Search

Online teaching has become the main teaching method during the epidemic period. Online teaching mode has broken through the current mode of higher education, through the application of educational technology; the teaching form has been expanded in time and space. This paper analyzes the challenges of online teaching in Chinese Universities during the epidemic period, discusses the coping strategies of online teaching in Colleges and universities after the epidemic, and puts forward the construction of a new ecology of online teaching to effectively promote the scientific development of online teaching in Colleges and universities.

Chinese enterprises are facing the opportunity of digital transformation, and all enterprises are advancing in exploration. This paper introduces the trend and challenge of digital transformation of Chinese enterprises. This paper expounds the digital transformation strategy of enterprises as the center. This paper discusses the four development processes of enterprise digital transformation, including digital empowerment, process optimization, digital transformation and digital reengineering. This paper puts forward the methods that Chinese enterprises should adopt in the process of transformation. First of all, the digital transformation of enterprises should be scientifically planned. Then select pilot projects in enterprises and try them out first. After that, the trial effect was evaluated. After summarizing and improving, copy and enlarge the scope. Finally, optimize the operation of the enterprise, and constantly adjust.

The rock thin section images are of great significance to the study of petroleum geological characteristics and oil and gas exploration. Due to the limitations of various factors, the obtained images of rock thin-sections often have low resolution, which limits the researchers’ grasp of their detailed information to some extent. The traditional super-resolution algorithm of neural network will need a large amount of data as a training set, in order to improve rock thin-section image super-resolution reconstruction algorithm texture detail information reduction ability, the paper using single image generative adversarial network for rock thin-section image super-resolution reconstruction, does not need to input a large number of data sets, of single image super-resolution reconstruction image. Rock cast thin section images from an oil field area in Ordos basin were used for training, and peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) evaluation indexes were used for model evaluation. The experimental results show that the super-resolution image processing based on this method has good visual effects and evaluation indexes.

The automatic image annotation is a technology that uses deep neural network to extract features from the input image, and finally converts it into text description. It is currently one of the hot researches of explainable artificial intelligence. The thin section image of rock is an important data source in the field of geological exploration and oil and gas development. It can reflect the microstructure inside the rock. However, in actual research, if you only rely on manual observation to extract features from hundreds of rock images, it will affect the research efficiency and take time and effort. This paper uses GoogLeNet model in the deep convolutional neural network to implement the feature extraction of rock images, and also uses the LSTM model in the deep recurrent neural network to convert the image features into text features, and finally converts the rock images into text descriptions. The automatic image annotation technology of rock images based on deep neural networks not only realizes a step of converting rock images into text, but also assists scholars in the field of petroleum geology to realize efficient research.

In recent years, convolution neural networks have attracted extensive attention from researchers. It has outstanding performance in large-scale image processing, especially in the field of pattern recognition. Combining geological exploration with computer technology, it has achieved good achievements in rock image processing, and it is still being explored in order to better integrate it into practice. For geological exploration researchers, how to perform rapid and effective retrieval of a large number of rock thin sections image is worth investigating. Traditional text-based retrieval methods can no longer meet the requirements. For this reason, this paper attempts to introduce the convolution neural network into the retrieval of rock thin sections and analyze its feasibility in the retrieval of rock thin sections images.

This paper first reviews the concept of business model and business model innovation, the business model frameworks and issues in current enterprise data centres, and then investigates the key factors which drive the data centre transformation and the challenges and risks that the operators of the current or traditional data centres are facing. This paper discusses the main characteristics of the next generation data centre - cloud computing oriented data centre and presents the key concerns of building the cloud computing oriented data centres. Based on the above analysis and discussion, this paper presents a new and practical integrated business model framework to strategically address the key issues regarding the planning, building and operation of cloud computing oriented data centre collectively from business, management and technology perspective based on the strong belief that an enterprise data centre should be built as service oriented platform, and be managed and operated as a pure business. The author has presented, used and applied this framework in several real cases in China during last one year and half with positive feedbacks from the clients.

Last several years, industrial and information technology field have undergone profound changes, entering "Industry 4.0" era. Industry4.0, as a representative of the future of the Fourth Industrial Revolution, evolved from embedded system to the Cyber Physical System (CPS). Manufacturing will be via the Internet, to achieve Internal and external network integration, toward the intelligent direction. This paper introduces the development of Industry 4.0, and the Cyber Physical System is introduced with the example of the Wise Information Technology of 120 (WIT120), then the application of Industry 4.0 in intelligent manufacturing is put forward through the digital factory to the intelligent factory. Finally, the future development direction of Industry 4.0 is analyzed, which provides reference for its application in intelligent manufacturing.

A large number of advanced technology dedicated to research and development smart home applications in the IOT environment, especially using of open-source Arduino and ZigBee wireless communication protocol to build a interoperability smart home system have major value. In the designing of this smart home, researching on the characteristics of ZigBee technology and network topology, making a special effort to analyze the ZigBee protocol specification.It mainly studied and designed the smart gateway based on CC2530 and Arduino, that realize the communication of each devices, and achieve the remote monitoring and wireless control in the home. I n addition, the performance test and power analysis are completed, which provides a strong guarantee for the further development of smart home.

Cooperation of sensors and actors is an important research field in WSAN. To improve the efficiency of WSAN, based on QPSO (Quantum-behaved Particle Swarm Optimization), this paper proposed a new coverage optimization strategy for actor deployment in WSAN. By adopting a number of particles independently searching for solution space, they can share the current global optimal value at a certain communication rate. Through experiments, the results show that the proposed method is more effective than conventional ones in terms of coverage rate and real-time performance.

Based on Leach-C, this paper proposes a novel routing algorithm for energy consumption balance, named EBLeach-C. Using Self-organization Mapping and Kmeans clustering algorithm, the nodes that are adjacent with equal energy are self-organized into a cluster. A new cost function is introduced to select an optimum relay node between cluster head and base station. Simulation results demonstrate that the proposed algorithm can effectively avoid the early dying of cluster which is far away from base station, and it can also balance the energy consumption, and improve the network coverage range. KEYWORD: Wireless Sensor Network; Self-organization Mapping; Clustering routing algorithm; Network life cycle; Particle Swarm Optimization

The flipped classroom is a new pedagogical method, which employs asynchronous video lectures and practice problems as homework, and active, group-based problem solving activities in the classroom. It represents a unique combination of learning theories once thought to be incompatible. Active, problem-based learning activities founded upon a constructivist ideology and instructional lectures derived from direct instruction methods founded upon behaviorist principles. Among others, these include the type of in-class and out-of-class activities, the measures used to evaluate the study, and methodological characteristics for each study. Student perceptions of the flipped classroom are somewhat complex, but are mainly positive overall. Students tend to prefer in-person lectures to video lectures, but prefer interactive classroom activities over lectures. This paper provides course teaching design in universities of China based on the thought of the flipped classroom. Studies are characterized on several dimensions. It suggests that student learning is improved for the flipped compared to traditional classroom. It proposes to study the analysis of teaching effects with different patterns of Chinese university course. It also recommends that teachers consider carefully for leadership of univer sity courses theory frame of the class activities design.

For the reason of high costing on 3D core reconstruction by using CT scanning method, a new method named 3D digital core reconstruction based on rock casting slice images under optical microscope is proposed in this paper. Firstly, the collected casting slice images are processed to acquire the reconstructed image templates, and then multiple-point geostatistics is applied for feature extracting on these image templates and 3D reconstructing on the digital core. The core samples used in the experiment are taken from Sulige region in Ordos basin. The experiment outcome shows that the core aperture distributions and the real value have the same trend and the relative error of porosity is lower than 8%. The above researches show that the rock casting slice image based 3D Digital Core Reconstruction methodology is effective.

Simulations and verifications on graphene electronic devices are foundations for application of graphene in integrated circuits. Modeling on graphene metal-oxide-semiconductor field-effect transistor is implemented with artificial neural network. The proposed model has high accuracy and high efficiency. The computational time for the MOSFET model is decreased significantly. More importantly, the novel model for graphene MOSFET is realized in HSPICE software as a subcircuit, which may obviously increase the efficiency of simulations on graphene large scale integrated circuits. Keywords-graphene; field-effect transistors; modeling; artificial neural network; HSPICE

According to the rough set theory, this paper introduced a neuro-rough model and extends this to a probabilistic domain using a Bayesian framework, trained using a Markov Chain Monte Carlo simulation and the Metropolis algorithms. Firstly, rough set theory was presented, including the granulation of rough set membership function, the network weight formula of probability and rough set formulation. Secondly, the neuro-rough set that was discussed exploits the generalization capacity of neural networks and the transparency advantages of rough set theory. Thirdly, the neuro-rough model was then compared with the genetic algorithm optimized rough set model for the case of modeling of militarized interstate dispute data. Finally, it proposed to construct a neuro-rough model to model interstate conflict between China and its neighboring countries.

Kohonen's Self-Organizing Maps (SOM) is a class of typical artificial neural networks (ANN) with unsupervised learning which has been widely used in clustering tasks, dimensionality reduction, data mining, information extraction, density approximation, data compression, etc. A basic principle of unsupervised learning is the competition mechanism, in which the output neurons compete for activation. In most competitive learning algorithms only one output neuron is activated at any given time. This is realized by means of the so-called winner- takes-all mode. Another mode is winner-takes-more. In this paper, the competitive learning is firstly introduced, the SOM topology and leaning mechanism are then illustrated. Thirdly, some self-organizing maps with incremental learning (SOMIL), such as self-organizing surfaces, evolve self-organizing maps, incremental grid growing and growing hierarchical self-organizing map, are outlined. Finally, the new development of SOMIL is reviewed. Some conclusions are given at the end of the paper.

Reviewing old ones is to better understand new ones and also for innovating. The mapping capability of artificial neural networks is dependent on their structure, i.e., the number of layers and the number of hidden units. Presently, there is no formal way of computing network topology as a function of the complexity of a problem; it is usually selected by trial-and-error and can be rather time consuming. Basically, we make use of two mechanisms that may modify the topology of the network: growth and pruning. This paper firstly discusses some learning algorithms and topologies of classical constructive neural networks. Only incremental or growing algorithms employing supervised learning algorithms are outlined here which includes Tiling algorithm, Tower algorithm, Upstart algorithm, Cascade-Correlation algorithm, Restricted coulomb energy network and Resource-allocation network. For each neural network model, we review their topology structure and learning features. The new development of constructive neural networks is given at the end of the paper.

The mapping capability of artificial neural networks (ANN) is dependent on their structure, i.e., the number of layers and the number of hidden units. There is no formal way of computing network topology as a function of the complexity of a problem. It is usually selected by trial-and-error and can be rather time consuming. Basically, we make use of two mechanisms that may modify the topology of the network: growth and pruning. This paper gives an overview of some classical Growing Neural Networks (GNN) and their new developments. This kind of GNN is also called the ANN with incremental learning. Firstly, some classical GNN with supervised learning are outlined which includes tiling algorithm, tower algorithm, upstart algorithm, cascade-correlation algorithm, restricted coulomb energy network and resource-allocation network. Secondly, a class of classical GNN with unsupervised learning is reviewed, such as self-organizing surfaces, evolve self-organizing maps, incremental grid growing and growing hierarchical self-organizing map. Thirdly, the new developments of GNN, including both supervised learning and unsupervised learning, are surveyed. The conclusion is given at the end of the paper.