Ebook: Proceedings of CECNet 2021

Electronics, Communication and Networks coexist and it is not possible to conceive the current society without any of the previous terms. 6G network is currently under development and more researchers are joining the research on 6G. Additionally, some chips able to operate at the Terahertz (THz) scale have been already introduced. Probably, next decade would be the scenario to observe the consolidation of 6G-based technology as well as lots of compliant devices.

The Conference on Electronics, Communications and Networks (CECNet) series has been established as a mature event after ten previous years of existence. CECNet is held annually covering many interrelated groups of topics such as:

• Electronics technology.

• Communication engineering and technology.

• Wireless communications engineering and technology.

• Computer engineering and technology.

The 11th International Conference on Electronics, Communications and Networks (CECNet 2021) was primarily scheduled to be held in Beijing, China on November 18–21, but was finally transformed into an online conference for the same reason as last year (COVID-19).

This book contains the papers accepted and presented at the 11th International Conference on Electronics, Communications and Networks (CECNet 2021), held on 18–21 November 2021 in a virtual way instead of onsite participation in Beijing (China). All papers were carefully reviewed by program committee members and took into consideration the breadth and depth of the research topics that fall into CECNet scope.

CECNet 2021 received 325 submissions and after a vivid discussion stage, the committee decided to accept 88 papers, which represents an acceptance rate of 27.07%.

I would like to thank all the keynote speakers and authors for their effort in preparing a contribution for this leading international conference. Moreover, I am very grateful to the people, especially the program committee members and reviewers, who devoted time to evaluate the papers. It is a great honour to continue with the publication of these proceedings in the prestigious series Frontiers in Artificial Intelligence and Applications (FAIA) by IOS Press. Our particular thanks also go to J. Breuker, N. Guarino, J.N. Kok, R. López de Mántaras, J. Liu, R. Mizoguchi, M. Musen, S.K. Pal and N. Zhong, who are the FAIA series editors, for supporting again this conference.

Finally, I hope you enjoy, so far, your virtual visit to Beijing, although with hopes of attending the conference in the future, face-to face.

Antonio J. Tallón-Ballesteros

Huelva city (Spain)

University of Huelva (Spain)

This paper mainly explores how the user’s perceptual interaction towards a specific website affects the user stickiness and the interaction mechanism of various influencing factors of user stickiness, which may encourage socialized Q & A community operators to adopt more appropriate ways to enhance user’s stickiness. We comprehensively use the planning behavior theory and technology acceptance model with the perceptual perspective of interaction. Based on the framework of “belief → attitude → intention”, an attempt is made to construct a conceptual model of influencing factors of user stickiness in socialized Q & A community by collecting the data through questionnaire survey, and using spss23.0 and amos23.0 to analyze the data and validate the model. The empirical research results prove that the factors such as perceived usefulness, perceived ease of use, information exchange perception, social interaction perception satisfaction, and heart flow experience have positive effects on social users. We conclude that the operators can build and consolidate user engagement, attract and retain the users by enhancing interactive perception, optimizing user experience, and improving their satisfaction.

The article deals with the issues related to the scientometric indexing of the net resources of the group of language teachers and scientists. A detailed accounting of all types of publications allows us to obtain initial information about the level of their Internet engagement. The analysis was carried out including a wide range of genres of publications, the structure of publications, the format and language of publications, the corpus of academic subjects, the language aspects of the publications under study, the composition of the authors of publications, based on their position. The authors’ use of wide opportunities to present their developments on various Internet resources provides them with the opportunity to be detected by search systems based on artificial intelligence (AI) as well as Big Data techniques and to be most fully characterized by existing and prospective scientometric systems.

State-of-Health (SOH) prediction of a Lithium-ion battery is essential for preventing malfunction and maintaining efficient working behaviors for the battery. In practice, this task is difficult due to the high level of noise and complexity. There are many machine learning methods, especially deep learning approaches, that have been proposed to address this problem recently. However, there is much room for improvement because the nature of the battery data is highly non-linear and exhibits higher dependence on multidisciplinary parameters such as resistance, voltage and external conditions the battery is subjected to. In this paper, we propose an approach known as bidirectional sequence-in-sequence, which exploits the dependency of nested cycle-wise and channel-wise battery data. Experimented with real dataset acquired from NASA, our method results in significant reduction of error of approximately up to 32.5%.

Numerical simulation is widely used to study physical systems, although it can be computationally too expensive. To counter this limitation, a surrogate may be used, which is a high-performance model that replaces the main numerical model by using, e.g., a machine learning (ML) regressor that is trained on a previously generated subset of possible inputs and outputs of the numerical model. In this context, inspired by the definition of the mean squared error (MSE) metric, we introduce the pointwise MSE (PMSE) metric, which can give a better insight into the performance of such ML models over the test set, by focusing on every point that forms the physical system. To show the merits of the metric, we will create a dataset of a physics problem that will be used to train an ML surrogate, which will then be evaluated by the metrics. In our experiment, the PMSE contour demonstrates how the model learns the physics in different model regions and, in particular, the correlation between the characteristics of the numerical model and the learning progress can be observed. We therefore conclude that this simple and efficient metric can provide complementary and potentially interpretable information regarding the performance and functionality of the surrogate.

In order to reduce the tracking error of the computer numerical control (CNC) feed system and improve the CNC machining accuracy, a novel prediction model is proposed based on fuzzy C-means robust variational echo state network. Firstly, the feed speed time series is clustered, and then reconstructed for different categories. The multi-stage robust prediction models are established to realize the multi-state robust prediction of the CNC machining feed velocity to reduce the tracking error of the feed system. Finally, the reference and actual time series with different feed speed are used to verify the established models. The results show that the proposed method can reduce the tracking error and realize the effective prediction of the time series of the feed system.

Corporate bond default risk prediction is important for regulators, issuers and investors in the bond market. We propose a new approach for multi-class imbalanced corporate bond risk prediction based on the OVO-SMOTE-Adaboost ensemble model, which integrates the one-versus one (OVO) decomposition method, the synthetic minority over-sampling technique (SMOTE) and the Adaboost ensemble method. We categorize corporate bond default risk into three classes: very low default risk, relatively low default risk and high default risk, which is more scientific than the traditional two-class bond default risk, and carry out empirical experiments by respectively using DT, SVM, Logit and MDA as basic classifiers. Empirical results show that the prediction performance of the OVO-SMOTE-Adaboost (DT) model is overall better than the other three ensemble models such as OVO-SMOTE-Adaboost (SVM), OVO-SMOTE-Adaboost (Logit) and OVO-SMOTE-Adaboost (MDA). In addition, the OVO-SMOTE-Adaboost (DT) model greatly outperforms the OVO-SMOTE (DT) model, which is a single classifier model based on OVO and SMOTE without Adaboost. Therefore, the OVO-SMOTE-Adaboost (DT) model has satisfying performance of multi-class imbalanced corporate bond default risk prediction and is of great practical significance.

For several decades, the detection of epileptic seizures has been an active research topic. The performance of current patient-specific algorithms is satisfactory. However, due to significant variability of EEG data between patients, cross-subject seizure characterization and detection remains a challenging task. The purpose of this study is to propose and investigate a modified convolutional neural network (CNN) architecture based on separable depth-wise convolution for effective automatic cross-subject seizure detection. The architecture is conceived with a reduced number of trainable parameters to reduce the model complexity and storage requirements to easily deploy it in connected devices for real-time seizure detection. The performance of the proposed method is evaluated on two public datasets collected in the Children’s Hospital Boston and the University of Bonn respectively. The method achieves the highest sensitivity-false positive rate/h of 91.93%–0.005, 100%–0.057 for the CHB-MIT and Ubonn datasets respectively.

Alzheimer’s disease (AD) is a degenerative disease of the nervous system. Mild cognitive impairment (MCI) is a condition between brain aging and dementia. The prediction will be divided into stable sMCI and progressive pMCI as a binary task. Structural magnetic resonance imaging (sMRI) can describe structural changes in the brain and provide a diagnostic method for the detection and early prevention of Alzheimer’s disease. In this paper, an automatic disease prediction scheme based on MRI was designed. A dense convolutional network was used as the basic model. By adding a channel attention mechanism to the model, significant feature information in MRI images was extracted, and the unimportant features were ignored or suppressed. The proposed framework is compared with the most advanced methods, and better results are obtained.

Take the parabolic dune of Hobq desert in Inner Mongolia as research object. Based on the GIS platform by using differential GPS data and spatial interpolation to generate DEM, then using Multi-periods high resolution images to acquire the environmental background, at the same time combine with regional wind regime and vegetation condition to measure and analyze the morphology of the parabolic dune. The result shows that the parabolic dune showed U shape in plane, and dune arms point to the west which was also wind direction. The windward slope of longitudinal profile is gentler, while leeward slope is steeper. And cross section wasn’t symmetric. The dune’s average moving speed is 11.76 m/yr. Desert ridge line’s medial axis direction is WNW-ESE, in accord with the direction of prevailing wind and resultant drift potential. Artemisia Ordosicas mainly distribute on leeward slope, two arms, and the plane ground between them, and the annual average vegetation coverage decreased 0.95%. In the long-term effect of resultant wind, the dune keeps moving forward and Artemisia Ordosica between two arms show gradual natural stage recovery which presented zonal distribution. 3S technology has already become important research method in modern Aeolian sand morphology.

As a unique wetland type, forest swamps play an important role in regional carbon cycling and biodiversity conservation. Taking Hani wetland in Jilin province as the research object, we integrated the application of Sentinel-1 radar and Sentinel-2 multispectral images, fully exploited the potential of Sentinel-1 multi-polarization band features and Sentinel-2 red edge index for forest swamp remote sensing identification, and applied the random forest method to realize the extraction of forest swamp distribution information of Hani wetland. The results show that when the optimal number of decision trees for forest swamp information extraction is 1200, the fusion of Sentinel-1VV and VH backscattering coefficient radar band features and Sentinel-2 red-edge band features can significantly improve the extraction accuracy of forest swamp distribution information, and the overall accuracy and Kappa coefficient of forest swamp information extraction in protected areas are as high as 89% and 0.85, respectively. The overall accuracy and Kappa coefficient of forest swamp information extraction in the protected area were 89% and 0.85, respectively. The landscape types of Hani Wetlands of International Importance are diversified, with natural wetlands, artificial wetlands and non-wetland landscape types co-existing. Among the natural wetland types, the forest swamp has the largest area of 27.1 km², accounting for 11.2% of the total area of the reserve; the river has the smallest area of 0.7 km², accounting for 0.3% of the total area of the reserve. The forest swamp extraction method provides data support for the sustainable management of Hani wetlands and case guidance for forest swamp mapping in other regions.

RBF metamodels, which are commonly used in expensive optimization problems, rely on a hyperparameter which affects their prediction. The optimal hyperparameter value is typically unknown and hence needs to be estimated by additional procedures. As such this study examines if this overhead is justified from an overall search effectiveness perspective, namely, if changes in the hyperparameter yield significant performance differences. Analysis based on extensive numerical experiments shows that changes are significant in functions with low to moderate multimodality but are less significant in functions with highly multimodality.

For the purpose of increasing the accuracy of power cable life forecasting and status assessment, improving its life cycle management process, this paper proposes a power cable online life forecasting method and status assessment system based on recurrent neural network and Internet of Things (IoTs). Power cable electrical insulation online monitoring system is established on the first place. Then, recurrent neural network and fuzzy analytical hierarchy process are used in the IoTs based power cable online status assessment architecture to proceed life forecasting and status assessment process. Lastly, example analysis is presented to verify the effectiveness and superiority of the methodology introduced in this paper. It is shown that artificial intelligence and IoTs will also have broad development and application prospect when combined with power cable life cycle management.

It is a trend to use virtual power plant technology to realize demand response and participate in electricity trading. We design and implement the software control platform of virtual power plant for demand response. For this software platform, we analysed the requirements and got the overall architecture of the platform. On this basis, we design and implement the microservice architecture, interface design, basic application function design, advanced application function design, hardware architecture, communication architecture and security encryption of the platform. Finally, we summarize the application of the platform, and put forward the direction of further research and development.

To fully adapt to the distributed access of renewable energy, microgrid technology has been developed rapidly. Aiming at the coordination and efficient regulation of distributed resources in microgrid, this paper proposes a distributed autonomous economic control strategy for microgrid considering event triggering mechanism. First, a distributed autonomous economic control architecture is built to provide a distributed operation architecture for optimal regulation of the microgrid. Secondly, a distributed secondary control strategy based on the consensus control theory is established to realize the economic allocation of active power as well as safe and stable operation of the microgrid. On this basis, an event trigger protocol based on the consensus error of the control variables is constructed, which is conductive to reduce redundant communication. The stability of the event trigger protocol is deduced by means of Lyapunov function analysis. The simulation analysis based on the equivalent microgrid verifies that the proposed control strategy can reduce redundant communication and acquire fair distribution of reactive power and active power among DGs, realizing distributed, economical and safe operation of microgrid.

In this paper, the development and prospect of tower-shaped solar thermal power generation technology are briefly introduced, and the importance of production quality of molten salt storage tank in tower thermal power storage system is proposed. The production technology and construction process of molten salt storage tank are described in detail, and the key technology and multiple problems affecting quality are analysed. Aiming at the problem of fillet weld deformation, this paper proposes a new anti-deformation tooling and welding operation technology. At last, this paper presents a construction technology method and a solution to improve the welding quality of molten salt storage tank, which can effectively solve the problem that the bottom plate of molten salt storage tank is out of standard due to welding.

The solar thermal power generation system adopts a dual-axis timely tracking instrument device, which realizes that the sunlight and the central axis of the heliostat instrument device are kept parallel, and greatly improves the utilization efficiency of the light source and the power generation efficiency. At the same time, the study of instrumentation selection in the solar thermal power generation industry cannot be ignored, which can guarantee the normal operation and basic work quality of solar thermal power projects. Therefore, based on instrumentation devices in the solar thermal power generation industry, this article explores the drawbacks of instrumentation devices in the application, and puts forward several research ideas for the drawbacks. Finally, by taking the tower-type solar thermal power generation instrument device as an example.

During the operation of a 300MW subcritical boiler of a power plant, there is a low temperature of the SCR inlet flue gas under medium and low load conditions. In order to effectively solve the problem of low SCR inlet temperature under low load conditions, and improve the adaptability of the coal type. Three kinds of wide load denitration technology reform schemes are proposed. With the boiler thermal system simulation software BESS, the thermal calculations of the three transformation schemes were carried out. The results show that: the Scheme C is the optimal solution. After the transformation, the temperature of the SCR inlet flue gas increased by 21°C under the ultra-low load condition, and the exhaust gas temperature increased by about 7°C. At the same time, the possible impacts of the reform of the Scheme C and the key issues that need to be paid attention to during the transformation process are evaluated and discussed.

With the gradual reform and development of the power grid, it is of great significance to study how to effectively identify and evaluate the weak links of the power grid for the actual planning, construction, and operation of the power grid. This paper analyzed the power grid’s historical component data and real-time operation state parameters. We established a weak link identification model based on Bayesian reasoning. Firstly, we constructed the node branch Bayesian network according to the network topology relationship. The power transmission distribution factor is modified according to the historical operation load of the grid components, and the conditional probability table is calculated based on the grid structure; finally, we used the maximum possible explanation algorithm in the Bayesian network. The weakness degree of all components in the network is calculated, and the maximum probability weak link sequence is obtained. The correctness and effectiveness of the proposed method are verified by IEEE 39 bus simulation and regional power grid data.

At present, the substation SCD model mainly aims at the modeling of primary equipment and secondary equipment, and the description of auxiliary equipment and substation area model is missing. According to the characteristics of equipment monitoring of the new generation centralized control station, the description of auxiliary equipment model and area model needs to be added to the original IEC61850 standard. In the first mock exam station, the current business requirements of centralized control station are analyzed. A unified model structure of master station is designed. Based on the definition of IEC61850 standard, a method and example of extending auxiliary device model and regional model are given. The proposed auxiliary equipment and area modeling method based on IEC61850 standard can make up for the shortcomings of the original standard, support the equipment monitoring of the new generation centralized control station and realize rich application functions.

Based on the principle of transcritical CO₂ two-stage compression refrigeration system, a virtual simulation teaching platform was developed. Two operation modes can be selected which are practice mode and test mode. According to questions and tips about experiments, students can do simulation experiments by open required valves, running the refrigeration system, adjusting pressure control valves and so on. When these operations are completed, students can save the file of the simulation experiment and exit the system. Then, test marks of students can be exported to Excel for teachers to view. In addition, some risks of operational errors can also be avoided, such as equipment damage. Moreover, if there is a computer, the simulation experiments can be done by this virtual simulation teaching platform, which is very convenient. The virtual simulation teaching platform is innovative and practical. The application of this virtual simulation teaching platform can improve the quality of the traditional teaching in the refrigeration field.

This study accounts current energy consumption of various types of equipments in Chinese container terminals through investigating typical terminals; compares and analyzes the clean energy application technologies from the perspectives of technical level, investment cost, and others; on this basis, construct the predictive model of energy consumption structure, and uses scenario analysis to carry out energy consumption predictions under each scenario and analyzes the effect of policy intervention, technological development and other factors. According to the predictive results, this study holds that in order to optimize energy structure of container terminal, container terminals should strongly promote the application of clean energy to port machinery instead of fuel on the basis of the industrial development and cost reduction of high-power and large-capacity power batteries; at the same time, strengthen policy encouragement and guidance are needed.

This paper mainly studies the development and implementation of the positioning technology of the electric vehicle wireless charging coil, so as to accurately detect the position deviation of the receiving coil, so that the electric vehicle wireless charging system can provide electric energy for electric vehicles more efficiently. Based on the positioning method of electric vehicle based on three detection coils, this paper proposes a calculation method to describe the offset degree of coil based on fuzzy mathematics theory. The algorithm is verified by simulation and experiment, and the influence factors of the error accuracy and the source of the error are analyzed. The work done in this paper has a strong practical significance for the efficient realization of electric vehicle wireless energy transmission.

The outdoor terminal box of converter station’s complex working characteristics and working environment easily leads to the failure of relays in it. The paper analyzes the key factors in relay selection from the perspectives of the characteristics of the operating environment. By comparing the characteristics of different component materials and structure designs, the paper proposes suggestions of type selection of relays in outdoor terminal boxes of converter stations.

This paper presents an estimation method of distribution network reliability planning Investment Based on sequence linearization correlation analysis. Firstly, the planning business index closely related to reliability are selected, and the control objectives of reliability index are decomposed into the promotion objectives of each planning business index through sequence linearization correlation analysis. Then, the typical engineering construction scenarios corresponding to each planning business index are constructed, and the investment required to achieve the corresponding promotion objectives of business index is estimated according to the typical scenarios, Finally, the total investment of reliability planning is obtained. The example shows that the method can be applied to the actual distribution network with complex grid conditions and various planning schemes, and can provide powerful guidance for power supply enterprises to improve the efficiency of capital use