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.

The purpose of this study is to formulate an algorithm designed to discern the optimal routes for efficient municipal solid waste (MSW) collection.

The research method is simulation. The proposed algorithm combines heuristics derived from the constructive genetic algorithm (CGA) and tabu search (TS). The algorithm is applied in a municipality located at Southern Brazil, with 40,000 inhabitants, circa.

The implementation achieved a remarkable 25.44% reduction in daily mileage of the vehicles, resulting in savings of 150.80 km/month and 1,809.60 km/year. Additionally, it reduced greenhouse gas emissions (including fossil CO₂, CH₄, N₂O, total CO₂e and biogenic CO₂) by an average of 26.15%. Moreover, it saved 39 min of daily working time.

Further research should thoroughly analyze the feasibility of decision-making regarding planning, scheduling and scaling municipal services using digital technology.

The municipality now has a tool to improve public management, mainly related with municipal solid waste. The municipality reduced the cost of public management of municipal solid waste, redirecting funds to other priorities, such as public health and education.

The study integrates MSW collection service with an online platform based on Google MapsTM. The advantages of employing geographical information systems are agility, low cost, adaptation to changes and accuracy.

The United Nations member countries adopted a set of 17 sustainable development goals (SDGs) to achieve a better and more sustainable future for all. It encourages the use of sustainable practices during new product development (NPD). Competitiveness has put pressure on organizations to maintain their market share and look for new approaches related to NPD. The current study aims to focus on creating a framework that can help to achieve the SDGs by adopting agile new product development (ANPD) practices and Industry 4.0 technologies.

From the literature, various ANPD practices, Industry 4.0 technologies, performance metrics, their interconnection and their contribution toward achieving SDGs are extracted. The weights of selected Industry 4.0–ANPD practices are computed by robust best worst method (RBWM), and the Fuzzy-VIKOR method is used to rank the selected performance metrics. To test the robustness of the developed framework, sensitivity analysis is also performed.

The results show that among the various Industry 4.0–ANPD practices “Multi-skilled employees” have the highest weight followed by “Customer requirement analysis and prioritization.” Whereas for performance metrics, “The number of innovative products launched per year” is ranked first, with the “Average time between two launches” at second place.

This research contributes to the adoption of ANPD practices and Industry 4.0 technologies for the achievement of the business SDGs. The shortlisted Industry 4.0–ANPD practices will help in resolving the social and environmental issues. The set of performance metrics will help practitioners and managers to evaluate the performance of ANPD in the context of business SDGs.

This study adds to the understanding related to Industry 4.0–ANPD practices adoption. And to the best of the authors’ knowledge, it is believed that no similar work has been done previously and by using industry insights into technology components, this work contributes to valuable insights into the subject.

GraphQL is a new Open API specification that allows clients to send queries and obtain data flexibly according to their needs. However, a high-complexity GraphQL query may lead to an excessive data volume of the query result, which causes problems such as resource overload of the API server. Therefore, this paper aims to address this issue by predicting the response data volume of a GraphQL query statement.

This paper proposes a GraphQL response data volume prediction approach based on Code2Vec and AutoML. First, a GraphQL query statement is transformed into a path collection of an abstract syntax tree based on the idea of Code2Vec, and then the query is aggregated into a vector with the fixed length. Finally, the response result data volume is predicted by a fully connected neural network. To further improve the prediction accuracy, the prediction results of embedded features are combined with the field features and summary features of the query statement to predict the final response data volume by the AutoML model.

Experiments on two public GraphQL API data sets, GitHub and Yelp, show that the accuracy of the proposed approach is 15.85% and 50.31% higher than existing GraphQL response volume prediction approaches based on machine learning techniques, respectively.

This paper proposes an approach that combines Code2Vec and AutoML for GraphQL query response data volume prediction with higher accuracy.

This study aims to examine the impact of digital transformation on firms’ value and explore the mediating impact of ESG performance and moderating impact of information interaction.

Data was collected from companies listed on the Shanghai and Shenzhen stock exchange between 2012 and 2020 with 21,488 observational samples, featuring a selection of 3,348 companies. Panel data regression techniques were used to test the mediating role of ESG performance and the moderating role of information interaction.

The study found that digital transformation can improve firms’ ESG performance, which in turn positively affects their value. The firms that engage in more interaction with outsiders benefit more from digital transformation and have a higher value.

This study provides new theoretical insight into improving firms’ value through digital transformation and ESG performance. It is the first to discuss and study the moderating role of information interaction in the relationship between digital transformation and firms’ value.

In recent years, there has been significant interest in adopting XR (extended reality) technologies such as VR (virtual reality) and AR (augmented reality), particularly in retail. However, extending activities through reality-mediation is still mostly believed to offer an inferior experience due to their shortcomings in usability, wearability, graphical fidelity, etc. This study aims to address the research gap by experimentally examining the acceptance of metaverse shopping.

This study conducts a 2 (VR: with vs. without) × 2 (AR: with vs. without) between-subjects laboratory experiment involving 157 participants in simulated daily shopping environments. This study builds a physical brick-and-mortar store at the campus and stocked it with approximately 600 products with accompanying product information and pricing. The XR devices and a 3D laser scanner were used in constructing the three XR shopping conditions.

Results indicate that XR can offer an experience comparable to, or even surpassing, traditional shopping in terms of its instrumental and hedonic aspects, regardless of a slightly reduced perception of usability. AR negatively affected perceived ease of use, while VR significantly increased perceived enjoyment. It is surprising that the lower perceived ease of use appeared to be disconnected from the attitude toward metaverse shopping.

This study provides important experimental evidence on the acceptance of XR shopping, and the finding that low perceived ease of use may not always be detrimental adds to the theory of technology adoption as a whole. Additionally, it provides an important reference point for future randomized controlled studies exploring the effects of technology on adoption.

The purpose of this paper is to fill a gap in the literature regarding the open innovation management approaches that small and medium-sized enterprises (SMEs) can use to access digital technologies and incorporate them into their organizational processes. The research question is: What organizational and process-level managerial actions do SMEs take to successfully access and implement digital technologies within their organizational processes?

Using Guertler et al.'s (2020) Action Innovation Management Research (AIM-R) framework, this study examines the digital transformation experiences of 10 European SMEs to gain insights into the managerial actions that foster successful digital transformation.

The findings of the paper reveal two major contributions. First, a digital transformation roadmap for SMEs is proposed, with a focus on accessing external resources and reconfiguring internal ones to ease their digital transformation journey. Second, three distinct paradoxes that influence the digital transformation process in SMEs are highlighted, providing useful insights into the challenges and tensions SMEs face during this journey.

This paper provides a unique perspective on the digital transformation of SMEs by examining the managerial actions required for successful technology adoption and revealing the paradoxes that may emerge during this transformative process. The findings form the basis for future research, deepening our understanding of digital transformation in SMEs and providing actionable advice to managers and practitioners navigating this journey.

The purpose of this study is to use the grounded theory to summarize the types of celebrity persona and to construct a theoretical model for celebrity persona on consumer purchase intention. Based on the study results, it provides better suggestions for merchants and live streamers and is an expansion of previous research on live-streaming e-commerce.

The grounded theory is recognized as the most scientific qualitative research method and is the ideal explorative method for generating theory. First, the participants were interviewed, and interview data were collected. Then the interview data were organized and analyzed. Finally, this paper summarizes the types of celebrity persona and constructes a theoretical model framework of celebrity persona on consumers' purchase intention.

The results show that the celebrity live streamer persona can be divided into two types: personalized persona and professional persona. Through emotional attachment, the celebrity's persona affects the consumer's purchase intentions. As well as, product type plays a moderating role between celebrity persona and consumer purchase intentions.

The contribution of this research is to start from the celebrity persona, link the celebrity persona with the consumer purchase intentions and expand the research scope of the celebrity persona. It opens the “black box” of the heterogeneity of celebrity live streamers' characteristics on consumer purchase intentions.

The textile industry harms the environment at every stage of production, from the acquisition of raw materials to the disposal of finished products. It is very important for the textile industry to adapt to the basic policies on environmental sensitivity and sustainability to keep up with the transformation in production processes and the rapid changes occurring around the world in order to exist in global competition. Within the scope of sustainable development goals, it is of great importance to measure and evaluate indicators of all processes of the sector. This paper aims to present application of multi-criteria decision making (MCDM) methods for the assessment of sustainable development in textile industry.

The data of a multinational clothing company’s four-year sustainability performance between 2018 and 2021 were evaluated under 22 sustainability parameters determined using two new MCDM techniques, namely the combined consensus solution method and multi-attribute ideal real comparative analysis. In determining the criteria, priority key indicators were determined by taking into account the sector’s relationship with the environment, raw material consumption and social adequacy.

According to the application results of both methods, the year 2021 shows the best performance. It has been seen that the sustainability performance of the Inditex group has increased over the years and the results of the applied models support each other. It can be suggested that the proposed approach be applied to evaluate the progress in the textile sector with the relevant data on a particular company or on a macro scale.

This study makes an important contribution to the field in terms of the fact that the methods used are recent and have no application in the field of textiles. It allows the evaluation of different sustainability criteria together using a single method. It is very important to share data on sustainability indicators with customers, employees, suppliers, investors, partner organizations and society and evaluate performance. Analyzing sustainability performance on the basis of annual reports is important in terms of identifying good practices, sharing them with the community and setting an example. In addition, using scientific methods in the evaluation of the sustainability report data published by companies regularly provides significant feedback for policymakers and academics.

This study aims to synthesize two different benzoxazines (Bz) monomers using bio-based and petroleum-based primary amines, respectively, and they have been compared to study their thermal and mechanical performances.

A bio-based bisphenol, Divanillin (DiVa), was formed by reacting two moles of vanillin with one mole of ethylenediamine (EDA) which was then reacted firstly with paraformaldehyde and EDA to form the benzoxazine DiVa-EDA-Bz, and secondly with paraformaldehyde and furfuryl amine (FFA) to form the benzoxazine DiVa-FFA-Bz. The molecular structure and thermal properties of the benzoxazines were characterized by fourier transform infrared spectroscopy and nuclear magnetic resonance (1H,13C) spectroscopies, differential scanning calorimetry (DSC) and thermogravimetric analysis (TGA), respectively. The benzoxazines were further coated on mild steel panels to evaluate their mechanical properties and chemical resistance.

The DSC results of DiVa-FFA-Bz showed two exothermic peaks related to crosslinking compared to the one in DiVa-EDA-Bz. The DiVa-FFA-Bz also showed a higher heat of polymerization than DiVa-EDA-Bz. The TGA results showed that DiVa-FFA-Bz exhibited higher thermal stability with a residual char of 54.10% than 43.24% for DiVa-EDA-Bz. The chemical resistance test results showed that DiVa-FFA-Bz showed better chemical resistance and mechanical properties due to its higher crosslinking density.

This study shows the use of bio-based materials, vanillin and FFA, for synthesizing a benzoxazine resin and its application at high temperatures.