A Comparative Analysis Employing Adaptive Layers of RCNN Technique and Transfer Learning Pre-Trained Networks
Bibliographic record
Abstract
The study aimed to classify two classes of vehicles, Tuktuk and Motorcycle, using a modified RCNN model.The MAjN_IRAQ Dataset, created from a camera system in Baghdad city, was used for training, detection, and classification of some vehicles to allow them to enter some crowded streets of Baghdad and to prevent others from entering the same streets.New layers were added and the number and size of filters were changed, which led to improve the process of training, detection and classification of vehicles with high accuracy, which leads to improving the proposed model's performance.The results showed that the modified RCNN model performed better when trained for 80 epochs.It improved performance measures such as precision, recall, and F1 score measure.The model was compared to other transfer learning methods (Alex Net, VGG16, and VGG19) and showed superior results for the Tuktuk class.The training and testing time for the proposed RCNNmodified model was also lower compared to the other models.At 80 epochs, the precision for the Tuktuk class was approximately 0.94, while for the Motorcycle class, it was approximately 0.89.The TPR was higher for the Tuktuk class at approximately 0.93, while the lower value was approximately 0.84 for VGG16.When the VGG16 model was used, the F1 score was better in the Motorcycle category (about 0.95) but worse in the Tuktuk category (0.86%).Both the suggested RCNN-modified model and the Alex Net model worked well in a reasonable amount of time.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 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 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".