little resistant to soil conditions. Otherwise, indirect methods can estimate nitrogen levels in-situ and in real time, based on the measure of other parameters, and at the expense of accuracy. This paper proposes an indirect method to estimate the nitrogen level in agricultural soil through the measurement of the levels of electrical conductivity, temperature and humidity. The proposed model uses a nonlinear estimator based on Gaussian kernels. The results after training the model with real data showed values very close to the actual measured values. © 2016 IEEE.
  • No Thumbnail Available
    Item
    Sensor nodes fault detection for agricultural wireless sensor networks based on NMF
    (Elsevier B.V., 2018) Ludeña Choez, Jimmy Diestin; Choquehuanca Zevallos, Juan José; Mayhua López, Efraín Tito
    Nowadays, Wireless Sensor Networks (WSN) are widely been employed to solve agricultural problems related to the optimization of scarce farming resources, decision making support, and land monitoring. However, the small sensing devices that are part of WSNs – known as sensor nodes – suffer from degradation and so producing erroneous measurements. In this paper, a machine learning method based on Non-Negative Matrix Factorization (NMF) is applied to the spectral representation of data acquired by a WSN to extract features that model the normal behavior of sensor node readings leading to a good representation of data using a low number of features. This procedure is accompanied by a classifier that decides if there is a set of features that deviates from the normal ones. Experiments on soil moisture data show that NMF achieves good results detecting flaws in readings from sensors. Results are compared with other method based on Principal Component Analysis (PCA), the Multi-scale PCA (MSPCA) algorithm. © 2018 Elsevier B.V.