Maria Claudia F. Castro

A low-cost instrumented glove for monitoring forces during object manipulation

A rehabilitation program toward restoring upper limb movements based on neuromuscular electrical stimulation (NMES) depends on closed-loop control performance, which has been limited by the development of sensors for practical daily use. This work proposes a system to obtain force feedback. The system is comprised of a Lycra commercial glove with force sensing resistors (FSRs) attached to the distal phalanxes of the thumb, index and long fingers. After amplification and filtering, the signal is digitized through an analog-to-digital (A/D) converter. The polynomial fitting coefficients for the characteristic curves, obtained during the sensor calibration process, were inserted in the software thus enabling the reading of forces exerted during object manipulation. The system was applied to 30 normal subjects in order to verify its feasibility and to acquire knowledge of the normal hand function. Different ways of grasping have been detected according to the Force versus Time curve pattern and to the fingers predominantly used in grasping. Results have also shown the influence of parameters such as gender, age, hand size, and object weight in the normal function. The system did show efficacy. It was able to determine grasp forces during object manipulation for up to 73% of the studied sample. This is significant since a single glove was used in a wide range of subjects. For best results in medical applications, the glove should be tailored to the particular characteristics of an individual user.

Selection of suitable hand gestures for reliable myoelectric human computer interface

BackgroundMyoelectric controlled prosthetic hand requires machine based identification of hand gestures using surface electromyogram (sEMG) recorded from the forearm muscles. This study has observed that a sub-set of the hand gestures have to be selected for an accurate automated hand gesture recognition, and reports a method to select these gestures to maximize the sensitivity and specificity.MethodsExperiments were conducted where sEMG was recorded from the muscles of the forearm while subjects performed hand gestures and then was classified off-line. The performances of ten gestures were ranked using the proposed Positive–Negative Performance Measurement Index (PNM), generated by a series of confusion matrices.ResultsWhen using all the ten gestures, the sensitivity and specificity was 80.0% and 97.8%. After ranking the gestures using the PNM, six gestures were selected and these gave sensitivity and specificity greater than 95% (96.5% and 99.3%); Hand open, Hand close, Little finger flexion, Ring finger flexion, Middle finger flexion and Thumb flexion.ConclusionThis work has shown that reliable myoelectric based human computer interface systems require careful selection of the gestures that have to be recognized and without such selection, the reliability is poor.

Classification of executed upper limb movements by means of EEG

This work presents the performance of a Linear Discriminant Analysis classifier that used EEG data from 3 different subsets of the signal, which was gathered during the execution of 4 upper limb movements. The mean Power of the signal, segmented in 8 EEG frequency bands, was used as the features for the classifier and the effect of spatial feature selection was also investigated. A non-conventional potential difference based on an 8-electrode clinical transversal setup was used in the acquisition of EEG signal during arm and hand movements, which were segmented in Movement Planning, Movement Execution and Steady Position. The results showed that the Movement Planning subset achieved the best classification accuracy, suggesting that the speed for a BCI can be improved by using pre-movement information. Spatial feature selection showed that non-motor areas should be considered as an information source. Best classification accuracy of right and left limbs was 67.95%, hands versus arms achieved 82.69%, and 49.36% of classification was the best result for the 4-class set up. Results are promising, however further experiments are required to obtain better classification accuracy and to generalize these conclusions.

sEMG feature evaluation for identification of elbow angle resolution in graded arm movement

Automatic and accurate identification of elbow angle from surface electromyogram (sEMG) is essential for myoelectric controlled upper limb exoskeleton systems. This requires appropriate selection of sEMG features, and identifying the limitations of such a system.This study has demonstrated that it is possible to identify three discrete positions of the elbow; full extension, right angle, and mid-way point, with window size of only 200 milliseconds. It was seen that while most features were suitable for this purpose, Power Spectral Density Averages (PSD-Av) performed best. The system correctly classified the sEMG against the elbow angle for 100% cases when only two discrete positions (full extension and elbow at right angle) were considered, while correct classification was 89% when there were three discrete positions. However, sEMG was unable to accurately determine the elbow position when five discrete angles were considered. It was also observed that there was no difference for extension or flexion phases.

Hand gesture recognition for the control of an exoskeleton

Despite the existence of many examples in multifunctional control systems there is a lack of studies that show hand gestures applied in daily life activities. Furthermore, isometric contractions, above certain thresholds, continue to be used once it is easier to deal with. However, it is a static contraction, that is not used to perform movements. Thus, a control system based on that is not intuitive, especially for subjects who have the limb with a diminished strength and that could also be benefited by rehabilitation devices, such as exoskeletons to train or regain function. In this context, the purpose of this work is to investigate the recognition of up to 4 hand gestures plus the neutral hand position, based on myoelectric signal obtained during the static phase at the end of the movement, without the use of any additional isometric contraction. Performance evaluation is done based on Linear Discriminant Analysis comparing the results of six myoelectric features and also the number of muscles necessary to achieve the best classification accuracy. The results show higher rates for the features in the frequency domain. The Spectral Magnitude Average reaches an average accuracy of 88.44% following by Spectral Moments with 85.56%. The best results achieved by each subject is variable, with a predominant use of 3 to 5 muscles depending on the feature that was used, with no standard pattern.

Statistical approach for angular position separability classes of EMG data

This paper focus on the application of a multivariate statistical analysis approach, based on Linear Discriminant Analysis (LDA), of EMG data that aims to identify the angular position of the elbow. Linear transformations applied to EMG signals of the Biceps brachii and Triceps brachii, acquired during flexion / extension movements, enabled good and reliable class separation for future classification.

Development of control strategies for restoring function to paralyzed upper and lower limbs

Neuromuscular Electrical Stimulation (NMES) systems are used worldwide to restore upper and lower limb functions in spinal cord patients. An integrated approach is being tried at UNICAMP, including multichannel stimulators, sensors and algorithms for closed-loop control, and artificial proprioception. This paper describes some of the devices developed and their applications, aiming at achieving well elaborated control strategies towards an effective man-machine system.

Mobile interface for neuroprosthesis control aiming tetraplegic users

This article proposes the development of a mobile interface for controlling a Neuroprosthesis, designed to restore grasp patterns, aiming tetraplegics users at C5 and C6 levels. Human Computer Interface paradigms and usability concepts guide its planning and development to garantee the quality of users interaction with the system and thus, the sucess and controlability of the neuroprostheses. The number of screens and menus were optimized, thus the user may feel the interface as more intuitive, leading to fast learning and increasing the trust on it.

Human Interface for a Neuroprothesis Remotely Control

Neuromuscular Electrical Stimulation (NMES) and Surface Electromyography (sEMG) have been widely explored by the scientific community for the rehabilitation of individuals with motor deficits due to stroke. The literature shows the benefits of sEMG-activated NMES use in both motor rehabilitation and neural plasticity stimulation. Currently, there is a strong tendency to expand the clinical environment, and the internet can be used by healthcare professionals to do detailed follow-up and interact with their patients remotely. This work presents a neuroprothesis activated by sEMG that allows configuration and monitoring of usage parameters remotely. Two control platforms were developed for different user profiles; health professionals (Web Interface) and neuroprosthesis users (Smartphone Application).

Parkinson's Disease Tremor Suppression - A Double Approach Study - Part 1.

Parkinson’s Disease (PD) is a neurodegenerative disorder that affects mostly elderly people. Approximately 2% of world population, over 60 years old, lives with PD. This pathology is recognized not only by motor symptoms such as tremor, postural gait and rigidity, but also, nonmotor symptoms as depression and sleep abnormalities may be developed as well. In Brazil, according to the Ministry of Health, 200,000 people face the challenge to develop day-by-day activities due to PD. More than just a disease causing motor disturbances, PD brings to patients uncertainties about their ability to take care of themselves independently. In this context, assistive technologies assume an important position in order to bring back life quality and self-trust to PD patients. This work aims to study techniques, develop hardware and software for a better approach in tremor suppression in order to bring back life quality to PD patients. This study approaches the problem of flexion/extension carpi radialis tremor suppression using two different strategies. The first is a mechanical suppression based on a servomotor opposing to tremor movement. The second strategy is a functional electrical stimulator. Both systems are triggered by electromyogram (EMG).