Human activity data based on wearable sensors, such as the Inertial Measurement Unit (IMU), have been widely used in human activity recognition. However, most publicly available datasets only collected data from few body parts and the type of data collected is relatively homogeneous. Activity data from local body parts is challenging for recognizing specific activities or complex activities. Hence, we create a new  HAR dataset which is colledted from the project named MPJA HAD: A Multi-Position Joint Angles Dataset for Human Activity Recognition Using Wearable Sensors.

We are presenting electromyography (EMG) and metabolic cost data collected during the optimization of a semi-active hip exoskeleton concept using impedance control at varying walking speeds. We collected 2-minute estimations of metabolic cost across 30 combinations of impedance parameters (stiffness and reference angle) to predict the most metabolically beneficial parameter set.

The use of modern Mobile Brain-Body imaging techniques, combined with hyperscanning (simultaneous and synchronous recording of brain activity of multiple participants) has allowed researchers to explore a broad range of different types of social interactions from the neuroengineering perspective. In specific, this approach allows to study such type of interactions under an ecologically valid approach.

These data sets are from the experimental part of the paper, mainly including hip angle obtained by IMU, plantar pressure obtained by FSR, gait division algorithm results, oscillator phase and so on.