Technical modelling of solar photovoltaic water pumping system and evaluation of system performance and their socio-economic impact.

Water is a precious resource for agriculture and most of the land is irrigated by tube wells. Diesel engines and electricity-operated pumps are widely used to fulfill irrigation water requirements; such conventional systems are inefficient and costly. With rising concerns about global warming, it is important to choose renewable energy source. In this study, SPVWPS has been optimally designed considering the water requirement, solar resources, tilt angle and orientation, losses in both systems and performance ratio. A PVSyst and SoSiT simulation tools were used to perform simulation analysis of the designed solar photovoltaic WPS. After designing and performance analysis, farmers were interviewed during fieldwork to assess socioeconomic impacts. In the result section, performance of PV system is analyzed at various tilt angles and it is established that system installed at a 15° tilt angle is more efficient. The annual PV array virtual energy at MPP of designed photovoltaic system is 33342 kWh and the annual energy available to operate the WPS is 23502 kWh. Module array mismatch and ohmic wiring losses are 374.16 kWh and 298.83 kWh, respectively. The total annual water demand of the selected site is 80769 m³ and designed SPWPS pumped 75054 m³ of water, supplying 92.93% of the irrigation demand. The normalized values of the effective energy, system losses, collection losses and unused energy in the SPVWP system are 2.6 kW/kWp/day, 0.69 kW/kWp/day, 0.72 kW/kWp/day and 0.48 kW/kWp/day, respectively. The annual average performance ratio of the proposed system is 74.62%. The results of the interviews showed that 70% of farmers are extremely satisfied with the performance of SPVWPS and 84% of farmers indicated that they did not incur any operating costs. The unit cost of the SPWPS is 0.17 €/kWh, which is 56.41% and 19.04% less expensive than the cost of diesel and grid electricity.

The environmental aspects of renewable energy consumption and structural change in Sweden: A new perspective from wavelet-based granger causality approach.

The current paper assessed the time-frequency analysis interrelationship between CO2 emissions and financial development, economic growth, renewable energy use, structural change, and non-renewable energy use in Sweden. We utilized a quarterly dataset stretching from 1980-2019. In order to unlock these interrelationships, we leverage wavelet tools (wavelet-based Granger causality and wavelet coherence). The wavelet-based Granger causality (WGC) test accounts for the issue of multiple time scales in a time series analysis. Another uniqueness of the WGC lies in its resistance to distribution assumption and misspecification in a time series model. Additionally, the wavelet coherence estimator instantaneously evaluates correlation and causality among the interacting indicators in a model. The outcomes of the wavelet coherence exposed that renewable energy, financial development, economic growth, structural change, and trade openness enhance the environment's quality while non-renewable energy intensifies CO2. Moreover, the WGC shows that all the variables can predict each other. Based on these findings, policymakers in Sweden should focus more on improving public understanding of renewable energy and environmental preservation. We believe that Sweden's shift to service-sector-led growth will help to safeguard the environment.

Does information and communication technology impede environmental degradation? fresh insights from non-parametric approaches.

Although ICT has played a critical role in the socio-economic growth of human cultures, it has also brought with it significant environmental risks. Nevertheless, scholars remain divided on this topic; some believe that ICT has had a positive influence on the quality of the environment, while others believe that ICT has created major environmental issues. Hence, this research is another effort to assess the effects of ICT on CO2 emissions in the top 10 ICT nations (Denmark, Japan, Luxemburg, South Korea, Netherlands, Iceland, Norway, Sweden, Switzerland, and the United Kingdom) using a dataset from the period between 1986Q1 and 2019Q4. All prior studies have established symmetric association between ICT and CO2. As a result, we applied the novel non-parametric approaches (quantile-on-quantile regression and Granger causality in quantile) to assess this association. The findings from the QQR uncovered that in the majority of the quantiles, for Denmark, Japan, Luxemburg, Netherland, Norway, Sweden, United Kingdom and Switzerland, the effect of ICT on CO2 emissions is negative, while in the majority of the quantiles, the effect of ICT on CO2 emissions is positive for the Netherlands, South Korea, and Iceland. Furthermore, we applied the novel Granger causality in the quantiles approach and the outcomes provided evidence of bidirectional causality between CO2 emissions and ICT in all the selected nations. The study proposes that sustainable ICT should be used to improve carbon reduction and energy savings potential by optimizing other industries, including managing and monitoring energy usage.

Effect of mutation and vaccination on spread, severity, and mortality of COVID-19 disease.

Coronavirus disease 2019 (COVID-19) has had different waves within the same country. The spread rate and severity showed different properties within the COVID-19 different waves. The present work aims to compare the spread and the severity of the different waves using the available data of confirmed COVID-19 cases and death cases. Real-data sets collected from the Johns Hopkins University Center for Systems Science were used to perform a comparative study between COVID-19 different waves in 12 countries with the highest total performed tests for severe acute respiratory syndrome coronavirus 2 detection in the world (Italy, Brazil, Japan, Germany, Spain, India, USA, UAE, Poland, Colombia, Turkey, and Switzerland). The total number of confirmed cases and death cases in different waves of COVID-19 were compared to that of the previous one for equivalent periods. The total number of death cases in each wave was presented as a percentage of the total number of confirmed cases for the same periods. In all the selected 12 countries, Wave 2 had a much higher number of confirmed cases than that in Wave 1. However, the death cases increase was not comparable with that of the confirmed cases to the extent that some countries had lower death cases than in Wave 1, UAE, and Spain. The death cases as a percentage of the total number of confirmed cases in Wave 1 were much higher than that in Wave 2. Some countries have had Waves 3 and 4. Waves 3 and 4 have had lower confirmed cases than Wave 2, however, the death cases were variable in different countries. The death cases in Waves 3 and 4 were similar to or higher than Wave 2 in most countries. Wave 2 of COVID-19 had a much higher spread rate but much lower severity resulting in a lower death rate in Wave 2 compared with that of the first wave. Waves 3 and 4 have had lower confirmed cases than Wave 2; that could be due to the presence of appropriate treatment and vaccination. However, that was not reflected in the death cases, which were similar to or higher than Wave 2 in most countries. Further studies are needed to explain these findings.

COVID-19 prediction using LSTM algorithm: GCC case study.

Coronavirus-19 (COVID-19) is the black swan of 2020. Still, the human response to restrain the virus is also creating massive ripples through different systems, such as health, economy, education, and tourism. This paper focuses on research and applying Artificial Intelligence (AI) algorithms to predict COVID-19 propagation using the available time-series data and study the effect of the quality of life, the number of tests performed, and the awareness of citizens on the virus in the Gulf Cooperation Council (GCC) countries at the Gulf area. So we focused on cases in the Kingdom of Saudi Arabia (KSA), United Arab of Emirates (UAE), Kuwait, Bahrain, Oman, and Qatar. For this aim, we accessed the time-series real-datasets collected from Johns Hopkins University Center for Systems Science and Engineering (JHU CSSE). The timeline of our data is from January 22, 2020 to January 25, 2021. We have implemented the proposed model based on Long Short-Term Memory (LSTM) with ten hidden units (neurons) to predict COVID-19 confirmed and death cases. From the experimental results, we confirmed that KSA and Qatar would take the most extended period to recover from the COVID-19 virus, and the situation will be controllable in the second half of March 2021 in UAE, Kuwait, Oman, and Bahrain. Also, we calculated the root mean square error (RMSE) between the actual and predicted values of each country for confirmed and death cases, and we found that the best values for both confirmed and death cases are 320.79 and 1.84, respectively, and both are related to Bahrain. While the worst values are 1768.35 and 21.78, respectively, and both are related to KSA. On the other hand, we also calculated the mean absolute relative errors (MARE) between the actual and predicted values of each country for confirmed and death cases, and we found that the best values for both confirmed and deaths cases are 37.76 and 0.30, and these are related to Kuwait and Qatar respectively. While the worst values are 71.45 and 1.33, respectively, and both are related to KSA.

A study of the possible factors affecting COVID-19 spread, severity and mortality and the effect of social distancing on these factors: Machine learning forecasting model.

BACKGROUNDS: SARS-CoV-2 is affecting different countries all over the world, with significant variation in infection-rate and death-ratio. We have previously shown a presence of a possible relationship between different variables including the Bacillus Calmette-Guérin (BCG) vaccine, average age, gender, and malaria treatment, and the rate of spread, severity and mortality of COVID-19 disease. This paper focuses on developing machine learning models for this relationship. METHODS: We have used real-datasets collected from the Johns Hopkins University Center for Systems Science and Engineering and the European Centre for Disease Prevention and Control to develop a model from China data as the baseline country. From this model, we predicted and forecasted different countries' daily confirmed-cases and daily death-cases and examined if there was any possible effect of the variables mentioned above. RESULTS: The model was trained based on China data as a baseline model for daily confirmed-cases and daily death-cases. This machine learning application succeeded in modelling and forecasting daily confirmed-cases and daily death-cases. The modelling and forecasting of viral spread resulted in four different regions; these regions were dependent on the malarial treatments, BCG vaccination, weather conditions, and average age. However, the lack of social distancing resulted in variation in the effect of these factors, for example, double-humped spread and mortality cases curves and sudden increases in the spread and mortality cases in different countries. The process of machine learning for time-series prediction and forecasting, especially in the pandemic COVID-19 domain, proved usefulness in modelling and forecasting the end status of the virus spreading based on specific regional and health support variables. CONCLUSION: From the experimental results, we confirm that COVID-19 has a very low spread in the African countries with all the four variables (average young age, hot weather, BCG vaccine and malaria treatment); a very high spread in European countries and the USA with no variable (old people, cold weather, no BCG vaccine and no malaria). The effect of the variables could be on the spread or the severity to the extent that the infected subject might not have symptoms or the case is mild and can be missed as a confirmed-case. Social distancing decreases the effect of these factors.

In vitro and in vivo performance modelling and optimisation of different dry powder inhalers: A complementary study of neural networks, genetic algorithms and decision trees.

INTRODUCTION: Aerosol delivery from DPIs could be affected by different factors. This study aimed to evaluate and predict the effects of different factors on drug delivery from DPIs. METHODS: Modelling and optimisation for both in vitro and in vivo data of different DPIs (Diskus, Turbohaler and Aerolizer) were carried out using neural networks associated with genetic algorithms and the results are confirmed using a decision tree (DT) and random forest regressor (RFR). All variables (the type of DPI, inhalation flow, inhalation volume, number of inhalations and type of subject) were coded as numbers before using them in the modelling study. RESULTS: The analysis of the in vitro model showed that Turbohaler had the highest emitted dose compared with the Diskus and the Aerolizer. Increasing flow resulted in a gradual increase in the emitted dose. Little differences between the inhalation volumes 2 and 4 litres were shown at fast inhalation flow, and interestingly two inhalations showed somewhat higher emitted doses than one-inhalation mode with Turbohaler and Diskus at slow inhalation flow. Regarding the in vivo model, the percent of drug delivered to the lung was highly increased with Turbohaler and Diskus in healthy subjects where continuous contour lines were observed. The Turbohaler showed increased lung bioavailability with the two-inhalation modes, the Diskus showed a nearly constant level at both one and two inhalations at slow inhalation. The Turbohaler and Aerolizer showed little increasing effect moving from one to two inhalations at slow inhalation. CONCLUSIONS: Modelling of the input data showed a good differentiating and prediction power for both in vitro and in vivo models. The results of the modelling refer to the high efficacy of Diskus followed by Turbohaler for delivering aerosol. With two inhalations, the three DPIs showed an increase in the percent of drug excreted at slow inhalations.

An evaluation of different bio-inspired feature selection techniques on multivariate calibration models in spectroscopy.

Herein, two new swarm intelligence based algorithms namely; grey wolf optimization (GWO) and antlion optimization (ALO) algorithms were presented, for the first time, as variable selection tools in spectroscopic data analysis. In order to assess the performance of these algorithms, they were applied along with the recently introduced firefly algorithm (FFA) and the well-established genetic algorithm (GA) and particle swarm optimization (PSO) algorithm on four different spectroscopic datasets of varying sizes and nature (UV and IR). Partial least squares (PLS) regression models were built using the selected variables by these algorithms along with the full spectral data as the reference models. The obtained results prove that the ALO and GWO optimization algorithms select variables in most cases less than GA and PSO while keeping the PLS performance almost the same. Accordingly, these algorithms can be successfully used for variable selection in spectroscopic data analysis.

Bacillus Calmette-Guérin vaccine, antimalarial, age and gender relation to COVID-19 spread and mortality.

COVID-19 is affecting different countries all over the world with great variation in infection rate and death ratio. Some reports suggested a relation between the Bacillus Calmette-Guérin (BCG) vaccine and the malaria treatment to the prevention of SARS-CoV-2 infection. Some reports related infant's lower susceptibility to the COVID-19. Some other reports a higher risk in males compared to females in such COVID-19 pandemic. Also, some other reports claimed the possible use of chloroquine and hydroxychloroquine as prophylactic in such a pandemic. The present commentary is to discuss the possible relation between those factors and SARS-CoV-2 infection.

Experienced Gray Wolf Optimization Through Reinforcement Learning and Neural Networks.

In this paper, a variant of gray wolf optimization (GWO) that uses reinforcement learning principles combined with neural networks to enhance the performance is proposed. The aim is to overcome, by reinforced learning, the common challenge of setting the right parameters for the algorithm. In GWO, a single parameter is used to control the exploration/exploitation rate, which influences the performance of the algorithm. Rather than using a global way to change this parameter for all the agents, we use reinforcement learning to set it on an individual basis. The adaptation of the exploration rate for each agent depends on the agent's own experience and the current terrain of the search space. In order to achieve this, experience repository is built based on the neural network to map a set of agents' states to a set of corresponding actions that specifically influence the exploration rate. The experience repository is updated by all the search agents to reflect experience and to enhance the future actions continuously. The resulted algorithm is called experienced GWO (EGWO) and its performance is assessed on solving feature selection problems and on finding optimal weights for neural networks algorithm. We use a set of performance indicators to evaluate the efficiency of the method. Results over various data sets demonstrate an advance of the EGWO over the original GWO and over other metaheuristics, such as genetic algorithms and particle swarm optimization.

Impact of Chaos Functions on Modern Swarm Optimizers.

Exploration and exploitation are two essential components for any optimization algorithm. Much exploration leads to oscillation and premature convergence while too much exploitation slows down the optimization algorithm and the optimizer may be stuck in local minima. Therefore, balancing the rates of exploration and exploitation at the optimization lifetime is a challenge. This study evaluates the impact of using chaos-based control of exploration/exploitation rates against using the systematic native control. Three modern algorithms were used in the study namely grey wolf optimizer (GWO), antlion optimizer (ALO) and moth-flame optimizer (MFO) in the domain of machine learning for feature selection. Results on a set of standard machine learning data using a set of assessment indicators prove advance in optimization algorithm performance when using variational repeated periods of declined exploration rates over using systematically decreased exploration rates.

Computational Intelligence Modeling of the Macromolecules Release from PLGA Microspheres-Focus on Feature Selection.

Poly-lactide-co-glycolide (PLGA) is a copolymer of lactic and glycolic acid. Drug release from PLGA microspheres depends not only on polymer properties but also on drug type, particle size, morphology of microspheres, release conditions, etc. Selecting a subset of relevant properties for PLGA is a challenging machine learning task as there are over three hundred features to consider. In this work, we formulate the selection of critical attributes for PLGA as a multiobjective optimization problem with the aim of minimizing the error of predicting the dissolution profile while reducing the number of attributes selected. Four bio-inspired optimization algorithms: antlion optimization, binary version of antlion optimization, grey wolf optimization, and social spider optimization are used to select the optimal feature set for predicting the dissolution profile of PLGA. Besides these, LASSO algorithm is also used for comparisons. Selection of crucial variables is performed under the assumption that both predictability and model simplicity are of equal importance to the final result. During the feature selection process, a set of input variables is employed to find minimum generalization error across different predictive models and their settings/architectures. The methodology is evaluated using predictive modeling for which various tools are chosen, such as Cubist, random forests, artificial neural networks (monotonic MLP, deep learning MLP), multivariate adaptive regression splines, classification and regression tree, and hybrid systems of fuzzy logic and evolutionary computations (fugeR). The experimental results are compared with the results reported by Szlȩk. We obtain a normalized root mean square error (NRMSE) of 15.97% versus 15.4%, and the number of selected input features is smaller, nine versus eleven.

Feature Selection via Chaotic Antlion Optimization.

BACKGROUND: Selecting a subset of relevant properties from a large set of features that describe a dataset is a challenging machine learning task. In biology, for instance, the advances in the available technologies enable the generation of a very large number of biomarkers that describe the data. Choosing the more informative markers along with performing a high-accuracy classification over the data can be a daunting task, particularly if the data are high dimensional. An often adopted approach is to formulate the feature selection problem as a biobjective optimization problem, with the aim of maximizing the performance of the data analysis model (the quality of the data training fitting) while minimizing the number of features used. RESULTS: We propose an optimization approach for the feature selection problem that considers a "chaotic" version of the antlion optimizer method, a nature-inspired algorithm that mimics the hunting mechanism of antlions in nature. The balance between exploration of the search space and exploitation of the best solutions is a challenge in multi-objective optimization. The exploration/exploitation rate is controlled by the parameter I that limits the random walk range of the ants/prey. This variable is increased iteratively in a quasi-linear manner to decrease the exploration rate as the optimization progresses. The quasi-linear decrease in the variable I may lead to immature convergence in some cases and trapping in local minima in other cases. The chaotic system proposed here attempts to improve the tradeoff between exploration and exploitation. The methodology is evaluated using different chaotic maps on a number of feature selection datasets. To ensure generality, we used ten biological datasets, but we also used other types of data from various sources. The results are compared with the particle swarm optimizer and with genetic algorithm variants for feature selection using a set of quality metrics.