The field of behavioral informatics has the potential to optimize interventions through monitoring, assessing, and modeling behavior in support of providing tailored and timely interventions.
The See Far patient-centered research is ongoing utilizing a wearable sensing ecosystem and machine learning/AI to optimize the interventions.
The latter is performed through the Smart Personalised profile which is a software component of the See Far solution. One of the dynamic parts of the proposed profile is the behavioural profile in the living and working environment
The technical partners have already developed a beyond the state-of-the-art AI pipeline for the human activity recognition (HAR) based on an LSTM architecture. In parallel an ML pipeline has been designed and developed based on the SVM with Radial Basis kernel Function classifier with an accuracy reaching ~84% and a real time performance on portable processing unit with no latencies in the inference.
