Ant Colony Optimization‐Based Deep Ensemble Learning Model for Improved Gastrointestinal Disease Detection
Bibliographic record
Abstract
ABSTRACT Gastrointestinal (GI) disorders represent a significant challenge in healthcare, underscoring the necessity for more precise and effective diagnostic techniques. Conventional approaches, which often rely on single models, have demonstrated shortcomings in both accuracy and efficacy, often failing to detect the intricate and varied patterns linked to these diseases. To overcome these challenges, this study introduces a novel ensemble learning framework tailored for GI detection. The framework utilizes a three‐layer architectural approach that integrates Convolutional Neural Networks (CNNs), the Ant Colony Optimization Algorithm (ACO), and Weighted Aggregation Ensemble Techniques (WAET). The methodology unfolds in three key stages: First, multiple CNNs are fine‐tuned using transfer learning, while ACO optimizes the hyperparameters of each CNN to enhance model adaptability and performance. Second, the predictions from the top three optimized models are combined using WAET to strengthen the system's robustness in GI detection. Lastly, ACO is employed to optimize the weight assignment for each model during the ensembling process. We use a dataset of 6000 endoscopy images, enhanced by cropping and augmentation techniques to boost diversity and improve classification performance. Additional experiments on CP‐Child‐A and CP‐Child‐B show that the proposed ensemble model achieves superior performance, with an accuracy of 99.88% on the primary dataset and 98.75% and 100% on CP‐Child‐A and B, respectively. It outperforms traditional hybrid methods and state‐of‐the‐art approaches. The effectiveness of the model is further validated through interpretability techniques like Grad‐CAM and SHAP, providing insights into the decision‐making process. This approach enhances diagnostic accuracy and provides a robust, interpretable solution for automated detection of GI diseases, improving clinical decision‐making.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".