Unlocking precision using k-means++- improved genetic algorithm-radial basis function neural network: data-driven evolution of smart gloves for gesture recognition

Human-computer interaction technologies have been used since the 1970s but have only gained growing popularity in recent years with new design paradigms. Ongoing research and development in gesture recognition systems with broad application prospects have focused on improving accuracy and real-time performance as well as the robustness of specific machine learning algorithms against environmental conditions. This paper addresses the accuracy enhancement of a novel Fifth Dimension Technologies data-glove-based gesture recognition system using a genetic-algorithm (GA)-trained k-means++-improved radial basis function (RBF) or GK-RBF neural network. First, we analyzed and modeled the sensor distribution in the data glove and proposed joint constraints based on the finger joint angle and sensor mapping. Then, we trained the model and conducted experimental verification to demonstrate the model´s excellent real-time performance. Our results showed a training accuracy of 100%, a reduction in training error rate by 89.3%, and an accuracy rate improvement of at least 3.5% between the different static gestures, even with different operators. Specifically, the GK-RBF neural network outperforms the RBF and GA-modified models by 4.36 and 2.21 abs.%, respectively, in terms of recognition accuracy. The 99.85-% accuracy rate of 10-fold cross validation proves a high degree of compatibility with data-glove-based recognition systems.