Device-Free Human Activity Recognition: A Systematic Literature Review
Bibliographic record
Abstract
Human activity recognition (HAR) has become a topic of interest in recent years. While device-based, object-tagged, and camera-based approaches to HAR have many advantages, device-free HAR offers new contributions to the field. Unlike device-based or object-tagged methods, it does not require users to carry sensory devices, and unlike camera-based methods, it respects privacy. Despite the significant number of original research studies and surveys on device-free HAR published in recent years, many scientific questions remain open. In this study, a systematic literature review on device-free HAR was conducted by exploring ACM, IEEExplore, ScienceDirect, Scopus, and WebOfScience. This mixed-method study assesses the quality of the reviewed papers and analyzes suggested HAR methods in both a scientometric and technical manner. The scientometric analysis investigates the trends of scientific publications in this field from the beginning of 2017 to the end of 2023 and reviews the types and distribution of publications among countries, universities, and media. The technical analysis categorizes methods based on device-free sensing modalities, the type, and granularity of recognized activities of proposed methods. It also discusses the common challenges and limitations of current device-free HAR approaches. Additionally, existing methods are compared based on their support for non-line-of-sight, multisubject, user-independent, and environment-independent recognition of human activities. This work provides foundational knowledge on each step of device-free HAR: data acquisition, preprocessing, classification, and evaluation, and identifies gaps and open questions in existing research.
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 | 0.012 | 0.062 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.006 |
| Bibliometrics | 0.027 | 0.020 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".