Capsule Networks and Lightweight Dual-Path Model With Fresnel Zone-Based Voting for Human Activity Recognition Using Wi-Fi Channel State Information
Bibliographic record
Abstract
Wi-Fi sensing has recently gained significant interest for human activity recognition (HAR), as it provides user privacy and adaptability to non-line-of-sight scenarios. This thesis presents two machine learning models, contributing novel approaches to Wi-Fi-based HAR. Firstly, a capsule network is trained on channel state information (CSI) from Wi-Fi to perform activity classification. Secondly, dual-path feature extraction is proposed, extracting information along both time and frequency dimensions of CSI. This thesis also extends both models into distributed architectures, eliminating communication overhead introduced in centralizing CSI from multiple access points (APs), while using a Fresnel zone-based voting scheme to combine distributed model outputs efficiently using spatial diversity. The proposed methods are evaluated on four datasets, covering various human activities, against state-of-the-art works. In particular, we surpass state-of-the-art classification performance with our capsule network, improve upon existing lightweight approaches with our dual-path feature extraction, and bring practicality with our Fresnel zone-based voting scheme.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| 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".