A Review of Machine Learning and TinyML in Healthcare
This work is the review of the contribution of the emerging technology of TinyML in healthcare applications at the edge, requiring the integration of Machine Learning algorithms, followed by the solutions it can bring, especially in wearable devices.
Abstract
Healthcare is the field that can benefit from the large amount of raw data generated from portable and wearable devices. This data must be sent to the Cloud for processing due to the computationally intensive nature of current state-of-the-art implementations of Neural Networks. The emerging technology of TinyML is an alternative approach proposed by the scientific community to create autonomous and safe devices that can collect, process, and alert without transmitting data to external entities. This work is the review of the contribution of the emerging technology of TinyML in healthcare applications at the edge, requiring the integration of Machine Learning algorithms, followed by the solutions it can bring, especially in wearable devices. Moreover, it is discussed how TinyML can optimize Neural Networks to bring intelligence and autonomy in devices used in fields such as healthcare.