Aiming at the problem that it is difficult for art teachers to take into account each student in the art appreciation education in colleges and universities, this paper proposes a retrieval system... Show More

Aiming at the problem that it is difficult for art teachers to take into account each student in the art appreciation education in colleges and universities, this paper proposes a retrieval system for traditional cultural works of art. Dense connections are used to replace residual connections between bottlenecks in MobileNetV2 network and gradient transmission in the network. The dilution factor is used to control the size of the network to solve the problem of the rapid increase in the number of network channels. In addition, the non-local attention mechanism is effectively combined with the improved MobileNetV2 network structure, which effectively improves the classification accuracy of the network. Compared with VGG16, ResNet18, and ResNet34, the classification accuracy is increased by 21.3%, 9.2%, and 3%, respectively. The method in this paper has achieved good results in the classification of art works. According to the images of art works to be appreciated, it helps students understand the relevant cultural knowledge independently and reduce the burden of teachers.

Given that the current microgrid incorporates highly connected distributed energy sources, the conventional model control methods do not suffice to support complex and ever-changing operating... Show More

Given that the current microgrid incorporates highly connected distributed energy sources, the conventional model control methods do not suffice to support complex and ever-changing operating scenarios. This paper proposes a deep learning-based energy optimization method for microgrid energy management in the new power system scenarios. This article constructs a microgrid cloud edge collaboration architecture, which collects interactive network status data through terminal devices and network edge sides. A microgrid energy management model is constructed based on Bi-LSTM attention in the network cloud. And the model is sunk to provide real-time and efficient comprehensive load and power generation prediction output optimal scheduling decisions at the edge of the network, achieving collaborative control of microgrid light load storage. The simulation based on the actual available microgrid data shows that the proposed Bi-LSTM attention energy management model can achieve rapid analysis and optimize decision-making within 7.3 seconds for complex microgrid operation scenarios.

With the deepening of the Belt and Road Initiative (BRI), many Chinese have been dispatched to Southeast Asian countries to participate in technical support and management. However, there are no OCE... Show More

With the deepening of the Belt and Road Initiative (BRI), many Chinese have been dispatched to Southeast Asian countries to participate in technical support and management. However, there are no OCE schools locally that can provide educational resources for their children. The decision of whether to invest in overseas Chinese-OCE has become a challenge for Chinese education groups. In this paper, the authors put forward an evolutionary game analysis scheme to study the OCE investment decisions among host country governments, students, and Chinese enterprises. The simulation results show that (1) the government's subsidy is always helpful to Chinese enterprise, especially at the beginning stage, (2) applying a soft strength of positive execution and combining with other methods could encourage the enterprise at the beginning and regulate the market later on, and (3) high strength of high support of government for the educational infrastructure is a win-win method for both students and the enterprise. Some managerial insights and suggestions are proposed based on these results.

Traditional residential electricity prediction methods have problems, such as difficulty in ensuring user privacy and poor convergence speed due to the influence of Different Residential Electricity... Show More

Traditional residential electricity prediction methods have problems, such as difficulty in ensuring user privacy and poor convergence speed due to the influence of Different Residential Electricity Consumption (REC) habits. A REC prediction method based on Deep Learning (D-L) and Fed-L under the Cloud Edge Collaboration (CEC) architecture is proposed to address the above issues. First, based on the CEC architecture, combining edge computing and cloud computing center server, the overall model of REC prediction is built. Then, Federated Learning (Fed-L) and D-L model Empirical Mode Decomposition - Long Short-Term Memory (EMD-LSTM) were introduced on the edge side, and the edge side Fed-L depth model was personalized by using EMD-LSTM. Finally, aggregation of edge side models was achieved in the cloud by receiving encrypted model parameters from the edge side and updating and optimizing all edge side models. The results show that the proposed method has the highest REC prediction accuracy, reaching 96.56%, and its performance is superior to the other three comparative algorithms.

While there are numerous serious games that explore cognitive behavioral therapy (CBT) techniques through gamification on smartphones, the framework for developing interactions is not often... Show More

While there are numerous serious games that explore cognitive behavioral therapy (CBT) techniques through gamification on smartphones, the framework for developing interactions is not often thoroughly discussed. The objective of this study is to outline the process of combining CBT techniques, narrative setup, and game mechanics to create two types of interactions (verbal- and physical-based) using the player interaction framework (PIF). The PIF consists of three key sections: setup, aim, and execution. In the setup section, it utilizes the ABCDE (activating events, beliefs, consequences, disputation of beliefs, and effective new approaches) model to combine narrative and CBT techniques such as gratitude and self-monitoring. The aim section is used to break down the intended experience of both the player and their main character, at the same time clarifying the CBT goal of the interaction. Finally, the execution section includes the representation of how players will interact in the game through input and feedback. The efficacy of the framework in visual narrative serious games remains to be investigated through a randomized controlled trial after the completion of our serious game, BlueLine.

In the evolving landscape of power grids, where green transportation and intermittent clean energy play a crucial role, ensuring the security and reliability of the urban network is of utmost... Show More

In the evolving landscape of power grids, where green transportation and intermittent clean energy play a crucial role, ensuring the security and reliability of the urban network is of utmost importance. However, the increasing volatility associated with these new energy sources poses a challenge to the traditional control methods. The large-scale integration of new energy in microgrids often leads to frequency instability and deviation in control performance standards. Addressing these issues, this paper introduces the SCQ(λ) algorithm, which accurately estimates the system's state to enhance controller capabilities. To evaluate the effectiveness of the proposed SCQ(λ) algorithm, the authors employ a load frequency control model in our simulation. In this model, they introduce various load change disturbances, including sine waves, square waves, and step disturbances to simulate realistic scenarios encountered in power systems. Throughout the simulation, they observe a significant reduction in frequency deviation in the case of step perturbation, with the deviation value decreasing by 0.0096.