Face recognition is an important part of computer vision, and has a vital role to play in public safety. Because of the problems of low accuracy and low efficiency in the case of uneven image quality and occlusion due to sudden changes in light in face recognition, we design a Siamese Neural Network based on Local Binary Pattern (also called LBP) and Frequency Feature Perception. The network is based on the Siamese neural network and adopts the Uniform LBP algorithm and Frequency Feature perception to achieve face recognition under non-restricted conditions. the LBP algorithm can eliminate the effect of lighting on the image and provide vector-level input to the network model; the frequency feature perception divides the image features into low-frequency features and high-frequency features, and compresses the low-frequency features in the Siamese neural network to increase the network’s recognition efficiency while exchanging information with high-frequency features to retain their feature data while eliminating target noise data. This maintains the recognition rate of the network and improves the computational speed of the network. Simulation experiments are conducted on the standard face datasets CASIA-WebFace, Yale-B, and LFW, and compared with other network models. The experimental results show that the proposed SN-LF network structure in this paper can improve the recognition accuracy of the algorithm and obtain a better recognition accuracy.

Efficient scheduling benefits productivity promotion, energy savings and the customer's satisfaction. In recent years, with a growing concern about the energy saving and environmental impact, energy oriented scheduling is going to be a hot issue for sustainable manufacturing. In this study, we investigate an energy-oriented scheduling problem deriving from the hybrid flow shop with unrelated parallel machine. First, we formulate the scheduling problem with a mixed integer linear programming (MILP) model, which considers two objectives including minimizing the completion time and energy consumption. Second, a hybrid multi-objective teaching-learning based optimization (HMOTLBO) algorithm based on decomposition is proposed. In the proposed HMOTLBO, a new solution presentation and five decoding rules are designed for mining the optimal solution. To reduce the standby energy consumption and turning on/off energy consumption, a greedy shifting algorithm is developed without changing the completion time of a scheduling. To improve the converge speed of the algorithm, a weight matching strategy is designed to avoid randomly matching weight vectors with students. To enhance the exploration and exploitation capacities of the algorithm, A teaching operator based on crossover and a self-learning operator based on a variable neighborhood search(VNS) are proposed. Finally, fourth different experiments are performed on 15 cases, the comparison result verified the effectiveness and the superiority of the proposed algorithm.

In this paper, the unrelated parallel batch processing machine (UPBPM) scheduling problem is addressed to minimize the total energy consumption (TEC) and makespan. Firstly, a mixed-integer line programming model (MILP) of the UPBPM scheduling problem is presented. Secondly, a self-adaptive multiobjective differential evolution (AMODE) algorithm is put forward. Since the parameter value can affect the performance of the algorithm greatly, an adaptive parameter control method is proposed according to the convergence index of the individual and the evolution degree of the population to improve the exploitation and exploration ability of the algorithm. Meanwhile, an adaptive mutation strategy is proposed to improve the algorithm’s convergence and the solutions’ diversity. Finally, to verify the effectiveness of the algorithm, comparative experiments are carried out on 20 instances with 5 different scales. Numerical comparisons indicate that the proposed method can achieve high comprehensive performance.