Search results

The amount of features in handwritten digit data is often very large due to the different aspects in personal handwriting, leading to high-dimensional data. Therefore, the employment of a feature selection algorithm becomes crucial for successful classification modeling, because the inclusion of irrelevant or redundant features can mislead the modeling algorithms, resulting in overfitting and decrease in efficiency.

The minimum redundancy and maximum relevance (mRMR) and the recursive feature elimination (RFE) are two frequently used feature selection algorithms. While mRMR is capable of identifying a subset of features that are highly relevant to the targeted classification variable, mRMR still carries the weakness of capturing redundant features along with the algorithm. On the other hand, RFE is flawed by the fact that those features selected by RFE are not ranked by importance, albeit RFE can effectively eliminate the less important features and exclude redundant features.

The hybrid method was exemplified in a binary classification between digits “4” and “9” and between digits “6” and “8” from a multiple features dataset. The result showed that the hybrid mRMR +  support vector machine recursive feature elimination (SVMRFE) is better than both the sole support vector machine (SVM) and mRMR.

In view of the respective strength and deficiency mRMR and RFE, this study combined both these methods and used an SVM as the underlying classifier anticipating the mRMR to make an excellent complement to the SVMRFE.

In time and accurate detection of cancer can save the life of the person affected. According to the World Health Organization (WHO), breast cancer occupies the most frequent incidence among all the cancers whereas breast cancer takes fifth place in the case of mortality numbers. Out of many image processing techniques, certain works have focused on convolutional neural networks (CNNs) for processing these images. However, deep learning models are to be explored well.

In this work, multivariate statistics-based kernel principal component analysis (KPCA) is used for essential features. KPCA is simultaneously helpful for denoising the data. These features are processed through a heterogeneous ensemble model that consists of three base models. The base models comprise recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The outcomes of these base learners are fed to fuzzy adaptive resonance theory mapping (ARTMAP) model for decision making as the nodes are added to the F_2ˆa layer if the winning criteria are fulfilled that makes the ARTMAP model more robust.

The proposed model is verified using breast histopathology image dataset publicly available at Kaggle. The model provides 99.36% training accuracy and 98.72% validation accuracy. The proposed model utilizes data processing in all aspects, i.e. image denoising to reduce the data redundancy, training by ensemble learning to provide higher results than that of single models. The final classification by a fuzzy ARTMAP model that controls the number of nodes depending upon the performance makes robust accurate classification.

Research in the field of medical applications is an ongoing method. More advanced algorithms are being developed for better classification. Still, the scope is there to design the models in terms of better performance, practicability and cost efficiency in the future. Also, the ensemble models may be chosen with different combinations and characteristics. Only signal instead of images may be verified for this proposed model. Experimental analysis shows the improved performance of the proposed model. This method needs to be verified using practical models. Also, the practical implementation will be carried out for its real-time performance and cost efficiency.

The proposed model is utilized for denoising and to reduce the data redundancy so that the feature selection is done using KPCA. Training and classification are performed using heterogeneous ensemble model designed using RNN, LSTM and GRU as base classifiers to provide higher results than that of single models. Use of adaptive fuzzy mapping model makes the final classification accurate. The effectiveness of combining these methods to a single model is analyzed in this work.

Fault-related monitoring variables selection is a process of obtaining a subset of variables from the original set, which is of great significance for reducing information redundancy and improving the performance of the fault diagnosis models. This paper aims to propose a novel variables selection approach based on complex networks.

Firstly, a dual-layer correlation networks (DlCN) which consists of mechanism-oriented correlation sub-network (MoCSN) and data-oriented correlation sub-network (DoCSN) is constructed. Secondly, an algorithm for identifying critical fault-related monitoring variables based on dual correlations is introduced. In the algorithm, the topological attributes of the MoCSN and correlation threshold of the DoCSN are used successively.

In the experiments of vertical elevator fault diagnosis, the critical fault-related monitoring variables selected by the DlCN-based approach is more effective than the traditional approaches. It indicates that fusion mechanism-oriented correlation can enhance the comprehensiveness of variable correlation analysis. Moreover, the approach has been proved to be adaptable to different fault diagnosis models.

In the DlCN-based variables selection approach, the mechanism-oriented correlation and data-oriented correlation are comprehensively considered. It improves the precision of variables selection. Meanwhile, it is an unsupervised and model-agnostic approach which addresses the shortcomings of some conventional approaches that require data labels and have insufficient adaptability for fault diagnosis models.

Engineering knowledge continuity is crucial for the life cycle management of long-lived and complex assets, such as nuclear plants, locks and storm surge barriers. At the storm surge barriers in the Netherlands, engineering knowledge continuity is not yet fully assured, despite long-standing efforts. This study aims to explore the relationship between system characteristics, the organizational demarcation of maintenance and operation and the challenges in achieving engineering knowledge continuity and provides suggestions for improvement of theory and policy.

Ten semi-structured interviews were conducted with professionals from various backgrounds in construction, engineering and asset management of the Dutch storm surge barriers, augmented with visits to barriers and barrier teams. A thematic analysis was used to identify and describe the challenges to engineering continuity, their origins and potential solutions. We reviewed knowledge management policy documents and asset management consultancy reports to validate the findings. Additionally, we engaged in frequent interactions with professionals at the barriers. We achieved saturation and validation once no new issues were raised during these discussions.

The thematic analysis developed multiple themes describing the challenges to engineering continuity, their origins and potential solutions. The key findings are that expert engineers are critically important to deal with redesigns induced by obsolescence. Moreover, due to barrier uniqueness, long redesign cycles and reliability requirements, conventional knowledge continuity tools are insufficient to enable new engineers to reach expert level. Finally, the thematic analysis shows that, in some cases, outsourcing should be reduced to facilitate internal learning.

The study introduces the application of the knowledge-based view of the firm and the concept of requisite knowledge redundancy to the long-term management of complex assets. It calls for more attention to long gaps in the use of unique knowledge and the effect on knowledge continuity.

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 US platelet supply is almost exclusively dependent on apheresis donors who are “aging out.” As a result, blood centers and hospitals have been experiencing spot shortages and have resorted to transfusing low-dose platelets. This paper explores using whole blood–derived platelets (WB-PLTs) to supplement the apheresis platelet (APH-PLT) supply.

This paper reviews the history leading to the current state of the US platelet supply and includes the impact of recent events such as the COVID-19 pandemic and the implementation of the US Food and Drug Administration (FDA)-mandated bacterial mitigation strategies.

WB-PLTs represent a viable source of platelets that can be used to supplement the APH-PLT supply. Whole blood automation represents a new methodology to more easily prepare WB-PLTs. Advances in donor testing and screening as well as pre-storage leukoreduction have improved the safety of WB-PLTs to the same level as APH-PLTs. Blood services in the US and abroad transfuse WB-PLTs interchangeably in all patient populations.

This paper highlights how the US blood industry is essentially “sole-sourced” in terms of APH-PLTs. In this post-COVID-19 period, when most industries are building redundancies in their supply chains, blood centers should consider WB-PLTs as an additional source of platelets to bolster the US platelet supply.

This study aims to examine the influence of Audit Committee (AC) composition on Firm Performance (FP) by measuring AC composition (ACC) with a composite score based on the varying effect of each composition-characteristic.

Partial Least Squares- Structural Equation Modeling (PLS-SEM) technique is used to weigh ACC characteristics. Based on 133 companies and covering five years from 2016 to 2020, the study analyses data after controlling endogeneity through the Gaussian Copula approach.

We find a significant positive influence of ACC on Firm Performance. Among the ACC characteristics, the absence of executive directors has the highest positive weight on ACC to influence FP, followed by AC size and Gender diversity. AC independence and members' accounting and financial expertise have no significant weight on its composition.

Apart from the theoretical contribution, the study reveals that each ACC characteristic has a varying effect on AC effectiveness to influence the FP that needs to be considered by regulators while framing regulations on ACC and by BOD while constituting AC for a company.

The study claims originality by being pioneering to reveal that AC composition, with a synergy of its disparate characteristics, positively impacts FP. It highlights that the absence of executive directors and gender diversity in AC (characteristics overlooked by the extant literature) significantly and positively influence FP. Methodologically, it introduces the use of the PLS-SEM algorithm to weigh the characteristics in governance studies. Further, these findings remain relevant amid recent Indian legal reforms, offering contemporary insights for policy consideration.

This paper expands on existing analyses of corporate energy and sustainability communication and shows the potential of evolutionary theory to study and conceptualize sustainable corporate communication as niche construction and its transformative and transformational potential.

With a qualitative content analysis of non-financial reporting of energy corporations and a deep dive into one selected case (Yin, 2013) with a two-step categorization of the sustainability related text and (n = 5) expert interviews (QCAmap, Mayring, 2019; Fenzl and Mayring, 2017), the paper reflects on alterations within the organization and in the organization–stakeholder relationships through corporate sustainability communication.

The analytical deep dive into one case of corporate sustainability communication of a multinational energy corporation shows the difference between a transformative and transformational character of corporate communication. The insights from the interviews support the assumption that corporates not only adapt to changes of environmental factors (perturbative communication) but also – however rarely – alter their spatiotemporal relationships with their external environment (relocational communication), so there is a lack of actual transformational communication.

Corporates in the (renewable) energy sector as well as industry networks like gas (infrastructure) suppliers have the potential to impact their environment (stakeholder, energy communities, etc.), change cultural patterns and norms and co-construct new socio-ecological niches through communication. The study presented gives evidence and examples for transformative corporate sustainability communication. On a conceptual level, it offers an innovative framework to understand sustainability as a guiding principle for corporate communication that will stimulate corporate communication research in the future.

This paper is dedicated to elaborating, proposing and validating an action plan to enhance the mitigation of risks generated by the COVID-19 pandemic in the electric sector supply chain, aiming to promote a more resilient supply chain.

For this, a systematic review of the literature was carried out to prepare an action plan that was validated by a group of experts, through the Delphi methodology.

As a result, an action plan was obtained, with 18 actions subdivided into 13 resilience elements and related to 20 main risks arising from the pandemic. The actions oriented to the development of relationships among supply chain members, promotion of a culture oriented to learning and problem solving, contingency plan, safety stock and risk management were pointed as those capable of generating resilience in the chain analyzed in the moment of crisis.

The results achieved can contribute to the expansion of debates in the area of resilient supply chain management, as well as contribute to supply chain managers in their elaboration and definition of actions that aim to make the supply chain more resilient. It is noteworthy that no similar study was found in the literature considering the specificities of supply chain management in the Brazilian Amazon region.

Global climate change characterized by an increase in temperature has become the focus of attention all over the world. China is a sensitive and significant area of global climate change. This paper specifically aims to examine the association between agricultural productivity and the climate change by using China’s provincial agricultural input–output data from 2000 to 2019 and the climatic data of the ground meteorological stations.

The authors used the three-stage spatial Durbin model (SDM) model and entropy method for analysis of collected data; further, the authors also empirically tested the climate change marginal effect on agricultural productivity by using ordinary least square and SDM approaches.

The results revealed that climate change has a significant negative effect on agricultural productivity, which showed significance in robustness tests, including index replacement, quantile regression and tail reduction. The results of this study also indicated that by subdividing the climatic factors, annual precipitation had no significant impact on the growth of agricultural productivity; further, other climatic variables, including wind speed and temperature, had a substantial adverse effect on agricultural productivity. The heterogeneity test showed that climatic changes ominously hinder agricultural productivity growth only in the western region of China, and in the eastern and central regions, climate change had no effect.

The findings of this study highlight the importance of various social connections of farm households in designing policies to improve their responses to climate change and expand land productivity in different regions. The study also provides a hypothetical approach to prioritize developing regions that need proper attention to improve crop productivity.

The paper explores the impact of climate change on agricultural productivity by using the climatic data of China. Empirical evidence previously missing in the body of knowledge will support governments and researchers to establish a mechanism to improve climate change mitigation tools in China.