The dielectric properties prediction of the vegetation depending on the moisture content using the deep neural network model

Abstract

In this paper, dielectric properties of citrus leaves are predicted with long shortterm memory (LSTM) which is one of the well-known deep neural network (DNN) models and real-time measurements for any moisture content (MC) values in the range of 4.90 to 7.05 GHz at a fixed temperature of 24 C for microwave applications, as a novelty. Firstly, S-parameters of samples are measured with WR-159 waveguide and Waveguide Transmission Line Method. In addition, the MCs of samples depending on their weights are calculated. Thus, the dataset depending on various MC and frequency is obtained with the measurement results to both training and testing the DNN model. Secondly, a total of 4000 datasets are obtained, 80% of which is used for training, and 20% for testing. The proposed DNN model consists of four inputs (f, MC, S 11 , and S 21) and two outputs (ε 0 and ε 00). Finally, the dielectric parameters for the desired MC and f are displayed with the graphical user interface in real-time. Success criteria for the prediction such as mean absolute error, root mean squared error, mean absolute percentage error, and R-squared are calculated. The results indicated that there is good agreement between the measured and predicted ones. R-squared are calculated as 0.962 and 0.968 for ε 0 and ε 00 , respectively.

Prediction of the effect of temperature on electric power in photovoltaic thermal systems based on natural zeolite plates

“…Especially in the process of obtaining meaningful information from large amounts of data with deep learning algorithms, significant support is received from computer hardware. Thanks to this hardware, deep learning algorithms can be used in many applications such as curve fitting and classification 14,27 . In the study, the LSTM method, which is preferred in regression data in deep learning applications, was used.…”

“…The most important deficiency here is the determination of the parameters that affect the time series. Especially the rapid development of machine learning algorithms is promising to solve this problem 14 …”

Arı hastalıklarının hibrit bir derin öğrenme yöntemi ile tespiti

“…Yapay sinir ağları günümüzde askeriyeden tıba, tıptan ziraate, ziraatten eğitime kadar birçok multidisipliner alanda tercih edilen bir hesaplama yöntemidir [50][51][52][53]. Bu yöntem biyolojik sinir ağlarının dış ortamdan aldığı sinyale göre uyarılma, aldığı uyarıyı iletme, uyarıya göre karar verme gibi düşünsel davranışları örnek alarak geliştirilmiş bir esnek hesaplama yöntemidir [54][55][56].…”

Disease Detection From Cassava Leaf Images With Deep Learning Methods in Web Environment

“…Recently, it is possible to see deep neural networks applications in many different fields from health to education [37][38][39][40]. There are different models such as trained and pre-trained in the literature [41][42][43]. It is frequently preferred in image processing applications, especially due to its success in feature extraction.…”