No 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.

No abstract

Dielectric parameters (i.e. permittivity) are fundamental to the simulation, design, modeling, and developing of microwave applications. For targeted objects, the complex permittivity is an essential parameter that affects its characteristics of scattering and microwave radiation. Thus, in microwave remote sensing applications, the knowledge of the dielectric property of vegetable materials is used not only to detect planting areas for monitoring and to able to specify the growth stage of them in seasonal variations, but also to determine the water requirement of the plant for controlling (water stress). This paper focuses on determining the dielectric parameters of orange and lemon leaves, grown in the Mediterranean coasts of Turkey, depending on the moisture content (MC) and frequency by measuring the samples (leaves) with waveguide transmission line technique in the larger part of the C band frequency range (4.90-7.05 GHz) (compatible with WR159) in order to propose a novel model based on curve fitting method for estimating the real part of dielectric constant ( ϵ ′ ) and the imaginary part of dielectric constant ( ϵ ′′ ). Using dielectric measurement results of orange leaves, our model based on frequency and MC is compared with the dielectric measurement results of the lemon leaves, which is in the same family with orange species, to specify the accuracy of the proposed model. The determination coefficient, R 2 , and mean square root of errors values are also obtained as 0.966 and 0.824, respectively.

The accuracy of the path loss models directly affects the performance of the wireless sensor networks (WSN) and the efficiency of coverage planning. In this article, as a novelty, new empirical path loss models with foliage depth are proposed at two different 5G frequencies (3.5 and 4.2 GHz) based on volumetric density rate (v) of the trees in citrus orchards for WSN. In order to generate/verify empirical models, measurements are performed at different locations with similar environment characteristics. First, the measurements are compared with commonly used empirical models such as LITU-R, FITU-R, Cost 235, and log-normal, and they are found to be compatible with these models. Second, empirical path loss model is generated based on these measurements. Accordingly, for 3.5 and 4.2 GHz, the coefficient of determination (R 2 ) values are 0.966 and 0.965, respectively. Thirdly, based on the proposed model, it is determined that increasing the v value by 30% increased path loss by 20 dB. Finally, the performance of the proposed models is compared with four different empiric models for calculated v as 0.571. Additionally, the 3.08 and 3.46 root mean square error values of the proposed models are considerably better than those of other models.