Pendeteksi Mobil Berdasarkan Merek dan Tipe Menggunakan Algoritma YOLO
Bibliographic record
Abstract
The government system in an area or city has regulations in regulating the activities of its residents, especially those related to driving on the highway. Traffic violations often occur on urban roads and highways, this can trigger accidents due to violating traffic regulations. This has prompted the government to take firm measures against motorists who violate regulations. Therefore we need a system that can help monitor traffic conditions. So, the aims this research is create a system that is able to detect car vehicles based on the brand and type with a high level of detection accuracy, so that it can make it easier to recognize car objects around. The detection system will be developed using the YOLO (You Only Look Once) Algorithm, because YOLO is one of the fastest and most accurate methods of object detection and is even capable of exceeding 2 times the capabilities of other algorithms. The YOLO (You Only Look Once) algorithm is an architecture of Deep Learning and an algorithm developed to detect an object in real-time. Detection is carried out on the image, and when accessing a laptop webcam, which contains a car object, uses a model from a dataset that has been trained using the Darknet framework. The detected car object will have a bounding box in the object area, and there will be a description of the car name and type and year of production in the bounding box area. Based on the classification performance test of the data that has been trained, it shows that the accuracy value reaches 92% so it can be concluded that the system can work well.
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 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.018 | 0.008 |
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".