MétaCan
Menu
Back to cohort

Synthetic Data Generation for Alleviating Class Imbalance with Reinforcement Learning

2025· article· W7125580023 on OpenAlexaff
Ethan Pigou, Lucas Hartman, Nicholas Strzelczyk, Santiago Gomez-Rosero, Miriam A. M. Capretz

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsWestern University
Fundersnot available
KeywordsReinforcement learningClassifier (UML)Synthetic dataActivity recognitionGenerative grammarAdversarial systemClass (philosophy)Training setData modeling

Abstract

fetched live from OpenAlex

Wearable sensors are increasingly used in daily life for applications such as fitness monitoring, rehabilitation, and workplace safety. Human activity recognition (HAR) models play a central role in these systems by classifying movement patterns. Nevertheless, class imbalance reduces model reliability, particularly in health-related contexts. This paper proposes an adaptive reinforcement learning framework for synthetic data generation that operates as a feedback-driven process. In each training episode, the agent generates minority-class samples, a reference classifier evaluates their utility, and the policy is updated based on both the improvement in minority-class performance and the proximity of samples to decision boundaries. Experimental results show that the proposed method improves minority-class F1 scores over random undersampling, random oversampling, and generative adversarial network baselines, particularly in low-separability scenarios where class overlap is significant. These results demonstrate that feedback-based adaptive synthesis effectively addresses imbalance by targeting underrepresented regions in the feature space, leading to fairer and more reliable activity recognition.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation 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: none
Teacher disagreement score0.002
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.008
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.077
GPT teacher head0.306
Teacher spread0.229 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicContext-Aware Activity Recognition SystemsFrench-language works237,207