Aleksa Bogdanović

Mr. Aleksa Bogdanović

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2026 in AI
Verified
Journal Article
Open access
PDF file
ABAleksa Bogdanović
Aleksa Bogdanović
LVLazar Z. Velimirović
Lazar Z. Velimirović
JVJelena Velimirovic
Jelena Velimirovic
Zoran StajićZoran Stajić
Zoran Stajić
Accurate prediction of multivariate datasets increasingly relies on deep learning models, often increasing complexity and computing requirements, particularly for multi-horizon predictions. This work proposes a model designed to significantly reduce computing requirements while retaining predictive accuracy. By replacing standard convolutions with depthwise and grouped pointwise operations, the model preserves temporal processing and captures dependencies without substantially complicating the architecture. Evaluated on five multivariate datasets across four forecasting horizons, the proposed model is compared against conventional and depthwise Temporal Convolutional Networks; lightweight variants, such as TSMixer and FITS; and advanced models like Informer, Autoformer, and iTransformer. It reduces multiply–accumulate operations by 58.9–70.8% and trainable parameters by 14.15–35.8% compared to standard temporal convolution networks. Notably, forecasting accuracy varies across datasets and horizons, with small differences between TCN variants corresponding to run-to-run variability. The findings reveal that the model excels in accuracy–efficiency trade-offs, offering an alternative for multivariate time-series forecasting when computational cost is a critical consideration.