Tiny-RFNet: Enabling Modulation Classification of Radio Signals on Edge Systems
Bibliographic record
Abstract
Automatic Modulation Classification (AMC) is a key task to identify the type of modulation used to Radio Frequency (RF) communications. Conventional AMC methods are often computationally expensive and inaccurate making them not applicable for Edge systems. In this paper, we propose Tiny-RFNet, a novel deep learning model that achieves high performance and low resource consumption for AMC. Tiny-RFNet takes advantage of a novel multi-scale convolutional layer to extract robust features at different resolutions. The proposed network features the concept of Separable Convolution Blocks (SCB) to adjust the network complexity as needed. For further optimization for Edge, we implement different variants of Tiny-RFNet on Jetson Orin Nano as a representative of high performance edge devices. Obtained hardware results show that Tiny-RFNet fits resources available on Jetson Orin Nano i.e., enabling AMC at the Edge. Moreover, we investigate Tiny-RFNet’s data efficiency and the impact of network depth on its accuracy, confirming that the different variants of Tiny-RFNet are data-efficient
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 | 0.000 | 0.001 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".