Principal component analysis based feature extraction methods applied to biomedical and communication network data
Bibliographic record
Abstract
This thesis focuses on the development of multi-variate feature extraction methods and their applications to biomedical signals, communication networks and other types of multi-scale data. Three new feature extraction methods are examined. The first is a multi-scale principal component analysis (PCA) method, which combines discrete wavelet transform and PCA for feature extraction of multi-variate signals in both spatial and temporal domains. The second one is a multi-scale wavelet kernels to kernel PCA (KPCA) as a feature extraction method for multi-scale data classification problems. Finally, a modified dynamic PCA method is proposed for feature extraction of long-period univariate time series data in classification and event detection problems. The multi-scale PCA feature extraction method for signal classification is illustrated by applying it to EEG data. This method is also applicable to communication networks data. The feature extraction method via multi-scale wavelet kernels for KPCA is explored using simulated clustered data sets and concentric circle data sets. The feature extraction method via modified dynamic PCA is tested on EEG data to help diagnose epilepsy and to detect onset of epileptic seizures. Additionally, the statistical analysis of communication network data in order to improve quality of service by better understanding the dynamics of number of packets in transit (NPT) is carried out. Our study shows that feature extraction by multi-scale PCA leads to a high classification accuracy for data that appears to be functional in the Fourier feature space. This methodology enables extraction of feature information in both spatial and temporal domains of multi-variate signals. The multi-scale wavelet kernel makes kernel PCA a more robust method for transforming data and enables it to perform well in extracting data features. This methodology is potentially useful for spatial event cluster detection problems. The study of diagnosing epilepsy, of detecting epileptic seizures, and of detecting network load increase suggests that the modified dynamic PCA methodology and its associated detection schemes are very promising in analyzing these type of data because of the low type I error and high value of power of the test statistic.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".