Search results

As many businesses faced economic disruption due to the Covid-19 pandemic and sought financial relief, existing bank relationships became critical to getting a loan. This study examines factors associated with the development of personal relationships of rural small businesses with community bank representatives.

We applied a mixed-method approach. We employed descriptive statistics, principal factor analysis and logistic regression for data analysis. We distributed an online survey to rural small businesses in five states in the United States. Key informant interviews with community bank representatives supplemented the survey results.

A business owner’s trust in a banker was positively associated with the establishment of a business–bank relationship. However, an analysis of individual trust’s components revealed that the nature of trust is complex, and a failure of one or more components may lead to decreased trustworthiness in a banker. Small businesses that preferred personal communication with a bank were more inclined to relationship banking.

Due to the relatively small sample size and cross-sectional data, our results may not be conclusive but should be viewed as preliminary and as suggestions for future research. Bankers should be aware of the importance of trust for small business owners and of the actions that lead to increased trustworthiness.

The study extends the existing knowledge on the business–bank relationship by focusing mainly on social (instead of economic) factors associated with the establishment of the business–bank relationship in times of crisis and high uncertainty.

A stroke is a serious, life-threatening condition that occurs when the blood supply to a part of the brain is cut off. The earlier a stroke is treated, the less damage is likely to occur. One of the methods that can lead to faster treatment is timely and accurate prediction and diagnosis. This paper aims to compare the binary integer programming-data envelopment analysis (BIP-DEA) model and the logistic regression (LR) model for diagnosing and predicting the occurrence of stroke in Iran.

In this study, two algorithms of the BIP-DEA and LR methods were introduced and key risk factors leading to stroke were extracted.

The study population consisted of 2,100 samples (patients) divided into six subsamples of different sizes. The classification table of each algorithm showed that the BIP-DEA model had more reliable results than the LR for the small data size. After running each algorithm, the BIP-DEA and LR algorithms identified eight and five factors as more effective risk factors and causes of stroke, respectively. Finally, predictive models using the important risk factors were proposed.

The main objective of this study is to provide the integrated BIP-DEA algorithm as a fast, easy and suitable tool for evaluation and prediction. In fact, the BIP-DEA algorithm can be used as an alternative tool to the LR model when the sample size is small. These algorithms can be used in various fields, including the health-care industry, to predict and prevent various diseases before the patient’s condition becomes more dangerous.

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

In a dual-robot system, the relative position error is a superposition of errors from each mono-robot, resulting in deteriorated coordination accuracy. This study aims to enhance relative accuracy of the dual-robot system through direct compensation of relative errors. To achieve this, a novel calibration-driven transfer learning method is proposed for relative error prediction in dual-robot systems.

A novel local product of exponential (POE) model with minimal parameters is proposed for error modeling. And a two-step method is presented to identify both geometric and nongeometric parameters for the mono-robots. Using the identified parameters, two calibrated models are established and combined as one dual-robot model, generating error data between the nominal and calibrated models’ outputs. Subsequently, the calibration-driven transfer, involving pretraining a neural network with sufficient generated error data and fine-tuning with a small measured data set, is introduced, enabling knowledge transfer and thereby obtaining a high-precision relative error predictor.

Experimental validation is conducted, and the results demonstrate that the proposed method has reduced the maximum and average relative errors by 45.1% and 30.6% compared with the calibrated model, yielding the values of 0.594 mm and 0.255 mm, respectively.

First, the proposed calibration-driven transfer method innovatively adopts the calibrated model as a data generator to address the issue of real data scarcity. It achieves high-accuracy relative error prediction with only a small measured data set, significantly enhancing error compensation efficiency. Second, the proposed local POE model achieves model minimality without the need for complex redundant parameter partitioning operations, ensuring stability and robustness in parameter identification.

The focus of this study is on how online-only retailers, known as pure-play e-retailers, leverage e-commerce platforms to identify and pursue market opportunities. Through the perspective of entrepreneurial marketing, this study aims to explore the influence of e-commerce technologies on the decision-making process of entrepreneurial marketing. This exploration is conducted via a case study of pure-play e-retailers based in China.

This study utilised a qualitative case study methodology to examine the complex processes of entrepreneurial marketing in an online environment. The study gathered detailed insights from both owner-managers and staff members of eight pure-play e-retail businesses. Additionally, the research involved a careful review of the firms' webpages and social media pages. This holistic approach facilitated a comprehensive understanding of their marketing strategies and practices.

The case study findings indicate that while many core aspects of entrepreneurial marketing remain important, there are distinct factors influencing the entrepreneurial marketing decision-making in the online marketplace. The online EM framework can be visualised as follows: (1) trend-orientated as well as innovative-orientated (2) data-orientated and entrepreneur-orientated (3) innovative-driven customer stimulation (4) orientated towards both platforms and proactiveness.

The paper provides an initial understanding of how digitalisation is enabling and transforming entrepreneurship in companies with high level digitalisation but low level digital development. Building on current entrepreneurial marketing literature, this paper develops an online entrepreneurial marketing framework to enhance understanding of the interaction between e-commerce technology and entrepreneurial marketing decision making.

At present, there is no reference to Attention Autism (AA) as a framework and therapeutic tool with autistic children in occupational therapy (OT) literature. By way of introducing AA as a potential intervention to the OT community, this study aims to investigate the extent to which participation in a two-day AA training could contribute to increasing confidence and inspire changes in practice for Irish occupational therapists (OTs) supporting autistic children.

A pilot study design with mixed qualitative and quantitative methods was used to evaluate the impact of a two-day AA training on six OTs. The OTs support autistic children throughout Ireland across public, private and voluntary sectors. They completed brief, non-standardised questionnaires 2 weeks before the training (Time 1) and again 12 weeks post (Time 2) training session. At Time 2, additional exploratory questions were answered by OTs regarding their use of AA in practice.

This explorative study’s quantitative findings presented percentage change increases within three areas of confidence for all OTs. These include establishing attention, motivating and developing functional skill goals with autistic children. One of the participants did not score any change in confidence in a fourth area, building rapport, however, the five other participants scored percentage change increases. Qualitative data provided by participants showed that they were implementing AA in practice since attending the training. Five of the participants reported positive experiences of using AA and one participant reported the programme was not suitable for her caseload because of their level of understanding and need.

This was a small, exploratory, practice-based study. As this is the first study exploring this area of practice for OTs, to the best of the authors’ knowledge, there were no standardised methods of assessment available, therefore a self-designed survey was used by the author which had a limited number of open-ended questions and four Likert scale questions. This study was also limited in that there was one main researcher who also delivered the two-day AA training. The sample data set was small which resulted in the limitation of the choice of methods used to analyse the quantitative data. Percentage changes were used as the only available and reliable method for a small data set.

Findings of this study, despite their preliminary nature, indicate that AA training may be a useful professional development consideration for OTs who provide a service for autistic children. Further AA research in OT is required including larger and more rigorous studies. An alternative training option of The Curiosity Programme may be considered for OTs supporting children who may not yet be ready to participate in AA.

For privacy protection, federated learning based on data separation allows machine learning models to be trained on remote devices or in isolated data devices. However, due to the limited resources such as bandwidth and power of local devices, communication in federated learning can be much slower than in local computing. This study aims to improve communication efficiency by reducing the number of communication rounds and the size of information transmitted in each round.

This paper allows each user node to perform multiple local trainings, then upload the local model parameters to a central server. The central server updates the global model parameters by weighted averaging the parameter information. Based on this aggregation, user nodes first cluster the parameter information to be uploaded and then replace each value with the mean value of its cluster. Considering the asymmetry of the federated learning framework, adaptively select the optimal number of clusters required to compress the model information.

While maintaining the loss convergence rate similar to that of federated averaging, the test accuracy did not decrease significantly.

By compressing uplink traffic, the work can improve communication efficiency on dynamic networks with limited resources.

Starting from intention–behaviour models and building upon the growing evidence that aggregated internet search query data represent a good proxy of human interests and intentions. The purpose of this study is to demonstrate that the internet search traffic information related to the selected key terms associated with establishing new businesses, reflects well the dynamics of entrepreneurial activity in a country and can be used for predicting entrepreneurial activity at the national level.

Theoretical framework is based on intention–behaviour models and supported by the knowledge spillover theory of entrepreneurship. Monthly data on new business registration from 2018 to 2021 is derived from the open database of the Russian Federal Tax Service. Terms of internet search interest are identified through interviews with the recent founders of new businesses, whereas the internet search query statistics on the identified terms are obtained from Google Trends and Yandex Wordstat.

The results suggest that aggregated data about web searches related to opening a new business in a country is positively correlated with the dynamics of entrepreneurial activity in the country and, as such, may be useful for predicting the level of that activity.

The results may serve as a starting point for a new approach to measure, monitor and predict entrepreneurial activities in a country and can help in better addressing policymaking issues related to entrepreneurship.

To the best of the authors’ knowledge, this study is original in its approach and results. Building on intention–behaviour models, this study outlines, to the best of the authors’ knowledge, the first usage of big data for analysing the intention–behaviour relationship in entrepreneurship. This study also contributes to the ongoing debate about the value of big data for entrepreneurship research by proposing and demonstrating the credibility of internet search query data as a novel source of quality data in analysing and predicting a country’s entrepreneurial activity.

Competition in the banking sector is more complex than in the past, and survival has become more difficult than before. The purpose of this paper is to propose a grey methodology for evaluating, clustering and ranking the performance of bank branches with imprecise and uncertain data in order to determine the relative status of each branch.

In this study, the two-stage data envelopment analysis model with grey data is applied to assess the efficiency of bank branches in terms of operations. The result of grey two-stage data envelopment analysis model is a grey number as efficiency value of each branch. In the following, the branches are classified into three grey categories of performance by grey clustering method, and the complete grey ranking of branches are performed using “minimax regret-based approach” and “whitening value rating”.

The results show that after grey clustering of 22 branches based on grey efficiency value obtained from the grey two-stage DEA model, 6 branches are assigned to “excellent” class, 4 branches to “good” class and 12 branches to “poor” class. Moreover, the results of MRA and whitening value rating models are integrated, and a complete ranking of 22 branches are presented.

Grey clustering of branches based on grey efficiency value can facilitate planning and policy-making for branches so that there is no need to plan separately for each branch. The grey ranking helps the branches find their current position compared to other branches, and the results can be a dashboard to find the best practices for benchmarking.

Compared with traditional DEA methods which use deterministic data and consider decision-making units as black boxes, in this research, a grey two-stage DEA model is proposed to evaluate the efficiency of bank branches. Furthermore, grey clustering and grey ranking of efficiency values are used as a novel solution for improving the accuracy of grey two-stage DEA results.

This study aims to explore how network visualization provides opportunities for learners to explore data literacy concepts using locally and personally relevant data.

The researchers designed six locally relevant network visualization activities to support students’ data reasoning practices toward understanding aggregate patterns in data. Cultural historical activity theory (Engeström, 1999) guides the analysis to identify how network visualization activities mediate students’ emerging understanding of aggregate data sets.

Pre/posttest findings indicate that this implementation positively impacted students’ understanding of network visualization concepts, as they were able to identify and interpret key relationships from novel networks. Interaction analysis (Jordan and Henderson, 1995) of video data revealed nuances of how activities mediated students’ improved ability to interpret network data. Some challenges noted in other studies, such as students’ tendency to focus on familiar concepts, are also noted as teachers supported conversations to help students move beyond them.

To the best of the authors’ knowledge, this is the first study the authors are aware of that supported elementary students in exploring data literacy through network visualization. The authors discuss how network visualizations and locally/personally meaningful data provide opportunities for learning data literacy concepts across the curriculum.