Comunidad LaCima · FINESI
LaCimaLaCimaLaboratory of Computing in Research, Methodology and Analytics

Scientific output

Publications

Articles, conference papers and chapters produced by the lab, with an emphasis on indexed journals.

Editorial pipeline
0Submitted · under review
2Accepted · in press
1Published
2026
Accepted · in pressL2Indexed in Scopus

Machine Learning-Based Runtime Prediction and Energy Optimization for HPC Job Scheduling Using the NREL Eagle Supercomputer Dataset

Renato Quispe-Vargas, Dina Maribel Yana-Yucra, Richar Andre Vilca-Solorzano, Vladimiro Ibañez-Quispe, Fred Torres-Cruz

Informatica — An International Journal of Computing and Informatics (Slovenian Society Informatika)

An analysis of 7.3 million completed jobs from the NREL Eagle supercomputer to predict runtimes with machine learning and optimize energy in HPC job scheduling: users consume a median of only 6.7% of their reserved time, and even under realistic temporal evaluation with concept drift, dynamic time-limit adjustment achieves 64.8% weighted energy savings — an estimated 7.25M kWh and 5,141 metric tons of CO2 per year.

Accepted · in pressL2Indexed in Scopus

Physics-Informed Ensemble Learning for Exoplanet Transit Detection: Combining Box Least Squares, Attention-Based CNNs, and Gradient Boosting

Renato Quispe-Vargas, Dina Maribel Yana-Yucra, Richar Andre Vilca-Solorzano, Vladimiro Ibañez-Quispe, Fred Torres-Cruz

Journal of Astrophysics and Astronomy (Springer / Indian Academy of Sciences)

A hybrid, interpretable machine-learning pipeline for detecting exoplanets in Kepler transit photometry: it combines Box Least Squares, an attention-based convolutional network and XGBoost over 15 physics-informed features, reaching a 0.9948 ROC-AUC with interpretability via SHAP and Grad-CAM.

View publication ↗
2025
PublishedL2L4Indexed in Scopus

Comparative Analysis of Statistical, Machine Learning, and Deep Learning Approaches for Frost Prediction in the Peruvian Altiplano

Fred Torres-Cruz, Dina Maribel Yana-Yucra, Richar Andre Vilca-Solorzano

International Journal of Advanced Computer Science and Applications (IJACSA), Vol. 16, N.º 9

A comparative study of statistical, machine learning and deep learning approaches for frost prediction in the Peruvian Altiplano, aimed at early warning systems that protect agricultural production in the Puno region.

View publication ↗