Performance analysis of the insomnia detection system using ANN in comparison with CatBoost

The aim of the study is to compare the effectiveness of Artificial Neural Networks (ANN) and CatBoost algorithms in analyzing sleep data for insomnia detection. The study seeks to evaluate their performance using metrics such as delicacy, perfection, recall, and F1 score. The study involves dividing the dataset into two groups: Group 1 utilizes CatBoost, while Group 2 employs Artificial Neural Networks (ANN). The total dataset comprises 375 samples. Various metrics including delicacy, perfection, recall, and F1 score are utilized to evaluate the performance of both algorithms in detecting insomnia from the sleep data. The results of the study indicate the performance of both CatBoost and ANN in the insomnia detection system. Specific metrics such as delicacy, perfection, recall, and F1 score are likely reported to illustrate the effectiveness of each algorithm. These metrics would provide insights into the sensitivity, specificity, and overall accuracy of the algorithms in identifying insomnia from the sleep data. In conclusion, the study likely provides insights into which algorithm, CatBoost or ANN, performs better in analyzing sleep data for insomnia detection. The conclusion would summarize the findings and possibly suggest recommendations for further research or practical applications based on the outcomes of the study.