This study presents a compact ultra-wideband (UWB) antenna fed by a coplanar waveguide (CPW) with huge bandwidth for the demands of modern wireless communities. To overcome some technical limitations of the employed substrate and UWB antenna design, a slotted patch resonator was used to create and simulate this antenna based on Locked-Key topology. It has been printed on a 1.5 mm-thick FR4 substrate with a dielectric constant of 4.4. A feeder with characteristic impedances of 50 Ω has been employed. A CST electromagnetic simulator has been employed to simulate and analyze the antenna design. It is operated within the UWB spectrum with a bandwidth of 10.354 GHz, spanning 3.581 to 14 GHz. The overall surface area is 27 × 25 mm². The gain and maximum efficiency within UWB are better than 3 dBi and 82%, respectively. The antenna is fabricated, and the simulated results are correlated with the measured ones. Finally, the equivalent circuit models for the antenna and rectifier circuit are simulated and measured.

A reinforcement neural network-based grid-integrated photovoltaic (PV) system with a battery management system (BMS) was developed to enhance the efficiency and reliability of renewable energy systems. In such a setup, the PV system generates electricity, which can be used immediately, stored in batteries, or fed into the grid. The challenge lies in dynamically optimizing the power flow between these components to minimize energy costs, maximize the use of renewable energy, and maintain grid stability. Reinforcement learning (RL) combined with NNs offers a powerful solution by enabling the system to learn and adapt its energy management strategy in real time. By using the proposed techniques, the convergence time was decreased with lower complexity compared with existing approaches. The RL agent interacts with the environment (i.e., the grid, PV system, and battery), continuously improving its decisions regarding when to store energy, draw from the battery, and supply power to the grid. This intelligent control approach ensures optimal performance, contributing to a more sustainable and resilient energy system.

The demand for vaccines is significantly increasing in various countries due to heightened population mobility and the prevalence of epidemics. This study employed machine learning methods to predict optimal vaccine stock levels, aiming to prevent both shortages and oversupply, and to compare the effectiveness of these predictions. The data utilized in the prediction models were sourced from the General Directorate of Border and Coastal Health. This study analyzed a 21-year retrospective dataset collected between 2003 and 2023, which contains monthly vaccination coverage data. Four different methods commonly used in the literature were applied to estimate annual vaccine demand. Among these, the most widely utilized method was the Autoregressive Integrated Moving Average (ARIMA). Additionally, Seasonal Autoregressive Integrated Moving Average (SARIMA), Linear Regression, and XGBoost models are employed. Certain events, such as the COVID-19 pandemic, disrupt patterns within the dataset. In pruning tests, variations in data frequency within the raw dataset are analyzed. The models are evaluated using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The entire dataset is then transformed to achieve stationarity. The models are re-evaluated after removing seasonality and white noise. Cross-validation is applied to the models that yield the most accurate predictions. The forecast results obtained from the optimized model serve as input for the Value at Risk (VaR) model. Actual, projected, and average vaccination numbers are presented with 95% and 99% confidence intervals (critical stock range) based on SARIMA, Linear Regresion and XGBoost estimates. Due to the vaccine forecast range balance, XGBoost’s outputs are input into the Value at Risk (VaR) model and the cost risk related to the safe vaccine stock that may arise in the coming days is evaluated. Throughout the study, the conditions under which models can continue to learn effectively, as well as the rationale for selecting these models, can be monitored.

Hospitals must continually monitor their patients’ actions to lower the chance of accidents, such as patient falls and slides. Human behavior is difficult to track due to the complexity of human activities and the unpredictable nature of their conduct. As a result, creating a static link that is used to influence human behavior is challenging, since it is hard to forecast how individuals will think or act in response to a certain event. Mobility tracking depends on intelligent monitoring systems that apply artificial intelligence (AI) applications referred to as “categories”. Because motion sensors, such as gyroscopes and accelerometers, output unconnected data that lack labels, event detection is a vital task. The fall feature parameters of tridimensional accelerometers and gyroscope sensors are presented and used, and the classification technique is based on distinguishing characteristics. This study focuses on the age-old problem of tracking turbulence in motion to improve detection precision. We trained the model, considering that detection accuracy is limited by factors such as the subject’s mass, velocity, and gait style. This is performed by employing an experimental dataset. When we used the sophisticated technique of particle swarm optimization (PSO) in combination with a four-stage forward neural network (4SFNN) to forecast four different types of turbulent motion, we observed that the total prediction accuracy was 98.615% accurate.

With the rapidly growing use of biometric authentication systems, the security of these systems and the privacy of users have attracted significant attention in recent years. Multi‐modal biometrics have been able to improve the accuracy of the system but require additional bandwidth to exchange the data. Fragile watermarking has been used to allow the transmission of both biometric templates using the amount of data required to transmit one of them, that is, the cover image, while securing these templates against attacks. Despite the high accuracy of these systems, communicating such templates imposes risks towards the privacy of the users. In this study, a new method is proposed to generate fixed‐size descriptors for the face and fingerprint templates, including the timestamp of the transmission and a unique system identifier. The inclusion of the timestamp enables the system to detect and deny replay attacks, while the unique system identifier maintains the privacy of the users. The experiments conducted to evaluate the proposed method have shown that the proposed method has been able to achieve these features while maintaining high recognition rates, 99.41% and 99.32%, similar to the use of the entire biometric templates in the matching stage.