Robust Egomotion Estimation for Automatic and Crowdsourcing-Based Indoor Localization and Tracking
Bibliographic record
Abstract
Indoor localization has been an active research in recent years. Among many different algorithms proposed, fingerprinting-based methods have found a great popularity due to ease of deployment and high accuracy. A major disadvantage to fingerprinting-based methods, is the burden of the training phase in which fingerprints of a certain type of a signal are recorded in many known locations inside the indoor environment. The collected dataset of fingerprints and corresponding locations is then used to model the relationship between fingerprints and locations in order to use that model to localize future queried fingerprints. This process is usually time consuming and requires considerable human effort and expertise. To overcome the burden of the training phase, in this thesis, we discuss two different perspectives towards solving these problems. We refer to these perspectives as: automatic fingerprinting and, crowdsourcing-based fingerprint-location dataset generation. The former, aims to reduce the time and effort put by an expert to generate the fingerprint dataset by automatically estimating the location of the collected fingerprints while the expert walks in the environment, hence reducing the training time from typically several hours to a few minutes needed to walk in the target indoor area. The latter method, aims to approach the problem by leveraging the shared data from the users in an indoor environment, hence eliminating the need for an expert to repeat the training process to update the dataset of fingerprints. Both perspectives above can expedite the widespread use of fingerprinting-based methods of localization for indoors by alleviating the burden of the training phase which currently seems to be the major drawback for this popular category of indoor localization systems. We will propose, design and validate algorithms for each of these methods.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".