LoRaWAN technology’s reliability is challenged by weather parameters, which can influence the communication channel design, especially when dealing with outdoor devices. We propose to analyze this effect by evaluating the relationship between the received signal strength indicator (RSSI) and different weather parameters, as well as its temporal changes. A rigorous statistical analysis of the RSSI sequences is conducted to assess if they could be represented by a specific statistical model. For this purpose, several models are investigated. The Artificial Intelligence (AI) algorithms cover machine learning (ML) and deep learning methods are appealing when dealing with time series forecasting. Nevertheless, the classical autoregressive integrated moving average (ARIMA) model can be an attractive alternative due to its simplicity. Therefore, this work proposes a comparative study of ARIMA, AI, and hybrid approaches to forecast the RSSI using weather parameters as regressors. The considered AI algorithms are the artificial neural network (ANN), support vector machine (SVM), random forest (RF), and Long Short-Term Memory (LSTM). Also, hybrid models are constructed, coupling the ARIMA with them. The models are evaluated in time series of RSSI, measured by eight different LoRaWAN transmitter nodes and considering the temperature, pressure, relative humidity, and rain as weather parameters. Our analysis reveals that temperature is the dominant factor among weather parameters, and negatively affects RSSI. The ARIMA model that uses only the temperature as a regressor provides consistently better fits than the ARIMA without regressors. Moreover, coupling the ARIMA with the temperature as a regressor and the ANN (ARIMA-ANN) is the best option among the pure AI and hybrid approaches. However, it provided accuracy measures very close to those obtained from the ARIMA model fitted in the first stage, with similar performance. Therefore, the ARIMA model considering the temperature is the most competitive alternative when analyzing RSSI measurements, with the advantage of being the most straightforward method. These results suggest that the RSSI from the analyzed LoRaWAN receiver nodes may not present nonlinear patterns and, considering several weather parameters, they are affected mainly by the outdoor temperature.

This letter introduces the Rayleigh generalized autoregressive score (Ray-GAS) model, a dynamic model useful for synthetic aperture radar (SAR) data interpretation. It is derived from the generalized autoregressive score (GAS) framework, assuming that the Rayleigh conditional mean is an index-varying parameter. We discuss estimation, diagnostic, and prediction tools. Additionally, we perform numerical experiments with simulated and measured single-look amplitude SAR data for forest and lake region data. The results show the Ray-GAS model’s benefits in understanding stochastic behavior and filtering SAR amplitude returns.

Intra-body communication (IBC) will foster personalized medicine by enabling interconnection of implanted devices. Communication takes place through energy-efficient technologies such as capacitive coupling (CC) and galvanic coupling (GC); however, their modeling is still incomplete. This paper tackles characterization of the human body channel using impulse response, including a first-ever comparison of CC and GC in both wearable and implantable configurations. Experimental data are leveraged to evaluate the measured impulse response in ex-vivo chicken tissue and in-vivo human tissue in a frequency range up to 100 kHz. Pseudorandom noise (PN) sequences are transmitted in baseband and a correlative channel sounding system is implemented. Experimental results demonstrate that the channel is relatively flat in the frequency range of interest, thus offering the opportunity to simplify the design of an IBC transceiver. The relationship between the channel responses and the transmitter-to-receiver distance is also examined using linear correlation, and two regression models are developed. The results show that CC channels are not affected by distance within the range of investigation, while a negative relationship is found for GC channels. Finally, experiments reveal that implantable CC with isolated ground -not deeply investigated yet- is a very promising solution for IBC.

Multitemporal satellite images can be represented as a three-dimensional cube. This remote sensing data type require modeling techniques comprising spatial and temporal dependence altogether. This work aims at developing a hybrid framework combining the three-dimensional autoregressive (3D-AR) statistical model and machine learning algorithms to accommodate spatial and temporal correlations in a stack of temporal synthetic aperture radar (SAR) images. We propose using the 3D-AR to model the linear dependence among the voxels and one among artificial neural networks (ANN), support vector regression (SVR), and random forest (RF) for modeling the nonlinear component. The resulting models, labeled as 3D-AR-ANN, 3D-AR-SVR, and 3D-AR-RF hybrid models, respectively, can help to predict missing voxels or to forecast a one-step-ahead image of a remote sensing data sequence in the presence of linear and nonlinear patterns. The procedure is validate by applying the proposed hybridization approach to predict different parts of a SAR image stack from the urban area of Cordoba, Argentina. The results show the usefulness of our approach in predicting multitemporal SAR data, being more accurate than the state-of-the-art 3D-AR model.

This article introduces a continuous probability distribution as an approximation to the${\mathcal {G}}^{0}_{A}$distribution for amplitude synthetic aperture radar (SAR) imagery modeling. Called${\mathcal {L}}_{A}$distribution, it is an empirical model and an analytically more tractable alternative than${\mathcal {G}}^{0}_{A}$model, with the same number of parameters and no special functions in its formulation. It also has a closed form for the quantile function, making it easier to calculate quantiles and generate pseudorandom numbers and obtain closed-form expressions for skewness and kurtosis coefficients. Useful properties of the${\mathcal {L}}_{A}$distribution are introduced, and the maximum likelihood method is considered for parameter estimation. Based on the Kullback–Leibler divergence (KLD), it is shown that the average information missed when using the${\mathcal {L}}_{A}$instead of${\mathcal {G}}^{0}_{A}$distribution is negligible. Numerical studies in simulated and measured SAR images obtained by different systems and representing different land-use regions are conducted to compare the performances of the${\mathcal {G}}^{0}_{A}$and${\mathcal {L}}_{A}$distributions. The simulation results suggest that the parameter estimation performances of both distributions are similar. Applications to real data show that the images were best fit with the${\mathcal {L}}_{A}$distribution in all considered cases and figure-of-metrics.