UAV Navigation Using Modified Neural Networks
Bibliographic record
Abstract
With the development of modern communications systems, and the increased need for effective air defense and surveillance systems to improve tracking, command and guidance systems for unmanned aerial vehicles (UAVs), the need to improve and develop aerial monitoring devices to assist in the process of detecting moving targets with high accuracy and efficiency has increased.Since air surveillance systems and radars require human monitoring, they remain subject to error and inaccuracy.As a result of relying on this human factor, aircraft surveillance and navigation systems cannot be completely relied on human effort as their performance varies depending on the efficiency of the operators.In this study, an air surveillance system for navigation and radar devices was proposed that works with smart technologies to detect moving targets and control air navigation.Artificial neural networks (ANNs) and conventional neural network (CNN) technologies are used to automatically identify and classify moving targets in the navigation system.The data of the moving object through reflected signals and radar images is fed into the training module of the Artificial Intelligence (AI) system, which is an algorithm to plot and track the path of the moving object based on the reflected radar signals.The accuracy of the results of the AI system depends on the accuracy of the radar signals reflected from the moving object to represent the data output to the ANN.Simulation results showed that intelligent navigation can accurately identify various targets and chart their path with high efficiency.Through the results obtained by implementing AI algorithms, it is possible to control air navigation by following and detecting moving targets.The simulation results of the CNNs technology showed a high efficiency in controlling and tracking targets, reaching 97%, with robust implementation for moving target detection and tracking simulation using efficient deep learning FRCNN algorithm updated by applying MATLAB and tested on a set of data for images of various moving UAVs.Also, the results of several tests showed the success of the applied algorithm design in identifying and detecting moving targets at small error rate of 0.01 with a good training speed for the tested data set of 12 seconds.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".