The purpose of the present study was to fully and reliably decompose surface electromyograms (s-EMGs) into their constitutive motor action unit potential trains (MUAPTs) at higher levels of contraction than that possible by using established methods. An algorithm for s-EMG signals decomposition based on preprocessing filters, independent component analysis (ICA), and on a template-matching technique was developed. In this study, it was demonstrated how ICA can be used successfully for solving overlaps of MUAPs. In each iteration of the algorithm, the action potentials of one motor unit (MU) could generally be separated from the others. Subsequently, using a template-matching technique, we were able to identify the action potential train of the selected MU. Results show that the algorithm satisfactorily decomposed the s-EMGs into their constitutive MUAPTs up to 30, 50, and even 60% maximum voluntary contraction (MVC). The results are in agreement with the generally accepted behavior of MUs firing rates.
In the present work we introduce a preliminary study on a new type of dry electrodes to asses their possible use for performing long-term recordings of surface electromyographic signals. These signals would be used for the control of artificial prostheses in a non-invasive manner. In addition, a comparison was carried out between the new dry electrodes and a commercial, pre-gelled electrode. The results showed that both kinds of electrodes have similar impedance values and behavior at different frequencies, which are the main parameters to take into account when characterizing electrodes. For daily use in prosthesis control, dry electrodes are preferred over gelled or pre-gelled electrodes because they can be embedded in fabric and hence be worn seamlessly.
Child-robot interaction (CRI) has been mostly studied in labs and classroom settings. In this work, we share a CRI language processing study carried out in children’s homes. Any automated system deployed “in-the-wild” faces practical problems, but when the target users are children, these problems get even more sensitive and challenging. In this work we analyse how each language processing layer performs with children at home with no researcher present. We carried out an experiment with 7 families [N=14 children, 6-13 years old] cohabiting with a simulated robot for 2 weeks in their own homes. Our goal in this study is to evaluate the performance of voice recognition, language understanding and dialogue management when children interact with a robot at home. Our results indicate that dialogue management capabilities are becoming the key element in the language processing pipeline; they also denote that the dialogue engine should include mixed-initiative capabilities and show the relative usage of different common built-in intents.