Ramana Vinjamuri | Stevens Institute of Technology (original) (raw)

Papers by Ramana Vinjamuri

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

This paper outlines the construction, current state, and future goals of HERCULES, a three degree... more This paper outlines the construction, current state, and future goals of HERCULES, a three degree-of-freedom (DoF) pneumatically actuated exoskeleton for stroke rehabilitation. The exoskeleton arm is capable of joint-angle control at the elbow in flexion and extension, at the shoulder in flexion and extension, and at the shoulder in abduction and adduction. In the near future we plan to embed kinematic synergies into the control system architecture of this arm to gain dexterous and near-natural movements.Clinical Relevance— This device can be used as an upper limb rehabilitation testbed for individuals with complete or partial upper limb paralysis. In the future, this system can be used to train individuals on synergy-based rehabilitation protocols.

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

Post-stroke rehabilitation, occupational and physical therapy, and training for use of assistive ... more Post-stroke rehabilitation, occupational and physical therapy, and training for use of assistive prosthetics leverages our current understanding of bilateral motor control to better train individuals. In this study, we examine upper limb lateralization and model transference using a bimanual joystick cursor task with orthogonal controls. Two groups of healthy subjects are recruited into a 2-session study spaced seven days apart. One group uses their left and right hands to control cursor position and rotation respectively, while the other uses their right and left hands. The groups switch control methods in the second session, and a rotational perturbation is applied to the positional controls in the latter half of each session. We find agreement with current lateralization theories when comparing robustness to feedforward perturbations in feedback and feedforward measures. We find no evidence of a transferable model after seven days, and evidence that the brain does not synchronize...

To meet the growing need of robust and secure identity verification systems, a new biometric base... more To meet the growing need of robust and secure identity verification systems, a new biometric based on neural representations of synergistic hand grasps is proposed here. In this preliminary study five subjects were asked to perform six synergistic hand grasps that are shared most often in common activities of daily living. Their scalp electroencephalographic (EEG) signals were analyzed using 20 scalp electrodes. In our previous work, we found that hand kinematics of these synergistic grasps showed potential as a biometric. In the current work, we asked if the neural representations of these synergistic grasps can provide a unique signature to be a biometric. The results show that across 300 entries, the system, in its best configuration, achieved an accuracy of 92.2% and an EER of ~4.7% when tasked with identifying these five individuals. The implications of these preliminary results and applications in the near future are discussed. We believe that this study could lead to the deve...

SpringerBriefs in Electrical and Computer Engineering

Rationale: The human central nervous system (CNS) effortlessly performs complex hand movements wi... more Rationale: The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom (DoF), but how those mechanisms are encoded in the CNS remains unclear. In order to investigate the neural representations of human upper limb movement, scalp electroencephalography (EEG) was recorded to decode cortical activity in reaching and grasping movements. Methods: Upper limb movements including arm reaching and hand grasping tasks were observed in this study. EEG signals of 15 healthy individuals were recorded (g.USBamp, g.tec, Austria) when performing reaching and grasping tasks. Spectral features of the relevant cortical activities were extracted from EEG signals to decode the relevant reaching direction and hand grasping information. Upper limb motion direction and hand kinematics were captured with sensors worn on the hands. Directional EEG features were classified using stacked autoencoders; hand kinematic synergies were reconstructed to model the relationship of hand movement and EEG activities. Results: An average classification accuracy of three-direction reaching tasks achieved 79 ± 5.5% (best up to 88 ± 6%). As for hand grasp decoding, results showed that EEG features were able to successfully decode synergy-based movements with an average decoding accuracy of 80.1 ± 6.1% (best up to 93.4 ± 2.3%). Conclusion: Upper limb movements, including directional arm reaching and hand grasping expressed as weighted linear combinations of synergies, were decoded successfully using EEG. The proposed decoding and control mechanisms might simplify the complexity of high dimensional motor control and might hold promise toward real-time neural control of synergy-based prostheses and exoskeletons in the near future.

Biomimetic Prosthetics, Feb 14, 2018

IEEE Transactions on Biomedical Circuits and Systems

Soft hand exoskeletons offer a lightweight, low-profile alternative to rigid rehabilitative robot... more Soft hand exoskeletons offer a lightweight, low-profile alternative to rigid rehabilitative robotic systems, enabling their use to restore activities of daily living (ADL) in those with hand paresis due to stroke or other conditions. The hand exoskeleton with embedded synergies (HEXOES) is a soft cable-driven hand exoskeleton capable of independently actuating and sensing 10 degrees of freedom (DoF) of the hand. Control of the 10 DoF exoskeleton is dimensionally reduced using three manually defined synergies in software corresponding to thumb, index, and 3-finger flexion and extension. In this paper, five healthy subjects control HEXOES using a neural network which decodes synergy weights from contralateral electromyography (EMG) activity. The three synergies are manipulated in real time to grasp and lift 15 ADL objects of various sizes and weights. The neural network's training and validation mean squared error, object grasp time, and grasp success rate were measured for five healthy subjects. The final training error of the neural network was 4.8 ± 1.8% averaged across subjects and tasks, with 8.3 ± 3.4% validation error. The time to reach, grasp, and lift an object was 11.15 ± 4.35 s on average, with an average success rate of 66.7% across all objects. The complete system demonstrates real time use of biosignals and machine learning to allow subjects to operate kinematic synergies to grasp objects using a wearable hand exoskeleton. Future work and applications are further discussed, including possible design improvements and enrollment of individuals with stroke.

IEEE Access

Recent advances in assistive hand devices have produced high degree of freedom systems which are ... more Recent advances in assistive hand devices have produced high degree of freedom systems which are capable of complex grasping, however user-friendly control of these sophisticated devices is still an open topic in research. Synergy-based controllers which dimensionally reduced the control problem were present in the literature, however they used spatial/postural synergies which are static over time. In this paper, we proposed the first control system based on spatiotemporal synergies which is scalable to any number of degrees of freedom, any number of synergies, and any duration of synergy. The controller was tested on prior data in which ten subjects performed 50 object grasps and 36 American Sign Language letters and numbers. The tuned response of the controller, the-norm reconstruction error, and the simulation error were all reported in detail. The angular error between the simulated model and recorded states decayed rapidly from 23.1±19.98% with the first synergy to 6.18±8.75% for synergies 1 to 6 and 2.29±3.35% for synergies 1 to 10 and was statistically similar to the reconstruction error of the angular trajectories. Minor improvements in performance were observed when using higher-order synergies, implying a tradeoff between accuracy and control complexity. The data shown here can be used to select the number of synergies to use in control based on the accuracy of the controller and the accuracy of the controlled robotic system. The resulting system achieved high grasping dexterity with minimal computational or manual effort for assistive devices.

IEEE Access

The human central nervous system (CNS) effortlessly performs complex hand movements with the cont... more The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom (DoF). It is hypothesized that the CNS might use kinematic synergies to reduce the complexity of movements, but how these kinematic synergies are encoded in the CNS remains unclear. In order to investigate the neural representations of kinematic synergies, scalp electroencephalographic (EEG) signals and hand kinematics were recorded from 10 subjects during six representative types of hand grasping. Kinematic synergies were obtained from recorded hand kinematics using singular value decomposition. The recorded kinematics were then reconstructed using weighted linear combinations of synergies and optimal weights were computed using optimal linear estimation. Using EEG spectral powers as neural features, a multivariate linear regression model was trained on the weights of the kinematic synergies. Using this model, kinematics from the testing subset of data were decoded from EEG features with 3-fold cross validation. Results show that the weights of kinematic synergies used in a particular movement reconstruction were strongly correlated to EEG features obtained from that movement. EEG features were able to successfully decode synergy-based movements with an average decoding accuracy of 80.1±6.1% (best up to 93.4±2.3%). These results have promising applications in noninvasive neural control of synergy-based prostheses and exoskeletons.

IEEE Access

Electroencephalography (EEG)-based brain-computer interfaces (BCIs) that decode cortical activity... more Electroencephalography (EEG)-based brain-computer interfaces (BCIs) that decode cortical activity in reaching and grasping movements can enable natural upper limb motor control. In this paper, we studied the performance of stacked autoencoders in decoding asynchronous reaching movements in the dominant upper limb using EEG. Five individuals without any motor disabilities performed three self-paced reaching tasks while the endpoints of the arm movements were recorded with a motion tracker. Power spectral densities of the relevant cortical signals were extracted among eight bandwidths in the range of 1-45Hz to train a stacked autoencoder. For comparison, convolutional neural network (CNN) and traditional linear decoding using principal component analysis (PCA) for feature selection and linear discriminant analysis (LDA) for classification were also used. An average classification accuracy of 79±5.5% (best up to 88±6%) was achieved from all subjects on wide frequency band (1-45Hz) in offline analysis with stacked autoencoders while average classification accuracies of 68±9.1% (best up to 74±9.1%) with PCA-LDA and 49±13.8% (best up to 56±7.2%) with CNN were achieved. The simultaneous dimensionality reduction and feature extraction capabilities of stacked autoencoders can have significant advantages in BCI applications. INDEX TERMS Electroencephalography, arm reaching movement, stacked autoencoders, machine learning, deep learning, classification, principal component analysis, linear discriminant analysis.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, Aug 1, 2016

The complex prevalence of Parkinson's disease (PD) symptoms has pushed research towards asses... more The complex prevalence of Parkinson's disease (PD) symptoms has pushed research towards assessment tools that can assist in their quantification. There remains a need for a system capable of measuring symptoms during various tasks at multiple motor levels (kinematics and electromyography). In this paper, we present the development and initial validation of a quantitative assessment tool for Parkinson's disease (QAPD), a system designed to assist researchers and clinicians in the study of PD. The system integrates motion tracking, data gloves, and electromyography to collect movement related data from multiple body parts. As part of the system, a custom MATLAB® based toolbox has been designed to quantify bradykinesia, tremor, micrographia, and muscle rigidity using both standard and contemporary data analysis techniques. We believe this system can be a useful assessment tool to assist clinicians and researchers in diagnosing and estimating movement dysfunction in individuals ...

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, Jul 1, 2017

Numerous hand exoskeletons have been proposed in the literature with the aim of assisting or reha... more Numerous hand exoskeletons have been proposed in the literature with the aim of assisting or rehabilitating victims of stroke, brain/spinal cord injury, or other causes of hand paralysis. In this paper a new 3D printed soft hand exoskeleton, HEXOES (Hand Exoskeleton with Embedded Synergies), is introduced and mechanically characterized. Metacarpophalangeal (MCP) and proximal interphalangeal/interphalangeal (PIP/IP) joints had measured maximum flexion angles of 53.7 ± 16.9° and 39.9 ± 13.4°, respectively; and maximum MCP and PIP angular velocities of 94.5 ± 41.9 degrees/s and 74.6 ± 67.3 degrees/s, respectively. These estimates indicate that the mechanical design has range of motion and angular velocity characteristics that meet the requirements for synergy-based control. When coupled with the proposed control loop, HEXOES can be used in the future as a test-bed for synergy-based clinical hand rehabilitation.

Frontiers in Bioengineering and Biotechnology

Kinematic and neuromuscular synergies have been found in numerous aspects of human motion. This s... more Kinematic and neuromuscular synergies have been found in numerous aspects of human motion. This study aims to determine how effectively kinematic synergies in bilateral upper arm movements can be used to replicate complex activities of daily living (ADL) tasks using a sparse optimization algorithm. Ten right-handed subjects executed 18 rapid and 11 natural-paced ADL tasks requiring bimanual coordination while sitting at a table. A position tracking system was used to track the subjects' arms in space, and angular velocities over time for shoulder abduction, shoulder flexion, shoulder internal rotation, and elbow flexion for each arm were computed. Principal component analysis (PCA) was used to generate kinematic synergies from the rapid-paced task set for each subject. The first three synergies accounted for 80.3 ± 3.8% of variance, while the first eight accounted for 94.8 ± 0.85%. The first and second synergies appeared to encode symmetric reaching motions which were highly correlated across subjects. The first three synergies were correlated between left and right arms within subjects, whereas synergies four through eight were not, indicating asymmetries between left and right arms in only the higher order synergies. The synergies were then used to reconstruct each natural-paced task using the l 1-norm minimization algorithm. Temporal dilations of the synergies were introduced in order to model the temporal scaling of movement patterns achieved by the cerebellum and basal ganglia as reported previously in the literature. Reconstruction error was reduced by introducing synergy dilations, and cumulative recruitment of several synergies was significantly reduced in the first 10% of training task time by introducing temporal dilations. The outcomes of this work could open new scenarios for the applications of postural synergies to the control of robotic systems, with potential applications in rehabilitation. These synergies not only help in providing near-natural control but also provide simplified strategies for design and control of artificial limbs. Potential applications of these bilateral synergies were discussed and future directions were proposed.

IEEE Access

Biometric systems can identify individuals based on their unique characteristics. A new biometric... more Biometric systems can identify individuals based on their unique characteristics. A new biometric based on hand synergies and their neural representations is proposed here. In this paper, ten subjects were asked to perform six hand grasps that are shared by most common activities of daily living. Their scalp electroencephalographic (EEG) signals were recorded using 32 scalp electrodes, of which 18 task-relevant electrodes were used in feature extraction. In our previous work, we found that hand kinematic synergies, or movement primitives, can be a potential biometric. In this paper, we combined the hand kinematic synergies and their neural representations to provide a unique signature for an individual as a biometric. Neural representations of hand synergies were encoded in spectral coherence of optimal EEG electrodes in the motor and parietal areas. An equal error rate of 7.5% was obtained at the system's best configuration. Also, it was observed that the best performance was obtained when movement specific EEG signals in gamma frequencies (30-50Hz) were used as features. The implications of these first results, improvements, and their applications in the near future are discussed. INDEX TERMS Biometrics, hand kinematics, movement primitives, hand synergies, neural representations, electroencephalography (EEG), coherence.

Frontiers in Bioengineering and Biotechnology

Recently, the need for more secure identity verification systems has driven researchers to explor... more Recently, the need for more secure identity verification systems has driven researchers to explore other sources of biometrics. This includes iris patterns, palm print, hand geo metry, facial recognition, and movement patterns (hand motion, gait, and eye movements). Identity verification systems may benefit from the complexity of human movement that integrates multiple levels of control (neural, muscular, and kinematic). Using principal component analysis, we extracted spatiotemporal hand synergies (movement synergies) from an object grasping dataset to explore their use as a potential biometric. These movement synergies are in the form of joint angular velocity profiles of 10 joints. We explored the effect of joint type, digit, number of objects, and grasp type. In its best configuration, movement synergies achieved an equal error rate of 8.19%. While movement synergies can be integrated into an identity verification system with motion capture ability, we also explored a camera-ready version of hand synergies-postural synergies. In this proof of concept system, postural synergies performed well, but only when specific postures were chosen. Based on these results, hand synergies show promise as a potential biometric that can be combined with other hand-based biometrics for improved security.

Frontiers in bioengineering and biotechnology, 2017

Traditionally, repetitive practice of a task is used to learn a new skill, exhibiting as immediat... more Traditionally, repetitive practice of a task is used to learn a new skill, exhibiting as immediately improved performance. Research suggests, however, that a more experience-based rather than exposure-based training protocol may allow for better transference of the skill to related tasks. In synergy-based motor control theory, fundamental motor skills, such as hand grasping, are represented with a synergy subspace that captures essential motor patterns. In this study, we propose that motor-skill learning through synergy-based mechanisms may provide advantages over traditional task repetition learning. A new task was designed to highlight the range of motion and dexterity of the human hand. Two separate training strategies were tested in healthy subjects: task repetition training and synergy training versus a control. All three groups showed improvements when retested on the same task. When tested on a similar, but different set of tasks, only the synergy group showed improvements in...

Medical & Biological Engineering & Computing, 2015

The human hand uses a combination of feedforward and feedback mechanisms to accomplish high degre... more The human hand uses a combination of feedforward and feedback mechanisms to accomplish high degree of freedom in grasp control efficiently. In this study, we used a synergy-based control model to determine the effect of sensory feedback on kinematic synergies in the grasping hand. Ten subjects performed two types of grasps: one that included feedback (real) and one without feedback (memory-guided), at two different speeds (rapid and natural). Kinematic synergies were extracted from rapid real and rapid memory-guided grasps using principal component analysis. Synergies extracted from memory-guided grasps revealed greater preservation of natural inter-finger relationships than those found in corresponding synergies extracted from real grasps. Reconstruction of natural real and natural memory-guided grasps was used to test performance and generalizability of synergies. A temporal analysis of reconstruction patterns revealed the differing contribution of individual synergies in real grasps versus memory-guided grasps. Finally, the results showed that memory-guided synergies could not reconstruct real grasps as accurately as real synergies could reconstruct memory-guided grasps. These results demonstrate how visual and tactile feedback affects a closed-loop synergy-based motor control system.

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

This paper outlines the construction, current state, and future goals of HERCULES, a three degree... more This paper outlines the construction, current state, and future goals of HERCULES, a three degree-of-freedom (DoF) pneumatically actuated exoskeleton for stroke rehabilitation. The exoskeleton arm is capable of joint-angle control at the elbow in flexion and extension, at the shoulder in flexion and extension, and at the shoulder in abduction and adduction. In the near future we plan to embed kinematic synergies into the control system architecture of this arm to gain dexterous and near-natural movements.Clinical Relevance— This device can be used as an upper limb rehabilitation testbed for individuals with complete or partial upper limb paralysis. In the future, this system can be used to train individuals on synergy-based rehabilitation protocols.

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

Post-stroke rehabilitation, occupational and physical therapy, and training for use of assistive ... more Post-stroke rehabilitation, occupational and physical therapy, and training for use of assistive prosthetics leverages our current understanding of bilateral motor control to better train individuals. In this study, we examine upper limb lateralization and model transference using a bimanual joystick cursor task with orthogonal controls. Two groups of healthy subjects are recruited into a 2-session study spaced seven days apart. One group uses their left and right hands to control cursor position and rotation respectively, while the other uses their right and left hands. The groups switch control methods in the second session, and a rotational perturbation is applied to the positional controls in the latter half of each session. We find agreement with current lateralization theories when comparing robustness to feedforward perturbations in feedback and feedforward measures. We find no evidence of a transferable model after seven days, and evidence that the brain does not synchronize...

To meet the growing need of robust and secure identity verification systems, a new biometric base... more To meet the growing need of robust and secure identity verification systems, a new biometric based on neural representations of synergistic hand grasps is proposed here. In this preliminary study five subjects were asked to perform six synergistic hand grasps that are shared most often in common activities of daily living. Their scalp electroencephalographic (EEG) signals were analyzed using 20 scalp electrodes. In our previous work, we found that hand kinematics of these synergistic grasps showed potential as a biometric. In the current work, we asked if the neural representations of these synergistic grasps can provide a unique signature to be a biometric. The results show that across 300 entries, the system, in its best configuration, achieved an accuracy of 92.2% and an EER of ~4.7% when tasked with identifying these five individuals. The implications of these preliminary results and applications in the near future are discussed. We believe that this study could lead to the deve...

SpringerBriefs in Electrical and Computer Engineering

Rationale: The human central nervous system (CNS) effortlessly performs complex hand movements wi... more Rationale: The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom (DoF), but how those mechanisms are encoded in the CNS remains unclear. In order to investigate the neural representations of human upper limb movement, scalp electroencephalography (EEG) was recorded to decode cortical activity in reaching and grasping movements. Methods: Upper limb movements including arm reaching and hand grasping tasks were observed in this study. EEG signals of 15 healthy individuals were recorded (g.USBamp, g.tec, Austria) when performing reaching and grasping tasks. Spectral features of the relevant cortical activities were extracted from EEG signals to decode the relevant reaching direction and hand grasping information. Upper limb motion direction and hand kinematics were captured with sensors worn on the hands. Directional EEG features were classified using stacked autoencoders; hand kinematic synergies were reconstructed to model the relationship of hand movement and EEG activities. Results: An average classification accuracy of three-direction reaching tasks achieved 79 ± 5.5% (best up to 88 ± 6%). As for hand grasp decoding, results showed that EEG features were able to successfully decode synergy-based movements with an average decoding accuracy of 80.1 ± 6.1% (best up to 93.4 ± 2.3%). Conclusion: Upper limb movements, including directional arm reaching and hand grasping expressed as weighted linear combinations of synergies, were decoded successfully using EEG. The proposed decoding and control mechanisms might simplify the complexity of high dimensional motor control and might hold promise toward real-time neural control of synergy-based prostheses and exoskeletons in the near future.

Biomimetic Prosthetics, Feb 14, 2018

IEEE Transactions on Biomedical Circuits and Systems

Soft hand exoskeletons offer a lightweight, low-profile alternative to rigid rehabilitative robot... more Soft hand exoskeletons offer a lightweight, low-profile alternative to rigid rehabilitative robotic systems, enabling their use to restore activities of daily living (ADL) in those with hand paresis due to stroke or other conditions. The hand exoskeleton with embedded synergies (HEXOES) is a soft cable-driven hand exoskeleton capable of independently actuating and sensing 10 degrees of freedom (DoF) of the hand. Control of the 10 DoF exoskeleton is dimensionally reduced using three manually defined synergies in software corresponding to thumb, index, and 3-finger flexion and extension. In this paper, five healthy subjects control HEXOES using a neural network which decodes synergy weights from contralateral electromyography (EMG) activity. The three synergies are manipulated in real time to grasp and lift 15 ADL objects of various sizes and weights. The neural network's training and validation mean squared error, object grasp time, and grasp success rate were measured for five healthy subjects. The final training error of the neural network was 4.8 ± 1.8% averaged across subjects and tasks, with 8.3 ± 3.4% validation error. The time to reach, grasp, and lift an object was 11.15 ± 4.35 s on average, with an average success rate of 66.7% across all objects. The complete system demonstrates real time use of biosignals and machine learning to allow subjects to operate kinematic synergies to grasp objects using a wearable hand exoskeleton. Future work and applications are further discussed, including possible design improvements and enrollment of individuals with stroke.

IEEE Access

Recent advances in assistive hand devices have produced high degree of freedom systems which are ... more Recent advances in assistive hand devices have produced high degree of freedom systems which are capable of complex grasping, however user-friendly control of these sophisticated devices is still an open topic in research. Synergy-based controllers which dimensionally reduced the control problem were present in the literature, however they used spatial/postural synergies which are static over time. In this paper, we proposed the first control system based on spatiotemporal synergies which is scalable to any number of degrees of freedom, any number of synergies, and any duration of synergy. The controller was tested on prior data in which ten subjects performed 50 object grasps and 36 American Sign Language letters and numbers. The tuned response of the controller, the-norm reconstruction error, and the simulation error were all reported in detail. The angular error between the simulated model and recorded states decayed rapidly from 23.1±19.98% with the first synergy to 6.18±8.75% for synergies 1 to 6 and 2.29±3.35% for synergies 1 to 10 and was statistically similar to the reconstruction error of the angular trajectories. Minor improvements in performance were observed when using higher-order synergies, implying a tradeoff between accuracy and control complexity. The data shown here can be used to select the number of synergies to use in control based on the accuracy of the controller and the accuracy of the controlled robotic system. The resulting system achieved high grasping dexterity with minimal computational or manual effort for assistive devices.

IEEE Access

The human central nervous system (CNS) effortlessly performs complex hand movements with the cont... more The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom (DoF). It is hypothesized that the CNS might use kinematic synergies to reduce the complexity of movements, but how these kinematic synergies are encoded in the CNS remains unclear. In order to investigate the neural representations of kinematic synergies, scalp electroencephalographic (EEG) signals and hand kinematics were recorded from 10 subjects during six representative types of hand grasping. Kinematic synergies were obtained from recorded hand kinematics using singular value decomposition. The recorded kinematics were then reconstructed using weighted linear combinations of synergies and optimal weights were computed using optimal linear estimation. Using EEG spectral powers as neural features, a multivariate linear regression model was trained on the weights of the kinematic synergies. Using this model, kinematics from the testing subset of data were decoded from EEG features with 3-fold cross validation. Results show that the weights of kinematic synergies used in a particular movement reconstruction were strongly correlated to EEG features obtained from that movement. EEG features were able to successfully decode synergy-based movements with an average decoding accuracy of 80.1±6.1% (best up to 93.4±2.3%). These results have promising applications in noninvasive neural control of synergy-based prostheses and exoskeletons.

IEEE Access

Electroencephalography (EEG)-based brain-computer interfaces (BCIs) that decode cortical activity... more Electroencephalography (EEG)-based brain-computer interfaces (BCIs) that decode cortical activity in reaching and grasping movements can enable natural upper limb motor control. In this paper, we studied the performance of stacked autoencoders in decoding asynchronous reaching movements in the dominant upper limb using EEG. Five individuals without any motor disabilities performed three self-paced reaching tasks while the endpoints of the arm movements were recorded with a motion tracker. Power spectral densities of the relevant cortical signals were extracted among eight bandwidths in the range of 1-45Hz to train a stacked autoencoder. For comparison, convolutional neural network (CNN) and traditional linear decoding using principal component analysis (PCA) for feature selection and linear discriminant analysis (LDA) for classification were also used. An average classification accuracy of 79±5.5% (best up to 88±6%) was achieved from all subjects on wide frequency band (1-45Hz) in offline analysis with stacked autoencoders while average classification accuracies of 68±9.1% (best up to 74±9.1%) with PCA-LDA and 49±13.8% (best up to 56±7.2%) with CNN were achieved. The simultaneous dimensionality reduction and feature extraction capabilities of stacked autoencoders can have significant advantages in BCI applications. INDEX TERMS Electroencephalography, arm reaching movement, stacked autoencoders, machine learning, deep learning, classification, principal component analysis, linear discriminant analysis.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, Aug 1, 2016

The complex prevalence of Parkinson's disease (PD) symptoms has pushed research towards asses... more The complex prevalence of Parkinson's disease (PD) symptoms has pushed research towards assessment tools that can assist in their quantification. There remains a need for a system capable of measuring symptoms during various tasks at multiple motor levels (kinematics and electromyography). In this paper, we present the development and initial validation of a quantitative assessment tool for Parkinson's disease (QAPD), a system designed to assist researchers and clinicians in the study of PD. The system integrates motion tracking, data gloves, and electromyography to collect movement related data from multiple body parts. As part of the system, a custom MATLAB® based toolbox has been designed to quantify bradykinesia, tremor, micrographia, and muscle rigidity using both standard and contemporary data analysis techniques. We believe this system can be a useful assessment tool to assist clinicians and researchers in diagnosing and estimating movement dysfunction in individuals ...

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, Jul 1, 2017

Numerous hand exoskeletons have been proposed in the literature with the aim of assisting or reha... more Numerous hand exoskeletons have been proposed in the literature with the aim of assisting or rehabilitating victims of stroke, brain/spinal cord injury, or other causes of hand paralysis. In this paper a new 3D printed soft hand exoskeleton, HEXOES (Hand Exoskeleton with Embedded Synergies), is introduced and mechanically characterized. Metacarpophalangeal (MCP) and proximal interphalangeal/interphalangeal (PIP/IP) joints had measured maximum flexion angles of 53.7 ± 16.9° and 39.9 ± 13.4°, respectively; and maximum MCP and PIP angular velocities of 94.5 ± 41.9 degrees/s and 74.6 ± 67.3 degrees/s, respectively. These estimates indicate that the mechanical design has range of motion and angular velocity characteristics that meet the requirements for synergy-based control. When coupled with the proposed control loop, HEXOES can be used in the future as a test-bed for synergy-based clinical hand rehabilitation.

Frontiers in Bioengineering and Biotechnology

Kinematic and neuromuscular synergies have been found in numerous aspects of human motion. This s... more Kinematic and neuromuscular synergies have been found in numerous aspects of human motion. This study aims to determine how effectively kinematic synergies in bilateral upper arm movements can be used to replicate complex activities of daily living (ADL) tasks using a sparse optimization algorithm. Ten right-handed subjects executed 18 rapid and 11 natural-paced ADL tasks requiring bimanual coordination while sitting at a table. A position tracking system was used to track the subjects' arms in space, and angular velocities over time for shoulder abduction, shoulder flexion, shoulder internal rotation, and elbow flexion for each arm were computed. Principal component analysis (PCA) was used to generate kinematic synergies from the rapid-paced task set for each subject. The first three synergies accounted for 80.3 ± 3.8% of variance, while the first eight accounted for 94.8 ± 0.85%. The first and second synergies appeared to encode symmetric reaching motions which were highly correlated across subjects. The first three synergies were correlated between left and right arms within subjects, whereas synergies four through eight were not, indicating asymmetries between left and right arms in only the higher order synergies. The synergies were then used to reconstruct each natural-paced task using the l 1-norm minimization algorithm. Temporal dilations of the synergies were introduced in order to model the temporal scaling of movement patterns achieved by the cerebellum and basal ganglia as reported previously in the literature. Reconstruction error was reduced by introducing synergy dilations, and cumulative recruitment of several synergies was significantly reduced in the first 10% of training task time by introducing temporal dilations. The outcomes of this work could open new scenarios for the applications of postural synergies to the control of robotic systems, with potential applications in rehabilitation. These synergies not only help in providing near-natural control but also provide simplified strategies for design and control of artificial limbs. Potential applications of these bilateral synergies were discussed and future directions were proposed.

IEEE Access

Biometric systems can identify individuals based on their unique characteristics. A new biometric... more Biometric systems can identify individuals based on their unique characteristics. A new biometric based on hand synergies and their neural representations is proposed here. In this paper, ten subjects were asked to perform six hand grasps that are shared by most common activities of daily living. Their scalp electroencephalographic (EEG) signals were recorded using 32 scalp electrodes, of which 18 task-relevant electrodes were used in feature extraction. In our previous work, we found that hand kinematic synergies, or movement primitives, can be a potential biometric. In this paper, we combined the hand kinematic synergies and their neural representations to provide a unique signature for an individual as a biometric. Neural representations of hand synergies were encoded in spectral coherence of optimal EEG electrodes in the motor and parietal areas. An equal error rate of 7.5% was obtained at the system's best configuration. Also, it was observed that the best performance was obtained when movement specific EEG signals in gamma frequencies (30-50Hz) were used as features. The implications of these first results, improvements, and their applications in the near future are discussed. INDEX TERMS Biometrics, hand kinematics, movement primitives, hand synergies, neural representations, electroencephalography (EEG), coherence.

Frontiers in Bioengineering and Biotechnology

Recently, the need for more secure identity verification systems has driven researchers to explor... more Recently, the need for more secure identity verification systems has driven researchers to explore other sources of biometrics. This includes iris patterns, palm print, hand geo metry, facial recognition, and movement patterns (hand motion, gait, and eye movements). Identity verification systems may benefit from the complexity of human movement that integrates multiple levels of control (neural, muscular, and kinematic). Using principal component analysis, we extracted spatiotemporal hand synergies (movement synergies) from an object grasping dataset to explore their use as a potential biometric. These movement synergies are in the form of joint angular velocity profiles of 10 joints. We explored the effect of joint type, digit, number of objects, and grasp type. In its best configuration, movement synergies achieved an equal error rate of 8.19%. While movement synergies can be integrated into an identity verification system with motion capture ability, we also explored a camera-ready version of hand synergies-postural synergies. In this proof of concept system, postural synergies performed well, but only when specific postures were chosen. Based on these results, hand synergies show promise as a potential biometric that can be combined with other hand-based biometrics for improved security.

Frontiers in bioengineering and biotechnology, 2017

Traditionally, repetitive practice of a task is used to learn a new skill, exhibiting as immediat... more Traditionally, repetitive practice of a task is used to learn a new skill, exhibiting as immediately improved performance. Research suggests, however, that a more experience-based rather than exposure-based training protocol may allow for better transference of the skill to related tasks. In synergy-based motor control theory, fundamental motor skills, such as hand grasping, are represented with a synergy subspace that captures essential motor patterns. In this study, we propose that motor-skill learning through synergy-based mechanisms may provide advantages over traditional task repetition learning. A new task was designed to highlight the range of motion and dexterity of the human hand. Two separate training strategies were tested in healthy subjects: task repetition training and synergy training versus a control. All three groups showed improvements when retested on the same task. When tested on a similar, but different set of tasks, only the synergy group showed improvements in...

Medical & Biological Engineering & Computing, 2015

The human hand uses a combination of feedforward and feedback mechanisms to accomplish high degre... more The human hand uses a combination of feedforward and feedback mechanisms to accomplish high degree of freedom in grasp control efficiently. In this study, we used a synergy-based control model to determine the effect of sensory feedback on kinematic synergies in the grasping hand. Ten subjects performed two types of grasps: one that included feedback (real) and one without feedback (memory-guided), at two different speeds (rapid and natural). Kinematic synergies were extracted from rapid real and rapid memory-guided grasps using principal component analysis. Synergies extracted from memory-guided grasps revealed greater preservation of natural inter-finger relationships than those found in corresponding synergies extracted from real grasps. Reconstruction of natural real and natural memory-guided grasps was used to test performance and generalizability of synergies. A temporal analysis of reconstruction patterns revealed the differing contribution of individual synergies in real grasps versus memory-guided grasps. Finally, the results showed that memory-guided synergies could not reconstruct real grasps as accurately as real synergies could reconstruct memory-guided grasps. These results demonstrate how visual and tactile feedback affects a closed-loop synergy-based motor control system.