Myoelectric 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. Experiments 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. When 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. This 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.

This study presents a new approach for an sEMG hand prosthesis based on a 3D printed model with a fully embedded computer vision (CV) system in a hybrid version. A modified 5-layer Smaller Visual Geometry Group (VGG) convolutional neural network (CNN), running on a Raspberry Pi 3 microcomputer connected to a webcam, recognizes the shape of daily use objects, and defines the pattern of the prosthetic grasp/gesture among five classes: Palmar Neutral, Palmar Pronated, Tripod Pinch, Key Grasp, and Index Finger Extension. Using the Myoware board and a finite state machine, the user's intention, depicted by a myoelectric signal, starts the process, photographing the object, proceeding to the grasp/gesture classification, and commands the prosthetic motors to execute the movements. Keras software was used as an application programming interface and TensorFlow as numerical computing software. The proposed system obtained 99% accuracy, 97% sensitivity, and 99% specificity, showing that the CV system is a promising technology to assist the definition of the grasp pattern in prosthetic devices.

People taken by upper limb disorders caused by neurological diseases suffer from grip weakening, which affects their quality of life. Researches on soft wearable robotics and advances in sensor technology emerge as promising alternatives to develop assistive and rehabilitative technologies. However, current systems rely on surface electromyography and complex machine learning classifiers to retrieve the user intentions. In addition, the grasp assistance through electromechanical or fluidic actuators is passive and does not contribute to the rehabilitation of upper-limb muscles. Therefore, this paper presents a robotic glove integrated with a force myography sensor. The glove-like orthosis features tendon-driven actuation through servo motors, working as an assistive device for people with hand disabilities. The detection of user intentions employs an optical fiber force myography sensor, simplifying the operation beyond the usual electromyography approach. Moreover, the proposed system applies functional electrical stimulation to activate the grasp collaboratively with the tendon mechanism, providing motion support and assisting rehabilitation.

The affective computing aims to detect emotional states during the interaction between the user and the machine allowing the use of this information in decision-making processes. EEG signals related to emotional states can be applied to the context of software usability providing more resources to the validation process and the identification of the degree of user satisfaction. This work aims to establish a relationship between EEG signals and the user opinion about the usability of some Facebook privacy features. Based on the assumption that there are variation in brain activity during the execution of tasks labeled as “easy” or “difficult”, a performance evaluation was done based on a Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM) classifiers. The Mean Power Spectral Density, in 7 frequency bands, from 8 electrodes in F, C, P, and O areas were used as features. The classification rates showed a small advantage of the SVM when all the 28 variables were used. However, when the 13 variables pointed by the Mann-Whitney U test were used, LDA showed good discrimination capability. The electrodes in F and C areas, related with cognition and motor functions, rejected null hypothesis in almost all frequency bands during the execution of the tasks, showing that it is possible to recognize the studied emotional states. Despite the fact that this was a preliminary study, it showed the feasibility of using the EEG as a potential source of information to be added to software usability testing.

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.

Objective: A pathological tremor (PT) is an involuntary rhythmic movement of varying frequency and amplitude that affects voluntary motion, thus compromising individuals’ independence. A comprehensive model incorporating PT’s physiological and biomechanical aspects can enhance our understanding of the disorder and provide valuable insights for therapeutic approaches. This study aims to build a biomechanical model of pathological tremors using OpenSim’s realistic musculoskeletal representation of the human wrist with two degrees of freedom. Methods: We implemented a Matlab/OpenSim interface for a forward dynamics simulation, which allows for the modeling, simulation, and design of a physiological H _∞ closed-loop control. This system replicates pathological tremors similar to those observed in patients when their arm is extended forward, the wrist is pronated, and the hand is subject to gravity forces. The model was individually tuned to five subjects (four Parkinson’s disease patients and one diagnosed with essential tremor), each exhibiting distinct tremor characteristics measured by an inertial sensor and surface EMG electrodes. Simulation agreement with the experiments for EMGs, central frequency, joint angles, and angular velocities were evaluated by Jensen-Shannon divergence, histogram centroid error, and histogram intersection. Results: The model emulated individual tremor statistical characteristics, including muscle activations, frequency, variability, and wrist kinematics, with greater accuracy for the four Parkinson’s patients than the essential tremor. Conclusion: The proposed model replicated the main statistical features of subject-specific wrist tremor kinematics. Significance: Our methodology may facilitate the design of patient-specific rehabilitation devices for tremor suppression, such as neural prostheses and electromechanical orthoses.