Solar photovoltaic (PV) power generation is gradually increasing, but its intermittent nature poses challenges to grid stability. To address this, advanced forecasting methods, such as deep learning (DL) algorithms, can be employed to ensure a more stable and reliable energy supply. Accurate short-term forecasts are essential for electricity grids to effectively mitigate the impact of solar intermittency and enhance grid performance. This research contributes by developing a hybrid DL model that combines a 1-dimensional convolutional neural network (1D CNN) with a gated recurrent unit (GRU), referred to as “1D CNN-GRU”. The 1D CNN module extracts essential features from time series data, such as solar PV power generation, while the GRU component provides high-precision short-term forecasts. Additionally, data preparation techniques, including feature selection using SHapley Additive exPlanations (SHAP), data smoothing with an exponential moving average (EMA), and data augmentation with Gaussian noise, are employed to enhance the performance of the proposed 1D CNN-GRU model. To evaluate the effectiveness of the proposed model, it was compared with other DL models, including CNN, GRU, long short-term memory (LSTM), and CNN-GRU. The forecasting was performed using the Hydro-Floating Solar Plant dataset, obtained from the 45 MW hydro-floating solar installation located at Sirindhorn Dam in Ubon Ratchathani province, Thailand. The proposed 1D CNN-GRU model was tested using data from three different seasons: winter, summer, and the rainy season. The model achieved the lowest root mean square error ( RMSE ) across all seasons, with values of 0.025 (winter), 0.050 (summer), and 0.094 (rainy), and demonstrated the shortest training time. The forecasting results indicated that the proposed model outperformed all other models in terms of both accuracy and training time.

This research introduces the PEnsemble 4 model, a weighted ensemble prediction model that integrates multiple individual machine learning models to achieve accurate maize yield forecasting. The model incorporates unmanned aerial vehicle (UAV) imagery and Internet of Things (IoT)-based environmental data, providing a comprehensive and data-driven approach to yield prediction in maize cultivation. Considering the projected growth in global maize demand and the vulnerability of maize crops to weather conditions, improved prediction capabilities are of paramount importance. The PEnsemble 4 model addresses this need by leveraging comprehensive datasets encompassing soil attributes, nutrient composition, weather conditions, and UAV-captured vegetation imagery. By employing a combination of Huber and M estimates, the model effectively analyzes temporal patterns in vegetation indices, in particular CIre and NDRE, which serve as reliable indicators of canopy density and plant height. Notably, the PEnsemble 4 model demonstrates a remarkable accuracy rate of 91%. It advances the timeline for yield prediction from the conventional reproductive stage (R6) to the blister stage (R2), enabling earlier estimation and enhancing decision-making processes in farming operations. Moreover, the model extends its benefits beyond yield prediction, facilitating the detection of water and crop stress, as well as disease monitoring in broader agricultural contexts. By synergistically integrating IoT and machine learning technologies, the PEnsemble 4 model presents a novel and promising solution for maize yield prediction. Its application holds the potential to revolutionize crop management and protection, contributing to efficient and sustainable farming practices.

In this paper, we investigate machine learning methods for enabling high performance non-cooperative spectrum sensing, for future cognitive radio systems. The fulfillment of sensing requirements is crucial for ensuring an efficient reuse of the scarce spectrum by unlicensed users, without causing harmful interference to primary users. In this work, we propose a deep convolutional neural network-based transfer learning framework for non-cooperative spectrum sensing in TV bands, applicable across various locations, wireless environments and even frequency assignments. Specifically, we design a four-layer convolutional neural network for limiting the computational costs while satisfying the sensing requirements, and apply transfer learning by freezing the first two convolutional layers. The performance of the proposed method is evaluated against benchmarks, based on over 29,000 spectrograms collected in UHF TV band from a recent measurement campaign. The experiments show that thanks to transfer learning, the proposed method is able to detect TV signals with high accuracy despite a significantly reduced amount of data, thereby providing a high adaptability to various locations, environments, and frequencies. Furthermore, the proposed method with transfer learning not only guarantees the sensing requirements but also realizes up to 94% reduction of training time of the network, as well as 20% reduction of the required sensing time, compared to the case without transfer learning.

This paper describes an experimental study of the ultra wideband (UWB) wireless body area network (WBAN) channel in a hospital environment. The measured data are used to develop statistical models for the channel, which can then be used to design efficient and safe communication networks. WBANs are expected to be used in the healthcare field to enable concepts such as telemedicine. The human body has a complex shape and consists of different tissues. It is then expected that the propagation of the electromagnetic waves near a patient's body will have unique characteristics. In a hospital environment, there are also a variety of electronic devices and specialised medical equipment, which have impact on the electromagnetic propagation. To properly design WBANs is then necessary to have a good understanding of the characteristics of the radio channel in the proximity of the human body within a hospital.

Multi-input-multi-output (MIMO) radio channel sounders commonly employ a time-division-multiplexing (TDM) technique to switch between transmit (TX) and receive (RX) antennas. The TDM-based switching enables very cost-effective solutions. Nevertheless, it can cause measurement errors due to phase noise in the local oscillators. In typical MIMO applications with a relatively small number of TX and RX antennas, the measurement cycle for a single snapshot of a MIMO radio channel is so short that independent or white Gaussian noise samples cannot be assumed. Indeed, the characteristics of the phase noise depend on the observing-time scale and the local oscillator design in the TX and the RX. In free-running systems, in which the local oscillators of the TX and the RX employ their own clocks, the properties of the phase noise have a strong dependence on the scale of the observing time. In particular, the short-term characteristics of the phase noise have not been considered in literature regarding MIMO measurements. In this paper, the characteristics of the short-term phase noise in time-switched MIMO radio channel measurements are disclosed. We show also that the Allan deviation, which commonly characterizes the frequency stability of the local oscillators, does not apply well to the short-term scale. Instead, an autoregressive model that is well suited for modeling of correlated noise is applied to characterize the short-term behavior of the phase noise. Finally, the effect of short-term phase noise on the estimation of MIMO channel capacity is analyzed. We also derive an upper bound for the ergodic channel capacity and show that it is dependent on the distribution of the largest eigenvalue of the noise covariance matrix. The results reveal that the effect of short-term phase noise always overestimates MIMO channel capacity.