Advancing Signal Processing through Transfer Learning Innovations in Health industry
Bibliographic record
Abstract
Our investigation addresses the critical deficit of high-fidelity electrocardiogram (ECG) datasets essential for detecting cardiac anomalies in advanced medical applications.In cardiology, capturing seismocardiograms (SCG) through sensors like wearable devices and smartphones during daily activities is more practical than obtaining ECGs.To facilitate the transformation of SCG to ECG, we explored advanced signal conversion architectures.Converting SCG to ECG signals is imperative, as ECGs provide a direct and reliable measure of cardiac electrical activity, crucial for accurate detection and diagnosis of cardiac anomalies.Among various models for transforming medical timeseries signals, we selected the Convolutional Neural Networks (CNN) Autoencoder SCG-to-ECG architecture as a target pipeline.We aimed to enhance the efficiency and accuracy of this architecture by incorporating domain adaptation within the framework of transfer learning.Specifically, we utilized supervised learning and unsupervised learning techniques for domain adaptation and employed homogeneous transfer learning to ensure the effective transfer of knowledge between domains.Additionally, we optimized the pretrained model weights through weight pruning, rather than traditional fine-tuning methods.This dual strategy of domain adaptation and weight pruning improves the model's ability to generalize across different datasets while reducing computational complexity and maintaining high diagnostic accuracy.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| 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".