Heterogeneous information networks, which consist of multi-typed vertices representing objects and multi-typed edges representing relations between objects, are ubiquitous in the real world. In this paper, we study the problem of entity matching for heterogeneous information networks based on distributed network embedding and multi-layer perceptron with a highway network, and we propose a new method named DEM short for Deep Entity Matching. In contrast to the traditional entity matching methods, DEM utilizes the multi-layer perceptron with a highway network to explore the hidden relations to improve the performance of matching. Importantly, we incorporate DEM with the network embedding methodology, enabling highly efficient computing in a vectorized manner. DEM’s generic modeling of both the network structure and the entity attributes enables it to model various heterogeneous information networks flexibly. To illustrate its functionality, we apply the DEM algorithm to two real-world entity matching applications: user linkage under the social network analysis scenario that predicts the same or matched users in different social platforms and record linkage that predicts the same or matched records in different citation networks. Extensive experiments on real-world datasets demonstrate DEM’s effectiveness and rationality.
This study aims to test two hypotheses: teaching building information modeling (BIM) in relation to construction science provides students with a remarkable understanding of the nature of construction science (Hypothesis 1), and if the student has positive attitude toward the use of the BIM program, then efficiency by which construction science is taught by its means is improved (Hypothesis 2). Results and process of a case study with a novel teaching methodology were discussed in terms of the benefits of the students. A questionnaire study was conducted on the student group with which the case study was performed to test each student's attitude. Results were evaluated statistically. When BIM is integrated with the teaching of basic construction courses within architecture degree programs, the students understood the building system principles simply and effectively. As a result of the statistical analysis, the students find the applied method effective. Moreover, their attitude toward BIM affects the process. 相似文献
ABSTRACTThis study measured the knowledge transfer and appeal of information and communication technologies (ICTs) used to deliver education for sustainable development (ESD) content to farmers in Niger experiencing major crop losses from the insect pest Maruca vitrata. ICT-ESD content consisted of two dialectically localized and animated videos that address food security problems of cowpea insect herbivory and the shortage of integrated pest management strategies in rural Niger. Comparing pre-test/post-test knowledge transfer for both animated videos when either (1) watched alone (AVO), or (2) in conjunction with a facilitated group discussion prior to post-testing (AVD), results from 90 farmers in 3 rural Nigerien villages showed statistically significant knowledge transfer in both AVO and AVD groups and still greater gains in the AVD group. Importantly, while a majority of participants expressed a preference for learning from such animated videos and a willingness to share their new knowledge and the videos with others, this finding did not statistically significantly associate with education level, supporting the idea that AVO/AVD is an inclusive strategy for low-literate learners within developing-nation contexts. Recommendations and theoretical implications for ICT-ESD implementations in resource-limited areas are also discussed. 相似文献
Regulations, such as the Health Insurance Portability and Accountability Act (HIPAA), establish standards to protect patients' medical records from security breaches. Insiders' prosocial misbehaviour within healthcare organisations can cause significant damage to relevant stakeholders. Such behaviour without malicious intention needs to be better understood and carefully managed from the perspective of prosocial behaviour. For this study, a research model was developed that includes the factors influencing student nurses' intention to disclose patient health information. The model was empirically tested with nursing students in South Korea with a scenario-based experiment. We find that both altruistic (impact on others) and egoistic (impact on the self) motivations are significantly important in raising situational empathy. On the other hand, an egoistic motivation (impact on the self) significantly affects people's perception of their responsibility, which mediates the relationship between situational empathy and prosocial intention to disclose. The implications of our findings are discussed. 相似文献