A Cloud Edge Based Heart Disease Detection Using DenseNet Convoluted Radial Basis Neural Network for Diabetic Patients
Bibliographic record
Abstract
Heart disease (HD) is a complex medical condition that has the potential to affect a vast number of people globally.The quick and precise identification of HD is crucial in healthcare, particularly in the cardiology field.In the pre-processing stage of the data mining process, a high-dimensional database is employed to classify HD.This unprocessed dataset contains redundant and inconsistent data, which expands the search space as well as data storage.Using deep-learning methods, the suggested research tries to recognize significant cardiac complaint prediction properties.This research proposed novel heart disease detection techniques by feature extraction and classification through the DL (Deep Learning) architectures.Data collection of 1 Lakh samples has carried out from Cleveland, UCI open-source repository, which has 74 features with a balanced instance rate.Here the input heart disease data has been pre-processed and segmented for filtering and edge normalization.The input image has been processed based on contrast-based histogram equalization (CHE) and segmented based on a threshold of the image.Then the segmented image was extracted to obtain the in-depth features and classifying the features using DenseNet with a Convoluted radial basis neural network.Several clinical measures are used to measure the risk contour in patients, which aid in early diagnosis.In the proposed model, various regularization methods are applied to avoid overfitting.On the dataset, the suggested model attains 72% sensitivity, 90% recall, 88% F-measure, 94% throughput, 92% training accuracy, and 95% testing accuracy.This is compared to other deep learning (DL) methods using a variety of performance metrics, demonstrating the effectiveness of the proposed approach.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".