Intelligent Ice Detection Based on Artificial Neural Network Using Microwave Sensor
Bibliographic record
Abstract
Microwave-based material detection involves vector network analyzer measurements with high frequency sweep points (e.g.,> 1000), which increases the cost of subsequent data processing. When implementing artificial intelligence (AI) on a chip for data processing, a large number of frequency sweep points increases the size of the neural network which adds significant power and area overheads. This work presents a machine learning (ML) model using an artificial neural network architecture for detecting ice, water, and air by only using four frequency points. At the core, the sensing of material and the collection of datasets are based on the response of a microwave SRR sensor. This microwave resonator is designed to operate at 5.1 GHz, enabling the sensing of ice, water, and air based on the permittivity and thickness variations. After the proper selection of four frequency points based on the change of the resonator's characteristics over a narrow frequency range of 4.6 GHz to 5.2 GHz, the ML model is trained and tested using gradient descent with the backpropagation method. The ML model achieves a high inference accuracy of 98.8%. This development based on a microwave resonator sensor and AI-chip provides a practical solution for ice detection applications, where lowering the cost in terms of power consumption and device implementation are the major criteria.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".