Transformer-based deep learning architecture for time series forecasting

Time series forecasting faces challenges due to the non-stationarity, nonlinearity, and chaotic nature of the data. Traditional deep learning models like RNNs, LSTMs, and GRUs process data sequentially but are inefficient for long sequences. To overcome the limitations of these models, we proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. This paper presents user-friendly code for the implementation of the proposed transformer-based deep learning architecture utilizing an attention mechanism for parallel processing. • Proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. • It overcomes the limitations of traditional deep learning models. • User-friendly Python code for the implementation of the proposed transformer-based deep learning architecture.

Authors

Institutions

Publication Details

Journal
Software Impacts
Published
2024-11-01
DOI
https://doi.org/10.1016/j.simpa.2024.100716
Citations
28
Primary Topic
Time Series Analysis and Forecasting
Type
article
Field-Weighted Citation Impact
10.16
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Transformer-based deep learning architecture for time series forecasting

Prasenjit Pal, Samir Barman, G. H. Harish Nayak, N. M. Alam et al.
28 citations
Software Impacts
Time Series Analysis and Forecasting
10.16
article

Transformer-based deep learning architecture for time series forecasting

Prasenjit Pal, Samir Barman, G. H. Harish Nayak, N. M. Alam, Mrinmoy Ray, G. Avinash, Rajeev Ranjan Kumar, Santosha Rathod, Kehar Singh, B. Samuel Naik, Jaiprakash Bisen, Md Wasi Alam
article en
28 citations

Abstract

Time series forecasting faces challenges due to the non-stationarity, nonlinearity, and chaotic nature of the data. Traditional deep learning models like RNNs, LSTMs, and GRUs process data sequentially but are inefficient for long sequences. To overcome the limitations of these models, we proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. This paper presents user-friendly code for the implementation of the proposed transformer-based deep learning architecture utilizing an attention mechanism for parallel processing. • Proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. • It overcomes the limitations of traditional deep learning models. • User-friendly Python code for the implementation of the proposed transformer-based deep learning architecture.

Software ImpactsVol. 22
Indian Agricultural Statistics Research Institute (IN), Indian Grassland and Fodder Research Institute (IN), Indian Institute of Rice Research (IN), University of Agricultural Sciences, Dharwad (IN), National Institute of Occupational Health (IN), Central Research Institute for Jute and Allied Fibres (IN), National Institute of Research on Jute and Allied Fibre Technology (IN), Indian Agricultural Research Institute (IN), Central Agricultural University (IN), Banaras Hindu University (IN)
Openalex Percentile: Top 1%
Time Series Analysis and Forecasting
10.16
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.