In our daily lives, amidst hectic schedules, the critical intersection of sleep and mental health is highlighted, emphasizing the pivotal role of sleep in maintaining mental well-being. This study underscores the importance of optimal classifications for analyzing various sleep patterns, given the well-established link between poor mental health and the quality of sleep issues like depression and anxiety, as recognized by the WHO. Understanding sleep habits, including circadian rhythm disarray, hypersomnia, insomnia, restless legs syndrome, and sleep apnea, is crucial for gaining insights into mental health. This research focuses on enhancing accuracy in identifying customized sleep pattern abnormalities using EEG signal analysis and ensemble learning approaches. The study employs ensemble learning approaches such as Random Forest, Support Vector Machine, Gradient Boosting Machine and Extreme Gradient Boosting Machine, emphasizing hyperparameter tuning to optimize model efficiency. By leveraging EEG signal data, the models can capture intricate patterns in brain activity that correlate with different sleep disorders, offering a more precise diagnostic tool. Furthermore, the study proposes future research avenues, including the utilization of real-time EEG data and personalized interventions, to further illuminate the connection between sleep and mental health. This research aims to advance the understanding and treatment of sleep-related mental health problems, promoting better general health. These findings can help create more accurate prediction models and tailored therapies to enhance sleep quality and mental health outcomes.