Search results

Machine learning (ML) techniques are increasingly important in enabling business-to-business (B2B) companies to offer personalized services to business customers. On the other hand, humans play a critical role in dealing with uncertain situations and the relationship-building aspects of a B2B business. Most existing studies advocating human-ML augmentation simply posit the concept without providing a detailed view of augmentation. Therefore, the purpose of this paper is to investigate how human involvement can practically augment ML capabilities to develop a personalized information system (PIS) for business customers.

The authors developed a research framework to create an integrated human-ML PIS for business customers. The PIS was then implemented in the energy sector. Next, the accuracy of the PIS was evaluated using customer feedback. To this end, precision, recall and F1 evaluation metrics were used.

The computed figures of precision, recall and F1 (respectively, 0.73, 0.72 and 0.72) were all above 0.5; thus, the accuracy of the model was confirmed. Finally, the study presents the research model that illustrates how human involvement can augment ML capabilities in different stages of creating the PIS including the business/market understanding, data understanding, data collection and preparation, model creation and deployment and model evaluation phases.

This paper offers novel insight into the less-known phenomenon of human-ML augmentation for marketing purposes. Furthermore, the study contributes to the B2B personalization literature by elaborating on how human experts can augment ML computing power to create a PIS for business customers.

Companies should enhance their market position and competitiveness by improving staff effectiveness, skills, resource commitment, and applying relevant managerial methods. This study aims to examine the impact of knowledge management (KM) and total quality management (TQM) on employee effectiveness (EE) and supply chain performance (SCP) in emerging economies.

The used methodology consists on conducting a survey within Tunisian companies, where the authors gathered 206 responses. Collected data was analyzed using statistical package for the social sciences (SPSS) software, enabling the authors to establish a conceptual model. This model was further examined through structural equation modeling, using analysis of moment structures (AMOS) software for hypothesis validation. Additionally, the authors’ research aimed to enhance SCP and boost EE while minimizing costs through a nonlinear mathematical model and the quality function deployment method.

The results indicate that TQM and KM positively impact EE, and KM and EE positively impact SCP. However, the significance of employee performance on SCP varies depending on company location and industry sector studied.

This work emphasized the involvement of small- and medium-sized enterprise managers from emerging economies in the studied concepts and confirmed the effects of KM and TQM practices on EE and SCP.

Recognising the as-built state of construction elements is crucial for construction progress monitoring. Construction scholars have used computer vision-based algorithms to automate this process. Robust object recognition from indoor site images has been inhibited by technical challenges related to indoor objects, lighting conditions and camera positioning. Compared with traditional machine learning algorithms, one-stage detector deep learning (DL) algorithms can prioritise the inference speed, enable real-time accurate object detection and classification. This study aims to present a DL-based approach to facilitate the as-built state recognition of indoor construction works.

The one-stage DL-based approach was built upon YOLO version 4 (YOLOv4) algorithm using transfer learning with few hyperparameters customised and trained in the Google Colab virtual machine. The process of framing, insulation and drywall installation of indoor partitions was selected as the as-built scenario. For training, images were captured from two indoor sites with publicly available online images.

The DL model reported a best-trained weight with a mean average precision of 92% and an average loss of 0.83. Compared to previous studies, the automation level of this study is high due to the use of fixed time-lapse cameras for data collection and zero manual intervention from the pre-processing algorithms to enhance visual quality of indoor images.

This study extends the application of DL models for recognising as-built state of indoor construction works upon providing training images. Presenting a workflow on training DL models in a virtual machine platform by reducing the computational complexities associated with DL models is also materialised.

Developing a reliable cost estimate at the early stage of construction projects is challenging due to inadequate project information. Most of the information during this stage is qualitative, posing additional challenges to achieving accurate cost estimates. Additionally, there is a lack of tools that use qualitative project information and forecast the budgets required for project completion. This research, therefore, aims to develop a model for setting project budgets (excluding land) during the pre-conceptual stage of residential buildings, where project information is mainly qualitative.

Due to the qualitative nature of project information at the pre-conception stage, a natural language processing model, DistilBERT (Distilled Bidirectional Encoder Representations from Transformers), was trained to predict the cost range of residential buildings at the pre-conception stage. The training and evaluation data included 63,899 building permit activity records (2021–2022) from the Victorian State Building Authority, Australia. The input data comprised the project description of each record, which included project location and basic material types (floor, frame, roofing, and external wall).

This research designed a novel tool for predicting the project budget based on preliminary project information. The model achieved 79% accuracy in classifying residential buildings into three cost_classes ($100,000-$300,000, $300,000-$500,000, $500,000-$1,200,000) and F1-scores of 0.85, 0.73, and 0.74, respectively. Additionally, the results show that the model learnt the contextual relationship between qualitative data like project location and cost.

The current model was developed using data from Victoria state in Australia; hence, it would not return relevant outcomes for other contexts. However, future studies can adopt the methods to develop similar models for their context.

This research is the first to leverage a deep learning model, DistilBERT, for cost estimation at the pre-conception stage using basic project information like location and material types. Therefore, the model would contribute to overcoming data limitations for cost estimation at the pre-conception stage. Residential building stakeholders, like clients, designers, and estimators, can use the model to forecast the project budget at the pre-conception stage to facilitate decision-making.

Major public cloud providers, such as AWS, Azure or Google, offer seamless experiences for infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS). With the emergence of the public cloud's vast usage, administrators must be able to have a reliable method to provide the seamless experience that a public cloud offers on a smaller scale, such as a private cloud. When a smaller deployment or a private cloud is needed, OpenStack can meet the goals without increasing cost or sacrificing data control.

To demonstrate these enablement goals of resiliency and elasticity in IaaS and PaaS, the authors design a private distributed system cloud platform using OpenStack and its core services of Nova, Swift, Cinder, Neutron, Keystone, Horizon and Glance on a five-node deployment.

Through the demonstration of dynamically adding an IaaS node, pushing the deployment to its physical and logical limits, and eventually crashing the deployment, this paper shows how the PackStack utility facilitates the provisioning of an elastic and resilient OpenStack-based IaaS platform that can be used in production if the deployment is kept within designated boundaries.

The authors adopt the multinode-capable PackStack utility in favor of an all-in-one OpenStack build for a true demonstration of resiliency, elasticity and scalability in a small-scale IaaS. An all-in-one deployment is generally used for proof-of-concept deployments and is not easily scaled in production across multiple nodes. The authors demonstrate that combining PackStack with the multi-node design is suitable for smaller-scale production IaaS and PaaS deployments.

The purpose of this paper is to examine the impact of affiliate marketing strategies as a tool for increasing customers' engagement and vulnerability over financial services. This is attempted by examining the connection between affiliate marketing factors and customers' brand engagement and vulnerability metrics.

The authors developed a three-staged methodological context, based on the 7 most known centralized payment network (CPN) firms' website analytical data, which begins with linear regression analysis, followed by hybrid modeling (agent-based and dynamic models), so as to simulate brand engagement and vulnerability factors' variation in a 180-day period. The deployed context ends by applying the cognitive modeling method of producing heatmaps and facial analysis of CPN websites to the selected 47 vulnerable website customers, for gathering more insights into their brand engagement.

Throughout the simulation results of the study, it becomes clear that a higher number of backlinks and referral domains tend to increase CPN firms' brand-engaged and vulnerable customers.

From the simulation modeling process, the implication for backlinks and referral domains as factors that enhance website customers' brand engagement and vulnerability has been highlighted. A higher number of brand-engaged website customers could mean that vulnerable categories of customers would be impacted by CPNs' affiliate marketing. Improving those customers' knowledge of the financial services utility is of utmost importance.

The outcomes of the research indicate that online banking service providers can increase their customers' engagement with their brands by adopting affiliate marketing techniques. To avoid the increase in customers' vulnerability, marketers should aim to apply affiliate marketing strategies to domains relevant to the provided financial services.

The paper's outcomes provide a new approach to the literature, where the website customer's brand engagement comes out as a valuable metric for estimating online banking sector customers' vulnerability.

Sustainable development goals and the climate change agenda are becoming widely promoted topics of research for the 21st century. The role of cities is increasingly recognised as central to investigating these topics. Yet, the field of informal sector entrepreneurship which so many urban entrepreneurs in developing countries depend upon is seldom considered. To redress this imbalance, this study aims to develop a decision model in accordance with institutional theory (IT) and resource dependency theory (RDT) for city managers to deploy. The model identifies and prioritises optimal strategies to address the three areas of sustainability requirements environment society and economy within the study context of Bangladesh.

This study used a mixed methods research design. In the qualitative part, the authors identified the three areas of sustainability requirements (i.e. environment, society and economy) and their corresponding strategies involving the informal sector that operates within the urban environment. In the quantitative part, the authors applied fuzzy quality function deployment (QFD) integrated with the 0-1 non-linear optimisation technique to identify optimal strategies.

The findings show that strategies such as legitimate frameworks, waste management, allocation of urban public space and training programs contribute in important ways to the three areas of sustainability requirements.

The proposed decision model will assist policy-makers and city managers to prioritise sustainability requirements and implement optimal strategies to address those requirements.

Through the integration of IT and RDT, the decision model developed in this study is unique in its application to urban-based informal entrepreneurship in the context of developing countries. The effective application of the fuzzy QFD approach and the optimisation model in the context of urban-based informal entrepreneurship also offers unique contributions to the field of study.

The purpose of the study is to develop a cloud supporting model for green computing. In today's contemporary world, information technology (IT) plays a significant role. Because of the rapid growth of the IT business and the high level of greenhouse gas emissions, salient data centers are increasingly considering green IT techniques to reduce their environmental impacts. Both developing and underdeveloped countries are widely adopting green infrastructure and services over the cloud because of its cost-effectiveness, scalability and guaranteed high uptime. Several studies have investigated the fact that cloud computing provides beyond green information and communication technology (ICT) services and solutions. Therefore, anything offered over clouds also needs to be green to reduce the adverse influence on the environment.

This paper examines the rationale for the use of green ICT in higher education and finds crucial success variables for the implementation of green ICT on the basis of an analysis of chosen educational organizations and interviews with key academic experts from the Universities of Ethiopia, in general, and BuleHora University, in particular.

Finally, this paper described the design and development of a green cloud selection supporting model for green ICTs in higher educational institutions that helps cloud service customers choose the most green cloud-based ICT products as well as services.

This study may be a significant source of new information for green ICT design and implementation in higher education institutions to preserve the environment and its impact on human life.

The paper examines the historical shifts in policing strategies towards individuals with SMI and vulnerable populations, highlighting the development of co-response models, introducing the concept of “untethered” co-response.

This paper conducts a review of literature to trace the evolution of police responses to individuals with serious mental illness (SMI) and vulnerable populations. It categorizes four generations of police approaches—zero-policing, over-policing, crisis intervention and co-response—and introduces a fifth generation, the “untethered” co-response model exemplified by Project SCOPE in Philadelphia.

The review identifies historical patterns of police response to SMI individuals, emphasizing the challenges and consequences associated with over-policing. It outlines the evolution from crisis intervention teams to co-response models and introduces Project SCOPE as an innovative “untethered” co-response approach.

The research acknowledges the challenges in evaluating the effectiveness of crisis intervention teams and co-response models due to variations in implementation and limited standardized models. It emphasizes the need for more rigorous research, including randomized controlled trials, to substantiate claims about the effectiveness of these models.

The paper suggests that the “untethered” co-response model, exemplified by Project SCOPE, has the potential to positively impact criminal justice and social service outcomes for vulnerable populations. It encourages ongoing policy and evaluative research to inform evidence-based practice and mitigate collateral harms associated with policing responses.

Given the rising interactions between police and individuals with mental health issues, exacerbated by the COVID-19 pandemic, the paper highlights the urgency for innovative, non-policing-driven responses to vulnerable persons.

The paper contributes to the literature by proposing a fifth generation of police response to vulnerable persons, the “untethered” co-response model and presenting Project SCOPE as a practical example.

Professional Identity Formation is the dynamic evolution to “think, act and feel” to become part of a professional community. This document presents the development and the study that aimed to assess the usability of a m-Learning Identity App (MLIA) focused on the formation of professional identity among undergraduate medical students.

MLIA development included four phases: Conceptual, prototype, pilot and implementation, before further deployment. The conceptual model was designed by eight faculty members from three Latin American universities. The prototype was developed and tested with stakeholders. The pilot was performed during 5 weeks before the implementation. Cross-sectional data collected during implementation from 138 medical students who completed a survey to assess the usability of MLIA are presented. During deployment, 977 posts were made on Professional Identity Formation, and examples of these posts are presented.

The prototype and pilot phases demanded improvements. The survey explored (1) Familiarity, (2) Perceived ease of use, (3) Perceived usefulness for Professional Identity Formation, (4) Satisfaction, (5) Intention to reuse (6) Digital aesthetics and (7) Safety. Results from the usability assessment suggest that students perceived MLIA as a secure space with positive aesthetics and ease of use.

Important limitations of the present study include, firstly, that it does not provide information on the effectiveness of the MLIA in shaping professional identity in medical students, it focuses exclusively on its development (conceptual model, prototype, pilot and implementation) and usability. Secondly, the study design did not consider a control group and, therefore, does not provide information on how the App compares with other strategies addressing self-reflection and sharing of meaningful experiences related to professional identity.

MLIA introduces a different approach to education, simulating a secure, easy-to-use, social media with a friendly interface in a safe environment to share academic and motivational moments, transitioning from being to becoming a professional.