Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
FANTF: Fuzzy attention network based transformers for time series analysis
Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
Techno Int New Town, India.
2026 (English)In: Information Sciences, ISSN 0020-0255, E-ISSN 1872-6291, Vol. 757, article id 123893Article in journal (Refereed) Published
Abstract [en]

This paper introduces Fuzzy Attention Network-Based Transformer (FANTF), an approach for time series forecasting, classification, and anomaly detection. FANTF combines fuzzy logic concepts with transformer architectures through a novel fuzzy attention mechanism. The proposed mecha nism is inspired by Type-2 fuzzy set theory. It uses a learnable Gaussian uncertainty perturbation to model uncertainty in attention relevance scores. This makes it possible for the model to accu rately capture uncertainty in temporal relationships better than normal deterministic attention. Transformers' capacity to record complex temporal patterns and multivariate connections is en hanced by FANTF. The approach is both architecture-agnostic and task-agnostic. The proposed fuzzy attention module can be used as a direct replacement for the standard attention layer. To evaluate its effectiveness, FANTF is integrated into five transformer backbones: Transformer, Informer, PatchTST, Crossformer, and iTransformer. The fuzzy attention mechanism produces softer and more diverse attention distributions. It provides uncertainty-aware interpretations through attention heatmap visualizations. Experimental evaluations on some real-life datasets re veal that FANTF enhances the forecasting performance, classification, and anomaly detection tasks over traditional transformer-based models. FANTF achieves statistically significant and compet itive performance improvements over standard transformer-based baselines on most benchmark datasets (p < 0.05, Wilcoxon signed-rank test), observed under noisy and non-stationary time series conditions.

Place, publisher, year, edition, pages
ELSEVIER SCIENCE INC , 2026. Vol. 757, article id 123893
Keywords [en]
Time series forecasting; Time series classification; Time series anomaly detection; Transformers; Fuzzy attention networks
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-226513DOI: 10.1016/j.ins.2026.123893ISI: 001827004700002Scopus ID: 2-s2.0-105044605012OAI: oai:DiVA.org:liu-226513DiVA, id: diva2:2091595
Available from: 2026-08-12 Created: 2026-08-12 Last updated: 2026-08-12

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Chakraborty, Sanjay
By organisation
Artificial Intelligence and Integrated Computer SystemsFaculty of Science & Engineering
In the same journal
Information Sciences
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 6 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf