Classification of eye gestures using machine learning for use in embedded switch controller

The classification of signals captured by sampling devices through analysis is a powerful tool with application spanning nearly every industry. Using such classification on real time signals to detect different events or anomalies provides a fast and reliable way of implementing monitoring or control systems. Machine learning classification models include support vector machines (SVM), K-nearest neighbors (KNN), decision trees, and many more. These algorithms separate labelled datasets based on features extracted from the inputs. In the assistive technology field, the use of eye tracking technology provides patients of quadriplegia, ALS, or other neurodegenerative disease with the ability to control speech devices using their eyes. To provide a low-cost alternative to the existing costly devices, an electrooculography (EOG) controller was utilized for obtaining signal data and classifying gestures. A dataset consisting of these gestures was collected over several trials and classified using an SVM, KNN, and decision tree's algorithm with a moving window buffer suitable for an embedded device with peak overall accuracies of 96.8%, 96.9%, and 95.4% respectively. The trained models are converted to C code and uploaded to an ATmega328p AVR microcontroller. Using a decision tree implementation, the intentional blink signal classification is successfully predicted with an accuracy of 97.33% accuracy and filters out unintentional blinks with 100% accuracy on the embedded device.