Search results

This study proposes a predictive neural network model reference decoupling control method for the coupling problem between the leg joints of hydraulic quadruped robots, and verifies its decoupling effect..

The machine–hydraulic cross-linking coupling is studied as the coupling behavior of the hydraulically driven quadruped robot, and the mechanical dynamics coupling force of the robot system is controlled as the disturbance force of the hydraulic system through the Jacobian matrix transformation. According to the principle of multivariable decoupling, a prediction-based neural network model reference decoupling control method is proposed; each module of the control algorithm is designed one by one, and the stability of the system is analyzed by the Lyapunov stability theorem.

The simulation and experimental research on the robot joint decoupling control method is carried out, and the prediction-based neural network model reference decoupling control method is compared with the decoupling control method without any decoupling control method. The results show that taking the coupling effect experiment between the hip joint and knee joint as an example, after using the predictive neural network model reference decoupling control method, the phase lag of the hip joint response line was reduced from 20.3° to 14.8°, the amplitude attenuation was reduced from 1.82% to 0.21%, the maximum error of the knee joint coupling line was reduced from 0.67 mm to 0.16 mm and the coupling effect between the hip joint and knee joint was reduced from 1.9% to 0.48%, achieving good decoupling.

The prediction-based neural network model reference decoupling control method proposed in this paper can use the neural network model to predict the next output of the system according to the input and output. Finally, the weights of the neural network are corrected online according to the predicted output and the given reference output, so that the optimization index of the neural network decoupling controller is extremely small, and the purpose of decoupling control is achieved.

The purpose of this study is to systematically review the existing literature on the blood supply chain (BSC) from a network design perspective and highlight the research gaps in this area. Moreover, it also aims to pinpoint new research opportunities based on the recent innovative technologies for the BSC network design.

The study gives a comprehensive systematic review of the BSC network design studies until October 2021. This review was carried out in accordance with preferred reporting items for systematic reviews and meta-analyses (PRISMA). In the literature review, a total of 87 studies were analyzed under six main categories as model structure, application model, solution approach, problem type, the parties of the supply chain and innovative technologies.

The results of the study present the researchers’ tendencies and preferences when designing their BSC network models.

The study presents a guide for researchers and practitioners on BSC from the point of view of network design and encourages adopting innovative technologies in their BSC network designs.

The study provides a comprehensive systematic review of related studies from the BSC network design perspective and explores research gaps in the collection and distribution processes. Furthermore, it addresses innovative research opportunities by using innovative technologies in the area of BSC network design.

This paper aims to evaluate the performance of the Mashhad No. 5 wastewater treatment plant (WWTP) using a combination of data mining (regression) algorithms and artificial neural networks.

In this research, the performance of WWTP located in Mashhad, Iran, has been evaluated using two data mining models, neural network and regression model.

The proposed model has the potential of implementing in other WWTPs in Iran or other countries.

The authors would also like to thank Mashhad No.5 WWTP for data access.

With the rapid development of Internet technology, cybersecurity threats such as security loopholes, data leaks, network fraud, and ransomware have become increasingly prominent, and organized and purposeful cyberattacks have increased, posing more challenges to cybersecurity protection. Therefore, reliable network risk assessment methods and effective network security protection schemes are urgently needed.

Based on the dynamic behavior patterns of attackers and defenders, a Bayesian network attack graph is constructed, and a multitarget risk dynamic assessment model is proposed based on network availability, network utilization impact and vulnerability attack possibility. Then, the self-organizing multiobjective evolutionary algorithm based on grey wolf optimization is proposed. And the authors use this algorithm to solve the multiobjective risk assessment model, and a variety of different attack strategies are obtained.

The experimental results demonstrate that the method yields 29 distinct attack strategies, and then attacker's preferences can be obtained according to these attack strategies. Furthermore, the method efficiently addresses the security assessment problem involving multiple decision variables, thereby providing constructive guidance for the construction of security network, security reinforcement and active defense.

A method for network risk assessment methods is given. And this study proposed a multiobjective risk dynamic assessment model based on network availability, network utilization impact and the possibility of vulnerability attacks. The example demonstrates the effectiveness of the method in addressing network security risks.

Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.

The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.

This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.

As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.

Considering the network externalities of online selling, this paper builds three different online direct selling models: manufacturer direct selling (MN model), network platform direct selling (NN model) and retailer direct selling (RN model). The optimal advertising and pricing decision and corporate profits under each selling model are investigated.

Combining the characteristics of online direct selling, this paper formulates direct selling models that are dominated by different companies as Stackelberg game models. Numerical analyses are carried out, along with the comparison of the equilibrium solutions for each model.

The authors' research shows that increasing network externalities is conducive to the development of enterprises. The network platform's profit is the lowest in the RN model and the highest in the NN one. The comparison of manufacturers' profits between the MN model and the NN model primarily depends on consumers' sensitivities for sales price and advertising promotion level. The manufacturer does not benefit from the RN model due to the lowest efficiency.

Coupled with three different online direct selling models and detailed analyses of the optimal solutions, this study has enriched the theoretical foundation of online direct selling. Moreover, this study extends the research of network externalities to the field of e-commerce, revealing the network externalities' influence on the decision-making of the e-supply chain.

Forecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.

This study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.

The model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R² values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.

This study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Distribution network design involves a set of strategic decisions in supply chains because of their long-term impacts on the total logistics cost and environment. To incorporate a trade-off between financial and environmental aspects of these decisions, this paper aims to determine an optimal location, among candidate locations, of a new logistics center, its capacity, as well as optimal network flows for an existing distribution network, while concurrently minimizing the total logistics cost and gas emission. In addition, uncertainty in transportation and warehousing costs are considered.

The problem is formulated as a fuzzy multiobjective mathematical model. The effectiveness of this model is demonstrated using an industrial case study. The problem instance is a four-echelon distribution network with 22 products and a planning horizon of 20 periods. The model is solved by using the min–max and augmented ε-constraint methods with CPLEX as the solver. In addition to illustrating model’s applicability, the effect of choosing a new warehouse in the model is investigated through a scenario analysis.

For the applicability of the model, the results indicate that the augmented ε-constraint approach provides a set of Pareto solutions, which represents the ideal trade-off between the total logistics cost and gas emission. Through a case study problem instance, the augmented ε-constraint approach is recommended for similar network design problems. From a scenario analysis, when the operational cost of the new warehouse is within a specific fraction of the warehousing cost of third-party warehouses, the solution with the new warehouse outperforms that without the new warehouse with respective to financial and environmental objectives.

The proposed model is an effective decision support tool for management, who would like to assess the impact of network planning decisions on the performance of their supply chains with respect to both financial and environmental aspects under uncertainty.

This paper proposes the “fields and weapons of the competition model applied to business networks” – CAC-Redes (in Portuguese, Campos e Armas da Competição – Redes de negócio), an extension of the fields and weapons of the competition model (CAC) – to study the competition and competitiveness of companies operating in business networks in a competitive environment while integrating organizational competencies, interorganizational ties and company positioning to provide competitive advantage.

CAC-Redes is born from the cross-fertilization process of various theoretical perspectives, namely, industrial organization, traditional view of operational activities and resources, relational view, strategic alignment, transaction cost theory and social perspectives in networks, structured according to systems theory and under the mantle of competitive advantage theory. To discover the structure of existing models of competitiveness in networks, a bibliographic search was conducted in the Scopus database. Quali-quantitative empirical research was undertaken in companies from six different economic sectors through structured questionnaires and personal interviews to understand how companies competed and discover the determining factors of their competitive advantage.

Only seven models of competitiveness in network were found, and their structures and characteristics are quite different from those of CAC-Redes. Empirical research confirms all the hypotheses that support CAC-Redes, which, combined with those of CAC, indicate the CAC-Redes corroboration.

CAC-Redes does not apply to networks without intercompany competition, studies on network governance and corporate strategy formulation.

CAC-Redes is effective in studying complex competitiveness phenomena because it considers multiple influences; provides a process based on qualitative and quantitative variables that increase the probability of formulating successful competitive strategies; simplifies the differentiation of skills from core competencies and determines them; proposes a competitive advantage criterion to select suppliers; creates a unifying language to represent the different strategic specificities of companies, competitors, suppliers, customers and the company environment and provides a library containing 181 weapons (resources) and dozens of interorganizational ties that can be used in empirical studies with other methodologies.

CAC-Redes, due to its originality and peculiarities, theoretically contributes to theory of resources because it dispenses with the assumption, “unique resource, source of competitive advantage”; to relational view because it considers interorganizational relationships as a competence and treats it quali-quantitatively and to core competencies because if the strategy changes, different core competencies will be needed. Furthermore, it is an alternative to the dynamic capabilities perspective, and it transforms the five manufacturing performance objectives into nine for the entire company.

CAC-Redes is an original model because its structure and characteristics comparatively differ from those of existing models, and 14 singularities are detected.

The purpose of this paper is geared towards the capture and analysis of network traffic using an array ofmachine learning (ML) and deep learning (DL) techniques to classify network traffic into different classes and predict network traffic parameters.

The classifier models include k-nearest neighbour (KNN), multilayer perceptron (MLP) and support vector machine (SVM), while the regression models studied are multiple linear regression (MLR) as well as MLP. The analytics were performed on both a local server and a servlet hosted on the international business machines cloud. Moreover, the local server could aggregate data from multiple devices on the network and perform collaborative ML to predict network parameters. With optimised hyperparameters, analytical models were incorporated in the cloud hosted Java servlets that operate on a client–server basis where the back-end communicates with Cloudant databases.

Regarding classification, it was found that KNN performs significantly better than MLP and SVM with a comparative precision gain of approximately 7%, when classifying both Wi-Fi and long term evolution (LTE) traffic.

Collaborative regression models using traffic collected from two devices were experimented and resulted in an increased average accuracy of 0.50% for all variables, with a multivariate MLP model.