By observing the actions taken by operators, it is possible to determine the risk level of a work task. One method for achieving this is the recognition of human activity using biosignals and inertial measurements provided to a machine learning algorithm performing such recognition. The aim of this research is to propose a method to automatically recognize physical exertion and reduce noise as much as possible towards the automation of the Job Strain Index (JSI) assessment by using a motion capture wearable device (MindRove armband) and training a quadratic support vector machine (QSVM) model, which is responsible for predicting the exertion depending on the patterns identified. The highest accuracy of the QSVM model was 95.7%, which was achieved by filtering the data, removing outliers and offsets, and performing zero calibration; in addition, EMG signals were normalized. It was determined that, given the job strain index’s purpose, physical exertion detection is crucial to computing its intensity in future work.

Recognizing human movement intention in less controlled environment is the step needed to go beyond strict laboratory settings in order to improve intuitive and reliable human-robot interaction systems. By taking this into account, the present study evaluates the feasibility of decoding the intention to perform hand-arm gestures in self-paced tasks from electroencephalography (EEG) and electromyography (EMG) collected with wearable dry-electrode devices. An experimental protocol was designed to emulate three gestures in human-robot interaction: Neutral, Ask, and Take. The protocol was implemented in two laboratories using different EEG headsets, Ultracortex Mark IV and Muse 2, and a common EMG device, Mindrove armband. Signals were preprocessed and segmented around the start of movement to be classified with a Bidirectional Long Short-Term Memory network with a fully connected output layer (BiLSTM-FC). Although the typical waveform of intention, movement-related cortical potential (MRCP), could not be reliably identified, the results showed that the combination of EEG andEMGimproves the discriminability of intention patterns, achieving a mean of 88.95% in accuracy, and a maximum of 95.98% using the Ultracortex Mark IV and the Mindrove armband. These findings demonstrate the robustness of multimodal data gathered with accessible wearable technology to develop hybrid brain-computer interfaces.

Gesture recognition enables intuitive human–robot communication, where surface electromyography (sEMG) provides a minimally invasive interface for detecting motor activity. However, the lack of systematic evaluation of processing pipelines represents a critical barrier to reliable subject-independent deployment. This work presents a systematic evaluation of sEMG processing pipelines for three-gesture recognition (Neutral, Ask, Take) using a Bagged Trees classifier under Leave-One-Subject-Out (LOSO) cross-validation across ten participants. A mixed-effects ANOVA over 1872 experimental configurations revealed that the preprocessing pipeline is the dominant factor affecting classification accuracy, followed by inter-subject variability, while window size and overlap exhibit smaller but statistically significant effects. A consistency-based elbow analysis identified a compact subset of five features that reduced input dimensionality by 94.79% while improving accuracy from 68.10% to 69.86% and reducing training time by 51.62%. Bayesian hyperparameter optimization was also tested, but it did not yield statistically significant improvements over the five-feature baseline; given the limited cohort (n = 10), this indicates the absence of a detectable difference and points to inter-subject variability as a leading factor limiting performance rather than model configuration. These findings provide empirically grounded guidelines for designing computationally efficient sEMG-based gesture recognition systems for collaborative robotics.