SensIoT: An Extensible and General Internet of Things Monitoring Framework
Bibliographic record
Abstract
SensIoT is an open-source sensor monitoring framework for the Internet of Things, which utilizes proven technologies to enable easy deployment and maintenance while staying flexible and scalable. It closes the gap between highly specialized and, therefore, inflexible sensor monitoring solutions, which are only adjusted to a specific context, and the development of every other solution from scratch. Our framework fits a variety of use cases by providing an easy to set up, extensible, and affordable solution. The development is based on our former published framework MonTreAL, whose goal is to offer an environmental monitoring solution for libraries to guarantee cultural heritage to be conserved and prevented from serious damage, for example, from mold formation in closed stocks. It is a solution with virtualized microservices delivered by a famous container technology called Docker that is solely executable on one or more single board computers like the Raspberry Pi by providing automatic scaling and resilience of all sensor services. For SensIoT we extended the capability of MonTreAL to integrate commodity servers into the cluster to enhance the ease of setup and maintainability on already existing infrastructures. Therefore, we followed the paradigm to distribute microservices on small computing nodes first, thus not utilizing well-known cloud computing concepts. To achieve resilience and fault tolerance we also based our system on a microservice architecture, where the service orchestration is solved by Docker Swarm. As proof of concept, we are able to present our current data collection of the University of Bamberg’s Library that runs our system since autumn 2017. To make our system even better we are working on the integration of other sensor types and better performance management of SD-cards in Raspberry Pis.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".