There is an acute need to evaluate the energy consumption of buildings in response to climate change. The “occupant” factor has been largely overlooked in building energy analysis. This research aims at investigating occupancy existence in the office environment using a hybrid artificial neural network with metaheuristic algorithms for improved energy management. It proposes and compares three classification models, namely particle swarm optimization (PSO), gravitational search algorithm (GSA), and hybrid PSO-GSA in combination with the feedforward neural network (FFNN). The inputs to these models are data related to temperature, humidity, light, and carbon dioxide emissions. Two data sets are used for testing the models while the office door is open and closed. The capabilities of the optimized models are evaluated using best, average, median, and standard deviation of the mean squared error. Most of the performance metrics indicate that the FFNN-PSO-GSA model exhibits better performance compared to the other models using the two datasets. The proposed model yields a classification accuracy ranging between 98.47-98.73% using one predictor (i.e., temperature). Besides, it yields an accuracy ranging between 85.45-94.03% using temperature and CO2 predictors. It can be concluded that the FFNN combined with PSO and GSA algorithms can be a useful tool for occupancy detection modeling.

This research aims to enhance portfolio selection by integrating machine learning regression algorithms for predicting stock returns with various risk measures. These measures include mean-value-at-risk (VaR) variance (Var), semi-variance mean-absolute-deviation (MAD) and conditional value-at-risk (C-VaR). Addressing gaps in existing literature. Traditional methods lack adaptability to dynamic market conditions. We propose a hybrid approach optimized by genetic algorithms. The study employs multiple machine learning models. These include Random Forest, AdaBoost XGBoost, Support Vector Machine Regression (SVR) K-Nearest Neighbors (KNN) and Artificial Neural Network (ANN). These models are used to forecast stock returns. Utilizing monthly data from the Tehran Stock Exchange, the results indicate that the genetic algorithm prediction model combined with mean-VaR, Var semi-variance and MAD, produces the most efficient portfolios. These portfolios offer superior returns with minimized risk compared to other models. This hybrid strategy provides a robust and efficient method for investors aiming to optimize returns while managing risk effectively. To implement this approach successfully it is crucial to balance investments. This involves both traditional and alternative asset classes, ensuring diversification. It also capitalizes on market opportunities. Regular review and adjustment of fund allocation are essential. Maintain an optimized strategy for maximum returns and minimal risk.

Silver is a metal that offers significant value to both investors and companies. The purpose of this study is to make an estimation of the price of silver. While making this estimation, it is planned to include the frequency of searches on Google Trends for the words that affect the silver price. Thus, it is aimed to obtain a more accurate estimate. First, using the Latent Dirichlet Allocation method, the keywords to be analyzed in Google Trends were collected from various articles on the Internet. Mining data from Google Trends combined with the information obtained by LDA is the new approach this study took, to predict the price of silver. No study has been found in the literature that has adopted this approach to estimate the price of silver. The estimation was carried out with Random Forest Regression, Gaussian Process Regression, Support Vector Machine, Regression Trees and Artificial Neural Networks methods. In addition, ARIMA, which is one of the traditional methods that is widely used in time series analysis, was also used to benchmark the accuracy of the methodology. The best MSE ratio was obtained as 0,000227131 ± 0.0000235205 by the Regression Trees method. This score indicates that it would be a valid technique to estimate the price of "Silver" by using Google Trends data using the LDA method.

The continuous increase in energy consumption has brought worldwide attention to its significant environmental effect, which is triggered by the increase in greenhouse gas emissions, global warming, and rapid climate change. As such, more energy efficient buildings are required to minimize the energy consumption of heating and cooling. The present study introduces a set of machine learning-based models to predict the heating and cooling loads in buildings. This includes back-propagation artificial neural network, generalized regression neural network, radial basis neural network, radial kernel support vector machines and ANOVA kernel support vector machines. The comparisons were conducted as per mean absolute percentage error (MAPE), mean absolute error (MAE) and root-mean squared error (RMSE). Finally, the significance of the capacities of the machine learning models are evaluated using two-tailed student’s t-tests. Results demonstrate that the radial basis function network outperformed the aforementioned machine learning models.

The increasing amount of IoT devices increases the size of network traffic data, causing an increase in the incidence of security breaches in IoT networks. Cybercriminals have developed malware to compromise the security of sensitive data, among other cyber threats. In the presence of inadequate and robust security mechanisms, sensitive data is prone to vulnerability. Hence, protecting data in the IoT environment is becoming a mandatory task. Various approaches have addressed malware detection using network data features. However, there is still room for improvement in developing superior techniques and utilizing more comprehensive datasets. This paper presents a novel lightweight ensemble voting classifier to detect malware traffic by deploying the best possible network data. The merits of the correlation coefficient and Opposition-Based Crow Search Algorithm (OCS) have been leveraged to compute the best possible features. Another advantage of this proposed experiment is its focus on a dataset tailored to malware traffic features. This focus enables highly accurate malware detection. After feature selection using OCS, the proposed malware classifier is trained and validated with both 5-fold and 10-fold cross-validation techniques. The tested results confirm that the presented malware classifier performs best using a minimal feature set, which is highly advantageous for IoT networks due to resource constraints.

With flexible learning, students are actively engaged in their own education and are held to high standards of performance. Online academic courses make it easier for students to receive personalized education because they provide students with more flexibility to concentrate on what is most important to them and give them greater control over their own education. This study’s objective was to investigate whether there is a correlation between how well students succeed in online classes and the extent to which they make use of the schedule and the geographical and resource flexibility offered by such programmes. This article uses a developing approach for predicting and classifying the flexibility in online learning of students who are at risk of failing due to academic and demographic variables. The K-nearest neighbours (KNN) method, the random forest (RF) method, and the logistic regression method were used to categorise the students participating in flexible online learning. The information for the dataset came from Kaggle, and it was gathered for use in testing machine learning. The dataset had a total of 1,875 instances representing 11 different features. Also, accuracy, precision, sensitivity and f-score metrics were applied to evaluate the system. The results show that the RF algorithm has a high accuracy percentage of 85%. The empirical findings demonstrate that students formed distinct patterns of learning time, location and access to knowledge. This suggests that flexibility was used to a significant degree. Patterns in learning time and the availability of learning materials were shown to have a substantial relationship with the accomplishments of the students. Understanding flexibility use habits may help adapt lessons and boost collaboration among similar students.

This study conducted a thorough analysis of a dataset from a video game to reveal the relationship between game content, interactive features, and classification ratings. The project attempted to convert raw data into meaningful insights by employing Python for data processing and machine learning. The analysis uncovered strong relationships between content descriptors and ESRB ratings, indicating a market that strategically customizes game material to different demographic groupings. Moreover, the inclusion of interactive features such as 'Users Interact' and 'In-Game Purchases' suggests a transition towards gaming experiences that are more immersive and financially interactive. The highlight of this project was the creation of a web-based tool that can accurately forecast game classifications, utilizing advanced models such as XGBoost. The application offers developers and rating organizations a vital tool to achieve accuracy in game classification. The study's conclusions provide a detailed comprehension of console market dynamics, clarifying the present patterns and possible future developments in the gaming industry.

The COVID-19 pandemic has led to different health outcomes, including long COVID (LCo) and mental health (MH) disorders, impacting millions globally. To enable early healthcare diagnosis, including the prediction of MH conditions and LCo, various research studies have utilized machine learning (ML) techniques. However, there is still a gap in understanding the mental health of recovered COVID-19 patients with long COVID using ML techniques. This study aims to bridge this gap by developing and evaluating ML models, including support vector machine, multilayer perceptron (MLP), k-nearest neighbor, gradient boosting, voting classifier, and extreme gradient boosting, tailored for mental health and long COVID datasets from recovered COVID-19 patients. Additionally, feature selection methods, e.g., Recursive Feature Elimination (RFE) and Extra Trees (ET), and optimized models with hyper-parameter tuning will be employed. Our experiments utilize the dataset of recovered COVID-19 patients. Among these ML models, the MLP with ET-based features achieved the highest accuracy and AUC scores in this dataset, with 1.00 and 0.97 ± 0.02, respectively. The research reveals the high prevalence and risk factors of mental health disorders and long COVID from the dataset. These findings will contribute to personalized healthcare strategies for individuals navigating the complexities of post-COVID-19 recovery, integrating machine learning insights into mental health and long COVID support.

The IoT ecosystem faces increasingly complex security challenges due to the rapid growth of global IoT devices. Security risks related to device identification and credential compromise are on the rise, especially with the proliferation of IoT devices in various aspects of life. This research highlights the need to address these vulnerabilities through the development of robust security protocols, aiming to create a more secure IoT ecosystem and enhance user trust in this technology. The objective of the research is the development of an innovative IoT security protocol; High-Accuracy Device Identification and Resilience Against Credential Compromise (HADIRACC). This paper contributes significantly to enhancing the security and reliability of the IoT ecosystem. The research methods employed encompass the development of security protocols, the development of a proximity-based solution, and the classification of IoT devices using data processing techniques and machine learning-based classification. This study involves the collection and pre-processing of datasets, training different classifiers using 70% of the dataset, and testing the classifiers using the remaining 30%. The proposed protocol can effectively enhance the security of IoT devices by addressing various scenario-based attacks. Furthermore, the results of the analysis of the five classifiers used in this study indicate that Random Forest has the highest F1 score accuracy, reaching 88.8%. This suggests that Random Forest, as a classifier, can make the most accurate predictions compared to other classifiers.

Smart contracts offer automation for various decentralized applications but suffer from vulnerabilities that cause financial losses. Detecting vulnerabilities is critical to safeguarding decentralized applications before deployment. Automatic detection is more efficient than manual auditing of large codebases. Machine learning (ML) has emerged as a suitable technique for vulnerability detection. However, a systematic literature review (SLR) of ML models is lacking, making it difficult to identify research gaps. No published systematic review exists for ML approaches to smart contract vulnerability detection. This research focuses on ML-driven detection mechanisms from various databases. 46 studies were selected and reviewed based on keywords. The contributions address three research questions: vulnerability identification, machine learning model approaches, and data sources. In addition to highlighting gaps that require further investigation, the drawbacks of machine learning are discussed. This study lays the groundwork for improving ML solutions by mapping technical challenges and future directions.