A Multi-Objective Approach Based on Differential Evolution and Deep Learning Algorithms for VANETs
Bibliographic record
Abstract
Intelligent transportation systems (ITS) are becoming more prominent in our society (for example, in smart cities), although a number of challenges remain to be (fully) addressed (e.g., high vehicle mobility). In this paper, we propose a scheme that combines both a cluster algorithm and a Multi-Objective Task Distribution algorithm based on Differential Evolution (MOTD-DE), designed to ensure stability and reliability in vehicular ad-hoc network (VANET) deployments. Specifically, we use Kubernetes container-base as the cluster algorithm to select various vehicles that fulfill the algorithm's conditions. Hence, this allows us to perform complex tasks on behalf of data owner vehicles. In our approach, the vehicles' information will be available on the master vehicle (data owner vehicle) when the vehicle joins the cluster, and a deep learning model is used to define the fit complexity of sub-tasks. The proposed MOTD-DE distributes sub-tasks between vehicle clusters to reduce the execution time and the resources (vehicles) used to perform a task. We also assume the sub-tasks to be independent. To evaluate our work, we propose scenarios with varying number of tasks, vehicles, CPU and memories values, and distances between cluster vehicles and data owner vehicle. A comparative summary of the evaluation findings between MOTD-DE and four other widely used approaches (i.e., Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Ant-Colony algorithm (ACO), and Artificial-Bee-Colony (ABC) algorithm) shows that MOTD-DE outperforms these competing approaches.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| 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 | 0.002 | 0.001 |
| 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".