Breast cancer was a prevalent form of cancer worldwide. Thermography, a method for diagnosing breast cancer, involves recording the thermal patterns of the breast. This article explores the use of a convolutional neural network (CNN) algorithm to extract features from a dataset of thermographic images. Initially, the CNN network was used to extract a feature vector from the images. Subsequently, machine learning techniques can be used for image classification. This study utilizes four classification methods, namely Fully connected neural network (FCnet), support vector machine (SVM), classification linear model (CLINEAR), and KNN, to classify breast cancer from thermographic images. The accuracy rates achieved by the FCnet, SVM, CLINEAR, and k-nearest neighbors (KNN) algorithms were 94.2%, 95.0%, 95.0%, and 94.1%, respectively. Furthermore, the reliability parameters for these classifiers were computed as 92.1%, 97.5%, 96.5%, and 91.2%, while their respective sensitivities were calculated as 95.5%, 94.1%, 90.4%, and 93.2%. These findings can assist experts in developing an expert system for breast cancer diagnosis.

Purpose—In the business sector, reliable and timely data are crucial for business management to formulate a company’s strategy and enhance supply chain efficiency. The main goal of this study is to examine how strong brand strength affects shareholder value with a new Supplier Relationship Management System (SRMS) and to find the specific system qualities that are linked to SRMS adoption. This leads to higher brand strength and stronger shareholder value. Design/Methodology/Approach—This study employed a cross-sectional design with an explanatory survey as a deductive technique to form hypotheses. The primary method of data collection used a drop-off questionnaire that was self-administered to the UAE-based healthcare suppliers. Of the 787 questionnaires sent to the healthcare suppliers, 602 were usable, yielding a response rate of 76.5%. To analyze the data gathered, the study used Partial Least Squares Structural Equation modelling (PLS-SEM) and artificial neural network (ANN) techniques. Findings—The study’s data proved that SRMS adoption and brand strength positively affected and improved healthcare suppliers’ shareholder value. Additionally, it demonstrates that user satisfaction is the most significant predictor of SRMS adoption, while the results show that the mediating role of brand strength is the most significant predictor of shareholder value. The results demonstrated that internally derived constructs were better explained by the ANN technique than by the PLS-SEM approach. Originality/Value—This study demonstrates its practical value by offering decision-makers in the healthcare supplier industry a reference on what to avoid and what elements to take into account when creating plans and implementing strategies and policies.

To evaluate the efficiency of decision-making units, researchers continually develop models simulating the production process of organizations. This study formulates a network model integrating undesirable outputs to measure the efficiency of Vietnam’s banking industry. Employing methodologies from the data envelopment analysis (DEA) approach, the efficiency scores for these banks are subsequently computed and comparatively analyzed. The empirical results indicate that the incorporation of undesirable output variables in the efficiency evaluation model leads to significantly lower efficiency scores compared to the conventional DEA model. In practical terms, the study unveils a deterioration in the efficiency of banking operations in Vietnam during the post-Covid era, primarily attributed to deficiencies in credit risk management. These findings contribute to heightening awareness among bank managers regarding the pivotal importance of credit management activities.

This paper utilizes an advanced Network Data Envelopment Analysis (DEA) model to examine the impact of mobile payment on the efficiency of Taiwan banking industry. Inheriting the literature, we separate the banking operation process into two stages, namely profitability and marketability. Mobile payment is then considered as the core factor in the second stage. Our paper discovers network DEA model can effectively enhance the analysis of banking industry’s efficiency, and mobile payment has a notable impact on Taiwan banking industry. Regarding the profitability stage, there is only one efficient bank in 2019 and 2022, respectively. These banks also perform better in terms of “mobile payment production”. In the marketability stage, there is also only one bank in 2021 and one bank in 2022, that can reach to unique efficiency score. This indicates many banks attempt to increase earnings per share through investing in mobile payment services. However, the achievement still needs more wait. This leads to the fact that no bank can reach the ultimate overall efficiency. Within our sample, we also find that regarding promoting mobile payment services, Private Banks outperform Government Banks.

In view of the fact that the convolution neural network segmentation method lacks to capture the global dependency of infected areas in COVID-19 images, which is not conducive to the complete segmentation of scattered lesion areas, this paper proposes a COVID-19 lesion segmentation method UniUNet based on UniFormer with its strong ability to capture global dependency. Firstly, a U-shaped encoder-decoder structure based on UniFormer is designed, which can enhance the cooperation ability of local and global relations. Secondly, Swin spatial pyramid pooling module is introduced to compensate the influence of spatial resolution reduction in the encoder process and generate multi-scale representation. Multi-scale attention gate is introduced at the skip connection to suppress redundant features and enhance important features. Experiment results show that, compared with the other four methods, the proposed model achieves better results in Dice, loU and Recall on COVID-19-CT-Seg and CC-CCIII dataset, and achieves a more complete segmentation of the lesion area.