Multi-level lag scheme significantly improves training efficiency in deep learning: a case study in air quality alert service over sub-tropical area

Benedito Chi Man Tam; Su Kit Tang; Alberto Cardoso

doi:10.1186/s40537-024-01043-z

Multi-level lag scheme significantly improves training efficiency in deep learning: a case study in air quality alert service over sub-tropical area

Benedito Chi Man Tam
, Su Kit Tang
, Alberto Cardoso

Faculty of Applied Sciences

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

Abstract

An adaptively formulated Multi-level Lag Scheme can significantly. Improve the training process efficiently, and can be applied in mostly ANN-type deep learning model, with a practical case of Air Quality Alert Service in a city of sub-tropical area.

Original language	English
Article number	3
Journal	Journal of Big Data
Volume	12
Issue number	1
DOIs	https://doi.org/10.1186/s40537-024-01043-z
Publication status	Published - Dec 2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Air quality forecasting
Deep learning
Multi-level lag scheme
Multivariate

Access to Document

10.1186/s40537-024-01043-z

Cite this

@article{42b261ac980f4aeb9fe30e2cf8bdf482,

title = "Multi-level lag scheme significantly improves training efficiency in deep learning: a case study in air quality alert service over sub-tropical area",

abstract = "An adaptively formulated Multi-level Lag Scheme can significantly. Improve the training process efficiently, and can be applied in mostly ANN-type deep learning model, with a practical case of Air Quality Alert Service in a city of sub-tropical area.",

keywords = "Air quality forecasting, Deep learning, Multi-level lag scheme, Multivariate",

author = "Tam, \{Benedito Chi Man\} and Tang, \{Su Kit\} and Alberto Cardoso",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2025",

month = dec,

doi = "10.1186/s40537-024-01043-z",

language = "English",

volume = "12",

journal = "Journal of Big Data",

issn = "2196-1115",

publisher = "Springer Nature",

number = "1",

}

TY - JOUR

T1 - Multi-level lag scheme significantly improves training efficiency in deep learning

T2 - a case study in air quality alert service over sub-tropical area

AU - Tam, Benedito Chi Man

AU - Tang, Su Kit

AU - Cardoso, Alberto

N1 - Publisher Copyright: © The Author(s) 2024.

PY - 2025/12

Y1 - 2025/12

N2 - An adaptively formulated Multi-level Lag Scheme can significantly. Improve the training process efficiently, and can be applied in mostly ANN-type deep learning model, with a practical case of Air Quality Alert Service in a city of sub-tropical area.

AB - An adaptively formulated Multi-level Lag Scheme can significantly. Improve the training process efficiently, and can be applied in mostly ANN-type deep learning model, with a practical case of Air Quality Alert Service in a city of sub-tropical area.

KW - Air quality forecasting

KW - Deep learning

KW - Multi-level lag scheme

KW - Multivariate

UR - https://www.scopus.com/pages/publications/85214101110

U2 - 10.1186/s40537-024-01043-z

DO - 10.1186/s40537-024-01043-z

M3 - Article

AN - SCOPUS:85214101110

SN - 2196-1115

VL - 12

JO - Journal of Big Data

JF - Journal of Big Data

IS - 1

M1 - 3

ER -

Multi-level lag scheme significantly improves training efficiency in deep learning: a case study in air quality alert service over sub-tropical area

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this