Hand gesture recognition (HGR) using flexible sensors (flex-sensor) and the MPU6050 sensor has proved to be a key area of research in human-machine interaction, with major applications in biasing, rehabilitation, and assisted robotics. This paper proposes a wearable intelligent glove designed to operate a robotics arm in real time, relying on multi-sensor fusion and machine learning methods to enhance the system's responsiveness and precision. The proposed system enables the intuitive reproduction of hand movements and precise control of the robotic arm. In the context of Industry 4.0 and internet of things (IoT), the classification of gestures is necessary for maintaining operational efficiency. To guarantee gesture recognition, data signals from the smart glove are collected and trained by a recurrent neural network (RNN), which achieves 98.67% accuracy for real-time classification of seven gestures. Beyond industrial applications, the wearable smart glove can be exploited in a recognized circuit of all systems, including rehabilitation exercises that involve recording the progression of muscular activity for the assessment of motor functions and serve as a tool for patient recovery.
Collaboration network of the authors
17 authors ·
42 co-authorship links
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
University of Hassan II Casablanca
Affiliation unknown
Different organisations
Same organisation
Affiliation unknown
Thicker line = more joint articles · bigger circle = more articles
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.