The development and validation of new multisensory biomarkers and sensor-triggered interventions requires collecting raw sensor data and associated labels in the natural field environment. A software platform for such studies needs to not only support high-rate data ingestion, but also the entire sense-analyze-act pipeline at high-data rate. We present, mCerebrum, a general-purpose mobile software platform for conducting such studies.
Features & Capabilities
- mCerebrum supports raw data collections from multiple high-rate sensors and real-time assessment of data quality to ensure data fidelity.
- It includes a scalable storage architecture to ensure quick response despite rapidly growing data volume.
- It provides efficient sharing of sensor data among multiple sources and sinks with flexibility to represent current and future data types while ensuring a high throughput.
- It implements the entire sense-analyze-act pipeline for concurrent computation of several multi-sensor digital biomarkers at high data rate by efficient reuse of computations.
Finally, it has a reconfigurable scheduler that manages all prompts to participants that is burden- and context-aware. With a modular design spanning 23+ apps, mCerebrum provides a complete ecosystem of system services and utility apps. The design of mCerebrum is informed by its concurrent use in field studies at ten sites spanning 106,806 person days.
Details & Specifications
Computer Systems Organization
- National Institutes of Health – Big Data to Knowledge Initiative
- Grants: R01MD010362, 1UG1DA04030901, 1U54EB020404, 1R01CA190329, 1R01DE02524, R00MD010468, 3UH2DA041713, 10555SC
- National Science Foundation
- Grants: 1640813, 1722646
- Intelligence Advanced Research Projects Activity
- Contract: 2017-17042800006
mCerebrum provides a complete ecosystem of system services and utility apps.
The design of mCerebrum is informed by its concurrent use in field studies across ten sites spanning multiple days.