Parallel and GPU-Based Optimization of XGBoost and Neural Networks for Effective Landmine Classification
Bibliographic record
Abstract
The problem of mine clearance in both open and closed areas remains highly relevant in the modern world, especially in the context of military conflicts, humanitarian crises, and post-war reconstruction processes.Traditional mine detection methods require significant human and technical resources, making the demining process costly, time-consuming, and potentially dangerous for operators.Therefore, there is a need to develop automated systems capable of ensuring high accuracy, efficiency, and speed in identifying explosive objects, thereby enhancing the safety of those conducting the operations.Existing landmine classification methods face limitations in speed, scalability, and deployment feasibility due to computational constraints and lack of optimization.This paper presents a mine classification method based on a combination of neural networks and gradient boosting, aimed at improving the accuracy and speed of the recognition process.Two main optimization strategies are proposed: (1) data-driven and algorithmic parallelization, which improve training speed and computational efficiency; and (2) GPU-accelerated model training to leverage parallel processing capabilities.A series of experiments were conducted, and the results confirmed the effectiveness of the proposed methods.For open environments, the classification accuracy reached 94.32% for gradient boosting and 93.89% for neural networks, while for closed environments, the accuracy was 93.25% and 92.75%, respectively.The optimization allowed for a fivefold increase in model training speed due to parallel computations and GPU data processing, making the proposed method suitable for real-world applications.An analysis of the results indicates the potential of this approach not only for further improvement of automated mine clearance systems but also for solving other classification and object identification tasks in complex environments.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".