Deep learning disease prediction model for use with intelligent robots.

Area of Science:

• Robotics
• Machine Learning
• Deep Learning
• Medical Informatics

Background:

• The COVID-19 pandemic necessitates rapid and accurate disease detection for effective treatment.
• Existing machine learning models face challenges in addressing the complexities of deep learning applications in robotics for disease prediction.

Purpose of the Study:

• To develop and evaluate a novel deep learning-based prediction model for early COVID-19 detection.
• To improve the accuracy and efficiency of COVID-19 diagnosis through advanced feature selection and classification techniques.

Main Methods:

• Data preprocessing involved cleaning missing values and outlier detection using spline interpolation and entropy-correlation.
• Feature extraction was performed using Principle Component Analysis, followed by optimal feature selection with a Fitness Oriented Dragonfly Algorithm.
• The selected features were fed into a Deep Belief Network for classification.

Main Results:

• The proposed model demonstrated superior performance compared to traditional state-of-the-art methods.
• Accuracy improvements were observed: 6.96% over Firefly, 6.7% over Particle Swarm Optimization, 6.96% over Gray Wolf Optimization, and 7.22% over the Dragonfly Algorithm.

Conclusions:

• The developed deep learning model offers a highly accurate and effective approach for early COVID-19 detection.
• This advancement in predictive modeling can significantly aid in proactive treatment strategies and potentially reduce mortality rates.