Human Identification Using Neural Network-Based Classification of Periodic Behaviors in Virtual Reality
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
There are a lot of techniques that help computer systems or devices identify their users in order to not only protect privacy, personal information, and sensitive data but also provide appropriate treatments, advertisements, or benefits. With passcode, password, fingerprint, or iris, people need to explicitly do some required activities such as typing their codes, showing their eyes, and putting their fingers on the scanners. Those solutions should be used in high-secure scenarios such as executing banking transactions and unlocking personal phones. In other systems such as gaming machines and collaborative frameworks, which aim to prioritize user experience and convenience, it would be better if user profile can be collected and built implicitly. Among those systems, virtual reality (VR) is a new trend, a new platform supporting not only fully immersive experience for gamers but also a collaborative environment for students, researchers, and other people. Currently, VR systems can track user physical activities via trackable devices such as HMD and VR controllers. Therefore, we aim to use virtual reality as our identification equipment. In virtual reality, we can easily simulate an invariant condition at any time so that people have larger probability to replicate their behaviors without any external affections. Therefore, we want to investigate if we could classify VR users based on their periodic interaction with virtual objects. We collect the position and direction of user's head or hands when doing a task and build a classification model based on those data using convolutional neural network approach. We have done an experiment to explore the capability of our proposed technique. The result was motivated with the highest accuracy of 90.92%. Identification in VR hence is potentially applicable. In the future, we plan to do a large-scale experiment with a larger group of participants to examine the strength of our method.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it