This article investigates the bipartite consensus problem for a class of multi-agent systems (MASs) with parameter uncertainty and leader of nonzero input under a signed digraph. Due to the unknown and time-varying input signal of the leader, followers are unable to obtain accurate information about the leader. For this purpose, a distributed adaptive observer is designed based on parameterization theory. Then, considering the existence of parameter uncertainty in the MASs, an auxiliary function is designed to compensate the impact of uncertainty. Afterwards, an adaptive controller with dynamic coupling gain is designed based on observation errors and auxiliary function. Subsequently, it is demonstrated that the MASs with parameter uncertainty and leader of nonzero input can achieve bipartite consensus by stability analysis. Finally, the effectiveness of the proposed scheme is verified through simulation.

This paper presents a new energy optimization management scheme for the smart grid system (SGS), which considers not only the inclusion of renewable energy in energy management but also the feedback sale of redundant renewable energy to the grid, so as to obtain better optimization management results and avoid energy waste. A new performance index function is constructed, which aims to save users' electricity costs and protect energy storage batteries. We construct a periodic iterative self-learning method based on the characteristics that the relevant data of SGS are approximately periodic. The proposed self-learning optimization method is based on adaptive dynamic programming (ADP). The initial iterative control law is obtained by pre-training, and the designed method can be realized by neural networks. Simulation experiments are carried out by using the relevant data of SGS for four weeks. The experimental results show that the new energy management scheme can help users save a lot of electricity costs, and is more effective than some common methods.

In this paper, cluster synchronization of fractional-order complex community networks (FOCCNs) in quaternion-valued filed is addressed based on the non-separation approach. To carry out tasks with different requirements, quaternion-valued FOCCNs are divided into several clusters, each of which owns different dynamic behaviors. Considering the interaction of nodes in the cluster and the influence of external driving, a hybrid controller is designed, in which the coupling strength and feedback control gains are simultaneously regulated with the evolution of states. To establish the cluster synchronization criteria for the quaternion-valued FOCCNs, some analytical approaches, such as the mean value theorem and the proof by contradiction are utilized. Furthermore, for the asymptotical synchronization of fractional-order complex networks, the case with identical nodes is also considered as a special case. Finally, two quaternion-valued FOCCNs are divided to synchronize to the desired trajectory, and a numerical simulation shows the validity of the proposed approach.

Broad learning system (BLS) is an emerging neural network characterized by its rapid processing and robust generalization capabilities. However, determining the appropriate structure for broad learning system is also a challenge. In addition, broad learning system may perform overfitting due to the dependence between nodes in processing fully connected network. To deal with these problems, an efficient ensemble broad learning system based on Dropout and Dropconnect is proposed in this paper. The proposed Dropout ensemble broad learning system randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction stability. The Dropconnect ensemble broad learning system randomly drops connection weights to generate more complementary models by adding input attribute disturbance. The experimental results on the UCI datasets confirm that the method proposed in this paper can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning system. The proposed algorithm outperforms the original BLS in terms of prediction stability and classification accuracy.

Timely detection of abnormal electricity consumption behaviors plays a key role in saving energy. However, the detection of abnormal electricity consumption faces many problems. Imbalanced data are important challenges in this field. When the normal data are much more than the abnormal data, the network can hardly recognize the features of the minority class data, which generates low detection efficiency. Therefore, in this paper, we employ adaptive synthetic sampling (ADASYN) to achieve effective expansion of the minority class data. In addition, we adopt gated recurrent units to complete the classification of electricity consumption data. We conduct detailed experiments to verify this proposed method. Experimental results show that this method is more effective than other methods.

With the development of the Internet, more and more people like to share their daily food, which makes the Internet rich in food image data. Many researchers collect food images on the Internet, label them, and combine machine learning and other methods to achieve food recognition systems. These food recognition systems can quickly help users record their daily diets and analyze their eating habits. The advanced food identification system can currently accurately identify hundreds of foods. At the same time, it can explore the food nutrition content and give food reference suggestions by accessing the food nutrition database. In this paper, we collect and evaluate large-scale food image datasets and food recognition systems.