Robot assisted bone milling state classification network with attention mechanism

In the process of medical robot assisted bone milling surgery, the accuracy of recognition of milling state is crucial for surgical safety. However, previous studies have rarely used neural networks for signal analysis and processing, and not included attention mechanisms in neural networks to distinguish the weights of different signal features. In this paper a tactile-auditory attention model for milling state recognition is proposed. The model combines attention mechanism with fully connected neural networks. First, the milling state is divided into four types: idling, cortical bone, cancellous bone, and muscle. The acceleration and sound pressure information are extracted in 13 dimensions each, including 3-dimensional time-domain features and 10-dimensional frequency-domain features. Second, a milling state classification network with attention mechanism was established, including pre-connected attention mechanism (Pre-AT) and embedded attention mechanism (Emb-AT). The experimental results showed greater performance than other traditional methods, with test set accuracy of 94.57% and 95.29%, respectively. Afterwards, the impact of single signal and fused signal on recognition results was explored. From the experimental results, fused tactile-auditory signals had higher accuracy than single signal recognition. The accuracy rates of the test set using fused signals and acceleration and sound pressure signals were 95.29%, 92.09% and 90.07%. In addition, attention vectors are visualized to identify the degree of emphasis on different signals during the recognition process.