Nowadays, the huge amount of monitoring data generated by wearable devices is mainly transmitted and processed in large cloud servers. This approach has many of advantages in terms of algorithms and data management, but it is hardly scalable and poses a high privacy risk.
Our vision consists of a multi-layer distributed approach, in which most of the data is processed just where it is produced, and only the necessary information for data-fusion or high-level inference is transmitted.
For example, in the picture we can see our proposed self-aware distributed system for epileptic seizure monitoring. The Electroencephalographic signal is captured by our e-Glass system, that includes the necessary machine learning for detecting the baseline normal situation in cooperation with a wrist band for monitoring the heart rate. However, if at some point the confidence on this local analysis is not enough, we can include a higher-level analysis involving the smartphone of the user, that can run more complex signal processing and machine learning algorithms. The smartphone can also act as a Fog coordinator, exploiting the available resources on other neighbor smartphones, or relying on the cloud if a heavy, global analysis is required to provide an answer.
|Self-Aware Anomaly-Detection for Epilepsy Monitoring on Low-Power Wearable Electrocardiographic Devices|
|Forooghifar, Farnaz; Aminifar, Amin; Teijeiro, Tomas; Aminifar, Amir; Jeppesen, Jesper; Beniczky, Sandor; Atienza Alonso, David|
|Resource-Aware Distributed Epilepsy Monitoring Using Self-Awareness From Edge to Cloud|
|Forooghifar, Farnaz ; Aminifar, Amir ; Atienza Alonso, David|
|2019-11-04||IEEE Transactions on Biomedical Circuits and Systems|
|A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection|
|Forooghifar, Farnaz ; Aminifar, Amir ; Cammoun, Leila ; Atienza Alonso, David ; Wisniewski, Ilona ; Ciumas, Carolina ; Ryvlin, Philippe|
|2019-08-08||Mobile Networks and Applications|