Based on the influence of block chain technology on information sharing among supply chain participants, mean-CVaR (conditional value at risk) is used to characterize retailers’ risk aversion behavior, while a Stackelberg game is taken to study the optimal decision-making of manufacturers and retailers during decentralized and centralized decision-making processes. Finally, the mean-CVaR-based revenue-sharing contract is used to coordinate the supply chain and profit distribution. The research shows that, under the condition of decentralized decision-making, when the retailer’s optimal order quantity is low, it is an increasing function of the weighted proportion and the risk aversion degree, while, when the retailer’s optimal order quantity is high, it is an increasing function of the weighted proportion, and has nothing to do with the risk aversion degree. The manufacturer’s blockchain technology application degree is a reduction function of the weighted proportion. When the retailer’s order quantity is low, the manufacturer’s blockchain technology application degree is a decreasing function of risk aversion, while, when the retailer’s order quantity is high, the manufacturer’s blockchain technology application is independent of risk aversion. The profit of the supply chain system under centralized decision-making is higher than that of decentralized decision-making. The revenue sharing contract can achieve the coordination of the supply chain to the level of centralized decision-making. Through blockchain technology, transaction costs among members of the supply chain can be reduced, information sharing can be realized, and the benefits of the supply chain can be improved. Finally, the specific numerical simulation is adopted to analyze the weighted proportion, risk aversion and the impact of blockchain technology on the supply chain, and verify the relevant conclusions.
As one of the most prevalent cancers among women worldwide, breast cancer has attracted the most attention by researchers. It has been verified that an accurate and early detection of breast cancer can increase the chances for the patients to take the right treatment plan and survive for a long time. Nowadays, numerous classification methods have been utilized for breast cancer diagnosis. However, most of these classification models have concentrated on maximum the classification accuracy, failed to take into account the unequal misclassification costs for the breast cancer diagnosis. To the best of our knowledge, misclassifying the cancerous patient as non-cancerous has much higher cost compared to misclassifying the non-cancerous as cancerous. Consequently, in order to tackle this deficiency and further improve the classification accuracy of the breast cancer diagnosis, we propose an improved cost-sensitive support vector machine classifier (ICS-SVM) for the diagnosis of breast cancer. In the proposed approach, we take full account of unequal misclassification costs of breast cancer intelligent diagnosis and provide more reasonable results over previous works and conventional classification models. To evaluate the performance of the proposed approach, Wisconsin Breast Cancer (WBC) and Wisconsin Diagnostic Breast Cancer (WDBC) breast cancer datasets obtained from the University of California at Irvine (UCI) machine learning repository have been studied. The experimental results demonstrate that the proposed hybrid algorithm outperforms all the existing methods. Promisingly, the proposed method can be regarded as a useful clinical tool for breast cancer diagnosis and could also be applied to other illness diagnosis.
With the help of machine learning (ML) techniques, the possible errors made by the pathologists and physicians, such as those caused by inexperience, fatigue, stress and so on can be avoided, and the medical data can be examined in a shorter time and in a more detailed manner. However, while the conventional ML techniques, such as classification, achieved excellent performance in classification accuracy when applied in medical diagnoses, they have a fatal shortcoming of poor performance since the imbalanced dataset, especially for the detection of the minority category. To tackle the shortcomings of conventional classification approaches, this study proposes a novel ensemble learning paradigm for medical diagnosis with imbalanced data, which consists of three phases: data pre-processing, training base classifier and final ensemble. In the first data pre-processing phase, we introduce the extension of Synthetic Minority Oversampling Technique (SMOTE) by integrating it with cross-validated committees filter (CVCF) technique, which can not only synthesize the minority sample and thereby balance the input instances, but also filter the noisy examples so as to perform well in the process of classification. In the classification phase, we introduce ensemble support vector machine (ESVM) classification technique, which were constructed by multiple diversity structures of SVM classifiers and thus has the advantages of strong generalization performance and classification precision. Additionally, in the last phase of the final ensemble strategy, we introduce the weighted majority voting strategy and introduce simulated annealing genetic algorithm (SAGA) to optimize the weight vector and thereby enhance the overall classification performance. The efficiency of our proposed ensemble learning method was tested on nine imbalanced medical datasets and the experimental results clearly indicate that the proposed ensemble learning paradigm outperforms other state-of-the-art classification models. Promisingly, our proposed ensemble learning paradigm can effectively facilitate medical decision making for physicians.INDEX TERMS support vector machine; imbalanced data; ensemble learning; medical diagnosis.
Purpose – The problem of manufacturer-customer relationships is becoming the key factor of enterprise development, and the contradiction between manufacturer’s objective and customer’s satisfaction still exists. Customers claim for product safety from manufacturers, so manufacturers should take corporate social responsibility (CSR) into their company philosophy or even enhance the degree of CSR during their production. The purpose of this paper is to investigate the influences of parameters on the stability of risk-averse complementary product manufacturers. Design/methodology/approach – In this study, three dynamic game models are developed: manufacturer 1 – leader Stackelberg game model, manufacturer 2 – leader Stackelberg game model and Nash game model. Using bifurcation diagrams, the largest Lyapunov exponent, 0-1 test for chaos and parameter basin plots, the influences of parameters on the complex behaviors of the three models are analyzed. Findings – The authors demonstrate that the system exists in deterministic chaos when the parameter exceeds a certain value. The lead manufacturer will not be a beneficiary in chaotic state, and when two manufacturers have the same status the stability of the system weakens, which renders it easily chaotic. Research limitations/implications – In this paper, the authors make some assumptions, which when applied broadly could lead to some findings. Practical implications – The authors find that the lead manufacturer will derive the greatest profit and will exert the least effort compared with the follower manufacturer, but that both manufacturers will exert greater effort in the Nash game. The two manufacturers should be cautious while selecting the parameter ' s value so that the stability of the system is maintained. Social implications – The research will serve as a guide for the two complementary manufacturers in their decision-making process. Originality/value – The originality and value of the research rest on the use of dynamic thinking in ensuring stability in the quality of complementary products considering the firms’ market powers. The research will serve as a guide for the two complementary manufacturers in their decision-making process.
Purpose -The purpose of this research is to provide a comparison of customer satisfaction of two largest US parcel delivery companies, the UPS and FedEx. Design/methodology/approach -The paper is contrast the overall customer satisfaction and five critical factors (availability, responsiveness, reliability, completeness, and professionalism of service) that directly affect customer satisfaction for these two parcel delivery companies. Written questionnaire responses from university departments/units in the USA were collected and used for the comparison analysis. An independent samples t-test was used to compare the ratings of customer satisfaction of these two parcel companies. Findings -The paper find's no significant differences in the ratings of service quality of that these two parcel delivery companies provide with respect to both incoming and outgoing mail. The results of this research suggest that the similarity in ratings of service quality of these two companies explain their equally dominant positions in the parcel service industry.Research limitations/implications -The survey subjects only include units/departments within universities, with most of the participants located in Nebraska. By expanding the total number of surveys to include more industries and locations, this research could provide additional insight into the parcel service industry and customer satisfaction. Additionally, price of parcel delivery service was not included as a factor impacting customer satisfaction. Price of service may play an important role in customers' selection of parcel carrier. Originality/value -Findings of this research provide customers insights into the service quality of parcel delivery companies in order for them to make a choice of which carriers to use.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.