Localisation basée sur l'information de l'état des canaux (CSI) dans un environnement minier souterrain
Bibliographic record
Abstract
RÉSUMÉ Dans le cadre de notre recherche approfondie au sein des industries minières canadiennes, notre objectif est de renforcer les réseaux de communication souterrains à l'aide de solutions sans fil innovantes, essentielles pour améliorer la productivité et garantir une coordination efficace entre les équipes. Notre étude s'est concentrée sur la précision de localisation des dispositifs mobiles dans les environnements souterrains, grâce à une analyse détaillée de l’état de canal sans fils (CSI). Notre méthodologie s'est développée en deux phases distinctes de collecte de données CSI. La première a impliqué l'utilisation de cartes NIC5300, puis l'adoption de modules ESP32 pour une collecte plus approfondie. Cette approche a permis de couvrir exhaustivement un espace intérieur. Un volet crucial de notre recherche réside dans l'ajustement minutieux des paramètres de canal, visant à optimiser la performance des réseaux de neurones artificiels (ANN) pour la localisation précise des dispositifs mobiles en milieu souterrain. Nous avons évalué rigoureusement différentes configurations de perceptrons multicouches (MLP) et avons utilisé des outils avancés tels que Tensor Flow et Scikit-learn pour déterminer la configuration offrant la meilleure précision de localisation. ABSTRACT In the context of our comprehensive research within the Canadian mining industries, our goal has been to enhance underground communication networks through innovative wireless solutions, crucial for improving productivity and ensuring effective coordination among teams. Our study focused on the accuracy of mobile device localization in subterranean environments, leveraging a detailed analysis of Channel State Information (CSI). Our methodology unfolded in two distinct phases of CSI data collection. Initially, it involved the use of NIC5300 cards, followed by the adoption of ESP32 modules for more in-depth collection. This strategy enabled us to thoroughly cover an indoor space. A critical aspect of our research was the meticulous adjustment of channel parameters to boost the performance of artificial neural networks (ANN) in precisely locating mobile devices underground. We rigorously evaluated various configurations of multilayer perceptrons (MLP) and employed advanced tools such as TensorFlow and Scikit-learn to ascertain which configuration yielded the highest localization accuracy.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".