@misc{10481/92001, year = {2023}, month = {9}, url = {https://hdl.handle.net/10481/92001}, abstract = {The growing energy consumption caused by IT is forcing application developers to consider energy efficiency as one of the fundamental design parameters. This parameter acquires great relevance in HPC systems when running artificial neural networks and Machine Learning applications. Thus, this article shows an example of how to estimate and consider energy consumption in a real case of EEG classification. An efficient and distributed implementation of the KNN algorithm that uses mRMR as a feature selection technique to reduce the dimensionality of the dataset is proposed. The performance of three different workload distributions is analyzed to identify which one is more suitable according to the experimental conditions. The proposed approach outperforms the classification results obtained by previous works. It achieves an accuracy rate of 88.8% and a speedup of 74.53 when running on a multi-node heterogeneous cluster, consuming only 13.38% of the energy of the sequential version.}, organization = {Spanish Ministry of Science, Innovation, and Universities under grants PGC2018-098813-B-C31 and PID2022-137461NB-C32}, organization = {ERDF fund}, keywords = {Parallel and distributed programming}, keywords = {Heterogeneous clusters}, keywords = {Energy-aware computing}, keywords = {EEG classification}, keywords = {KNN}, keywords = {mRMR}, title = {Energy-aware KNN for EEG Classification: A Case Study in Heterogeneous Platforms}, doi = {10.1007/978-3-031-43085-5_40}, author = {Escobar Pérez, Juan José and Rodríguez, Francisco and Savran Kiziltepe, Rukiye and Prieto Campos, Beatriz and Kimovski, Dragi and Ortiz, Andrés and Damas Hermoso, Miguel}, }