DissIdent: A Dissimilarity-based Approach for Improving the Identification of Unknown UAVs
Bibliographic record
Abstract
In Unmanned Aerial Vehicles (UAVs), the real-time detection and identification of unauthorized UAVs is a significant challenge to be appropriately addressed. Currently, supervised-based learning models (e.g., Deep Neural Networks) can detect the presence of authorized UAVs with reasonable accuracy. Still, they can not handle properly the wide range of unknown signals in the airspace, mainly their categorization. Clustering techniques (e.g., DBSCAN) can be applied to identify and classify unfamiliar signals. However, the uncertainty regarding the nature of unknown sounds can lead to a large dimensional problem, hampering the performance of these techniques. Given these issues, we proposed DissIdent, a dissimilarity-based method for identifying unknown drones. Our approach takes advantage of the dissimilarity concept, in which a function of proximity maps extensive and multi-dimensional problems to a binary problem. DissIdent can identify patterns from different features through an intelligent workflow, mitigating the trade-off between the traceability and accuracy of massive multi-class problems. We carried out an extensive evaluation of DissIdent, comparing it with eight different approaches. The results pointed out DissIdent as a robust approach to detection and identification tasks, overcoming the compared methods. DissIdent addressed accuracy rates higher than 93% in all scenarios, presenting a concise detection and identification of unauthorized drones.
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 | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".