MétaCan
Menu
Back to cohort
Record W4413248274 · doi:10.1504/ijqet.2024.147893

Harnessing deep learning for quality engineering and technology: innovations in process optimisation, defect detection, and predictive quality control

2024· article· en· W4413248274 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInternational Journal of Quality Engineering and Technology · 2024
Typearticle
Languageen
FieldEngineering
TopicIndustrial Vision Systems and Defect Detection
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsQuality (philosophy)Process (computing)Model predictive controlEngineeringControl (management)Process controlManufacturing engineeringRisk analysis (engineering)Computer scienceArtificial intelligenceBusiness

Abstract

fetched live from OpenAlex

If you are in charge of water sources, you need to be able to guess how streams will flow. We can learn a lot from this study about how well complicated deep learning models can guess when the Gilgit River Basin's water level will be high and low every month. CNN-LSTM, CNN-BiLSTM, CNN-GRU, CNN-BiGRU, LSTM, BiLSTM, and GRU were all employed. Each of the final four is a combination of these. The model did well for our study based on its RMSE, MAE, NSE, and R2 marks. There is a problem. R2 tells you how strong a link is. Simple models like LSTM and GRU did not do as well with that data, but the mix models did a lot better. CNN-BiGRU and CNN-BiLSTM did the best most of the time. It was taught with an R2 of 0.962 and tested with an R2 of 0.929. It got 144.1%, which was good enough for second place. CNN can help you find things in space. Now, things have a better chance of going well.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.419
Threshold uncertainty score0.816

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.016
GPT teacher head0.302
Teacher spread0.286 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it