The COVID-19 outbreak resulted in preventative measures and restrictions for Bangladesh during the summer of 2020—these unstable and stressful times led to multiple social problems (e.g., domestic violence and divorce). Globally, researchers, policymakers, governments, and civil societies have been concerned about the increase in domestic violence against women and children during the ongoing COVID-19 pandemic. In Bangladesh, domestic violence against women and children has increased during the COVID-19 pandemic. In this article, we investigated family violence among 511 families during the COVID-19 outbreak. Participants were given questionnaires to answer, for a period of over ten days; we predicted family violence using a machine learning-based model. To predict domestic violence from our data set, we applied random forest, logistic regression, and Naive Bayes machine learning algorithms to our model. We employed an oversampling strategy named the Synthetic Minority Oversampling Technique (SMOTE) and the chi-squared statistical test to, respectively, solve the imbalance problem and discover the feature importance of our data set. The performances of the machine learning algorithms were evaluated based on accuracy, precision, recall, and F-score criteria. Finally, the receiver operating characteristic (ROC) and confusion matrices were developed and analyzed for three algorithms. On average, our model, with the random forest, logistic regression, and Naive Bayes algorithms, predicted family violence with 77%, 69%, and 62% accuracy for our data set. The findings of this study indicate that domestic violence has increased and is highly related to two features: family income level during the COVID-19 pandemic and education level of the family members.

Hypertension in Bangladesh is a leading cause of cardiovascular diseases, stroke, and kidney failure, resulting in significant morbidity and mortality. Preventive measures and simple health practices can effectively reduce hypertension and its complications. This study utilizes machine learning algorithms (Naive Bayes, support vector machine, logistic regression, random forest) to predict hypertension in high-risk individuals. The proposed hybrid model achieves a prediction accuracy of 78.17%, surpassing other machine learning methods. Random forest has the highest accuracy among the individual algorithms at 73.86%. Classification performance is evaluated using sensitivity, specificity, precision, and F-score, along with receiver operating characteristic analyses and confusion matrices through 10-fold cross-validation. These findings emphasize the importance of managing risk factors for better population health and highlight the efficacy of the hybrid model in hypertension prediction. The study underscores the significance of preventive measures in reducing the burden of hypertension-related diseases and improving overall well-being.

In Southern Asia, Bangladesh is a well-known developing country. Because of COVID-19, we continuously face challenges. Not only can these issues occur beyond economic or health concerns, but they also generate dangerous social problems, such as family abuse. Since the inception of this epidemic, multiple social crimes are looming. Remaining home during the lockout period enhances divorce rates. This research presents a customized forecast of family violence during the COVID-19 outbreak by using machine learning methods. In this paper, we have applied Random Forest, Logistic Regression, and Naive Bayes machine learning classifiers to predict family violence and discovered the feature importance. The performance of the classifiers is evaluated based on accuracy, precision, recall, and F-score. We have employed an oversampling strategy named synthetic minority oversampling technique (SMOTE) to solve the imbalance problem of our data. Even, we have tried to compare three machine learning model performances before and after balancing of normalization data. Finally, ROC analyses and confusion matrices were developed and analyzed by using data augmentation. Our proposed system with the random forest classifier performed better with 77% accuracy in comparison with other two machine learning classifiers.

The COVID-19 pandemic has provided an unprecedented amount of information in news outlets, which include scientific, health-related, political, economic, and social narratives. This study compares the effectiveness of machine learning and deep learning algorithms for classifying text data, with a certain emphasis on how well the former handle COVID-19 news narratives. The study dataset contains news articles regarding COVID-19. To achieve the primary purpose of this research is to classify COVID19 related news, we integrate multiple datasets. The analysis reveals machine learning models exhibit superior performance in text data classification. In particular, the Random Forest model reaches a 98% accuracy rate. In contrast, with regards to deep learning models, the Bidirectional Long Short-Term Memory model with FastText integration turns out to be the best option due to its exceptional accuracy. Exploratory data techniques such as topic modeling and word cloud approaches are incorporated to uncover hidden patterns in the data. Pre-trained (e.g., deep learning) and non-pre-trained ML models are implemented highlighting the versatility of ML in text classification tasks. The specific purpose to compare to the deep learning and machine learning algorithm to classification of the new article. Notably, a predictive model employing Bi-LSTM with the FastText pre-trained model achieved an impressive 94% accuracy in classifying COVID-19 news reports.

Daily maximum temperature prediction plays an important role in climate‐risk management, agriculture, public health and energy planning and disaster preparedness in climate vulnerable country like Bangladesh. This study assesses the individual and ensemble predictive power of machine learning (ML), deep learning (DL) and hybrid ensemble‐based frameworks for daily maximum temperature prediction using 2013–2022 daily records from meteorological stations. Materials and methods Correlation‐based screening followed forward‐backward stepwise regression, standard scaling, a train‐test partitioning by chronology, and comparative validation with mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), Mean Absolute Percentage Error (MAPE) coefficient of determination () as performance measures. Four classical ML algorithms were evaluated such as Linear Regression, Random Forest, Support Vector Regression, and Extreme Gradient Boosting. Data driven recurrent DL models like Simple Recurrent Neural Network and Long Short Term Memory were trained with multivariate temporal windows. Three hybrid approaches were also tested: RNN‐LSTM sequential hybrid, stacking‐based ML ensemble, and combined DL‐ML super‐hybrid. The ML‐based models significantly outperformed standalone recurrent DL models in the given data configuration. XGBoost was also the best performing single ML model in terms of MAE = 0.76°C, MSE = 1.19°C ² , RMSE = 1.09°C, MAPE = 3.21 and R ² = 0.94. The ML stacking ensemble produced MAE = 0.76°C, MAPE = 3.18, MSE = 1.21°C ² , RMSE = 1.05°C, and R ² = 0.94. The best overall performance was obtained by using the proposed DL‐ML hybrid (MAE = 0.74°C, MAPE = 3.07, MSE = 1.08°C ² , RMSE = 1.04°C, R ² = 0.95). Our findings suggest that hybrid learning can enhance temperature prediction by integrating different types of meteorological relationships and representations in tabular and sequential forms. It also stresses, however, the requirement for independent multi‐station validation, leakage‐free stacking analysis, explain ability tests and extreme‐temperature conditions tests ahead of first deployment in the field.