Intelligent Beamforming for UAV-Assisted IIoT Based on Hypergraph Inspired Explainable Deep Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The development of industry is inseparable from the development of Industrial Internet of Things (IIoT), however, the limitations of previous wireless technologies can greatly affect the performance of all aspects of IIoT. With the continuous development of artificial intelligence (AI), deep learning enabled intelligent communication has been widely studied towards B5G and 6G. While, most existing neural networks for the current research often have poor performances on scalability and universality issues. In this paper, an unsupervised learning framework is introduced with mixed interference based graph neural network (MIGNN), to solve the distributed beamforming problem in unmanned aerial vehicle (UAV) assisted IIoT, including both machine to machine (M2M) and UAVs. Firstly, we constructed the system model of heterogeneous network and considered the beamforming of all the air-to-ground (A2G) and industrial M2M links with mutual co-channel interferences. Secondly, we formulated the resource allocation problem with a heterogeneous graph structure, to describe the relationships of different links and the interference among UAV assisted IIoT. Then, a MIGNN model is proposed and the hypergraph idea is integrated to compensate for the traditional graphs caused information loss. Furthermore, an unsupervised learning method is proposed to train the hyper-MIGNN for achieve the optimal beamforming results. At last, numerical simulations are conducted for both the proposed method and the traditional ones on beamforming performances and efficiencies. From the experimental results, it can be verified that comparisons with traditional deep learning methods, the proposed one has stronger scalability. Moreover, the hyper-MIGNN gets rid of the application limitations of traditional graph neural network (GNN) for just homogeneous networks.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it