International Journal of Humanoid Robotics

The present work aims to improve students’ interest in music teaching and promote modern teaching. A distributed application system of artificial intelligence gesture interactive robot is designed through deep learning technology and applied to music perception education. First, the user’s gesture instruction data is collected through the double channel convolution neural network (DCCNN). It uses the double-size convolution kernel to extract feature information in the image and collect the video frame’s gesture instruction. Secondly, a two-stream convolutional neural network (two-stream CNN) recognizes the collected gesture instruction data. The spatial and temporal information is extracted from RGB color mode (RGB) images and optical flow images and input into the two-stream CNN to fuse the prediction results of each network as the final detection result. Then, the distributed system used by the interactive robot is introduced. This structure can improve the stability of the interactive systems and reduce the requirements for local hardware performance. Finally, experiments are conducted to test the gesture command acquisition and recognition network, and the performance of the gesture interactive robot in practice. The results indicate that combining convolution kernels of $5\times 5$ and $7\times 7$ can increase the recognition accuracy of DCCNN to 98% and effectively collect gesture instruction data. The gesture recognition accuracy of two-stream CNN after training reaches 90%, higher than the mainstream dynamic gesture recognition algorithm trained with the same data set. Finally, the recognition test of gesture instructions is carried out on the gesture interactive robot reported here. The results show that the recognition accuracy of the gesture interactive robots is more than 90%, meeting the routine interaction needs. Therefore, the interactive gesture robot has good reliability and stability and is applicable to music perception teaching. The research reported here has guiding significance for establishing music teaching with multiple perception modes.

The objectives are to explore the application effect of deep learning (DL), neural network (NN) and human–machine interaction (HMI) technology in caricature style recognition and classification in the environment of artificial intelligence (AI). It provides a realistic basis for the integration of caricature and AI technology. The convolutional neural network (CNN) model is optimized, and the ARtoolkit, JAVA-based processing and photoshop are applied, combined with an augmented reality (AR) editor to register the logo of caricature. The results indicate that the output value of the optimized CNN is the largest near the fourth neural node, and the output values of the remaining neural nodes are almost all close to zero. The label value of the cat image is the same as the output value, and the image label range is [0, 10]. The use of AR technology can make caricature images have animation functions, giving people the visual experience that the lotus can move, and the caricature style has changed. When the screen is not touched, the fish under the lotus is in a static state. When the screen is touched with the hand, the fish swims away quickly, indicating that the function of HMI is realized. Therefore, the CNN and HMI technology under AI can successfully perform caricature style recognition and classification, which can provide an experimental reference for the subsequent intelligent development of caricature.

This work aims to construct and optimize the public emotion network communication model under the artificial intelligence (AI) environment and provide a new research direction for exploring public emotion network communication with intelligent human–computer interaction (HCI). The main challenge of this research is the lack of interactivity of intelligent human–computer expression design, and the accuracy of emotion recognition is not high. First, the theoretical analysis of network public opinion is made, and the network public opinion calculation method and emotion recognition method based on deep learning are proposed. On this basis, the public emotion network communication model is established, and the model’s communication mechanism and rules are described in detail. Next, the emotion calculation of human–computer expression interaction and the emotion expression mode of the humanoid robot are proposed, which provides an experimental basis for HCI and public emotion network communication analysis. According to the data of email network and microblog network in the real network, the network degree distribution map is established. The statistical results show that email and microblog networks belong to power law distribution, and the aggregation coefficient is relatively high. Microblog network degree changes slowly, and more points are scattered in the middle area. In a practical sense, when the positive and negative emotions in the public emotion network communication model are input into the bionic robot, the robot can show happy and lost expressions. The results show that compared with the traditional convolutional neural network (CNN) model or recurrent neural network (RNN) model, the RNN–CNN structure model of RNN combined with CNN reduces the waiting time by about 20% and improves the algorithm accuracy by at least 3.1%. The public emotion network communication model based on deep learning and intelligent HCI can accurately reflect the public emotion state in the network, which provides a practical basis for the application of AI technology in network public opinion judgment.

Autism is a disease that manifests as social communication disorders and repetitive sensory movements. The current incidence of autism continues to rise globally, and the number of children with autism is also increasing. The treatment of autistic children in China is mainly intervention, but experienced autism instructors are lacking. Here, machine learning and artificial intelligence (AI) algorithms are adopted as the technical foundation to build a system that measures the emotional performance of autistic students in the classroom based on actual application scenarios. By analyzing the classroom learning data of autistic children, the students’ emotions can be effectively judged to help teachers evaluate and track their classroom performance and reduce teachers’ burden. Results demonstrate that when the matrix composed of frame sequences and key point coordinates is used as the input, the spatio-temporal graph convolutional network is determined as the principal model of action recognition, with an accuracy of 90%, and the participation score can be obtained by calculating the action response time. In the experimental process of facial expression recognition, the random forest’s classification accuracy of the feature point sequence based on images can reach 99%. Therefore, the random forest is determined as the principal classifier for facial expression recognition. After the relationship between expression intensity, pleasure, and expression category is analyzed, the scoring method is designed. The experiment also discovers that painting can be a rehabilitation therapy for children with autism. The above results can provide a theoretical foundation for the treatment of autistic children.

Various artistic expressions of ice and snow landscapes are deeply loved by the public. To study the application of virtual reality (VR) technology in the design of ice and snow landscape based on human–computer interaction (HCI), Harbin ice and snow landscape is taken as the research object. By applying HCI technology and VR technology, the design of ice and snow landscape is explored. VR technology allows the public to appreciate related things through interactive technology. The application of HCI technology and VR technology in the design of ice and snow landscape has established a system with the theme of ice and snow design, and created a virtual world of ice and snow in the system, enabling designers to be in a VR environment. During the design process, creators can enjoy a more comprehensive experience, constantly looking for the best visual area to stimulate their innovative thinking and inspiration. The results found that the designed system can present a better ice and snow landscape for the public, promote the rapid and stable development of ice and snow sculptures and landscapes, and promote the development of the local economy to a certain extent. Besides, the system has certain reference significance for the use of VR technology to study ice and snow landscapes, and also provides new ideas for the design of other types of landscapes.

To enable educational robots to better accompany children’s learning and growth, first, the encoder part of the image description model is established based on the convolutional neural network (CNN), and the decoder part of the image description model is built by the long short-term memory (LSTM). The attention mechanism is combined with the input stage, LSTM, and the output stage of the model. Second, three-layer stacked LSTM is used to improve and optimize the model. Artificial intelligence (AI) challenger data set is used to test the constructed model, and bilingual evaluation understudy (BLEU) and metric for evaluation of translation with explicit ordering (METEOR) are used to evaluate the model. Finally, 48 children are used as the research objects to study the application effect of the model. The results show that the BLEU-1, BLEU-2, BLEU-3, and BLEU-4 values of the constructed model are higher than those of the neural image caption (NIC) model during the entire iteration process. This model begins to converge when the number of iterations is 20,000. However, the NIC model starts to converge when the number of iterations is 45,000. The constructed model has a faster convergence speed. The scores of BLEU-1, BLEU-2, BLEU-3, and BLEU-4 of the constructed model are 0.687, 0.54, 0.432, and 0.348, respectively, and the score of METEOR is 0.187, which is higher than other models. In the actual application, the learning efficiency and effect of children who use this model for learning are better than the traditional teaching effect. The research results can help to improve the auxiliary role of educational robots in children’s learning, which has very important practical significance.