The success of integrated pest management (IPM) depends on spraying the correct amount of pesticides at an appropriate time and releases of natural enemies or pathogens of the pest in appropriate proportions at critical times, with little cost and minimal effects on the environment. Therefore, control decisions require information on instantaneous killing rates of pesticides and numbers of natural enemies to be released, variables that should depend on the densities of both pest and natural enemy population densities in the field. To describe such a control strategy we have proposed a mathematical model of IPM involving releases of natural enemies in relation to a regulatory factor. The threshold condition for the existence and stability of the pest free periodic solution is provided using a cobweb model, the comparison principle and Floquet theory, which reveals the effects of nonlinear control actions on pest outbreaks. Bifurcation analyses show that the dynamics of the proposed model can be very complex, including multiple attractors and switch-like transition patterns following small random perturbations. Moreover, the random perturbations and nonlinear impulsive control measures could generate complex switching patterns, which show that the pest population could have outbreaks in complex ways due to environmental noise.

To study the role of energy system demand‐side regulation capacity on carbon emission reduction, we proposed a regional integrated energy system (RIES) optimal dispatch model considering carbon trading cost and dynamic demand response (DR). First, based on the framework of the RIES, the impact of DR of transferable load, reducible load, and substitutable load demand on system operation, considering the response characteristics of electrical and thermal load, was analyzed. Second, the carbon quota of the system was analyzed, and the effect of carbon emissions and carbon capture technology on system operation was considered. Finally, a low carbon optimized operation model of RIES was established with system operating cost and operating efficiency as the target, and system capacity and energy storage power as the constraints. The effectiveness of the optimized operation of the improved intelligent evolutionary algorithm nondominated sorting genetic algorithm II (NSGA‐II) was verified as a research method. The results show that the energy efficiency of the system can be improved by tuning the DR of load demand with the application of the optimal operation model, and a coordination optimization on the economic and low carbon in RIES operation can also be achieved by the improved NSGA‐II algorithm.

This paper studies secure consensus control for multi-agent systems subject to denial-of-service (DoS) attacks. The DoS attacks cause changes in topologies, which will destroy the channels of communication and result in network paralysis. Unlike the existing publications with Markov switching, this paper mainly studies the topological structure changes of the subsystem models after DoS attacks. To ensure the consensus of systems, this paper designs an event triggered to reduce the use of the controller and decrease the influence of channel breaks off caused by DoS attacks. On this basis, different Lyapunov functions are established in each period of attack. Then, stochastic and Lyapunov stable theory is used to form the consensus criteria. Moreover, Zeno behavior is excluded by theoretical analysis. Finally, the simulation experiment proves the effectiveness of the proposed protocol.

Melanoma segmentation based on a convolutional neural network (CNN) has recently attracted extensive attention. However, the features captured by CNN are always local that result in discontinuous feature extraction. To solve this problem, we propose a novel multiscale feature fusion network (MSFA-Net). MSFA-Net can extract feature information at different scales through a multiscale feature fusion structure (MSF) in the network and then calibrate and restore the extracted information to achieve the purpose of melanoma segmentation. Specifically, based on the popular encoder-decoder structure, we designed three functional modules, namely MSF, asymmetric skip connection structure (ASCS), and calibration decoder (Decoder). In addition, a weighted cross-entropy loss and two-stage learning rate optimization strategy are designed to train the network more effectively. Compared qualitatively and quantitatively with the representative neural network methods with encoder-decoder structure, such as U-Net, the proposed method can achieve advanced performance.