Emotion recognition is a research hotspot in the field of artificial intelligence. If the human‐computer interaction system can sense human emotion and express emotion, it will make the interaction between the robot and human more natural. In this paper, a multimodal emotion recognition model based on many‐objective optimization algorithm is proposed for the first time. The model integrates voice information and facial information and can simultaneously optimize the accuracy and uniformity of recognition. This paper compares the emotion recognition algorithm based on many‐objective algorithm optimization with the single‐modal emotion recognition model proposed in this paper and the ISMS_ALA model proposed by recent related research. The experimental results show that compared with the single‐mode emotion recognition, the proposed model has a great improvement in each evaluation index. At the same time, the accuracy of emotion recognition is 2.88% higher than that of the ISMS_ALA model. The experimental results show that the many‐objective optimization algorithm can effectively improve the performance of the multimodal emotion recognition model.
The current pneumonia image recognition mainly depends on the doctor's experience, but the CT images of some pneumonia are very similar, which leads to easy misdiagnosis. When using a neural network for pneumonia image recognition, there will be problems such as easy to fall into the local minimum, slow convergence speed and easy to cause oscillation due to the gradient descent method. This paper proposes a quantum BP neural network (QBP) based on quantum particle swarm optimization (QPSO) for pneumonia image recognition. QBP-QPSO realizes efficient training of quantum weights. By comparing the accuracy and speed of the QBP-QPSO and other algorithms for pneumonia CT image recognition, the QBP-QPSO has the advantages of fast convergence speed and high accuracy. Finally, the simulation results of pneumonia image recognition prove the correctness and effectiveness of the method.
In order to solve the NP-hard problem of mobile sink path planning in wireless sensor networks (WSN) where the communication range is modeled as a circular area and overlaps with each other, this paper proposes a sink node path planning method guided by the Hamiltonian of quantum annealing algorithm (EMGH) to balance the energy consumption of wireless sensor networks, improve the network life and solve the energy hole problem. First of all, this paper analyzes the problem in theory, and transforms the characteristics of the problem into a mathematical model. The mathematical model considers that the sensor network itself is a travelling salesman problem (TSP), but also requires the shortest path of the mobile sink node. Then, the path of each node in the sensor network is iterated by quantum annealing algorithm, and an optimal TSP path is obtained by using quantum tunneling effect and quantum circuit to achieve parallelism. Finally, in the case of compressing the solution space, the moving path of the mobile sink node is quantum coded, and the Hamiltonian in the quantum annealing algorithm is taken as the guiding factor, and then the individual dimensions are moved, which improves the accuracy of the algorithm and speeds up the convergence speed of the algorithm. Finally, the feasibility of EMGH is verified by simulation experiments and comparison with other algorithms, which provides a reference for the optimization and improvement of path planning method.