We have published three papers in the proceedings of the 1st International Conference on Bioengineering, Biomedical Signal and Image Processing (BIOMESIP), which was held in Gran Canaria (Spain) from July 19 to 21, 2021. A brief summary of each article can be found below:
- Recurrent Neural Networks and Efficiency in High-Dimensional EEG Classification
In this paper, we discuss the suitability of two popular recurrent network variants (GRU and LSTM) in terms of not only classification accuracy but also time and energy consumption. This is done with the particular aim of finding beneficial trade-offs in Electroencephalography (EEG) classification tasks, where datasets often have the disadvantage of being small but high-dimensional. - Performance Study of Ant Colony Optimization for Feature Selection in EEG Classification
Here, we analyze the energy-time performance of different swarm intelligence algorithms. Also, an innovative utilization of the ant colony optimization algorithm for feature selection is proposed with the objective of reducing the high number of features present in electroencephalogram signals. - Energy-time Profiling for Machine Learning Methods to EEG Classification
In this paper, we deal with the classification of electroencephalogram signals through five supervised classifiers, which are analyzed in terms of energy, time, and accuracy with the idea of determining which method offers the best trade-off among all the objectives.