An inset fed-microstrip patch antenna (MPA) with a partial ground structure is constructed and evaluated in this paper. This article covers how to evaluate the performance of the designed antenna by using a combination of simulation, measurement, creation of the RLC equivalent circuit model, and the implementation of machine learning approaches. The MPA’s measured frequency range is 7.9–14.6 GHz, while its simulated frequency range is 8.35–14.25 GHz in CST microwave studio (CST MWS) 2018. The measured and simulated bandwidths are 6.7 GHz and 5.9 GHz, respectively. The antenna substrate is composed of FR-4 Epoxy, which has a dielectric constant of 4.4 and a loss tangent of 0.02. The equivalent model of the proposed MPA is developed by using an advanced design system (ADS) to compare the resonance frequencies obtained by using CST. In addition, the measured return loss of the prototype is compared with the simulated return loss observed by using CST and ADS. At the end, 86 data samples are gathered through the simulation by using CST MWS, and seven machine learning (ML) approaches, such as convolutional neural network (CNN), linear regression (LR), random forest regression (RFR), decision tree regression (DTR), lasso regression, ridge regression, and extreme gradient boosting (XGB) regression, are applied to estimate the resonant frequency of the patch antenna. The performance of the seven ML models is evaluated based on mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and variance score. Among the seven ML models, the prediction result of DTR (MSE = 0.71%, MAE = 5.63%, RMSE = 8.42%, and var score = 99.68%) is superior to other ML models. In conclusion, the proposed antenna is a strong contender for operating at the entire X-band and lower portion of the Ku-band frequencies, as evidenced by the simulation results through CST and ADS, it measured and predicted results using machine learning approaches.

Fuel cells have drawn a lot of interest in recent years as one of the most promising alternative green power sources in microgrid systems. The operating conditions and the integrated components greatly impact the quality of the fuel cell’s voltage. Energy management techniques are required in this regard to regulate the fuel cell’s power in a microgrid. The active/reactive power in the microgrid should be adjusted in line with US Energy Star’s regulations whereas the grid current needs to follow the standard set by IEEE 519 2014 to enhance the power quality of the electrical energy injected into the microgrid. Uncontrolled energy injection from the fuel cell can have serious impacts including superfluous energy demand, overloading, and power losses, especially in high power and medium voltage systems. Although fuel cells have many advantages, they cannot yet produce high voltages individually to compensate for the demand of a microgrid system. Due to these reasons, the fuel cell must be interfaced with a DC-DC converter. This research proposes a novel high voltage gain converter integrated 1.26 kW fuel cell for microgrid power management that can boost the fuel cell’s voltage up to 20 times. Due to this high voltage gain, the voltage and current ripple of the fuel cell is also reduced substantially. According to the analysis, the proposed converter demonstrated optimal performance when compared to the other converters due to its high voltage gain and extremely low voltage ripple. As a result, the harmonic profile of the microgrid current persists with a reduced THD of 3.22% and a very low voltage ripple of 4 V. To validate the converter’s performance, along with extensive simulation, a hardware prototype was also built. The voltage of the fuel cell is regulated using a simplified proportional integral controller. The operating principle of the converter integrated fuel cell along with its application in microgrid power management is demonstrated. A comparative analysis is also shown to verify how the proposed converter is improving the system’s performance when compared against other converters.

Deep Learning is considered one of the most effective strategies used by hedge funds to maximize profits. But Deep Neural Networks (DNN) lack theoretical analysis of memory exploitation. Some traditional time series methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH) work only when the entire series is pre-processed or when the whole data is available. Thus, it fails in a live trading system. So, there is a great need to develop techniques that give more accurate stock/index predictions. This study has exploited fractional-order derivatives’ memory property in the backpropagation of LSTM for stock predictions. As the history of previous stock prices plays a significant role in deciding the future price, fractional-order derivatives carry the past information along with itself. So, the use of Fractional-order derivatives with neural networks for this time series prediction is meaningful and helpful.

The utilization of synthetic, natural, and waste fibers in asphalt mixtures is constantly increasing due to the capability of fibers to improve the mechanical performance of asphalt mixes. The combination of fibers in asphalt mixes contributes to ecological sustainability and cost benefits. The objective of this paper is to introduce a citation-based review on the incorporation of synthetic, natural, and waste fibers in bitumen, dense-graded asphalt mix, stone mastic asphalt, and porous asphalt mix. Additionally, this article aims to identify research gaps and provide recommendations for further work. The outputs of this article demonstrated that there has recently been a growing interest in the use of natural and waste fibers in asphalt mixtures. However, more future studies are needed to investigate the performance of fiber-modified stone mastic asphalt and porous asphalt mix in terms of resistance to aging and low-temperature cracking. Furthermore, the period of natural fibers' biodegradability in asphalt mixtures should be investigated.

The application of the Phasor Measurement Unit (PMU) in the power system is expanding day by day since it provides a higher reliability through fast symmetrically monitoring and protection and assists in controlling power systems. For power systems, islanding is a significant event due to its hazardous consequences. To detect islanding events, several schemes have been previously proposed but inappropriate threshold setting, higher computational time, and false tripping are the main limitations. In addition, differentiating between real island events and transient faults is another limitation. However, appropriate threshold setting plays a considerable part in detecting the island event, which is also important to differentiate between real and non-island events. Phasor Measurement Unit can assist in islanding detection, but it can generate 30 samples/s, so there is always the possibility of making particular period data disappear. The principal contribution of this review article is its detailed discussion of real-time symmetrical PMU data and it further presents different PMU data analytic techniques and the proposed schemes for the islanding detection system. An appropriate methodology tried to understand how to incorporate missing PMU data techniques along with the islanding detection system to ensure the higher reliability of the network.