The evolution of anthropomorphic robotic hands (ARH) in recent years has been sizable, employing control techniques based on machine learning classifiers for myoelectric signal processing. This work introduces an innovative multi-channel bio-signal transformer (MuCBiT) for surface electromyography (EMG) signal recognition and classification. The proposed MuCBiT is an artificial neural network based on fully connected layers and transformer architecture. The MuCBiT recognizes and classifies EMG signals sensed from electrodes patched over the arm’s surface. The MuCBiT classifier was trained and validated using a collected dataset of four hand gestures across ten users. Despite the smaller size of the dataset, the MuCBiT achieved a prediction accuracy of 86.25%, outperforming traditional machine learning models and other transformer-based classifiers for EMG signal classification. This integrative transformer-based gesture recognition promises notable advancements for ARH development, underscoring prospective improvements in prosthetics and human–robot interaction.
Autonomous object manipulation is a challenging task in robotics because it requires an essential understanding of the object’s parameters such as position, 3D shape, grasping (i.e., touching) areas, and orientation. This work presents an autonomous object manipulation system using an anthropomorphic soft robot hand with deep learning (DL) vision intelligence for object detection, 3D shape reconstruction, and object grasping area generation. Object detection is performed using Faster-RCNN and an RGB-D sensor to produce a partial depth view of the objects randomly located in the working space. Three-dimensional object shape reconstruction is performed using U-Net based on 3D convolutions with bottle-neck layers and skip connections generating a complete 3D shape of the object from the sensed single-depth view. Then, the grasping position and orientation are computed based on the reconstructed 3D object information (e.g., object shape and size) using U-Net based on 3D convolutions and Principal Component Analysis (PCA), respectively. The proposed autonomous object manipulation system is evaluated by grasping and relocating twelve objects not included in the training database, achieving an average of 95% successful object grasping and 93% object relocations.
This paper aims to automatically classify five classes of arrhythmia present in Electrocardiograms (ECG) by using two Deep Learning (DL)-based models. One based on Convolutional Neural Network (CNN) and the other based on Residual Networks (ResNet). The main motivation of this research is to enhance the field of medicine and assist doctors in the diagnosis of arrhythmia. The DL-based models were trained using the MIT Arrhythmia database. The evaluation of the DL-based models was performed by separating the data into 70% for training, 20% for testing and 10% for validation. Results with the testing dataset show an accuracy of 96.33 % and 95.40%; a F1-Score value of 96.34% and 95.34% for the CNN-and ResNet-based models, respectively. With the validation dataset, CNN-based model achieved an accuracy of 99.32% and a F1-Score of 99.32%; ResNet-based model achieved 98.55% and 98.55% for accuracy and F1-Score, respectively.