A Platform for Real-Time Space Health Analytics as a Service Utilizing Space Data Relays
Bibliographic record
Abstract
The health, wellness and adaptation response of astronauts during spaceflight is a key component for the success of any manned mission. Physiological and psychological responses of astronauts during spaceflight have been monitored from the first manned missions sixty years ago. However, limited communication networks to and within the spacecraft have limited methods to monitor the health, wellness and adaptation response of astronauts in real-time. This has resulted in a paradigm of astronaut monitoring as discontinuous samplings of physiological data that are captured on board the spacecraft and transported to Earth on storage devices for retrospective down sampled analysis. In 2009, as part of prior research, McGregor proposed a big data analytics framework and platform, that enables the capture and processing of physiological data and other clinical data in real-time for new approaches to real-time health monitoring. The platform, was named the Artemis platform after the Greek goddess of childbearing as the first domain it was used was neonatal intensive care. Its efficacy and reliability as a new approach for real-time health monitoring has been demonstrated in the critical care domain and specifically within the domain of neonatal intensive care. McGregor previously proposed the application of Artemis as an approach for autonomous health monitoring within the spacecraft to support missions within and beyond low Earth orbit. This would enable sophisticated realtime health, wellness and adaptation assessment that did not require the transmission of data beyond the spacecraft. Artemis Cloud has been proposed as a cloud-based approach to provide remote health monitoring. Artemis Cloud enables Health Analytics as a Service and has been demonstrated utilizing the Ontario Research and Innovation Optical Network (ORION) in Ontario and Artemis Cloud instances located at the Compute Ontario advanced research computing node within the Centre for Advanced Computing, Queen's University, Ontario providing remote health monitoring of neonatal intensive care patients at two hospitals in Ontario, Canada. There is great potential for this Health Analytics as a Service model enabled through Artemis Cloud to support the assessment of health, wellness and adaptation response of astronauts in space, however, robust and reliable networks are required. The next stage of space exploration will see unmanned missions using robots that will require prognostics and health management. This will be followed by manned lunar orbiters, Moon bases and Mars missions that will all require the support of health, wellness and adaptation assessment of astronauts engaged in those missions. Deep space hybrid radio frequency and optical networks have great potential to address the current gap in space communication networks. This paper presents a framework and infrastructure to enable real-time equipment monitoring for prognostics and health management and astronaut health monitoring through cloud-based Health Analytics as a Service utilizing space data relays. A key benefit of this approach is its ability to monitor their health and wellbeing onboard the spacecraft as well as enabling the equipment and astronaut's physiological data, and other clinical data, to be sent to an Earth based Mission Control Center within more manageable latencies of seconds or minutes. This will provide a more viable alternative to autonomous only approaches for equipment and astronaut monitoring.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.014 | 0.009 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".