According to a study published in Medical Engineering & Physics, wearable sensors are at the cusp of becoming truly pervasive and ubiquitous, with healthcare applications in a variety of areas including physiological monitoring, ambulatory monitoring and falls detection. However, the richness of data available using wearable sensors presents challenges in the way that it is processed to provide accurate and relevant outputs. To fully exploit this data for the purposes of healthcare monitoring, data fusion techniques that interpret the complex multidimensional information can be employed to make inferences and improve the accuracy of the output.
Chronolife has pioneered a patented neuromorphic algorithm called HOTS (Hierarchy Of event-based Time Surfaces), a machine learning predictive algorithm capable of continuously analyzing complex, multiparametric data streams on low bandwidth such as smartphones or tablets, and detecting pattern deviations. HOTS can be ported and integrated with a wide range of mobile devices and platforms for local analysis and relevant alerts generation.
Chronolife offers HOTS as an embedded predictive algorithm that can be easily integrated with any of your data-collecting devices, IoT platforms, smart objects across a variety of purposes and programs:
Some specific example use cases scenarios include: