Smartphone-Based Machine Learning for Automated Diagnosis Using Eye, Skin, and Voice Signals

Abstract Applying machine learning techniques to data produced by commonplace gadgets like smartphones offers a chance to improve the standard of medical treatment and diagnosis. Smartphones are perfect for collecting data, giving prompt feedback on diagnosis, and suggesting measures to enhance health. Cloud-based Internet of Things (IoT) apps provide smart cities with cutting-edge ways to reduce traffic accidents brought on by fatigued driving. In this work, we examined cutting-edge methods for identifying risky driving behaviors utilizing three popular IoT-based systems. Effective treatment requires an early and precise diagnosis. Artificial Intelligence (AI) has recently demonstrated encouraging possibilities in helping physicians diagnose pterygium. An overview of AI-assisted pterygium diagnosis is given in this work, along with information on the AI methods that are employed, including computer vision, deep learning, and machine learning. Dehydration is brought on by the body losing fluids, which interferes with normal bodily processes and leads to health issues. The current methods for detecting dehydration in clinical and laboratory settings are costly, time-consuming, and need visiting medical facilities, which are frequently absent in impoverished areas. We create a deep learning model based on Siamese networks to identify changes in facial features caused by dehydration that are invisible to the average person. Our model is light enough to operate on a smartphone processor and has an overall accuracy of 76.1%. By integrating it into the backdrop, we create a smartphone app called “Dehydration Scan” that merely takes pictures of people’s faces and determines how hydrated they are. People can use oral rehydration solutions and prevent severe dehydration if they are aware of dehydration early on. Keywords Rehydration Solutions, Human Body, Smartphones Presents, Laboratory-Based, Facial Landmarks, Hydration Status, Deep Learning Model.