A Novel DenseNet Framework for Brain Tumor Classification Enhanced by XgBoost and Fire Hawk Optimization
Bibliographic record
Abstract
Nowadays, Brain tumours are the most crucial disease that is spreading rapidly all around the world.According to the statistics, more than a thousand people are losing their lives to this tumour in every country.The early prediction of tumours can help to diagnose and overcome the disease quickly.For an earlier prediction, there are Numerous research techniques like deep learning (DL) and machine learning (ML) models used for feature extraction and classification.In some cases, the hybrid models are also used for feature extraction and classification.However, the accuracy is not attained up to the level of satisfaction for various tumours like Glioma, pituitary, and meningioma.We propose a novel DenseNet architecture incorporating Self-Calibrated Squeeze-and-Excitation (SC-SE) for enhanced feature extraction and representation.The SC-SE DenseNet integrates SC Convolutions (SC-Conv) and SE Blocks within a DenseNet framework.SC-Conv dynamically recalibrates both spatial and channel-wise features, which improves the model's ability to adapt to diverse input variations.SE blocks are used to concentrate important channels for better feature learning.The extracted features from SC-SE DenseNet are classified using the XGBoost classifier.To further optimize performance, the Fire Hawk Optimizer (FHO) is used for feature selection and hyperparameter tuning.FHO aids in selecting the most relevant features from the input image and reduces dimensionality.Additionally, FHO is used to fine-tune the parameters of the XGBoost classifier to increase the classification 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".