Comparison of Parallel and Single Neural Networks in Heart Arrhythmia Detection by Using ECG Signal Analysis
Bibliographic record
Abstract
In this study, we have presented a method for detecting four common arrhythmias by using wavelet analysis along with the neural network algorithms. The method firstly includes the extraction of feature vectors with wavelet analysis. Then, the vectors will be categorized by means of the neural network into four classes. Input signals are recorded from two different leads. In addition, we have used both continuous and discrete wavelet analyses simultaneously for feature extraction. This results into increasing the accuracy of feature vectors extraction. Also, using the continuous wavelet in a specific scale can lead to better extraction of coefficients as well as more accurate data. In order to decrease the computational efforts and increase the training speed, the dimensions of the feature vectors have been reduced by substituting the wavelet coefficients with their statistical parameters. Furthermore, two approaches are introduced in classification of feature vectors. The first approach comprises four neural networks in the parallel form for detection of four classes, while the second approach makes use of one network for four classes. Numerical simulation results show that in comparison with the previous studies, the proposed methods are more accurate and faster. In addition, it is observed that the second approach has better capabilities in classification of data than the first one. On the other hand, the first approach is believed to have a good function for complicated data spaces.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".