Sleep is a critical biological process required for physical recovery, cognitive function, emotional regulation, and sound health. Conventional techniques for evaluating the quality of sleep are usually costly and intrusive, especially when they use sleep clinics and advanced sensors. Instead of using several factors to predict sleep quality, the majority of earlier studies only employed one factor and a short dataset. Their results were less accurate since they did not apply machine learning to look into the cause of poor sleep quality. This paper initiates a machine-learning (ML) based method for assessing and predicting sleep quality using a larger dataset and the Pittsburgh Sleep Quality Index (PSQI). To find the best machine learning model for predicting sleep quality, the proposed system tests eight classifiers. The results show that the Cat Boost classifier outperforms other models, with an accuracy value of 90.1%, precision value of 87%, recall value of 88%, and f1-score value of 87%. The proposed prediction model also outperformed previous works in terms of accuracy, precision, and recall by 12%, 8%, and 11%, respectively. This paper also describes a web application with features such as personalized sleep quality prediction, result checking, improvement suggestions, and doctor consultation services. According to the review results, up to 65 percent of users agreed that the proposed sleep quality assistance web application features were appropriate and necessary.

Forecasting electrical energy consumption is becoming increasingly important for a country's citizens as it addresses rising energy demand and energy waste issues. A useful electrical energy consumption prediction scheme could help users estimate their monthly electricity bills and the use of new electrical appliances in their homes. Traditional energy consumption prediction methods are time-consuming and necessitate expert assistance to analyze and calculate energy use over time. The limitations of the existing works are that the existing literature does not accurately predict monthly energy consumption and costs using machine learning. They concentrated on electrical energy consumption over a short period of time in a single building, using seasonal data rather than automating the system for repeated use. To address these issues, this paper proposes machine learning-based automation systems that predict monthly energy consumption, estimate costs, and identify relevant features using data from electrical home appliances in Bangladesh. Several regression models, including Random Forest, Decision Tree, XGBoost, Boosting, and LightGBM Regressor, are tested to find the best prediction model. We have performed dataset collection, dataset cleaning, feature extraction, scaling, normalization, hyper parameter tuning, training, testing, and model selection activities. The simulation results clearly indicated that the Random Forest regressor model performed better than the other models, with higher R squared values and lower error values. The comparison results revealed that the proposed random forest regression model outperforms previous works by at least 4% in accuracy and 7% in mean absolute error. The proposed mobile application helps users make informed decisions by calculating energy consumption for new home appliances, making recommendations, delivering updated news from the power board, and providing required guidelines. The mobile application feature evaluation results revealed that our proposed application received an excellent rating from more than 70% of customers.