Mobile Information Systems

Mobile Information Systems / 2021 / Article
Special Issue

Edge Intelligence in Internet of Things using Machine Learning

View this Special Issue

Research Article | Open Access

Volume 2021 |Article ID 9938325 | https://doi.org/10.1155/2021/9938325

Qiao Qu, Cheng Liu, Xinzhong Bao, "E-Commerce Enterprise Supply Chain Financing Risk Assessment Based on Linked Data Mining and Edge Computing", Mobile Information Systems, vol. 2021, Article ID 9938325, 9 pages, 2021. https://doi.org/10.1155/2021/9938325

E-Commerce Enterprise Supply Chain Financing Risk Assessment Based on Linked Data Mining and Edge Computing

Academic Editor: Muhammad Usman
Received27 Mar 2021
Revised28 Apr 2021
Accepted07 May 2021
Published19 May 2021

Abstract

In recent years, the rapid development of information technology has affected the way the world economy operates. The emergence of e-commerce has greatly shortened the time and space distance between economic participants and maximized the sharing of resources. However, the financial management and risk assessment capabilities of the existing supply are insufficient to adapt to the rapidly developing new environment. This article uses a combination of normative analysis and empirical analysis to analyze the status quo of the supply chain of small and medium e-commerce companies. First, this article establishes an evaluation framework for the supply chain of e-commerce companies based on edge computing. Second, according to the distribution of the supply chain, this article adds the member’s predetermined quota, reputation, execution time, and other indicators as parameters to establish a fuzzy neural network model. On this basis, combined with the price regression model, the pricing plan is evaluated. The results show that the financing risk obtained by this model differs very little from the actual risk. The above-mentioned model constructs an e-commerce enterprise supply chain financing risk management model that adapts to the environment of the new era.

1. Introduction

Nowadays, with the rise of the network economy environment, e-commerce companies have gradually become the mainstream of domestic and foreign business activities, and they are in a period of rapid development [1, 2]. E-commerce companies can realize information exchange faster and more conveniently and provide more detailed resource information for both parties for the transaction as much as possible, which greatly shortens the time for transaction decision-making. This e-commerce model improves the success rate of transactions and plays an integrated role in the resources of the entire society [35]. The e-commerce enterprise platform is open and shared, and it has strong advantages for both enterprises and academia in research on consumer behavior and information control [6]. At present, there are still many problems and shortcomings, and they cause the relatively lagging development of the enterprise [7]. Therefore, studying the financial management mode has important theoretical and practical significance in this period [810].

In the aspect of enterprise supply chain management, Hameed et al. [11] pointed out that, due to the relatively flat and simple organizational structure, the main problem affecting the performance of SMEs is the lack of funding sources for purchasing complex and expensive software and hiring competitive intelligence experts. The market when continuously optimizing the financial management mode is to adapt to the constantly changing business environment [12, 13]. Dutta et al. [14] believes that what enterprises in the new era need is a new type of financial management model, so the financial management model should also be innovated and reformed in time to adapt to the development of the times. Jensen pointed out that the information system in enterprise management under e-commerce needs to be updated continuously. Tan et al. [15] pointed out that the contribution of SMEs to a country’s economic growth is widely recognized. In the context of e-commerce, the comprehensive evaluation of supply chain financing risks and the determination of a scientific and reasonable performance evaluation system are the most important. Consumers’ consumption habits have shifted from offline to online, which requires SMEs to adopt more e-commerce models for business operations [16].

However, the financial management and risk assessment capabilities of the existing supply are insufficient to adapt to the rapidly developing new environment [17, 18]. Therefore, studying the financial management mode that is suitable has important theoretical and practical significance in this period [19]. This article uses a combination of normative analysis and empirical analysis to analyze the status quo of the supply chain of small and medium e-commerce companies. In the second chapter, we introduced an overview of edge computing and enterprise supply chain management. In the third chapter, we discuss the selection model of e-commerce enterprise supply chain evaluation indicators based on cluster analysis and associated data mining. In the fourth chapter, we discuss the financing model of e-commerce enterprise supply chain based on fuzzy neural network. Finally, we summarize the methods and shortcomings of this article in the fifth chapter.

2.1. Edge Computing

In the field of intelligent computing, based on the development of cloud computing, edge computing is applied to the Internet service environment, and mobile edge computing (MEC) technology is born. MEC is a new type of network structure, running and providing information technology services and cloud computing capabilities [20, 21]. Now, this method has become a standardized technology. The basic framework of mobile edge computing is shown in Figure 1.

The actual value of edge computing continues to increase. With the explosive growth of the demand for Internet of Things device access, the demand for analysis and computing power on the MEC side will double [22, 23]. MEC, which has the characteristics of low latency and low energy consumption, can fully meet the needs of users adaptively, so as to achieve the goal of rapid response and agile deployment [24, 25]. In accordance with the trend, MEC will not only mobilize and integrate resources according to the needs of different scenarios in the development of terrestrial communications but also bring about major changes to future maritime communications.

2.2. E-Commerce Enterprise Supply Chain Evaluation

The emergence of e-commerce has greatly shortened the time and space distances between economic participants and maximized the sharing of resources [2628]. However, nowadays, most of the small- and medium-sized e-commerce companies in our country have low financial management and backward financial management models, which are unable to adapt to the new competition and new challenges brought about by rapid development [29]. E-commerce companies can realize information exchange faster and more conveniently and provide transaction parties with more detailed resource information as much as possible, which greatly shortens the time for transaction decision-making, improves the success rate of transactions, and also plays a significant role in the resources of the whole society. In the context of e-commerce, the comprehensive evaluation of supply chain financing risks and the determination of a scientific and reasonable performance evaluation system are the most important [30].

According to the characteristics of the supply chain financing of e-commerce enterprises and following the ideas and principles of the evaluation index system design, this paper will gradually carry out the relevant construction of the supply chain financing performance evaluation system under the background of e-commerce. In the context of e-commerce, the comprehensive evaluation of supply chain financing risks and the determination of a scientific and reasonable performance evaluation system are the most important. Consumers’ consumption habits have shifted from offline to online, which requires SMEs to adopt more e-commerce models for business operations. At present, there are still many problems and shortcomings, and they cause the relatively lagging development of the enterprise. Therefore, studying the financial management mode has important theoretical and practical significance in this period.

3. E-Commerce Enterprise Supply Chain Evaluation Index Selection Model

3.1. The Establishment of Cluster Analysis Model

When goods or labor is treated as commodities and exchanged to meet our own needs, we need to set prices for them [31]. When a commodity has no value, the price no longer exists, because its value corresponds to the corresponding price. The task pricing in this article first follows the basic principles of the law of value, and, secondly, the price cluster analysis is a multivariate statistical analysis to quantitatively study the classification problem according to the characteristics of the thing itself [32, 33]. The basic idea is to divide the data into several categories according to the distance, so that the “difference” of the data within the category is as small as possible, and the “difference” between the categories is as large as possible [34]. The clustering of sample individuals is usually called type clustering.

Use Euclidean distance to measure the closeness between indicators. Euclidean distance is the straight-line distance between two points in space [35]. In the context of e-commerce, the comprehensive evaluation of supply chain financing risks and the determination of a scientific and reasonable performance evaluation system are the most important. The weight of each feature parameter is equal, and the weight represents the distance between two indices. The calculation formula is as follows:

In the above formula, .

The specific process of cluster analysis is as follows:(1)Combine the two closest units into one category to form a category, and calculate the distance between the newly generated category and the other categories to form a new distance matrix [36].(2)According to the same principle as the second step, merge the two categories with the closest distance. If the number of categories is still greater than 1, the model continues to repeat this step until all the data is merged into one category.

The task points in Annex 1 are firstly clustered [37, 38]. Figure 2 shows pedigree diagram of the supply chain indicators of the e-commerce enterprise.

As shown in Figure 2, the 835 task points in Annex 1 can be divided into 3 clusters according to latitude and longitude. Each cluster represents a task area point in a different range of latitude and longitude [39, 40]. E-commerce companies can realize information exchange faster and more conveniently and provide transaction parties with more detailed resource information as much as possible, which greatly shortens the time for transaction decision-making, improves the success rate of transactions, and also plays a significant role in the resources of the whole society. The three clusters have large differences; that is, they are far apart [4143]. Next, the center positions of the three clusters are obtained by this method. Then, the distance between the component and the center of the area can also be obtained. Then the distance between the member and the center of the region can be obtained. At present, there are still many problems and shortcomings, and they cause the relatively lagging development of the enterprise [44]. Therefore, studying the financial management mode has important theoretical and practical significance in this period.

3.2. Establishment and Solution of K-Means Algorithm Model

The optimal clustering result is obtained through iterative optimization of the divided mean.

Algorithm steps are as follows:

Here, we substitute the data of the three classes obtained by the Q-type clustering analysis into the calculations and obtain the cluster centers of each class after 20 iterations [45]. The basic idea is to divide the data into several categories according to the distance, so that the “difference” of the data within the category is as small as possible, and the “difference” between the categories is as large as possible. The latitude and longitude coordinates of the cluster centers are shown in Table 1.


Final cluster center
Clustering
123

Latitude22.6723.0223.11
Longitude114.04113.73113.23

Next, use the data in Annex 1 to obtain the average value of task pricing in the 3 regions. Combine Annex 2 to obtain the distance from each member to the 3 cluster centers and then to obtain the average distance from all members to the 3 cluster centers. The distance from the member to the cluster center and the average price of various cluster tasks are shown in Table 2.


Clustering
123

Task pricing average69.0768.0468.11
Average distance between members and cluster center (km)1.5461.6021.825

The specific data of the number of corresponding members and the number of tasks in each cluster area is shown in Table 3.


Clustering
123

Number of members538451988
Number of tasks202190443

According to Table 3, analyzing the relationship between supply and demand and pricing, the results show that all three regions can meet the supply and demand ratio <1 [46]. The clustering of sample individuals is usually called type clustering, and the clustering of research variables is called type clustering; that is, the number of tasks is less than the number of members, so there will be no overtasking or understaffing.

3.3. Determination of Weights-Establishment and Solution of Analytic Hierarchy Process Model

By pairwise comparison, the method of establishing a pairwise comparison matrix is used to compare the influences of factors [47]. E-commerce companies can realize information exchange faster and more conveniently and provide transaction parties with more detailed resource information as much as possible, which greatly shortens the time for transaction decision-making, improves the success rate of transactions, and also plays a significant role in the resources of the whole society. According to the meaning of the question, the following judgment matrix can be constructed:

is the supply-demand ratio, and is the corresponding weight of the influence of the two factors on the task completion rate. Finally, we get the comprehensive index of task pricing:

Because the dimensions of and are different, large errors will occur in the calculation.

According to formula (5), the two types of data are normalized, and then the result is obtained by drawing the image. The relationship between comprehensive indicators and task pricing is shown in Figure 3.

It can be judged that the curve in Figure 3 fits well; that is, the relationship curve between the obtained comprehensive indicators and task pricing is more reasonable. Within the scope of the question data, the task pricing increases with the increase of the comprehensive index.

4. E-Commerce Enterprise Supply Chain Financing Model

4.1. Supply Chain Task Packaging Plan

If the tasks are concentrated and the members are also concentrated in this area, then, in this area, members will compete to choose the task, which may lead to malicious snatching, resulting in a low task completion rate. Therefore, we can consider a scheme of jointly packaged and released tasks; that is, several tasks are bundled and handed over to one user to complete. Since the task points are not very far apart, the neighboring task points can be packed [48]. Here, by drawing the scatter diagram of the task point distribution in Annex 1, 100 task point centers are selected, and the task points with a radius of 16 km from the task center point are packaged and released as a task package. The task executor will comprehensively consider the time when the member gets the task release status and the quota situation to obtain the final result. At present, there are still many problems and shortcomings, and they cause the relatively lagging development of the enterprise. Therefore, studying the financial management mode has important theoretical and practical significance in this period. The scatter diagram of the supply chain task point distribution is shown in Figure 4.

4.2. Establishment of Fuzzy Neural Network Model

The neural network that uses nonlinear prediction is usually a backpropagation neural model (BP model). Each represents the impact task. There are 7 factors related to price. The output layer has a node to build the relationship with the model. The neurons in the middle layer are not connected to each other, while the neurons in the adjacent layer are connected by weights. The structure of the fuzzy neural network model is shown in Figure 5.

The task is packaged; that is, several tasks are bundled and released, so that the tasks that originally need to be assigned to multiple members are completed by the same member. The basic idea is to divide the data into several categories according to the distance, so that the “difference” of the data within the category is as small as possible, and the “difference” between the categories is as large as possible. The clustering of sample individuals is usually called type clustering, and the clustering of research variables is called type clustering. The packaged task package will be priced slightly lower than the sum of the single pricing when it is not packaged.

After packaging, the task with the smallest number in the package is a relative single-package task. The number of tasks in other packages is a multiple of this relative to the actual number of single-package tasks as the relative number. Suppose that is the price of the commodity, is the price when it is not packaged, and is the relative cost coefficient of the relative single-package task.

When formula (7) satisfies the above conditions, there are

In the second search, the parameter obtained in the first search is searched again in its neighborhood. The sum of the relative error squares between actual and theoretical relative pricing is calculated and its minimum value is used as the objective function.

At this time, the relative error squared sum of the relative pricing is , and the relative error value is small.

The basic idea is to divide the data into several categories according to the distance, so that the “difference” of the data within the category is as small as possible, and the “difference” between the categories is as large as possible. The clustering of sample individuals is usually called type clustering, and the clustering of research variables is called type clustering. The evaluation of the supply chain level of e-commerce companies is shown in Figure 6.

The pricing obtained through the model is established by the fuzzy neural network. Therefore, it can be shown that the model established by this question is reasonable and can be used for packaging.

In this article, we will influence the new pricing parameters. Related parameters include the salary level of the employee where the task is located, the complexity of the task, the reputation value of the member, the member's scheduled task limit, and the member's scheduled task start time. For changes that affect the pricing parameters, 0 is not affected. The knowledge base of some rules of the e-commerce supply chain is shown in Table 4.


IfThen

Serial number






111
211
31−1
41−1
51−1
611
71−1

E-commerce companies can realize information exchange faster and more conveniently and provide transaction parties with more detailed resource information as much as possible, which greatly shortens the time for transaction decision-making, improves the success rate of transactions, and also plays a significant role in the resources of the whole society. All possible combinations of rules are obtained from the given rules after repeated learning, and the factors that affect pricing and the data that lead to price changes are input into the system, and the learning rate is . This chapter first designs a scale to test the credibility and validity of the questionnaire and do a factor analysis on the survey data. The analysis shows the benefits of capital and the degree of decentralization of financial management. Play a major role in the above three submodes. Through the structural equation test, it is concluded that the three hypotheses all pass the test, and the empirical model fits well with the survey data. Studies have shown that the capital management, accounting information disclosure, and financial organization of SMEs are mutually reinforcing and complementary.

At this stage, in the e-commerce environment, the core of financial management of SMEs in our country is the allocation of financial rights, capital operation, and information. It is disclosed that the three submodels can be the main content of the SME financial management model under the current environment. Therefore, the new model should integrate the above three submodels and make them an organic unity. At present, there are still many problems and shortcomings, and they cause the relatively lagging development of the enterprise. Therefore, studying the financial management mode has important theoretical and practical significance in this period. The three submodels restrict and cooperate with each other in function and can effectively play positive influence.

5. Conclusion

At present, there are still many problems and shortcomings, which hinder the good development of the enterprise and cause the relatively lagging development of the enterprise, and it is difficult to adapt to the current increasingly competitive market environment. Therefore, studying the financial management mode that is suitable under the e-commerce has important theoretical and practical significance in this period. In the context of e-commerce, the comprehensive evaluation of supply chain financing risks and the determination of a scientific and reasonable performance evaluation system are the most important. Consumers' consumption habits have shifted from offline to online, which requires SMEs to adopt more e-commerce models for business operations. E-commerce companies can realize information exchange faster and more conveniently and provide transaction parties with more detailed resource information as much as possible, which greatly shortens the time for transaction decision-making, improves the success rate of transactions, and also plays a significant role in the resources of the whole society. However, the financial management and risk assessment capabilities of the existing supply are insufficient to adapt to the rapidly developing new environment. Therefore, studying the financial management mode that is suitable under the e-commerce has important theoretical and practical significance in this period. This article uses a combination of normative analysis and empirical analysis to analyze the status quo of the supply chain of small and medium e-commerce companies. This paper conducts innovative research on the financial management mode under the environment of e-commerce enterprises and proposes a new financial management mode. Although some progress has been made, there are still some limitations in the research, and there are still many contents related to the paper which need to be studied.

Data Availability

The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.

Conflicts of Interest

The authors declare that there are no conflicts of interest.

References

  1. O. Durowoju, H. K. Chan, and X. Wang, “Investigation of the effect of e-platform information security breaches: a small and medium enterprise supply chain perspective,” IEEE Transactions on Engineering Management, vol. 73, no. 3, pp. 1–16, 2020. View at: Publisher Site | Google Scholar
  2. H. Lu, “Analysis of economic benefit of e-commerce business in oceangoing enterprises,” Journal of Coastal Research, vol. 106, no. 1, p. 217, 2020. View at: Publisher Site | Google Scholar
  3. B. Zhang, R. Tan, and C. J. Lin, “Forecasting of e-commerce transaction volume using a hybrid of extreme learning machine and improved moth-flame optimization algorithm,” Applied Intelligence, vol. 51, pp. 1–14, 2020. View at: Google Scholar
  4. S. Gao, X. Chen, Z. Ren, D. Zhao, and R. Yan, “Meaningful answer generation of e-commerce question-answering,” ACM Transactions on Information Systems, vol. 39, no. 2, pp. 1–26, 2021. View at: Publisher Site | Google Scholar
  5. A. Vinsensius, Y. Wang, E. P. Chew et al., “Dynamic incentive mechanism for delivery slot management in e-commerce attended home delivery,” Transportation Science, vol. 54, 2020. View at: Publisher Site | Google Scholar
  6. W. Xuan and T. N. Chi, “New retail versus traditional retail in e-commerce: channel establishment, price competition, and consumer recognition,” Annals of Operations Research, vol. 291, 2020. View at: Publisher Site | Google Scholar
  7. M. Mao, J. Lu, J. Han, and G. Zhang, “Multiobjective e-commerce recommendations based on hypergraph ranking,” Information Sciences, vol. 471, pp. 269–287, 2019. View at: Publisher Site | Google Scholar
  8. I. M. Gee, B. R. Heard, M. E. Webber, and S. A. Miller, “The future of food: environmental lessons from e-commerce,” Environmental Science & Technology, vol. 54, no. 23, pp. 14776–14784, 2020. View at: Publisher Site | Google Scholar
  9. S. Liu, C. Newman, C. D. Buesching et al., “E-commerce promotes trade in invasive turtles in China,” Oryx, vol. 55, pp. 1–4, 2020. View at: Publisher Site | Google Scholar
  10. A.-A. Guindon and D. J. Wright, “Analytical approach to quantitative risk assessment for solar power projects,” Renewable and Sustainable Energy Reviews, vol. 133, Article ID 110262, 2020. View at: Publisher Site | Google Scholar
  11. H. B. Hameed, Y. Ali, and A. Petrillo, “Environmental risk assessment of e-waste in developing countries by using the modified-SIRA method,” Science of the Total Environment, vol. 733, Article ID 138525, 2020. View at: Publisher Site | Google Scholar
  12. J. Leivo, E. Anttonen, S. S. Jolly et al., “3037The prognostic significance of grade of ischemia in patients with STEMI: a substudy of the randomized trial of primary PCI with or without routine manual thrombectomy (total trial),” European Heart Journal, vol. 40, no. 1, 2019. View at: Publisher Site | Google Scholar
  13. B. G. Reguero, M. W. Beck, D. Schmid et al., “Financing coastal resilience by combining nature-based risk reduction with insurance,” Ecological Economics, vol. 169, 2020. View at: Publisher Site | Google Scholar
  14. S. Dutta, G. Pregartner, F. G. Rücker et al., “Functional classification of tp53 mutations in acute myeloid leukemia,” Blood, vol. 134, no. 1, p. 2725, 2019. View at: Publisher Site | Google Scholar
  15. R. R. Tan, K. B. Aviso, and D. K. S. Ng, “Optimization models for financing innovations in green energy technologies,” Renewable and Sustainable Energy Reviews, vol. 113, Article ID 109258, 2019. View at: Publisher Site | Google Scholar
  16. P. Zhang, M. Durresi, and A. Durresi, “Multi-access edge computing aided mobility for privacy protection in Internet of Things,” Computing, vol. 101, no. 7, pp. 729–742, 2019. View at: Publisher Site | Google Scholar
  17. A. Boukerche and V. Soto, “Computation offloading and retrieval for vehicular edge computing,” ACM Computing Surveys (CSUR), vol. 53, 2020. View at: Publisher Site | Google Scholar
  18. S. Kim, T. Choi, S. Song et al., “Special issue on 5G & B5G enabling edge computing, big data and deep learning technologies,” ETRI Journal, vol. 42, no. 5, 2020. View at: Publisher Site | Google Scholar
  19. L. Lin, W. Zhou, and Z. Zhao, “Analytical modeling of noma-based mobile edge computing systems with randomly located users,” IEEE Communications Letters, vol. 24, no. 12, 2020. View at: Publisher Site | Google Scholar
  20. L. Zhou, Y. Hong, S. Wang et al., “Learning centric wireless resource allocation for edge computing: algorithm and experiment,” IEEE Transactions on Vehicular Technology, vol. 70, no. 1, 1 page, 2020. View at: Publisher Site | Google Scholar
  21. X. Xiong, K. Zheng, L. Lei et al., “Resource allocation based on deep reinforcement learning in iot edge computing,” IEEE Journal on Selected Areas in Communications, vol. 38, no. 6, 1 page, 2020. View at: Publisher Site | Google Scholar
  22. X. Hong, L. Liang, X. Jie et al., “Joint task assignment and resource allocation for d2d-enabled mobile-edge computing,” IEEE Transactions on Communications, vol. 67, no. 6, 2019. View at: Publisher Site | Google Scholar
  23. M.-P. Hosseini, T. X. Tran, D. Pompili, K. Elisevich, and H. Soltanian-Zadeh, “Multimodal data analysis of epileptic EEG and Rs-fMRI via deep learning and edge computing,” Artificial Intelligence in Medicine, vol. 104, Article ID 101813, 2020. View at: Publisher Site | Google Scholar
  24. Y. Dai, D. Xu, K. Zhang et al., “Deep reinforcement learning and permissioned blockchain for content caching in vehicular edge computing and networks,” IEEE Transactions on Vehicular Technology, vol. 69, no. 4, 2020. View at: Publisher Site | Google Scholar
  25. O. Laureniu, D. Norbert, C. Octavian et al., “Edge computing in space: field programmable gate array-based solutions for spectral and probabilistic analysis of time series,” The Review of Scientific Instruments, vol. 90, no. 11, Article ID 114501, 2019. View at: Publisher Site | Google Scholar
  26. A. Mehrabi, M. Siekkinen, Y-J. Antti et al., “Edge computing assisted adaptive mobile video streaming,” IEEE Transactions on Mobile Computing, vol. 18, 2019. View at: Publisher Site | Google Scholar
  27. W. Zhang, Z. Zhang, S. Zeadally et al., “Efficient task scheduling with stochastic delay cost in mobile edge computing,” IEEE Communications Letters, vol. 23, 2019. View at: Publisher Site | Google Scholar
  28. A. Gumaei, M. Al-Rakhami, M. M. Hassan et al., “Deep learning and blockchain with edge computing for 5g-enabled drone identification and flight mode detection,” IEEE Network, vol. 35, no. 1, pp. 94–100, 2021. View at: Publisher Site | Google Scholar
  29. W.-J. Chang, L.-B. Chen, C.-Y. Sie, and C.-H. Yang, “An artificial intelligence edge computing-based assistive system for visually impaired pedestrian safety at zebra crossings,” IEEE Transactions on Consumer Electronics, vol. 67, no. 1, pp. 3–11, 2021. View at: Publisher Site | Google Scholar
  30. B. Hu and J. Li, “An edge computing framework for powertrain control system optimization of intelligent and connected vehicles based on curiosity-driven deep reinforcement learning,” IEEE Transactions on Industrial Electronics, vol. 68, 2020. View at: Publisher Site | Google Scholar
  31. S. G. Chen, F. J. Lin, C. H. Liang et al., “Intelligent maximum power factor searching control using recurrent Chebyshev fuzzy neural network current angle controller for Synrm drive system,” IEEE Transactions on Power Electronics, vol. 36, no. 3, 2020. View at: Publisher Site | Google Scholar
  32. H. Li, C. Li, D. Ouyang, S. K. Nguang, and Z. He, “Observer-based dissipativity control for t-s fuzzy neural networks with distributed time-varying delays,” IEEE Transactions on Cybernetics, vol. 16, no. 99, pp. 1–11, 2020. View at: Publisher Site | Google Scholar
  33. Y. D. Koo, H. Seon Jo, M. G. Na, K. H. Yoo, and C.-H. Kim, “Prediction of the internal states of a nuclear power plant containment in LOCAs using rule-dropout deep fuzzy neural networks,” Annals of Nuclear Energy, vol. 156, no. 3, Article ID 108180, 2021. View at: Publisher Site | Google Scholar
  34. R. M. Wang, Y. N. Zhang, Y. Q. Chen et al., “Fuzzy neural network-based chaos synchronization for a class of fractional-order chaotic systems: an adaptive sliding mode control approach,” Nonlinear Dynamics, vol. 100, no. 4, 2020. View at: Publisher Site | Google Scholar
  35. A. Cz, C. Skob, and B. Zf, “Design of stabilized polynomial-based ensemble fuzzy neural networks based on heterogeneous neurons and synergy of multiple techniques,” Information Sciences, vol. 542, pp. 425–452, 2021. View at: Publisher Site | Google Scholar
  36. G. Yangyong and W. Juan, “Modeling of false information on microblog with block matching and fuzzy neural network,” International Journal of Modern Physics C, vol. 32, 2020. View at: Publisher Site | Google Scholar
  37. K. H. Tan, F. J. Lin, C. M. Shih et al., “Intelligent control of microgrid with virtual inertia using recurrent probabilistic wavelet fuzzy neural network,” IEEE Transactions on Power Electronics, vol. 35, no. 7, 2019. View at: Publisher Site | Google Scholar
  38. H. Zhou, H. Zhao, and Y. Zhang, “Nonlinear system modeling using self-organizing fuzzy neural networks for industrial applications,” Applied Intelligence, vol. 50, no. 5, pp. 1657–1672, 2020. View at: Publisher Site | Google Scholar
  39. V. Nasir, S. Nourian, S. Avramidis, and J. Cool, “Stress wave evaluation for predicting the properties of thermally modified wood using neuro-fuzzy and neural network modeling,” Holzforschung, vol. 73, no. 9, pp. 827–838, 2019. View at: Publisher Site | Google Scholar
  40. S. Hou and J. Fei, “Finite-time adaptive fuzzy-neural-network control of active power filter,” IEEE Transactions on Power Electronics, vol. 34, 2019. View at: Publisher Site | Google Scholar
  41. Y. Xu, D. Zhan, L. Liu, H. Lv, L. Xu, and J. Du, “A privacy-preserving cross-domain healthcare wearables recommendation algorithm based on domain-dependent and domain-independent feature fusion,” IEEE Journal of Biomedical and Health Informatics, vol. 14, no. 5, 2021. View at: Publisher Site | Google Scholar
  42. T. Rao and S. Srivastava, “Analyzing stock market movements using twitter sentiment analysis,” in Proceedings of the IEEE International Conference on Advances in Social Networks Analysis and Mining(ASONAM 2012), pp. 1–5, August 2012. View at: Google Scholar
  43. D. Enke, M. Grauer, and N. Mehdiyev, “Stock market prediction with multiple regression, fuzzy type-2 clustering and neural networks,” Procedia Computer Science, vol. 6, pp. 201–206, 2011. View at: Publisher Site | Google Scholar
  44. M. Qasem, R. Thulasiram, and P. Thulasiram, “Twitter sentiment classification using machine learning techniques for stock markets,” in Proceedings of the IEEE International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 834–840, Kochi, India, August 2015. View at: Google Scholar
  45. A. Feinberg and D. Genethliou, “Load forecasting,” in Applied Mathematics for Restructured Electric Power Systems, J. Chow, F. Wu, and J. Momoh, Eds., pp. 269–285, Springer, Berlin, Germany, 2005. View at: Google Scholar
  46. R. Rostamzadeh, M. K. Ghorabaee, K. Govindan, A. Esmaeili, and H. B. K. Nobar, “Evaluation of sustainable supply chain risk management using an integrated fuzzy TOPSIS- CRITIC approach,” Journal of Cleaner Production, vol. 175, pp. 651–669, 2018. View at: Publisher Site | Google Scholar
  47. M. Yu, T. Quan, Q. Peng, X. Yu, and L. Liu, “A model-based collaborate filtering algorithm based on stacked AutoEncoder,” Neural Computing and Applications, vol. 6, no. 12, 2021. View at: Publisher Site | Google Scholar
  48. X. Yu, F. Jiang, J. Du, and D. Gong, “A cross-domain collaborative filtering algorithm with expanding user and item features via the latent factor space of auxiliary domains,” Pattern Recognition, vol. 94, pp. 96–109, 2019. View at: Publisher Site | Google Scholar

Copyright © 2021 Qiao Qu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Related articles

No related content is available yet for this article.
 PDF Download Citation Citation
 Download other formatsMore
 Order printed copiesOrder
Views548
Downloads476
Citations

Related articles

No related content is available yet for this article.

Article of the Year Award: Outstanding research contributions of 2021, as selected by our Chief Editors. Read the winning articles.