In this paper, a hybrid-domain deep learning (DL)-based neural system is proposed to decode hand movement preparation phases from electroencephalographic (EEG) recordings. The system exploits information extracted from the temporal-domain and time-frequency-domain, as part of a hybrid strategy, to discriminate the temporal windows (i.e. EEG epochs) preceding hand sub-movements (open/close) and the resting state. To this end, for each EEG epoch, the associated cortical source signals in the motor cortex and the corresponding time-frequency (TF) maps are estimated via beamforming and Continuous Wavelet Transform (CWT), respectively. Two Convolutional Neural Networks (CNNs) are designed: specifically, the first CNN is trained over a dataset of temporal (T) data (i.e. EEG sources), and is referred to as T-CNN; the second CNN is trained over a dataset of TF data (i.e. TF-maps of EEG sources), and is referred to as TF-CNN. Two sets of features denoted as T-features and TF-features, extracted from T-CNN and TF-CNN, respectively, are concatenated in a single features vector (denoted as TTF-features vector) which is used as input to a standard multi-layer perceptron for classification purposes. Experimental results show a significant performance improvement of our proposed hybrid-domain DL approach as compared to temporal-only and time-frequency-only-based benchmark approaches, achieving an average accuracy of 76.21±3.77%.
I am happy and proud to announce that Cosimo Ieracitano, Ph.D., Carlo Morabito and me (Nadia Mammone) all from DICEAM Department, Università degli Studi Mediterranea di Reggio Calabria, Italy, together with our colleague Amir Hussain, Edinburgh Napier University, UK, have been awarded the prestigious "Hojjat Adeli Award for Outstanding Contributions in Neural Systems" (2022 edition), for our contribution to the advancement of Artificial Intelligence techniques in Brain-Computer Interface systems.
Our research, reported in the paper “A hybrid-domain deep learning-based BCI for discriminating hand motion planning from EEG sources ", was published in 2021 by the International Journal of Neural Systems (IJNS, IF 6.4), one of the most relevant journals in the field of neural systems (10th out of 133 worldwide journals in the field of computer science).
The "Hojjat Adeli Award for Outstanding Contributions in Neural Systems", established by World Scientific Publishing in 2010, is awarded annually to the most innovative scientific research published in the previous year.
Awarded for the first time to Italian scientists, winners of the past editions are from prestigious universities such as MIT Boston (USA), Stanford University (USA), ETH Zurich (Switzerland), University of Cambridge (USA), University of Oxfort (UK) and Columbia University (USA).
The prize is awarded by the journal's editorial board, which includes top scientists such as Stephen Grossberg, Shun-Ichi Amari, Bernard Widrow, Terry Sejnowski, Witold Pedrycz, Janusz Kacprzyk, as well as the founder and Editor-in-Chief Hojjat H. Adeli.
The "Hojjat Adeli Award for Outstanding Contributions in Neural Systems" is an extraordinary achievement which confirms that the scientific research carried out at the NeuroLab and AI_Lab Laboratories of the DICEAM Department of the Mediterranean University of Reggio Calabria is renowned at the world highest levels.
Nadia Mammone