Uncertainty Models in the Context of Biometric Authentication Systems
Bibliographic record
Abstract
This thesis focuses on developing computationally-efficient machine reasoning models. These models are based on causal graphs with various metrics of uncertainty. The application of such models is decision-making in a multi-sensor, multi-source system. In particular, we consider examples of biometric-enabled systems for human identification where false passes and false rejects are always present. Two main problems are addressed in this thesis: the potential lack of data that is needed to build an accurate model, and the computational complexity (worst case computing time) of the process of deriving conclusions from the model (uncertainty inference). To tackle the first problem, this research suggests the use of advanced models of uncertainty. These models require the development of a taxonomy of various approaches to quantifying uncertainty with the aim of being tolerant to incomplete data. Tasks related to uncertainty model design include but are not limited to: • Model training, which is the generation of uncertainty models from raw data and expert knowledge. • Major approaches to quantifying uncertainty include but are not limited to: probability distributions, fuzzy probability distributions, credal sets, probability interval distributions, Dempster-Shafer models, and Dezert-Smarandache models. To address the second problem, this work develops a platform and software to perform the calculations related to the uncertainty models in a computationally-efficient manner. Tasks related to the usage of uncertainty models include but are not limited to: • Uncertainty inference, which is the calculation of likely outcomes and uncertainty values when provided with both a model of the scenario under consideration and observed evidence. This thesis covers some approximate approaches to uncertainty inference. • Data/information fusion, which is a subset of uncertainty inference that involves the process of collecting uncertainty values or observations from various sensors, and then generating a “recommendation”. To address the problem of computational complexity, approximate approaches will be developed and utilized in this thesis. These approximate approaches are formulated with the aim of reducing the computational complexity, while maintaining a reasonable degree of accuracy. Examples of applications of the proposed theoretical developments, including risk assessment tasks in biometric-enabled systems, are provided.
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 | 0.005 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".