Artificial Intelligence and Computer Vision Research Lab, Department of Informatics and Computer Science, Escuela Politécnica Nacional, Quito 170517, Ecuador
Auto-generated profile, based on publicly available information
Andrés Jaramillo-Yánez
Artificial Intelligence and Computer Vision Research Lab, Department of Informatics and Computer Science, Escuela Politécnica Nacional, Quito 170517, Ecuador
Today, daily life is composed of many computing systems, therefore interacting with them in a natural way makes the communication process more comfortable. Human–Computer Interaction (HCI) has been developed to overcome the communication barriers between humans and computers. One form of HCI is Hand Gesture Recognition (HGR), which predicts the class and the instant of execution of a given movement of the hand. One possible input for these models is surface electromyography (EMG), which records the electrical activity of skeletal muscles. EMG signals contain information about the intention of movement generated by the human brain. This systematic literature review analyses the state-of-the-art of real-time hand gesture recognition models using EMG data and machine learning. We selected and assessed 65 primary studies following the Kitchenham methodology. Based on a common structure of machine learning-based systems, we analyzed the structure of the proposed models and standardized concepts in regard to the types of models, data acquisition, segmentation, preprocessing, feature extraction, classification, postprocessing, real-time processing, types of gestures, and evaluation metrics. Finally, we also identified trends and gaps that could open new directions of work for future research in the area of gesture recognition using EMG.
Hand gesture recognition consists of identifying the class and the instant of occurrence of a given movement of the hand. The solutions to this problem have many applications in science and technology. In this paper, we propose a model for hand gesture recognition in real time. This model takes as input the surface electromyography (EMG) measured on the muscles of the forearm by the Myo armband. For any user, the proposed model can learn to recognize any gesture of the hand through a training process. As part of this process a user needs to record 5 times, during 2 s each, the EMG on his forearm, close to the elbow, while performing the gesture to recognize. The ¿-nearest neighbor and the dynamic time warping algorithms are used for classifying the EMGs seen through a window. As part of the proposed model, we also include a detector of muscle activity that speeds the time of processing up and improves the accuracy of the recognition. We tested the proposed model at recognizing the 5 gestures defined by the proprietary recognition system of the Myo armband, achieving an accuracy of 89.5%. Finally, we also demonstrated that the model proposed in this work outperforms other systems, including the recognition system of the Myo.
In this paper, we propose the development of a model for real-time hand gesture recognition. We use surface electromyography (EMG) and Machine Learning techniques. The recognition of gestures using EMG is not a trivial task because there are several physiological processes in the skeletal muscles underlying their generation. In the scientific literature, there are several hand gesture recognition models, but they have limitations both in the number of gestures to be recognized (i.e., classes) and in the processing time. Therefore, the primary goal of this research is to obtain a real-time hand gesture recognition model for various applications in the field of medicine and engineering with a higher recognition accuracy than the real-time models proposed in the scientific literature and a higher number of gestures to recognize (i.e. in the order of the dozens). The proposed model has five stages: acquisition of the EMG signals, preprocessing (e.g., rectification and filtering), feature extraction (e.g., time, frequency and time-frequency), classification (e.g., parametric and nonparametric) and post-processing. Generally, the main difficulties of the hand gesture recognition models with EMG using Machine Learning are: the noisy behavior of EMG signal, and the small number of gestures per person relative to the number of generated data by each gesture (e.i., curse of dimensionality). Solving these two issues could also lead to solutions for other problems such as face recognition and audio recognition, for which these two issues are a major concern.