Agamemnon Krasoulis

Agamemnon Krasoulis


Research Interests

My research interests lie in the intersection of signal processing, machine learning and computational neuroscience. I aim to develop biologically informed tools and techniques to improve the performance of myoelectric prostheses and brain-machine interfaces (BMIs) for motor rehabilitation.

Publications:
2017
  Improved prosthetic hand control with concurrent use of myoelectric and inertial measurements
Krasoulis, A, Kyranou, I, Erden, MS, Nazarpour, K & Vijayakumar, S 2017, 'Improved prosthetic hand control with concurrent use of myoelectric and inertial measurements' Journal of Neuroengineering and Rehabilitation, vol 14, no. 1, 71, pp. 1-14. DOI: 10.1186/s12984-017-0284-4
Myoelectric pattern recognition systems can decode movement intention to drive upper-limb prostheses. Despite recent advances in academic research, the commercial adoption of such systems remains low. This limitation is mainly due to the lack of classification robustness and a simultaneous requirement for a large number of electromyogram (EMG) electrodes. We propose to address these two issues by using a multi-modal approach which combines surface electromyography (sEMG) with inertial measurements (IMs) and an appropriate training data collection paradigm. We demonstrate that this can significantly improve classification performance as compared to conventional techniques exclusively based on sEMG signals.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Krasoulis, Agamemnon, Kyranou, Iris, Erden, Mustapha Suphi, Nazarpour, Kianoush & Vijayakumar, Sethu.
Number of pages: 14
Pages: 1-14
Publication Date: 11 Jul 2017
Publication Information
Category: Article
Journal: Journal of Neuroengineering and Rehabilitation
Volume: 14
Issue number: 1
ISSN: 1743-0003
Original Language: English
DOIs: 10.1186/s12984-017-0284-4
  Use of Regularized Discriminant Analysis Improves Myoelectric Hand Movement Classification
Krasoulis, A, Nazarpour, K & Vijayakumar, S 2017, Use of Regularized Discriminant Analysis Improves Myoelectric Hand Movement Classification. in 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, pp. 395-398. DOI: 10.1109/NER.2017.8008373
Linear discriminant analysis (LDA) is the most commonly used classification method for movement intention decoding from myoelectric signals. In this work, we review the performance of various discriminant analysis variants on the task of hand motion classification. We demonstrate that optimal classification performance is achieved with regularized discriminant analysis (RDA), a method which generalizes various class-conditional Gaussian classifiers, including LDA, quadratic discriminant analysis (QDA), and Gaussian naive Bayes (GNB). The RDA method offers a continuum between these models via tuning two hyper-parameters which control the amount of regularization applied to the estimated covariance matrices. In this study, we performed a systematic classification performance comparison on four datasets. Hand motion was decoded from
myoelectric and inertial data recorded from 60 able-bodied and 12 amputee subjects whilst they performed a range of 40 movements. We found that when the regularization parameters of the RDA classifier were carefully tuned via cross-validation, classification accuracy was statistically higher by a large margin
as compared to any other discriminant analysis method (average improvement of 13.7% over LDA). Importantly, our findings were consistent across the able-bodied and amputee populations. This observation provides supporting evidence that our proposed methodology could improve the performance of pattern recognition-based myoelectric prostheses.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Krasoulis, Agamemnon, Nazarpour, Kianoush & Vijayakumar, Sethu.
Number of pages: 4
Pages: 395-398
Publication Date: 15 Aug 2017
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/NER.2017.8008373
2016
  Real-time classification of multi-modal sensory data for prosthetic hand control
Kyranou, I, Krasoulis, A, Erden, MS, Nazarpour, K & Vijayakumar, S 2016, Real-time classification of multi-modal sensory data for prosthetic hand control. in Biomedical Robotics and Biomechatronics (BioRob), 2016 6th IEEE International Conference on. IEEE, pp. 536-541. DOI: 10.1109/BIOROB.2016.7523681
Recent work on myoelectric prosthetic control has shown that the incorporation of accelerometry information along with surface electromyography (sEMG) has the potential of improving the performance and robustness of a prosthetic device by increasing the classification accuracy. In this study, we investigated whether myoelectric control could further benefit from the use of additional sensory modalities such as gyroscopes and magnetometers. We trained a multi-class linear discriminant analysis (LDA) classifier to discriminate between six hand grip patterns and used predictions to control a robotic prosthetic hand in real-time. We recorded initial training data by using a total number of 12 sEMG sensors, each of which integrated a 9 degree-of-freedom inertial measurement unit (IMU). For classification, four different decoding schemes were used; 1) sEMG and IMU from all sensors 2) sEMG from all sensors, 3) IMU from all sensors and, finally, 4) sEMG and IMU from a nearly optimal subset of sensors. These schemes were evaluated based on offline classification accuracy on the training data, as well as with task-related metrics such as completion rates and times for a pick-and-place real-time experiment. We found that the classifier trained with all the sensory modalities and sensors (condition 1) attained the best decoding performance by achieving a 90.4% completion rate with an average completion time of 41.9 sec in real-time experiments. We also found that classifiers incorporating sEMG and IMU information outperformed on average the ones that only used sEMG signals, even when the amount of sensors used was less than half in the former case. These results suggest that using extra modalities along with sEMG might be more beneficial than including additional sEMG sensors.
General Information
Organisations: School of Informatics.
Authors: Kyranou, I., Krasoulis, A., Erden, M. S., Nazarpour, K. & Vijayakumar, S..
Number of pages: 6
Pages: 536-541
Publication Date: Jul 2016
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/BIOROB.2016.7523681
2015
  Towards Low-Dimensionsal Proportional Myoelectric Control
Krasoulis, A, Nazarpour, K & Vijayakumar, S 2015, Towards Low-Dimensionsal Proportional Myoelectric Control. in Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE. IEEE, pp. 7155 - 7158. DOI: 10.1109/EMBC.2015.7320042
One way of enhancing the dexterity of powered myoelectric prostheses is via proportional and simultaneous control of multiple degrees-of-freedom (DOFs). Recently, it has been demonstrated that the reconstruction of finger movement is feasible by using features of the surface electromyogram (sEMG) signal. In such paradigms, the number of predictors and target variables is usually large, and strong correlations are present in both the input and output domains. Synergistic patterns in the sEMG space have been previously exploited to facilitate kinematics decoding. In this work, we propose a framework for simultaneous input-output dimensionality reduction based on the generalized eigenvalue problem formulation of multiple linear regression (MLR). We demonstrate that the proposed methodology outperforms simultaneous input-output dimensionality reduction based on principal component analysis (PCA), while the prediction accuracy of the full rank regression (FRR) method can be achieved by using only a few relevant dimensions.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Krasoulis, Agamemnon, Nazarpour, Kianoush & Vijayakumar, Sethu.
Number of pages: 4
Pages: 7155 - 7158
Publication Date: 2015
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/EMBC.2015.7320042
  Evaluation of regression methods for the continuous decoding of finger movement from surface EMG and accelerometry
Krasoulis, A, Vijayakumar, S & Nazarpour, K 2015, Evaluation of regression methods for the continuous decoding of finger movement from surface EMG and accelerometry. in Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on. IEEE, pp. 631-634. DOI: 10.1109/NER.2015.7146702
The reconstruction of finger movement activity from surface electromyography (sEMG) has been proposed for the proportional and simultaneous myoelectric control of multiple degrees-of-freedom (DOFs). In this paper, we propose a framework for assessing decoding performance on novel movements, that is movements not included in the training dataset. We then use our proposed framework to compare the performance of linear and kernel ridge regression for the reconstruction of finger movement from sEMG and accelerometry. Our findings provide evidence that, although the performance of the non-linear method is superior for movements seen by the decoder during the training phase, the performance of the two algorithms is comparable when generalizing to novel movements.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Krasoulis, Agamemnon, Vijayakumar, Sethu & Nazarpour, Kianoush.
Number of pages: 4
Pages: 631-634
Publication Date: 1 Apr 2015
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/NER.2015.7146702
2014
  Generalizability of EMG decoding using local field potentials
Krasoulis, A, Hall, TM, Vijayakumar, S, Jackson, A & Nazarpour, K 2014, Generalizability of EMG decoding using local field potentials. in Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE. IEEE, pp. 1630-1633, Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE , Chicago, IL, United States, 26-30 August. DOI: 10.1109/EMBC.2014.6943917
Motor cortical local field potentials (LFPs) have been successfully used to decode both kinematics and kinetics of arm movement. For future clinically viable prostheses, however, brain activity decoders will have to generalize well under a wide spectrum of behavioral conditions. This property has not yet been demonstrated clearly. Here, we provide evidence for the first time, that an LFP-based electromyogram (EMG) decoder can generalize reasonably well across two different types of behavior. We implanted intracortical microelectrode arrays in the primary motor (M1) and ventral pre-motor (PMv) cortices of a rhesus macaque, and recorded LFP and EMG activity from arm and hand muscles of the contralateral forelimb during a two-dimensional (2-D) centre-out isometric wrist torque task (TT), and during free reach and grasp behavior (FB). Selected temporal and spectral features of the LFP signals were used to train EMG decoders using data from both types of behavior separately. We assessed the decoding performance for both within- and across-task cases. The average achieved generalization score was 65 ± 20%, while in many cases individual scores reached 100%.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Krasoulis, A., Hall, T.M., Vijayakumar, S., Jackson, A. & Nazarpour, K..
Keywords: (biomechanics, biomedical electrodes, brain, decoding, electromyography, feature extraction, feature selection, generalisation (artificial intelligence), kinematics, learning (artificial intelligence), medical signal processing, microelectrodes, neurophysiology, prosthetics, sensor arrays, signal classification, spectral analysis, EMG activity recording, EMG decoder training, EMG decoding generalizability, LFP recording, LFP signal feature selection, LFP-based electromyogram decoder, across-task cases, arm movement kinematic decoding, arm movement kinetic decoding, arm muscles, average generalization score, behavioral conditions, brain activity decoders, contralateral forelimb, decoding performance assessment, free reach behavior, grasp behavior, hand muscles, intracortical microelectrode array implantation, local field potentials, motor cortical LFP, prosthesis, rhesus macaque primary motor cortices, rhesus macaque ventral premotor cortices, spectral feature selection, temporal feature selection, two-dimensional centre-out isometric wrist torque task, within-task cases, Decoding, Educational institutions, Electromyography, Kinematics, Muscles, Neuroscience, Wrist. )
Number of pages: 4
Pages: 1630-1633
Publication Date: 1 Aug 2014
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/EMBC.2014.6943917

Current CV

Projects:
Sparse signal processing for neural motor interfaces (PhD)