Objectives: This study used the Technology-Organization-Environment (TOE) framework to identify the factors involved in the decisions made by integrated medical and healthcare organizations to adopt artificial intelligence (AI) elderly care service resources.Method: This study identified the Decision-making Trial and Evaluation Laboratory-Interpretive Structural Modeling (DEMATEL-ISM) method was used to construct a multilayer recursive structural model and to analyze the interrelationships between the levels. A MICMAC quadrant diagram was used for a cluster analysis.Results: The ISM recursive structural model was divided into a total of seven layers. The bottom layer contained the four factors of High risk of data leakage (T1), Lack of awareness of the value and benefits of AI healthcare technology (T5), Lack of management leadership support (O1), and Government policies (E1). Having a low dependency but high driving force, these factors are the root causes of adoption by healthcare organizations. The topmost layer contained the most direct factors, which had a high dependency but the low driving force, influencing adoption: Competitive pressures (E2), Lack of patient trust (E5), and Lack of excellent partnerships (E7). Healthcare organizations are more concerned with technology and their environments when deciding to adopt intelligent healthcare resources.Conclusion: The combination of the three methods of DEMATEL-ISM-MICMAC construction models provides new ideas for smart healthcare services for hospitals. The DEMATEL method favors the construction dimension of the micro-model, while the ISM method favors the construction dimension of the macro-model. Combining these two methods may reduce the loss of information within the system, simplify the matrix calculation workload, and improve the efficiency of operations while decomposing the complex problems into several sub-problems in a more comprehensive and detailed way. Conducting cluster analysis of the adoption determinants utilizing MICMAC quadrant diagrams may provide strong methodological guidance and decision-making recommendations for government departments, senior decision-makers in healthcare organizations, and policy-makers in associations in the senior care industry.

Rail surface defect detection for traffic safety has received considerable attention. With the development of deep learning, numerous methods for combining RGB and depth information have been proposed. However, these methods directly fuse raw features extracted from the backbone, which can lead to ineffective use of the complementary information of the two modalities. In this study, we developed a contour and semantic feature alignment fusion network (CSANet) with bidirectional feature alignment to explore the internal consistency of cross-modal features from both contour and semantic perspectives. First, an adjacency contour feature extraction module was designed to capture high-quality contour information from adjacent low-level features. Second, an attention-aware graph convolution embedded semantic feature extraction module was designed to explore long-range dependencies and extract semantic information. Third, a bidirectional alignment mechanism was designed to explore the internal consistency of contours and semantics between bimodal features. Experimental results on the industrial RGB-D dataset (NEU RSDDS-AUG) revealed that the proposed CSANet outperformed 12 state-of-the-art algorithms in four evaluation metrics.

The purpose of this research is to determine whether users’ social interaction tie and trust have a mediating effect on the willingness to use the online healthcare community (OHC) platform on an ongoing basis to respond to food safety crises and monitor food safety practices. During the three-month survey, we conducted an online investigation of users who had experience sharing on the OHC platform and were concerned about food safety. Thereby, three hundred and fifty-two valid questionnaires were received and partial least squares was adopted in this study to test the proposed hypotheses. The empirical results show that perceived critical mass, image, and para-social interaction strengthen the social interaction tie between users and the food safety platform. In addition, this study found that social interaction tie and trust of OHC platform users increased users’ willingness to continue using the OHC platform. This research provides OHC platform managers with an in-depth understanding of online social interactions on food safety pages. Moreover, the results of this study can help food business owners, government regulators, hospitals, and physicians to improve the way they use the Web for opinion-led food safety crises and provide insight into the intent of promoting the ongoing use of OHC platforms.

The purpose of this research is to evaluate the continuance usage intention on online healthcare community (OHC) platform for patients and examine the "doctor-OHC-patient" relationship. The proposed model attempted to integrate social interaction ties, shared value, trust with the indirect effects on the relationship between the determinants and continuous usage intention of the OHC platform. The empirical results showed that perceived critical mass, social identity, and para-social interaction would strengthen continuance intention via the social interaction ties. In addition, this study found that the shared values and trust increase users' willingness to continue usage of OHC. This study provides OHC platform managers with an in-depth understanding of the "doctor-OHC-patient" online social interaction. The results of this study may also help hospitals, health policy makers, and related healthcare practitioners to improve the way they use the web for advocacy and guidance, and provide insight into the intent of promoting the ongoing use of OHC platforms.

Hesitant fuzzy set theory provides an effective technique for researchers and engineers to cope with vagueness and uncertainty. In recent years, to explore the correlation between hesitant fuzzy sets, traditional correlation measure in statistics has been constantly studied in hesitant fuzzy environments. In this study, extant studies of correlation measures in hesitant fuzzy contexts are recalled and analyzed. In view of the forgoing analysis, we find out that the extant correlation coefficients have some limitations. Moreover, a few correlation coefficients are not in line with the traditional definition of correlation coefficients. In order to address the flaws of the existing proposals, a novel hesitant fuzzy correlation coefficient is proposed in this study. The new proposal of this study can not only overcome the flaws of the old hesitant fuzzy correlation coefficients, but it also shows several desirable characteristics. The weighted form of the newly defined correlation coefficient and its features are also investigated. Finally, three numerical examples concerning supplier selection and medical diagnosis are examined using the developed correlation coefficients to demonstrate their applicability. Comparison analyses with existing proposals highlight the efficiency of our proposals.