Search results

This study aims to introduce an innovative approach to predictive maintenance by integrating time-series sensor data with event logs, leveraging the synergistic potential of deep learning models. The primary goal is to enhance the accuracy of equipment failure predictions, thereby minimizing operational downtime.

The methodology uses a dual-model architecture, combining the patch time series transformer (PatchTST) model for analyzing time-series sensor data and bidirectional encoder representations from transformers for processing textual event log data. Two distinct fusion strategies, namely, early and late fusion, are explored to integrate these data sources effectively. The early fusion approach merges data at the initial stages of processing, while late fusion combines model outputs toward the end. This research conducts thorough experiments using real-world data from wind turbines to validate the approach.

The results demonstrate a significant improvement in fault prediction accuracy, with early fusion strategies outperforming traditional methods by 2.6% to 16.9%. Late fusion strategies, while more stable, underscore the benefit of integrating diverse data types for predictive maintenance. The study provides empirical evidence of the superiority of the fusion-based methodology over singular data source approaches.

This research is distinguished by its novel fusion-based approach to predictive maintenance, marking a departure from conventional single-source data analysis methods. By incorporating both time-series sensor data and textual event logs, the study unveils a comprehensive and effective strategy for fault prediction, paving the way for future advancements in the field.

Applying critical analysis as the methodological framework for assessing the literature, the review seeks to present a summary and evaluation of the existing body of knowledge. This approach helps to establish the basis for developing forthcoming recommendations.

The articles were selected through a Systematic Literature Review following the PRISMA guidelines, and utilising Scopus, Web of Science, Science Direct, and the Education Resources Information Center database. Field taxonomy is presented based on the outcomes.

Through a critical review, we offer narrative arguments that document the shortcomings in the existing literature by scrutinising study designs and highlighting suboptimal approaches. Finally, we issue a call to action for future research, envisioning its potential to reorient and reconstruct the field while enhancing the quality of future studies. This proactive stance aims to foster the development of more competent and insightful perspectives, theories, and policy recommendations within design thinking in management education and training.

The research in this field holds significant potential for providing valuable practical and policy insights, contingent upon the rigorous and thorough execution of studies.

This article presents a robust critical review of 57 state-of-the-art articles investigating design thinking in the context of management education and training.

This systematic literature review aims to identify the pattern of data mining (DM) research by looking at the levels and aspects of education.

This paper reviews 113 conference and research papers from well-known publishers of educational data mining (EDM) and learning analytics-related research using a recognized literature review in computer science by Carrera-Rivera et al. (2022a). Two major stages, planning and conducting the review, were used. The databases of Elsevier, Springer, IEEE, SAI, Hindawi, MDPI, Wiley, Emerald and Sage were searched to retrieve EDM papers from the period 2017 to 2023. The papers retrieved were then filtered based on the application of DM to the three educational levels – basic, pre-tertiary and tertiary education.

EDM is concentrated on higher education. Basic education is not given the needed attention in EDM. This does not enhance inclusivity and equity. Learner performance is given much attention. Resource availability and teaching and learning are not given the needed attention.

This review is limited to only EDM. Literature from the year 2017 to 2023 is covered. Other aspects of DM and other relevant literature published in EDM outside the research period are not considered.

As the current trend of EDM shows an increase in zeal, future research in EDM should concentrate on the lower levels of education to identify the challenges of basic education which serves as the core of education. This will enable addressing the challenges of education at an early stage and facilitate getting a quality education at all levels of education. Appropriate EDM techniques for mining the data at this level should be the focus of the research. Specifically, techniques that can cater for the variation in learner abilities and the appropriate identification of learner needs should be considered.

Content sequencing is necessary in facilitating an easy understanding of concepts. Curriculum design from basic to higher education dwells much on this. Identifying the challenge of learning at the early stages will facilitate efficient learning. At the basic level of learning, data on learning should be collected by educational institutions just as it is done at the tertiary level. This will enable EDM to accurately identify the challenges and appropriate solutions to educational problems. Resource availability is a catalyst for effective teaching and learning. The attributes of a learner will enable knowing the true nature of the learner to determine the prospects of the learner.

This research has not been published in any journal. The information presented is the original knowledge of the authors. However, a pre-print of the work is in Research Square.

Large class sizes are becoming the norm in higher education against concerns of dropping learning qualities. To maintain the standard of learning and add value, one of the common strategies is for the course convenor to proactively monitor student engagement with learning activities against their assessment outcomes and intervene timely. Learning analytics has been increasingly adopted to provide these insights into student engagement and their performance. This case study explores how learning analytics can be used to meet the convenor’s requirements and help reduce administrative workload in a large health science class at the University of New South Wales.

This case-based study adopts an “action learning research approach” in assessing ways of using learning analytics for reducing workload in the educator’s own context and critically reflecting on experiences for improvements. This approach emphasises reflexive methodology, where the educator constantly assesses the context, implements an intervention and reflects on the process for in-time adjustments, improvements and future development.

The results highlighted ease for the teacher towards the early “flagging” of students who may not be active within the learning management system or who have performed poorly on assessment tasks. Coupled with the ability to send emails to the “flagged” students, this has led to a more personal approach while reducing the number of steps normally required. An unanticipated outcome was the potential for additional time saving through improving the scaffolding mechanisms if the learning analytics were customisable for individual courses.

The results provide further benefits for learning analytics to assist the educator in a growing blended learning environment. They also reveal the potential for learning analytics to be an effective adjunct towards promoting personal learning design.

Process mining (PM) has emerged as a leading technology for gaining data-based insights into organizations’ business processes. As processes increasingly cross-organizational boundaries, firms need to conduct PM jointly with multiple organizations to optimize their operations. However, current knowledge on cross-organizational process mining (coPM) is widely dispersed. Therefore, we synthesize current knowledge on coPM, identify challenges and enablers of coPM, and build a socio-technical framework and agenda for future research.

We conducted a literature review of 66 articles and summarized the findings according to the framework for Information Technology (IT)-enabled inter-organizational coordination (IOC) and the refined PM framework. The former states that within inter-organizational relationships, uncertainty sources determine information processing needs and coordination mechanisms determine information processing capabilities, while the fit between needs and capabilities determines the relationships’ performance. The latter distinguishes three categories of PM activities: cartography, auditing and navigation.

Past literature focused on coPM techniques, for example, algorithms for ensuring privacy and PM for cartography. Future research should focus on socio-technical aspects and follow four steps: First, determine uncertainty sources within coPM. Second, design, develop and evaluate coordination mechanisms. Third, investigate how the mechanisms assist with handling uncertainty. Fourth, analyze the impact on coPM performance. In addition, we present 18 challenges (e.g. integrating distributed data) and 9 enablers (e.g. aligning different strategies) for coPM application.

This is the first article to systematically investigate the status quo of coPM research and lay out a socio-technical research agenda building upon the well-established framework for IT-enabled IOC.

The purpose of this study is to present a methodical procedure on how to prepare event logs and analyse them through process mining, statistics and visualisations. The aim is to derive roots and patterns of quality deviations and non-conforming finished products as well as best practice facilitating employee training in the food processing industry. Thereby, a key focus is on recognising tacit knowledge hidden in event logs to improve quality processes.

This study applied process mining to detect root causes of quality deviations in operational process of food production. In addition, a data-ecosystem was developed which illustrates a continuous improvement feedback loop and serves as a role model for other applications in the food processing industry. The approach was applied to a real-case study in the processed cheese industry.

The findings revealed practical and conceptional contributions which can be used to continuously improve quality management (QM) in food processing. Thereby, the developed data-ecosystem supports production and QM in the decision-making processes. The findings of the analysis are a valuable basis to enhance operational processes, aiming to prevent quality deviations and non-conforming finished products.

Process mining is still rarely used in the food industry. Thereby, the proposed method helps to identify tacit knowledge in the food processing industry, which was shown by the framework for the preparation of event logs and the data ecosystem.

Reflective practice (RP) is a key skill for developing one’s professional practice. It has, however, not been unanimously prioritised in public health (PH) competency and education frameworks. Reflection activities are often unstructured in higher education. There is also a dearth of literature on the RPs of undergraduate PH students. This study aims to explore in greater depth how RP helps undergraduate PH students explore their own learning in internships.

Reflection prompts were designed using the DEAL model. 124 written reflection entries from 32 students were collected and analysed thematically using a deductive-inductive approach. The conceptual framework of internship learning goals by Ash and Clayton (2009) was used to guide the deductive analysis.

Three themes were identified: initial engagement with reflective learning; gradual integration of reflective learning, and a transformative phase involving professional development, personal growth, civic learning, growth through struggle, being confronted with differences in expectations, and skill acquisition.

This study extends the limited evidence regarding RP in undergraduate non-medical PH education, and contributes toward informing the revision of undergraduate PH programmes, for example, by integrating structured reflection earlier in the curricula, and establishing/supporting mentorship programmes between institutions. The findings call for PH educators to be more intentional in creating opportunities to nurture RP among budding PH professionals.

This study aims to present a model for detecting and predicting creative accounting in companies listed on the Tehran Stock Exchange (TSE).

The authors conduct this research in three stages. First, the authors review the literature to determine the dimensions, components, indicators and techniques of creative accounting. Second, the authors conduct semi-structured interviews with experts using the fuzzy Delphi technique to obtain screening and reach a consensus. Finally, the authors develop a model to predict creative accounting by classifying the financial statements of the sample companies into two groups based on the use or non-use of creative accounting techniques, measuring the indicators determined in the previous stage, running various machine learning algorithms and choosing the superior algorithm.

The results indicate the usefulness of accounting information for detecting and predicting creative accounting and the relevance of several financial attributes as important predictors. The results also indicate the superiority of extremely randomized trees over other algorithms in predicting creative accounting and suggest that the primary purpose of creative accounting in Iran is earnings management. Contrary to the political cost hypothesis, large Iranian companies use creative accounting to inflate profits.

The present research also has several limitations that must be considered, and caution must be exercised in interpreting and generalizing the findings as specified in the revised manuscript.

This study’s implications are significant for policymakers, standard-setters and practitioners. By recognizing the detrimental effects of creative accounting on financial transparency within companies, policymakers can address existing gaps in accounting standards to minimize the potential for earnings manipulation. Consequently, strengthening internal and external mechanisms related to a firm’s financial performance becomes achievable. The study provides evidence of the need for audit firms to recognize the importance of creative accounting and consider creative accounting in their audit plans to prevent insufficient or even misleading disclosure by companies that extensively use creative accounting practices in their financial reporting. Moreover, knowledge of creative accounting techniques can help auditors assess audit and detection risks and serve as a valuable guide for reducing audit costs and improving audit quality.

Given that creative accounting practices distort the true or real accounting results, curbing creative accounting practices reduces corporate failures and could lead to the reduction of job losses and other social consequences.

This study uses a unique database in Iran to determine a model for predicting creative accounting using a mixed-method methodology, qualitative and quantitative, to identify creative accounting techniques and run various machine learning algorithms.

The purpose of this study is to present a systematic and comprehensive review of personalized, adaptive and semantic e-learning systems.

Preferred reporting items of systematic reviews and meta-analyses guidelines have been used for a thorough insight into associated aspects of e-learning that complement the e-learning pedagogies and processes. The aspects of e-learning systems have been reviewed comprehensively such as personalization and adaptivity, e-learning and semantics, learner profiling and learner categorization, which are handy in intelligent content recommendations for learners.

The adoption of semantic Web based technologies would complement the learner’s performance in terms of learning outcomes.

The evaluation of the proposed framework depends upon the yearly batch of learners and recording is a cumbersome/tedious process.

E-Learning systems may have diverse and positive impact on society including democratized learning and inclusivity regardless of socio-economic or geographic status.

A preliminary framework of an ontology-based e-learning system has been proposed at a modular level of granularity for implementation, along with evaluation metrics followed by a future roadmap.

Unlike many existing methods that are primarily focused on two-dimensional localization, this research paper extended the scope to three-dimensional localization. This enhancement is particularly significant for unmanned aerial vehicle (UAV) applications that demand precise altitude information, such as infrastructure inspection and aerial surveillance, thereby broadening the applicability of UAV-assisted wireless networks.

The paper introduced a novel method that employs recurrent neural networks (RNNs) for node localization in three-dimensional space within UAV-assisted wireless networks. It presented an optimization perspective to the node localization problem, aiming to balance localization accuracy with computational efficiency. By formulating the localization task as an optimization challenge, the study proposed strategies to minimize errors while ensuring manageable computational overhead, which are crucial for real-time deployment in dynamic UAV environments.

Simulation results demonstrated significant improvements, including a channel capacity of 99.95%, energy savings of 89.42%, reduced latency by 99.88% and notable data rates for UAV-based communication with an average localization error of 0.8462. Hence, the proposed model can be used to enhance the capacity of UAVs to work effectively in diverse environmental conditions, offering a reliable solution for maintaining connectivity during critical scenarios such as terrestrial environmental crises when traditional infrastructure is unavailable.

Conventional localization methods in wireless sensor networks (WSNs), such as received signal strength (RSS), often entail manual configuration and are beset by limitations in terms of capacity, scalability and efficiency. It is not considered for 3-D localization. In this paper, machine learning such as multi-layer perceptrons (MLP) and RNN are employed to facilitate the capture of intricate spatial relationships and patterns (3-D), resulting in enhanced localization precision and also improved in channel capacity, energy savings and reduced latency of UAVs for wireless communication.