Search results

With the increasing number of mobile applications, efficiently recommending mobile applications to users has become a challenging problem. Although existing mobile application recommendation approaches based on user attributes and behaviors have achieved notable effectiveness, they overlook the diffusion patterns and interdependencies of topic-specific mobile applications among user groups. mobile applications among user groups. This paper aims to capture the diffusion patterns and interdependencies of mobile applications among user groups. To achieve this, a topic-aware neural network-based mobile application recommendation method, referred to as TN-MR, is proposed.

In this method, first, the user representations are enhanced by introducing a topic-aware attention layer, which captures both the topic context and the diffusion history context. Second, it exploits a time-decay mechanism to simulate changes in user interest. Multitopic user representations are aggregated by the time decay module to output the user representations of cascading representations under multiple topics. Finally, user scores that are likely to download the mobile application are predicted and ranked.

Experimental comparisons and analyses were conducted on the actual 360App data set, and the results demonstrate that the effectiveness of mobile application recommendations can be significantly improved by using TN-MR.

In this paper, the authors propose a mobile application recommendation method based on topic-aware attention networks. By capturing the diffusion patterns and dependencies of mobile applications, it effectively assists users in selecting their applications of interest from thousands of options, significantly improving the accuracy of mobile application recommendations.

The purpose of this study is to analyze state-of-the-art knowledge of artificial intelligence (AI) research in hospitality.

This study adopts the theory-context-methods framework to systematically review 100 AI-related articles recently published (i.e. from 2021 to April 2023) in three top-tier hospitality journals, namely, the International Journal of Contemporary Hospitality Management, International Journal of Hospitality Management and Journal of Hospitality Marketing and Management.

Findings suggest that studies of AI applications in hospitality are mostly theory-driven, whereas most AI methods research adopts a data-driven approach. State-of-the-art AI applications research exhibits the most interest in service robots. In AI methods research, little attention was paid to the amid-service/experience.

This study reveals inadequacies in theory, context and methods in contemporary AI research. More research from hospitality suppliers’ perspectives and research on generative AI applications are advocated in response to the unveiled research gaps and recent AI developments.

This study classifies the most recent AI research in hospitality into two main streams – AI applications research and AI methods research – and discusses the gaps in each research stream and latest AI developments. The paper then suggests future research directions to guide researchers in advancing AI research in hospitality.

This paper aims to propose a new method to derive custom dynamic cyber risk metrics based on the well-known Goal, Question, Metric (GQM) approach. A framework that complements it and makes it much easier to use has been proposed too. Both, the method and the framework, have been validated within two challenging application domains: continuous risk assessment within a smart farm and risk-based adaptive security to reconfigure a Web application firewall.

The authors have identified a problem and provided motivation. They have developed their theory and engineered a new method and a framework to complement it. They have demonstrated the proposed method and framework work, validating them in two real use cases.

The GQM method, often applied within the software quality field, is a good basis for proposing a method to define new tailored cyber risk metrics that meet the requirements of current application domains. A comprehensive framework that formalises possible goals and questions translated to potential measurements can greatly facilitate the use of this method.

The proposed method enables the application of the GQM approach to cyber risk measurement. The proposed framework allows new cyber risk metrics to be inferred by choosing between suggested goals and questions and measuring the relevant elements of probability and impact. The authors’ approach demonstrates to be generic and flexible enough to allow very different organisations with heterogeneous requirements to derive tailored metrics useful for their particular risk management processes.

The purpose of this paper is to examine the contribution that problem structuring methods – a branch of the decision support discipline of operational research – have made in helping managers deal with situations of high complexity. The paper reviews the limitations of traditional operational research and argues that problem structuring methods have expanded the entire discipline and significantly contributed to its holistic nature and problem-solving orientation.

The paper provides a critical discussion of the limitations of the traditional operational research approach and examines how the development and successful application of problem structuring methods have opened up a new paradigm of analysis in management science.

In theoretical terms, problem structuring methods have moved the discipline of operational research away from its positivistic epistemology and towards interpretivism and the acceptance of a subjective social reality. In practical terms, they offer managers a broad range of appropriate analytical tools which provide transparency and offer the opportunity to those affected by the problem situation to be actively involved in the entire modelling process within a facilitated environment.

The paper offers a critical discussion of the contribution that problem structuring methods have made while also identifying the challenges they face as they try to achieve higher levels of recognition and acceptance in management science.

Cotton fibre lots are graded and selected for yarn spinning based on their quality value which is a function of certain fibre properties. Cotton grading and selection has created a domain of emerging interest among the researchers. Several researchers have addressed the said issue using a few exponents of multi-criteria decision-making (MCDM) technique. The purpose of this study is to demonstrate a cotton selection problem using a recently developed measurement of alternatives and ranking according to compromise solution (MARCOS) method which can handle almost any decision problem involving a finite number of alternatives and multiple conflicting decision criteria.

The MARCOS method of the MCDM technique was deployed in this study to rank 17 cotton fibre lots based on their quality values. Six apposite fibre properties, namely, fibre bundle strength, elongation, fineness, upper half mean length, uniformity index and short fibre content are considered as the six decision criteria assigning weights previously determined by an earlier researcher using analytic hierarchy process.

Among the 17 alternatives, C9 secured rank 1 (the best lot) with the highest utility function (0.704) and C7 occupied rank 17 (the worst lot) with the lowest utility function (0.596). Ranking given by MARCOS method showed high degree of congruence with the earlier approaches, as evidenced by high rank correlation coefficients (Rs > 0.814). During sensitivity analyses, no occurrence of rank reversal is observed. The correlations between the quality value-based ranking and the yarn tenacity-based rankings are better than many of the traditional methods. The results can be improved further by adopting other efficient method of weighting the criteria.

The properties of raw cotton have significant impact on the quality of final yarn. Compared to the traditional methods, MCDM is reported as the most viable solution in which fibre parameters are given their due importance while formulating a single index known as quality value. The present study demonstrates the application of a recently developed exponent of MCDM in the name of MARCOS for the first time to address a cotton fibre selection problem for textile spinning mills. The same approach can also be extended to solve other decision problems of the textile industry, in general.

Novelty of the present study lies in the fact that the MARCOS is a very recently developed MCDM method, and this is a maiden application of the MARCOS method in the domain of textile, in general, and cotton industry, in particular. The approach is very simple, highly effective and quite flexible in terms of number of alternatives and decision criteria, although highly robust and stable.

This study aims to analyze lean wastes for the poultry sector in Turkey and link lean tools to this study, focusing on identifying each lean waste that affects poultry production and proposing solutions for preventing these lean wastes in the sector. The proposed solutions aim to improve processes by suggesting different lean tools and their applications for the poultry sector.

The study consists of two different applications. First, the waste relationship matrix (WRM) was created to reveal the relationship between seven lean wastes and their importance order. Then, after determining lean tools for eliminating lean wastes, the optimum weight ranking and consistency ratio of the most suitable lean tools were calculated for these wastes and ranked with the best-worst method (BWM).

Results showed that overproduction is the most critical waste that impacts other wastes, followed by defect waste. Due to the nature of the sector, these wastes not only result in economic loss for the company but also in food waste and loss and issues related to animal welfare. Furthermore, the Kaizen approach and 5S implementation are the methods to eliminate these wastes. Detailed discussion on the link between lean tools and lean wastes is provided for the poultry sector.

This is the first study that theoretically and empirically identifies the potential lean waste affecting the poultry sector and provides lean tools for eliminating these wastes. Sector-specific explanations and discussions are presented in the study to show the applicability of lean approaches in the poultry sector to eliminate waste. In addition, this study is the first to integrate the WRM and BWM.

Fiber reinforced additive manufacturing (FRAM) is an emerging technology that combines additive manufacturing and composite materials. As a result, design freedom offered by the manufacturing process can be leveraged in design optimization. The purpose of the study is to propose a novel method that improves structural performance by optimizing 3D print orientation of FRAM components.

This work proposes a two-part design optimization method that optimizes 3D global print orientation and topology of a component to improve a structural objective function. The method considers two classes of design variables: (1) print orientation design variables and (2) density-based topology design variables. Print orientation design variables determine a unique 3D print orientation to influence anisotropic material properties. Topology optimization determines an optimal distribution of material within the optimized print orientation.

Two academic examples are used to demonstrate basic behavior of the method in tension and shear. Print orientation and sequential topology optimization improve structural compliance by 90% and 58%, respectively. An industry-level example, an aerospace component, is optimized. The proposed method is used to achieve an 11% and 15% reduction of structural compliance compared to alternative FRAM designs. In addition, compliance is reduced by 43% compared to an equal-mass aluminum design.

Current research surrounding FRAM focuses on the manufacturing process and neglects opportunities to leverage design freedom provided by FRAM. Previous FRAM optimization methods only optimize fiber orientation within a 2D plane and do not establish an optimized 3D print orientation, neglecting exploration of the entire orientation design space.

Present study aims to extend the lattice Boltzmann method (LBM) to simulate radiation in geometries with curved boundaries, as the first step to simulate radiation in complex porous media. In recent years, researchers have increasingly explored the use of porous media to improve the heat transfer processes. The lattice Boltzmann method (LBM) is one of the most effective techniques for simulating heat transfer in such media. However, the application of the LBM to study radiation in complex geometries that contain curved boundaries, as found in many porous media, has been limited.

The numerical evaluation of the effect of the radiation-conduction parameter and extinction coefficient on temperature and incident radiation distributions demonstrates that the proposed LBM algorithm provides highly accurate results across all cases, compared to those found in the literature or those obtained using the finite volume method (FVM) with the discrete ordinates method (DOM) for radiative information.

For the case with a conduction-radiation parameter equal to 0.01, the maximum relative error is 1.9% in predicting temperature along vertical central line. The accuracy improves with an increase in the conduction-radiation parameter. Furthermore, the comparison between computational performances of two approaches reveals that the LBM-LBM approach performs significantly faster than the FVM-DOM solver.

The difficulty of radiative modeling in combined problems involving irregular boundaries has led to alternative approaches that generally increase the computational expense to obtain necessary radiative details. To address the limitations of existing methods, this study presents a new approach involving a coupled lattice Boltzmann and first-order blocked-off technique to efficiently model conductive-radiative heat transfer in complex geometries with participating media. This algorithm has been developed using the parallel lattice Boltzmann solver.

The purpose of this paper is to analyse and classify the literature that contributed to three questions, namely, what are the benefits of big data analytics (BDA) in the field of supply chain management (SCM) and logistics, what are the challenges in BDA applications in the field of SCM and logistics and what are the determinants of successful applications of BDA in the field of SCM and logistics.

This paper conducts a systematic literature review (SLR) to analyse the findings of 44 selected papers published in the period from 2016 to 2020, in the area of BDA and its impact on SCM. The designed protocol is composed of 14 steps in total, following Tranfeld (2003). The selected research papers are categorized into four themes.

This paper identifies sets of benefits to be gained from the use of BDA in SCM, including benefits in data analytics capabilities, operational efficiency of logistical operations and supply chain/logistics sustainability and agility. It also documents challenges to be addressed in this application, and determinants of successful implementation.

The scope of the paper is limited to the related literature published until the beginning of Corona Virus (COVID) pandemic. Therefore, it does not cover the literature published since the COVID pandemic.

This paper contributes to the academic research by providing a roadmap for future empirical work into this field of study by summarising the findings of the recent work conducted to investigate the uses of BDA in SCM and logistics. Specifically, this paper culminates in a summary of the most relevant benefits, challenges and determinants discussed in recent research. As the field of BDA remains a newly established field with little practical application in SCM and logistics, this paper contributes by highlighting the most important developments in contemporary literature practical applications.

Accounting information systems are mainly rule-based, and data are usually available and well-structured. However, many accounting systems are yet to catch up with current technological developments. Thus, artificial intelligence (AI) in financial accounting is often applied only in pilot projects. Using AI-based forecasts in accounting enables proactive management and detailed analysis. However, thus far, there is little knowledge about which prediction models have already been evaluated for accounting problems. Given this lack of research, our study aims to summarize existing findings on how AI is used for forecasting purposes in financial accounting. Therefore, the authors aim to provide a comprehensive overview and agenda for future researchers to gain more generalizable knowledge.

The authors identify existing research on AI-based forecasting in financial accounting by conducting a systematic literature review. For this purpose, the authors used Scopus and Web of Science as scientific databases. The data collection resulted in a final sample size of 47 studies. These studies were analyzed regarding their forecasting purpose, sample size, period and applied machine learning algorithms.

The authors identified three application areas and presented details regarding the accuracy and AI methods used. Our findings show that sociotechnical and generalizable knowledge is still missing. Therefore, the authors also develop an open research agenda that future researchers can address to enable the more frequent and efficient use of AI-based forecasts in financial accounting.

Owing to the rapid development of AI algorithms, our results can only provide an overview of the current state of research. Therefore, it is likely that new AI algorithms will be applied, which have not yet been covered in existing research. However, interested researchers can use our findings and future research agenda to develop this field further.

Given the high relevance of AI in financial accounting, our results have several implications and potential benefits for practitioners. First, the authors provide an overview of AI algorithms used in different accounting use cases. Based on this overview, companies can evaluate the AI algorithms that are most suitable for their practical needs. Second, practitioners can use our results as a benchmark of what prediction accuracy is achievable and should strive for. Finally, our study identified several blind spots in the research, such as ensuring employee acceptance of machine learning algorithms in companies. However, companies should consider this to implement AI in financial accounting successfully.

To the best of our knowledge, no study has yet been conducted that provided a comprehensive overview of AI-based forecasting in financial accounting. Given the high potential of AI in accounting, the authors aimed to bridge this research gap. Moreover, our cross-application view provides general insights into the superiority of specific algorithms.