Search results

This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.

Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.

The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.

The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.

Proper platform pose is important for the mobile manipulator to accomplish dexterous manipulation tasks efficiently and safely, and the evaluation criterion to qualify manipulation performance is critical to support the pose decision process. This paper aims to present a comprehensive index to evaluate the manipulator’s operation performance from various aspects.

In this research, a criterion called hybrid manipulability (HM) is proposed to assess the performance of the manipulator’s operation, considering crucial factors such as joint limits, obstacle avoidance and stability. The determination of the optimal platform pose is achieved by selecting the pose that maximizes the HM within the feasible inverse reachability map associated with the target object.

A self-built mobile manipulator is adopted as the experimental platform, and the feasibility of the proposed method is experimentally verified in the context of object-grasping tasks both in simulation and practice.

The proposed HM extends upon the conventional notion of manipulability by incorporating additional factors, including the manipulator’s joint limits, the obstacle avoidance situation during the operation and the manipulation stability when grasping the target object. The manipulator can achieve enhanced stability during grasping when positioned in the pose determined by the HM.

Research to date has yet to reach a consensus regarding the role of cross-channel consistency in omni-channel retailing. Therefore, this study aims to clarify the impact of cross-channel consistency on brand trust and loyalty by differentiating four dimensions of consistency (i.e. product, service, price and promotion consistency) and exploring the moderating roles of showrooming and webrooming motivation in these relationships.

A survey method is used to collect data. A total of 550 valid responses were obtained from multi-channel apparel brands' customers. Hypotheses were tested by employing structural equation modeling and hierarchical multiple regression analysis.

The results indicate that product and service consistency positively influence brand loyalty via brand trust, whereas price and promotion consistency do not. Furthermore, showrooming motivation negatively moderates the effects of service, price and promotion consistency on brand trust, while webrooming motivation positively moderates the effects of product, price and promotion consistency on brand trust.

This study contributes to the omni-channel retailing literature by examining the effects of different dimensions of cross-channel consistency and the moderating roles of showrooming and webrooming motivation to unravel the contradictions of previous studies. It reveals both the beneficial and dark sides of cross-channel consistency. It also extends the knowledge of brand building and cross-channel behavior in omni-channel retailing.

Companies are increasingly designing pro-environmental games to motivate users to implement pro-environmental behaviors (PEBs). However, how different types of virtual interactions affect PEBs in pro-environmental games is not clear. Thus, the authors propose that two types of virtual interaction, interactions with game objects and interactions with other users, can induce platform intimacy and love for nature and that platform intimacy has a direct effect on love for nature. Simultaneously, the authors examine the moderating effect of network externality on the relationship between the two types of virtual interaction and platform intimacy.

The authors, respectively, employed data from 92 students and 574 Chinese mobile users to empirically investigate the research framework.

The findings indicate that participants in interactions with game objects and interactions with other users reported stronger feelings regarding platform intimacy and love for nature, which, in turn, positively influences PEBs. Consumers with stronger perceptions of network externalities were more likely to be affected by the initiation effect of the interaction with game objects.

The authors introduce the notion of love for nature to the pro-environmental behaviors field and discuss the priming effect of two types of interactions on platform intimacy and love for nature. In addition, the authors focus on the important effect of network externality on users' emotions.

This paper aims to introduce corporate social responsibility into the green supply chain and analyse the impact of different decision makers’ decision-making schemes on carbon emission reduction in the supply chain.

This study uses a two-stage low-carbon supply chain composed of a manufacturer and retailer as the research object. It uses the Stackelberg game model to analyse optimal carbon emission reduction and its influence under different decision-making modes.

Increased consumer green preferences and trust can improve the manufacturing enterprises’ carbon emission reduction rate. The carbon emission reduction rate decreases with increased green innovation costs. When green technology innovation costs remain constant, the greater the market capacity, the higher the carbon emission reduction rate. Market capacity has the most significant impact on the optimal carbon emission reduction rate without considering social responsibility decisions and has the least impact on the optimal carbon emission reduction rate while fully considering the social responsibility decision. To achieve decarbonisation production, the market capacity must be small, and when green innovation costs are high, it is the optimal choice without considering social responsibility. To achieve a higher level of carbon emission reduction, when the market capacity is low and the research and development cost is high or when the market capacity is large, it is the optimal choice.

The results provide scientific policy decisions and management significance for governments and enterprises in low-carbon subsidies and supply chain management. The findings also provide a basis for future theoretical research and enterprise practice.

This study aims to investigate the process of developing loyalty in the Chinese mobile health community from the information seeking perspective.

A covariance-based structural equation model was developed to explore the mobile health community loyalty development process from information seeking perspective and tested with LISREL 9.30 for the 191 mobile health platform user samples.

The empirical results demonstrate that the information seeking perspective offers an interesting explanation for the mobile health community loyalty development process. All hypotheses in the proposed research model are supported except the relationship between privacy and trust. The two types of mobile health community loyalty—attitudal loyalty and behavioral loyalty are explained with 58 and 37% variance.

This paper has brought out the information seeking perspective in the loyalty formation process in mobile health community and identified several important constructs for this perspective for the loyalty formation process including information quality, communication with doctors and communication with patients.

This study aims to reduce the redundant weight of the anti-roll torsion bar brought by the traditional empirical design and improving its strength and stiffness.

Based on the finite element approach coupled with the improved beluga whale optimization (IBWO) algorithm, a collaborative optimization method is suggested to optimize the design of the anti-roll torsion bar structure and weight. The dimensions and material properties of the torsion bar were defined as random variables, and the torsion bar's mass and strength were investigated using finite elements. Then, chaotic mapping and differential evolution (DE) operators are introduced to improve the beluga whale optimization (BWO) algorithm and run case studies.

The findings demonstrate that the IBWO has superior solution set distribution uniformity, convergence speed, solution correctness and stability than the BWO. The IBWO algorithm is used to optimize the anti-roll torsion bar design. The error between the optimization and finite element simulation results was less than 1%. The weight of the optimized anti-roll torsion bar was lessened by 4%, the maximum stress was reduced by 35% and the stiffness was increased by 1.9%.

The study provides a methodological reference for the simulation optimization process of the lateral anti-roll torsion bar.

The purpose of this paper is to investigate remanufacturing operational strategies considering uncertain quality of end-of-life (EOL) products and differential consumers’ willingness-to-pay (WTP) for new products and provide suggestions on the remanufacturing mode selection for the original equipment manufacturer (OEM).

This study considers three remanufacturing modes, i.e. in-house, outsourcing and authorization modes. By establishing and comparing decision models of three modes from the perspectives of profit, consumer surplus and environment, the optimal remanufacturing mode is discussed.

The results suggest that if the OEM’s remanufacturing capability is high, the in-house mode brings to the highest environmental performance, OEM’s profit and consumer surplus. Otherwise, the outsourcing mode (authorization) is the best benefit to environment (consumers if the unit production cost of new products is not too high). As for the preference of two decision-makers to outsourcing and authorization modes, if the difference of consumers’ WTP for new products is low, the OEM prefers the outsourcing mode; otherwise, the OEM prefers the authorization mode. The preference of the third-party remanufacturer (TPR) to remanufacturing mode is affected by consumers’ WTP for remanufactured products, WTP difference for new products and remanufacturing quality level standard.

These results can provide operational insights into how to select remanufacturing mode when the quality of EOL products is uncertain and consumers’ WTP for new products is different under three remanufacturing modes.

This paper is among the first to investigate the joint effects of EOL products’ uncertain quality and differential consumers’ WTP for new products on the operational strategies and performance under different remanufacturing modes.

Gesture recognition plays an important role in many fields such as human–computer interaction, medical rehabilitation, virtual and augmented reality. Gesture recognition using wearable devices is a common and effective recognition method. This study aims to combine the inverse magnetostrictive effect and tunneling magnetoresistance effect and proposes a novel wearable sensing glove applied in the field of gesture recognition.

A magnetostrictive sensing glove with function of gesture recognition is proposed based on Fe-Ni alloy, tunneling magnetoresistive elements, Agilus30 base and square permanent magnets. The sensing glove consists of five sensing units to measure the bending angle of each finger joint. The optimal structure of the sensing units is determined through experimentation and simulation. The output voltage model of the sensing units is established, and the output characteristics of the sensing units are tested by the experimental platform. Fifteen gestures are selected for recognition, and the corresponding output voltages are collected to construct the data set and the data is processed using Back Propagation Neural Network.

The sensing units can detect the change in the bending angle of finger joints from 0 to 105 degrees and a maximum error of 4.69% between the experimental and theoretical values. The average recognition accuracy of Back Propagation Neural Network is 97.53% for 15 gestures.

The sensing glove can only recognize static gestures at present, and further research is still needed to recognize dynamic gestures.

A new approach to gesture recognition using wearable devices.

This study has a broad application prospect in the field of human–computer interaction.

The sensing glove can collect voltage signals under different gestures to realize the recognition of different gestures with good repeatability, which has a broad application prospect in the field of human–computer interaction.

The broader analytical framing of systematically distorted communication (SDC) helps extract value out of the enormous amount of scholarship on fake news.

The massive literature on fake news has been the subject of handbook overviews, systematic literature reviews, summaries, taxonomies, citation studies and so on. Deploying these tools, the approaches that the literature takes can be characterized, Habermas' concept of systematically distorted communication (SDC) will then be presented in its context, reviewed and put to work to frame fake news research to tell us new things that individual pieces of specific analysis and research do not. Conclusions will be offered from this analysis.

Fake news research has become repetitive, revolving around themes such as the fate of journalism, the role of technology, remediating its effects and deep dives into definitional components (disinformation, misinformation, lies and so on). A broader framing of systematically distorted communication allows us to arrive at some conclusions about contemporary fake news: that it is a power strategy with a particular right-wing slant and it creates a sociology – that is, its own interpretive environment – hostile to democratic functioning. It answers the question: what is fake news for?

A perspective on fake news research is much needed and Habermas' concept is a useful framing mechanism for the large corpus of research. Systematically distorted communication asks – and answers – different questions of the research. Meanwhile, SDC itself is modified by its application to fake news research and contemporary conditions.