Recent advances in rehabilitation robotics suggest that it may be possible for hand-amputated subjects to recover at least a significant part of the lost hand functionality. The control of robotic prosthetic hands using non-invasive techniques is still a challenge in real life: myoelectric prostheses give limited control capabilities, the control is often unnatural and must be learned through long training times. Meanwhile, scientific literature results are promising but they are still far from fulfilling real-life needs. This work aims to close this gap by allowing worldwide research groups to develop and test movement recognition and force control algorithms on a benchmark scientific database. The database is targeted at studying the relationship between surface electromyography, hand kinematics and hand forces, with the final goal of developing non-invasive, naturally controlled, robotic hand prostheses. The validation section verifies that the data are similar to data acquired in real-life conditions, and that recognition of different hand tasks by applying state-of-the-art signal features and machine-learning algorithms is possible.

In this paper, we characterize the Ninapro database and its use as a benchmark for hand prosthesis evaluation. The database is a publicly available resource that aims to support research on advanced myoelectric hand prostheses. The database is obtained by jointly recording surface electromyography signals from the forearm and kinematics of the hand and wrist while subjects perform a predefined set of actions and postures. Besides describing the acquisition protocol, overall features of the datasets and the processing procedures in detail, we present benchmark classification results using a variety of feature representations and classifiers. Our comparison shows that simple feature representations such as mean absolute value and waveform length can achieve similar performance to the computationally more demanding marginal discrete wavelet transform. With respect to classification methods, the nonlinear support vector machine was found to be the only method consistently achieving high performance regardless of the type of feature representation. Furthermore, statistical analysis of these results shows that classification accuracy is negatively correlated with the subject's Body Mass Index. The analysis and the results described in this paper aim to be a strong baseline for the Ninapro database. Thanks to the Ninapro database (and the characterization described in this paper), the scientific community has the opportunity to converge to a common position on hand movement recognition by surface electromyography, a field capable to strongly affect hand prosthesis capabilities.

Abstract-This paper is about (self-powered) advanced hand prosthetics and their control via surface electromyography (sEMG). We hereby introduce to the biorobotics community the first version of the NINAPRO database, containing kinematic and sEMG data from the upper limbs of 27 intact subjects while performing 52 finger, hand and wrist movements of interest. The setup and experimental protocol are distilled from existing literature and thoroughly described; the data are then analysed and the results are discussed. In particular, it is clear that standard analysis techniques are no longer enough when so many subjects and movements are taken into account. The database is publicly available to download in standard ASCII format.The database is an ongoing work lasting several years, which is planned to contain data from more than 100 intact subjects and 50 trans-radial amputees; characteristics of the amputations, phantom limbs and prosthesis usage will be stored. We therefore hope that it will constitute a standard, widely accepted benchmark for all novel myoelectric hand prosthesis control methods, as well as a fundamental tool to deliver insight into the needs of trans-radial amputees.

Improving the functionality of prosthetic hands with noninvasive techniques is still a challenge. Surface electromyography (sEMG) currently gives limited control capabilities; however, the application of machine learning to the analysis of sEMG signals is promising and has recently been applied in practice, but many questions still remain. In this study, we recorded the sEMG activity of the forearm of 11 male subjects with transradial amputation who were mentally performing 40 hand and wrist movements. The classification performance and the number of independent movements (defined as the subset of movements that could be distinguished with >90% accuracy) were studied in relationship to clinical parameters related to the amputation. The analysis showed that classification accuracy and the number of independent movements increased significantly with phantom limb sensation intensity, remaining forearm percentage, and temporal distance to the amputation. The classification results suggest the possibility of naturally controlling up to 11 movements of a robotic prosthetic hand with almost no training. Knowledge of the relationship between classification accuracy and clinical parameters adds new information regarding the nature of phantom limb pain as well as other clinical parameters, and it can lay the foundations for future "functional amputation" procedures in surgery.

BackgroundFall prevention interventions with home-based exercise programmes are effective to reduce the number and the rate of falls, by reducing risk factors. They improve balance, strength, function, physical activity, but it is known that older adults’ exercise adherence declines over time. However, it is unclear which delivery-modalities of the home-based exercise programmes show the best adherence and the largest effect.We created a new home-based exercise programme, the Test-and-Exercise (T&E) programme, based on the concepts of self-efficacy and empowerment. Patients learn to build their own exercise programme with a mobile application, a brochure and cards, as well as with eight coaching sessions by physiotherapists.The main objective of this study is to compare the T&E programme with the Otago Exercise Programme and the recommendation-booklet and exercise-cards of Helsana regarding incidence of falls. Other outcomes are severity of falls, functional capacities, quality of life and exercise-adherence.MethodsThe design of this study is a Swiss multicentre assessor blind randomized controlled trial. A block-randomization, stratified in groups for age and risk of fall categories, will be used to allocate the participants to three groups. The targeted study sample consists of 405 older adults, ≥ 65 years of age, living in the community and evaluated as at “risk of falling”. Experimental group will receive the T&E programme (N = 162). Second group will receive the Otago programme (N = 162) and the third group will receive the Helsana programme (N = 81). All interventions last six months. Blinded assessors will assess participants three times: at baseline before the start of the intervention, after six months of intervention and a final assessment after twelve months (six months of follow up).DiscussionAlthough home-based exercises programmes show positive effects in fall prevention in elderly persons, existing programmes do often not include patients in the decision-making process about exercise selection. In our programme the physiotherapist and the older adult work together to select the exercises; this collaboration helps to increase health literacy, pleasure of exercising, and empowers patients to be more autonomy.Trial registrationClinicalTrials.gov: NCT02926105, First Posted: October 6, 2016, Last Update: November 11, 2016: Enrolment of the first participant.