Search

China, India, and the United States consume the most energy and emit the most CO2. According to datacommons.org, India's CO2 emission is 1.80 tnes per capita, which is harmful to living beings: hence, this study exhibits India's harmful CO2 emission effect and forecasts CO2 emission for the next ten years using univariate time-series data from 1980 to 2019. A multilayer perceptron is used in this study to analyse 2099 experimental data of binary systems made up of CO2 and ionic liquids and predict solubility. 33 different types of ionic liquids are represented in the dataset, which spans a wide variety of solubilities, pressures, and temperatures. In recent decades, greenhouse gas (GHG) emissions have caused air pollution and environmental problems in several countries. A precise prediction is essential for managing and planning for the decrease of greenhouse gas emissions. Furthermore, the Modified Coyote Optimization Algorithm was used to extract required properties. The empirical data revealed that predictions obtained from Multi-Layer Perceptron's Neural Network (MPNN) were more accurate than those derived from other models. The MPNN-MCOA identified a link between CO2 emissions, economic growth, and entrepreneurship. Government, personal liberty, education, and pollution all have a negative correlation. We conclude by emphasising the critical role of machine learning in achieving carbon neutrality, from global-scale energy management to the revolutionary potential of atomic-scale MPNN-MCOA simulations for application development. As a result, one of the most reliable approaches for estimating greenhouse gas (GHG) emissions from agricultural regions and companies was recommended: the MPNN-MCOA model. The Artificial neural network is trained with three input combinations with three combinations of thermodynamic variables such as temperature (T), pressure (P), critical temperature (Tc), critical pressure, the critical compressibility factor (Zc), and the acentric factor (w). Moreover, the proposed MPNN–MCOA model demonstrates an improvement in the forecasting accuracy obtained from the LSTM, KNN, CNN, and MPNN–MCOA models by 50.82%, 34.91%, 44.19%, and 29.77% decrease in mean square error, respectively.

Machine learning (ML) is currently a crucial tool in the field of cyber security. Through the identification of patterns, the mapping of cybercrime in real time, and the execution of in-depth penetration tests, ML is able to counter cyber threats and strengthen security infrastructure. Security in any organization depends on monitoring and analyzing user actions and behaviors. Due to the fact that it frequently avoids security precautions and does not trigger any alerts or flags, it is much more challenging to detect than traditional malicious network activity. ML is an important and rapidly developing anomaly detection field in order to protect user security and privacy, a wide range of applications, including various social media platforms, have incorporated cutting-edge techniques to detect anomalies. A social network is a platform where various social groups can interact, express themselves, and share pertinent content. By spreading propaganda, unwelcome messages, false information, fake news, and rumours, as well as by posting harmful links, this social network also encourages deviant behavior. In this research, we introduce Deep Belief Network (DBN) with Triple DES, a hybrid approach to anomaly detection in unbalanced classification. The results show that the DBN-TDES model can typically detect anomalous user behaviors that other models in anomaly detection cannot. [ABSTRACT FROM AUTHOR]