Optimizer Comparison for a GoogleNet-Based Tuberculosis Classification Model
Bibliographic record
Abstract
Tuberculosis (TB) continues to pose a significant challenge to global public health, especially in countries with limited healthcare infrastructure.Early identification is key to mitigation; however, the interpretation of microscopic images poses a significant obstacle.This research proposes the use of Deep Learning Models, specifically GoogleNet, for the identification of TB bacteria from microscopic images.The study uses a dataset comprising 1,266 microscopic images to identify TB bacteria.This dataset is then divided into two parts, with 80% of the data used for training (1,012 images) and 20% for testing (254 images).Before being fed into the model, the images are processed using median filter techniques to enhance quality and consistency.This study proposes the use of Deep Learning models, particularly GoogleNet, as a method for detecting TB bacteria in microscopic images.Four optimization algorithms, RMSprop, SGD, Adam, and SGDM, are evaluated and compared to identify the most effective configuration for optimal performance.The experimental findings indicate that the Adam optimizer yields the best results for TB classification.By applying transfer learning techniques, the GoogleNet model is trained and evaluated using standard metrics.The evaluation results demonstrate high accuracy and efficiency in training time.The model achieved excellent accuracy, precision, recall, and F1-Score, each at 98.52%.
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".