Swallowing Pattern Recognition with IoT and Convolutional Neural Networks

Identification and observation of swallowing patterns are essential for diagnosing and treating dysphagia, a disorder characterized by difficulties with swallowing. This work presents a novel Internet of Things (IoT) device-integrated convolutional neural network (CNN) swallowing pattern recognition system. The system uses Wet Voice Detection Dataset to gather comprehensive swallowing data. These sensors send data wirelessly to a cloud-based platform, where the CNN model analyzes and categorizes swallowing events with high accuracy. Real-time monitoring and analysis made possible by integrating CNNs and IoT allows for prompt intervention and individualized treatment plans. The system's efficacy in identifying swallowing patterns is indicated by preliminary results, underscoring its potential to enhance patient outcomes in clinical settings. The proposed system is a new technique for improvements in the treatment and rehabilitation of dysphagia by providing a scalable and effective method for identifying continuous swallowing patterns.