Search results

Predicting student performance is crucial in educational settings to identify and support students who may need additional help or resources. Understanding and predicting student performance is essential for educators to provide targeted support and guidance to students. By analyzing various factors like attendance, study habits, grades, and participation, teachers can gain insights into each student’s academic progress. This information helps them tailor their teaching methods to meet the individual needs of students, ensuring a more personalized and effective learning experience. By identifying patterns and trends in student performance, educators can intervene early to address any challenges and help students acrhieve their full potential. However, the complexity of human behavior and learning patterns makes it difficult to accurately forecast how a student will perform. Additionally, the availability and quality of data can vary, impacting the accuracy of predictions. Despite these obstacles, continuous improvement in data collection methods and the development of more robust predictive models can help address these challenges and enhance the accuracy and effectiveness of student performance predictions. However, the scalability of the existing models to different educational settings and student populations can be a hurdle. Ensuring that the models are adaptable and effective across diverse environments is crucial for their widespread use and impact. To implement a student’s performance-based learning recommendation scheme for predicting the student’s capabilities and suggesting better materials like papers, books, videos, and hyperlinks according to their needs. It enhances the performance of higher education.

Thus, a predictive approach for student achievement is presented using deep learning. At the beginning, the data is accumulated from the standard database. Next, the collected data undergoes a stage where features are carefully selected using the Modified Red Deer Algorithm (MRDA). After that, the selected features are given to the Deep Ensemble Networks (DEnsNet), in which techniques such as Gated Recurrent Unit (GRU), Deep Conditional Random Field (DCRF), and Residual Long Short-Term Memory (Res-LSTM) are utilized for predicting the student performance. In this case, the parameters within the DEnsNet network are finely tuned by the MRDA algorithm. Finally, the results from the DEnsNet network are obtained using a superior method that delivers the final prediction outcome. Following that, the Adaptive Generative Adversarial Network (AGAN) is introduced for recommender systems, with these parameters optimally selected using the MRDA algorithm. Lastly, the method for predicting student performance is evaluated numerically and compared to traditional methods to demonstrate the effectiveness of the proposed approach.

The accuracy of the developed model is 7.66%, 9.91%, 5.3%, and 3.53% more than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-1, and 7.18%, 7.54%, 5.43% and 3% enhanced than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-2.

The developed model recommends the appropriate learning materials within a short period to improve student’s learning ability.

The objective of this research is to develop an solution to water management at the scale of buildings, through the technological resources. Automating analysis using 3D models helps increase efficiency in buildings during the operational phase, consequently promotes sustainability.

This study presents a methodology based on Design Science Research to automate water management at building scale integrating BIM-IoT-FM. Data from smart meters (IoT) and the BIM model were integrated to be applied in facilities management (FM) to improve performance of the building. The methodology was implemented in a prototype for the web, called AquaBIM, which captures, manages and analyzes the information.

The application of AquaBIM allowed the theoretical evaluation and practical validation of water management methodology. By BIM–IoT integration, the consumption parameters and ranges for 17 categories of activities were determined to contribute to fulfill the research gap for the commercial buildings. This criterion and other requirements are requirements met in order to obtain the AQUA-HQE environmental sustainability certification.

Traditionally, water management in buildings is based on scarce data. The practical application of digital technologies improves decision-making. Moreover, the creation of consumption indicators for commercial buildings contributes to the discussion in the field of knowledge.

This article emphasizes the investigation of the efficiency of use in commercial buildings using operational data and the use of sustainable consumption indicators to manage water consumption.

Financial technologies form the heart of considerable disruptive innovation. Fintech is the emerging financial infrastructure for modern business. Big data are the feedstock for artificial intelligence (AI) that drives many fintech sectors – start-up finance, commodities and investment instrumentation, payment systems, currencies, exchange markets/trading platforms, market-failure response forensics, underwriting, syndication, risk assessment, advisory services, banking, financial intermediaries, transaction settlement, corporate disclosure, and decentralized finance. This chapter demonstrates how analyzing big data, largely processed through cloud computing, drives fintech innovations, scholarship, forensics, and public policy. Despite their apparent virtues, some fintech mechanisms can externalize various social costs: flawed designs, opacity/obscurity, social media (SM) influences, cyber(in)security, and other malfunctions. Fintech suffers regulatory lag, the delay following the introduction of novel fintechs and later assessment, development, and deployment of reliable regulatory mechanisms. Big data can improve fintech practices by balancing three key influences: (1) fintech incentives, (2) market failure forensics, and (3) developing balanced public policy resolutions to fintech challenges.

This paper aims to critically examine the accounting and information systems literature to understand the changes that are occurring in the management accounting profession. The changes the authors are interested in are linked to technology-driven innovations in managerial decision-making and in organizational structures. In addition, the paper highlights research gaps and opportunities for future research.

The authors adopted a grounded theory literature review method (Wolfswinkel et al., 2013) to achieve the study’s aims.

The authors identified four research themes that describe the changes in the management accounting profession due to technology-driven innovations: structured vs unstructured data, human vs algorithm-driven decision-making, delineated vs blurred functional boundaries and hierarchical vs platform-based organizations. The authors also identified tensions mentioned in the literature for each research theme.

Previous studies display a rather narrow focus on the role of digital technologies in accounting work and new competences that management accountants require in the digital era. By contrast, the authors focus on the broader technology-driven shifts in organizational processes and structures, which vastly change how accounting information is collected, processed and analyzed internally to support managerial decision-making. Hence, the paper focuses on how management accountants can adapt and evolve as their organizations transition toward a digital environment.

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.

This paper aims to provide insights into the environment needed for advancing a digitally enabled circular plastic economy in Africa. It explores important technical and social paradigms for the transition.

This study adopted an interpretivist paradigm, drawing on thematic analysis on qualitative data from an inter-sectoral engagement with 69 circular economy stakeholders across the continent.

The results shows that, while substantial progress has been made with regard to the development and deployment of niche innovations in Africa, the overall progress of circular plastic economy is slowed due to relatively minimal changes at the regime levels as well as pressures from the exogenous landscape. The study highlights that regime changes are crucial for disrupting the entrenched linear plastic economy in developing countries, which is supported by significant sunk investment and corporate state capture.

The main limitation of this study is with the sample as it uses data collected from five countries. Therefore, while it offers a panoramic view of multi-level synergy of actors and sectors across African countries, it is limited in its scope and ability to illuminate country-specific nuances and peculiarities.

The study underlines the importance of policy innovations and regulatory changes in order for technologies to have a meaningful contribution to the transition to a circular plastic economy.

The study makes an important theoretical contribution by using empirical evidence from various African regions to articulate the critical importance of the regime dimension in accelerating the circular economy transition in general, and the circular plastic economy in particular, in Africa.

This study was conducted to address the methodical shortcomings and high associated cost of understanding the use of new, poorly understood architectural spaces, such as makerspaces. The proposed quantified method of enhancing current post-occupancy evaluation (POE) practices aims to provide architects, engineers and building professionals with accessible and intuitive data that can be used to conduct comparative studies of spatial changes, understand changes over time (such as those resulting from COVID-19) and verify design intentions after construction through a quantified post-occupancy evaluation.

In this study, we demonstrate the use of ultra-wideband (UWB) technology to gather, analyze and visualize quantified data showing interactions between people, spaces and objects. The experiment was conducted in a makerspace over a four-day hackathon event with a team of four actively tracked participants.

The study shows that by moving beyond simply counting people in a space, a more nuanced pattern of interactions can be discovered, documented and analyzed. The ability to automatically visualize findings intuitively in 3D aids architects and visual thinkers to easily grasp the essence of interactions with minimal effort.

By providing a method for better understanding the spatial and temporal interactions between people, objects and spaces, our approach provides valuable feedback in POE. Specifically, our approach aids practitioners in comparing spaces, verifying design intent and speeding up knowledge building when developing new architectural spaces, such as makerspaces.

As sustainability becomes more important in manufacturing, researchers recommend using the four-stage Hayes and Wheelwright (H-W) model of strategic manufacturing effectiveness (SME) to integrate sustainable manufacturing practices (SMPs) at a strategic level. However, there is limited research on this topic. This paper investigates SMPs encompassing four sustainable manufacturing capabilities (SMCs): pollution control, pollution prevention, product stewardship, and clean technology. It relates these SMCs to the four SME stages of the H-W model, both of which form a continuum of stages.

A theoretical model on the congruence between SMCs and SME stages is first established using organizational theories to identify the dominant combinations. This model is then tested by examining 178 SMPs of four large manufacturing firms.

The study reveals that the SMPs of the case firms clearly show SMC and SME stage characteristics. Few deviations from the relationships established in the theoretical model are observed, leading to a revision of the model. A major finding is that SMPs within an SMC category can span multiple SME stages.

The study proposes a revised model based on a small sample of case firms, which may limit its broader applicability.

Manufacturing practitioners can use the findings of this study to plan SMPs that align with their SME goals.

Towards incorporating sustainability in the H-W model, this is the first major exploratory study that establishes congruent relationship between SMCs and SME stages of the H-W model.

This study aims to assess the use of the Internet of Things (IoT) in retail stores to improve supply chain visibility and integration.

This study employed a qualitative methodology with data collected using semi-structured interviews from a sample selected using purposive sampling. The population consists of 48 employees, of which 6 were selected for the sample as they worked directly with IoT and supply chain issues. Participants were from a SPAR franchise store (Samenwerken Profiteren Allen Regalmatig).

Thematic analysis was used to analyse the transcribed data from the interviews. The themes identified include supply chain visibility, supply chain integration and IoT. The findings indicate that the main IoT used is an organisational-wide system, the SIGMA (SPAR Integrated Goods Management Application) system. Other technologies that aid supply chain visibility and integration are geotags, the internet, WhatsApp social media applications, emails and scanners.

From the findings, this study recommends that IoT systems should be frequently updated to reflect current trends and that IoT systems should enable the integration of small and medium Enterprises (SMEs) suppliers.

The Fourth Industrial Revolution has ushered in new technologies that revolutionise business operations. Among these technologies is the IoT, which has ushered in a new connectivity area. However, there is little research on the use of IoT for supply chain visibility and integration in the South African retail sector. It provides sector-specific insights and recommendations for retailers, which might not be covered in general supply chain management literature.

The primary objective of this paper is to show a systematic and methodological approach for the digitalization of critical clinical pathways (CPs) within the healthcare domain.

The methodology entails the integration of service design (SD) and action research (AR) methodologies, characterized by iterative phases that systematically alternate between action and reflective processes, fostering cycles of change and learning. Within this framework, stakeholders are engaged through semi-structured interviews, while the existing and envisioned processes are delineated and represented using BPMN 2.0. These methodological steps emphasize the development of an autonomous, patient-centric web application alongside the implementation of an adaptable and patient-oriented scheduling system. Also, business processes simulation is employed to measure key performance indicators of processes and test for potential improvements. This method is implemented in the context of the CP addressing transient loss of consciousness (TLOC), within a publicly funded hospital setting.

The methodology integrating SD and AR enables the detection of pivotal bottlenecks within diagnostic CPs and proposes optimal corrective measures to ensure uninterrupted patient care, all the while advancing the digitalization of diagnostic CP management. This study contributes to theoretical discussions by emphasizing the criticality of process optimization, the transformative potential of digitalization in healthcare and the paramount importance of user-centric design principles, and offers valuable insights into healthcare management implications.

The study’s relevance lies in its ability to enhance healthcare practices without necessitating disruptive and resource-intensive process overhauls. This pragmatic approach aligns with the imperative for healthcare organizations to improve their operations efficiently and cost-effectively, making the study’s findings relevant.