Nebojsa Malesevic

Feasibility of a hybrid brain-computer interface for advanced functional electrical therapy.

We present a feasibility study of a novel hybrid brain-computer interface (BCI) system for advanced functional electrical therapy (FET) of grasp. FET procedure is improved with both automated stimulation pattern selection and stimulation triggering. The proposed hybrid BCI comprises the two BCI control signals: steady-state visual evoked potentials (SSVEP) and event-related desynchronization (ERD). The sequence of the two stages, SSVEP-BCI and ERD-BCI, runs in a closed-loop architecture. The first stage, SSVEP-BCI, acts as a selector of electrical stimulation pattern that corresponds to one of the three basic types of grasp: palmar, lateral, or precision. In the second stage, ERD-BCI operates as a brain switch which activates the stimulation pattern selected in the previous stage. The system was tested in 6 healthy subjects who were all able to control the device with accuracy in a range of 0.64–0.96. The results provided the reference data needed for the planned clinical study. This novel BCI may promote further restoration of the impaired motor function by closing the loop between the “will to move” and contingent temporally synchronized sensory feedback.

A Wearable Multi-Site System for NMES-Based Hand Function Restoration

Reaching and grasping impairments significantly affect the quality of life for people who have experienced a stroke or spinal cord injury. The long-term well-being of patients varies greatly according to the restorable residual capabilities. Electrical stimulation could be a promising solution to restore motor functions in these conditions, but its use is not clinically widespread. Here, we introduce the HandNMES, an electrode array (EA) for neuromuscular electrical stimulation (NMES) aimed at grasp training and assistance. The device was designed to deliver electrical stimulation to extrinsic and intrinsic hand muscles. Six independent EAs, positioned on the user forearm and hand, deliver NMES pulses originating from an external stimulator equipped with demultiplexers for interfacing with a large number of electrodes. The garment was designed to be adaptable to user needs and anthropometric characteristics; size, shape, and contact materials can be customized, and stimulation characteristics such as intensity of stimulation and virtual electrode location, and size can be adjusted. We performed extensive tests with nine healthy subjects showing the efficacy of the HandNMES in terms of stimulation performance and personalization. Because encouraging results were achieved, in the coming months, the HandNMES device will be tested in pilot clinical trials.

Gait phase detection optimization based on variational bayesian inference of feedback sensor signal

Stroke patients often suffer from gait disorders which can remain chronic. Mechanical or electrical aids designed to deal with this problem often rely on accurate estimation of current gait phase as this information is used for active ankle joint control. In this paper we present the method for optimization of the gait phase detection algorithm. The method is based on Variational Bayesian inference which is employed on signals from feedback sensors positioned on both paretic and healthy foot of patient. Main aim of Variational Bayesian inference application was to remove noise and provide smooth sensor signal which is suitable for robust gait phase detection algorithm. We modeled foot trajectory with linear model. Results presented in this paper show significant reduction of high frequency noise in gyroscope signal. The reduction was dominant during transitions between gait phases making our method applicable in any algorithm based on signal features in time domain.

Novel multi-pad functional electrical stimulation in stroke patients : A single-blind randomized study

BACKGROUND Foot drop is common gait impairment after stroke. Functional electrical stimulation (FES) of the ankle dorsiflexor muscles during the swing phase of gait can help correcting foot drop. OBJECTIVE To evaluate efficacy of additional novel FES system to conventional therapy in facilitating motor recovery in the lower extremities and improving walking ability after stroke. METHODS Sixteen stroke patients were randomly allocated to the FES group (FES therapy plus conventional rehabilitation program) (n = 8), and control group (conventional rehabilitation program) n = 8. FES was delivered for 30 min during gait to induce ankle plantar and dorsiflexion. MAIN OUTCOME MEASURES gait speed using 10 Meter Walk Test (10 MWT), Fugl-Meyer Assessment (FMA), Berg Balance Scale (BBS) and modified Barthel Index (MBI). RESULTS Results showed a significant increase in gait speed in FES group (p < 0.001), higher than the minimal detected change. The FES group showed improvement in functional independence in the activities of daily living, motor recovery and gait performance. CONCLUSIONS The findings suggest that novel FES therapy combined with conventional rehabilitation is more effective on walking speed, mobility of the lower extremity, balance disability and activities of daily living compared to a conventional rehabilitation program only.

Adaptive Interface for Mapping Body Movements to Sounds.

Contemporary digital musical instruments allow an abundance of means to generate sound. Although superior to traditional instruments in terms of producing a unique audio-visual act, there is still an unmet need for digital instruments that allow performers to generate sounds through movements in an intuitive manner. One of the key factors for an authentic digital music act is a low latency between movements (user commands) and corresponding sounds. Here we present such a low-latency interface that maps the user’s kinematic actions into sound samples. The interface relies on wireless sensor nodes equipped with inertial measurement units and a real-time algorithm dedicated to the early detection and classification of a variety of movements/gestures performed by a user. The core algorithm is based on the approximate inference of a hierarchical generative model with piecewise-linear dynamical components. Importantly, the model’s structure is derived from a set of motion gestures. The performance of the Bayesian algorithm was compared against the k-nearest neighbors (k-NN) algorithm, which showed the highest classification accuracy, in a pre-testing phase, among several existing state-of-the-art algorithms. In almost all of the evaluation metrics the proposed probabilistic algorithm outperformed the k-NN algorithm.

Vector Autoregressive Hierarchical Hidden Markov Models for Extracting Finger Movements Using Multichannel Surface EMG Signals

We present a novel computational technique intended for the robust and adaptable control of a multifunctional prosthetic hand using multichannel surface electromyography. The initial processing of the input data was oriented towards extracting relevant time domain features of the EMG signal. Following the feature calculation, a piecewise modeling of the multidimensional EMG feature dynamics using vector autoregressive models was performed. The next step included the implementation of hierarchical hidden semi-Markov models to capture transitions between piecewise segments of movements and between different movements. Lastly, inversion of the model using an approximate Bayesian inference scheme served as the classifier. The effectiveness of the novel algorithms was assessed versus methods commonly used for real-time classification of EMGs in a prosthesis control application. The obtained results show that using hidden semi-Markov models as the top layer, instead of the hidden Markov models, ranks top in all the relevant metrics among the tested combinations. The choice of the presented methodology for the control of prosthetic hand is also supported by the equal or lower computational complexity required, compared to other algorithms, which enables the implementation on low-power microcontrollers, and the ability to adapt to user preferences of executing individual movements during activities of daily living.

Helping Hand grasp rehabilitation: Preliminary assessment on chronic stroke patients

The Helping Hand (HH) system is a novel grasp rehabilitation platform aimed at simplifying the clinical usage of wearable electrode arrays for neuromuscular electrical stimulation (NMES). In a randomized dose-matched, clinical study we evaluate usability and effectiveness of the HH treatment, and of other enriched upper limb rehabilitation treatments, and compare the outcomes. This paper shows the preliminary clinical results of the trial on 5 chronic stroke patients throughout a 9 weeks, 3 hours per week, hand preshaping training.

Decoding of individual finger movements from surface EMG signals using vector autoregressive hierarchical hidden Markov models (VARHHMM)

In this paper we present a novel method for predicting individual fingers movements from surface electromyography (EMG). The method is intended for real-time dexterous control of a multifunctional prosthetic hand device. The EMG data was recorded using 16 single-ended channels positioned on the forearm of healthy participants. Synchronously with the EMG recording, the subjects performed consecutive finger movements based on the visual cues. Our algorithm could be described in following steps: extracting mean average value (MAV) of the EMG to be used as the feature for classification, piece-wise linear modeling of EMG feature dynamics, implementation of hierarchical hidden Markov models (HHMM) to capture transitions between linear models, and implementation of Bayesian inference as the classifier. The performance of our classifier was evaluated against commonly used real-time classifiers. The results show that the current algorithm setup classifies EMG data similarly to the best among tested classifiers but with equal or less computational complexity.