Understanding the Impact of Machine Learning Models on the Performance of Different Flexible Strain Sensor Modalities
Bibliographic record
Abstract
Fibre strain sensors commonly use three major modalities to transduce strain—piezoresistance, capacitance, and inductance. The electrical signal in response to strain differs between these sensing technologies, having varying sensitivity, maximum measurable loading rate, and susceptibility to deleterious effects like hysteresis and drift. The wide variety of sensor materials and strain tracking applications makes it difficult to choose the best sensor modality for a wearable device when considering signal quality, cost, and difficulty of manufacture. Fibre strain sensor samples employing the three sensing mechanisms are fabricated and subjected to strain using a tensile tester. Their mechanical and electrical properties are measured in response to strain profiles designed to exhibit particular shortcomings of sensor behaviour. Using these data, the sensors are compared to identify materials and sensing technologies well suited for different textile motion tracking applications. Several regression models are trained and validated on random strain pattern data, providing guidance for pairing each sensor with a model architecture that compensates for non-ideal effects. A thermoplastic elastomer-core piezoresistive sensor had the highest sensitivity (average gauge factor: 12.6) and a piezoresistive sensor of similar construction with a polyether urethane-urea core had the largest bandwidth, capable of resolving strain rates above 300% s−1 with 36% signal amplitude attenuation. However, both piezoresistve sensors suffered from larger hysteresis and drift than a coaxial polymer sensor using the capacitive strain sensing mechanism. Machine learning improved the piezoresistive sensors’ root-mean-squared error when tracking a random strain signal by up to 58% while maintaining their high sensitivity, bandwidth, and ease of interfacing electronically.
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 | 0.008 | 0.029 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".