Deep Transfer Learning for Single-Channel Automatic Sleep Staging with\n Channel Mismatch
Bibliographic record
Abstract
Many sleep studies suffer from the problem of insufficient data to fully\nutilize deep neural networks as different labs use different recordings set\nups, leading to the need of training automated algorithms on rather small\ndatabases, whereas large annotated databases are around but cannot be directly\nincluded into these studies for data compensation due to channel mismatch. This\nwork presents a deep transfer learning approach to overcome the channel\nmismatch problem and transfer knowledge from a large dataset to a small cohort\nto study automatic sleep staging with single-channel input. We employ the\nstate-of-the-art SeqSleepNet and train the network in the source domain, i.e.\nthe large dataset. Afterwards, the pretrained network is finetuned in the\ntarget domain, i.e. the small cohort, to complete knowledge transfer. We study\ntwo transfer learning scenarios with slight and heavy channel mismatch between\nthe source and target domains. We also investigate whether, and if so, how\nfinetuning entirely or partially the pretrained network would affect the\nperformance of sleep staging on the target domain. Using the Montreal Archive\nof Sleep Studies (MASS) database consisting of 200 subjects as the source\ndomain and the Sleep-EDF Expanded database consisting of 20 subjects as the\ntarget domain in this study, our experimental results show significant\nperformance improvement on sleep staging achieved with the proposed deep\ntransfer learning approach. Furthermore, these results also reveal the\nessential of finetuning the feature-learning parts of the pretrained network to\nbe able to bypass the channel mismatch problem.\n
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.001 | 0.002 |
| 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".