ABSTRACT
Landslide susceptibility assessment (LSA) is fundamental for managing landslide geological disasters. This study presents a deep learning approach (DNN-MSFM) designed to enhance LSA modeling, particularly addressing limitations caused by the unbalanced distribution of data samples in applied datasets. DNN-MSFM approach combines a deep neural network (DNN) and a mean squared false misclassification loss function (MSFM) to handle unbalanced samples from the algorithmic perspective. The model's performance was evaluated on an unbalanced dataset containing mapping units' records of 293 landslide samples and 653 non-landslide samples from the Baota District, China. Its effectiveness was assessed through statistical metrics and compared against DNN and Support Vector Machine (SVM) basic models. The results demonstrated a significant performance enhancement from the DNN-MSFM (OverallAccuracy = 0.889 and area under the receiver operating characteristic curve (AUC) = 0.84), indicating its effectiveness in learning the underlying landslide susceptibility features and demonstrating its ability to provide improved predictions even in areas with unbalanced landslide samples. Moreover, the study emphasizes the importance of considering balanced loss functions in training DNN under various imbalance degrees and contributes to expanding the applicability of DNN in LSA modeling. Also, this study builds a foundation for further enhancements of deep learning methods for geological disaster assessments.
ABSTRACT
Introduction: Social media systems are instrumental in the dissemination of timely COVID-19 pandemic information to the general population and contribute to the fight against the pandemic and waves of disinformation during the COVID-19 pandemic. This study uses the information adoption model (IAM) as the theoretical framework to examine the moderating influence of perceived government information transparency on the adoption of COVID-19 pandemic information on social media systems from the Ghanaian perspective. Government information transparency regarding the pandemic is crucial since any lack of transparency can negatively affect the global response to the pandemic by destroying trust (in government and public health authorities/institutions), intensifying fears, and causing destructive behaviors. Methods: It applies a convenient sampling technique to collect the responses from 516 participants by using self-administrated questionnaires. The data analysis was computed and analyzed with SPSS-22. The following statistical tests were conducted to test the hypotheses: descriptive statistics, scale reliability test, Pearson bivariate correlation, multiple linear regressions, hierarchical regression, and slope analysis. Results: The results indicate that information quality, information credibility, and information usefulness are significant drivers of COVID-19 pandemic information adoption on social media systems. Furthermore, the perceived government information transparency positively moderates the influence of information quality, information credibility, and information usefulness on the adoption of COVID-19 pandemic information on social media systems. Conclusion: The theoretical and managerial implications of these findings suggest the utilization of social media systems as an effective tool to support the continued fight against the current COVID-19 pandemic and its future role in national and global public health emergencies.
ABSTRACT
This study explored the moderating impact of mobile self-efficacy on the adoption of mobile health services. The UTAUT was used as the theoretical foundation for this study. The results have indicated that mobile self-efficacy was significant in moderating the impact of both performance expectancy (ß = -0.005, p < 0.05) and effort expectancy (ß = -010, p < 0.05) on the adoption of mobile health services. In addition, it was revealed to our surprise that both performance (ß = 0.521, t = 9.311, p > 0.05) and effort expectancy (ß = 0.406, t = 7.577, p > 0.05) do not determine the behavioral intention to use mobile health services. Effort expectancy and behavioral intention to use were also, respectively, not significant in influencing performance expectancy (ß = 0.702, t = 12.601, p > 0.05) and intention to recommend the adoption of mobile health services (ß = 0.866, t = 13.814, p > 0.05). Mobile self-efficacy, however, was found to significantly predict the citizen's intention to recommend the adoption of mobile health services (ß = 0.139, t = 2.548, p < 0.05). The implications of these findings on mobile health are discussed.
Subject(s)
Intention , Telemedicine , Health Services , Patient Acceptance of Health Care , Self Efficacy , Telemedicine/methodsABSTRACT
This study examined the factors driving the public value of e-government from the viewpoint of the Chinese people. The usage of ICT through e-government systems must generate the adequate corresponding public value that can motivate the acceptance of e-government services. The sample 517 data generated from Chinese citizens were analyzed using AMOS 23 software by undertaking the structural equation model system of analysis. The results show that constructs such as information quality, service parameters, user orientation, efficiency, openness, and responsiveness were significantly related to the public value of e-government. Additionally, the research validated that the public value of e-government has a direct influence on the behavioral intention to adopt e-government services. The managerial and practical implications of these research findings on the public value of e-government and the acceptance of e-government services are dissected meticulously.