This project presents an intelligent crutch that enables continuous and personalized diagnosis of patients with functional mobility impairment. The proposed solution is based on Neural Sensors and Personalized Diagnostic Virtual Sensors, all of them designed using different Artificial Intelligence techniques, such as Spiking Neural Networks and Anomaly Detection techniques. As a result, a personalized diagnosis will make it easier for therapists to establish better and more precise personalized therapies, with the...

A HardWare Implementation of the PWM inspired encoding/decoding algorithm (IHA-PWM). A new supervised training approach of SNN for regression based on both backpropagation and PWM inspired encoding/decoding algorithm. Define the specification for a neuromorphic HardWare implementation of both IHA-PWM and the new supervised training algorithm.

The main challenge of this approach is to characterize the state of the patient in a given time, so that the Virtual Sensor is able to detect slight variations in this state. The final goal is to provide therapists with information that allows them to adapt easily the rehabilitation therapies, so that their efficiency is maximized, which will impact on the quality of life of patients.