Back to methods browser

First-pass extracted concept

MMCM

Candidate: toolkit itemType: computation method1 source documents2 linked claims
Jump to explainersJump to evidenceJump to sourcesJump to claims
Live refresh every 5sNext refresh in 5s

Aliases

Markov chain and multivariate Gaussian

Extracted Explainers

What the tool is doing

MMCM is a synthetic-data generation approach used to create augmented wastewater-virus datasets from physicochemical, virometry, and PCR-derived measurements. In this study it is used together with DA-LSTM for zero-shot prediction.

Source 1DOIPubMed

Resources required

It requires measured wastewater features including physicochemical parameters, virometry, and PCR-based data.

Source 1DOIPubMed

What problem it solves

It helps provide synthetic training data intended to improve prediction on unseen wastewater matrices affected by process drift.

Source 1DOIPubMed

Alternatives

The abstract lists MCM, GMM, and CM as alternative synthetic-data generators evaluated in the same study.

Source 1DOIPubMed

Evidence Snippets

Efficient data augmentation approaches based on Markov chain (MCM), Markov chain and multivariate Gaussian (MMCM), Gaussian mixture (GMM) and Copula (CM) were proposed to generate synthetic data from physicochemical parameters, virometry, and PCR-based method.
Evidence 1Source 1DOIPubMedprovenance

Supporting Sources

Linked Claims

Claim 1benchmark performancesupports2025Source 1DOIPubMed

DA-LSTM zero-shot generalization using MMCM achieved mean average R2 values of 0.91 in sand wastewater matrices and 0.97 in MBR wastewater matrices in region R1, and 0.97 across the chlorinated effluent treatment process in region R2.

Quoted textsource-backed
The results showed that DA-LSTM zero-shot generalization achieved remarkable viral particles prediction performance using MMCM with a mean average coefficient of determination R2 of 0.91, and 0.97 across the sand, and MBR wastewater matrices in region R1, respectively, and R2 of 0.97 across the chlorinated effluent treatment process in region R2.
Claim 2method capabilitysupports2025Source 1DOIPubMed

DA-LSTM with generative models was proposed to predict viral particles and evaluate removal efficiencies across AeMBRs while handling effluent processing drifts.

Quoted textsource-backed
Dual-attention long short-term memory network (DA-LSTM) with new generative models was proposed to predict viral particles and evaluate the removal efficiencies across AeMBRs, thereby handling effluent processing drifts.