Selective context fusion utilizing an integrated RFID-WSN architecture
Bibliographic record
Abstract
The abundance of sensed data and its correlation between wireless entities has recently increased significantly. Understanding the context of each entity in a given environment is not-trivial. Mainly due to the need of realizing an efficient scheme for context fusion over multiple sensing/polling technologies. In this paper we present a selective context fusion model that utilizes an integrated architecture which encompasses both RFID systems and information collected from Wireless Sensor Networks (WSNs). We integrate the identification capabilities of the former with the group intelligence sustained by the latter. A mediator acts as both the reader and relay (RR) node to communicate both technologies respectively. Thus, collecting context information from sensors and tags, then aggregating, filtering and carrying out analysis to selectively enhance the quality of context collected in its vicinity. As such, the network will fuse information over a multiplicity of devices. The goal of this system is to utilize contextual information about the devices generating the data to better the selection process. The filtration process eliminates irregularities in the data as well as redundancy. Moreover, a weighted function stresses the value of data generated by higher-end nodes. Weight is also attributed to log-based evaluation protocols that identify a reliability metric. To further strengthen the fusion approach, local RRs will collect and aggregate context information from neighboring RR nodes, as well as knowledge databases over the Internet. As a load balancing measure, and to avoid resource draining, participating nodes will have an inversely proportional likelihood of participation in providing context information as their contribution count increases. Our system is further elaborated upon via an extensive use case.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".