Heat exchangers play a crucial role in transferring heat between two mediums, directly impacting energy efficiency, product quality, and operational safety in industrial systems. This study presents a novel approach for fouling resistance estimation using two artificial intelligence models, the cascaded forward network (CFN) and the recurrent neural network (RN), with a minimal set of six input parameters. The proposed models utilize temperature and flow sensor data from heat exchangers to predict fouling resistance. The training process is optimized using the Levenberg–Marquardt (LM) algorithm, ensuring rapid convergence and high accuracy. Model performance is assessed based on mean squared error (MSE), regression values (R), and statistical error analysis. The results demonstrate that both models achieve high accuracy in predicting fouling resistance, with the CFN model outperforming the RN model. The CFN model achieves an MSE of 1.54 × 10⁻⁸, significantly lower than the RN model (MSE = 3.05 × 10⁻⁸), resulting in a 49.5% improvement in accuracy. Additionally, statistical analysis, including error histograms and correlation analysis, further confirms the robustness of the proposed models. Compared to traditional methods, the proposed AI-based models reduce computational complexity while maintaining superior accuracy. This study highlights the potential of AI in predictive maintenance and industrial optimization, paving the way for future enhancements in intelligent fouling estimation systems.

In this paper, time spent and the repetition of using the Social Network Sites (SNS) in Android applications are investigated. In this approach, we seek to raise the awareness and limit, but not eliminate the repeated uses of SNS, by introducing AndroidTrack. This AndroidTrack is an android application that was designed to monitor and apply valid experimental studies in order to improve the impacts of social media on Iraqi users. Data generated from the app were aggregated and updated periodically at Google Firebase Real-time Database. The statistical factor analysis (FA) was presented as a result of the user’s interactions.

The ubiquity of phones and their compatibilities provides a good opportunity to use them as lifelogging information devices. The tracking usage application helps to mitigate the widespread use of social media on smartphones. Tracking apps can be used to monitor and limit social media and smartphone use, which can ultimately reduce the negative effects of phenomena of fear of missing out (FOMO) and social media engagement on smartphone addiction and distraction. In this paper, a structural review for tracking social applications in smartphones is presented. Many commercial force stop applications are not use for recording but are also for analyzing the experienced samples in which it entered by the users and their behaviors. To address these challenges, previous research works are investigated from the user application activities and their event-driven activities are analyzed. In addition, the tracking applications are divided into three categories and our third-party application is highlighted that tracks the frequency of use and time stamp and suggests temporarily blocking any applications that are overused. Some recommendations for future work are provided at the end of the paper.

Wind turbines have attracted much attention from scientists who are aiming to achieve a prominent level of performance due to the environmental changes during the year. To meet the demand for renewable energy at the lowest cost, wind energy became the target of machine learning algorithms and was employed to predict the output power of wind turbines. The aim of this study is to utilise a causal inference approach to estimate the power output of wind turbines. Initially, the outcomes derived from numerical prediction are examined using a structural causal model. After causal discovery, we identify potential confounders for the filter factors that have the most significant impact on the outcome and decide whether to include or exclude these prospective confounders in our model. This method guarantees precise predictions using the Adaptive Neuro-Fuzzy Inference System ANFIS. ANFIS is a hybrid learning approach that combines neural network and fuzzy logic system for estimating the output model for nonlinear relationships. ANFIS employed the pressure surface, wind speed and air pressure as input data while the power of the wind turbine served as the output of the predicted model. Various practical experiments were conducted using different membership functions in neuro-fuzzy training to achieve the lowest possible mean square error. The data were gathered over two months on a farm in Egypt on the Suez Gulf. Approximately 85% of the data was utilised to train the three inputs, while the rest was used to evaluate the predicted model and assess the efficiency using Akaike Information Criterion (AIC) to choose the best fit model. A further study showed that changing the ANFIS parameters could deviate from the path of efficient outcomes, compared with the neural network approach.