Search results

A community demonstrates the unique qualities and relationships between its members that distinguish it from other communities within a network. Network analysis relies heavily on community detection. Despite the traditional spectral clustering and statistical inference methods, deep learning techniques for community detection have grown in popularity due to their ease of processing high-dimensional network data. Graph convolutional neural networks (GCNNs) have received much attention recently and have developed into a potential and ubiquitous method for directly detecting communities on graphs. Inspired by the promising results of graph convolutional networks (GCNs) in analyzing graph structure data, a novel community graph convolutional network (CommunityGCN) as a semi-supervised node classification model has been proposed and compared with recent baseline methods graph attention network (GAT), GCN-based technique for unsupervised community detection and Markov random fields combined with graph convolutional network (MRFasGCN).

This work presents the method for identifying communities that combines the notion of node classification via message passing with the architecture of a semi-supervised graph neural network. Six benchmark datasets, namely, Cora, CiteSeer, ACM, Karate, IMDB and Facebook, have been used in the experimentation.

In the first set of experiments, the scaled normalized average matrix of all neighbor's features including the node itself was obtained, followed by obtaining the weighted average matrix of low-dimensional nodes. In the second set of experiments, the average weighted matrix was forwarded to the GCN with two layers and the activation function for predicting the node class was applied. The results demonstrate that node classification with GCN can improve the performance of identifying communities on graph datasets.

The experiment reveals that the CommunityGCN approach has given better results with accuracy, normalized mutual information, F1 and modularity scores of 91.26, 79.9, 92.58 and 70.5 per cent, respectively, for detecting communities in the graph network, which is much greater than the range of 55.7–87.07 per cent reported in previous literature. Thus, it has been concluded that the GCN with node classification models has improved the accuracy.

This article proposes a novel hybrid simulation model for understanding the complex tobacco use behavior.

The model is developed by embedding the concept of the multistage learning-based fuzzy cognitive map (FCM) into the agent-based model (ABM) in order to benefit from advantageous of each methodology. The ABM is used to represent individual level behaviors while the FCM is used as a decision support mechanism for individuals. In this study, socio-demographic characteristics of individuals, tobacco control policies, and social network effect are taken into account to reflect the current tobacco use system of Turkey. The effects of plain package and COVID-19 on tobacco use behaviors of individuals are also searched under different scenarios.

The findings indicate that the proposed model provides promising results for representing the mental models of agents. Besides, the scenario analyses help to observe the possible reactions of people to new conditions according to characteristics.

The proposed method combined ABM and FCM with a multi-stage learning phases for modeling a complex and dynamic social problem as close as real life. It is expected to contribute for both ABM and tobacco use literature.

By anchoring on the ability-motivation-opportunity (AMO) framework, this research aims to examine the effect of tourists' green ability, motivation and opportunity to access green information on digital media platforms (green AMO) on their intention to stay at green hotels. The study also tests the moderating role of environmental concern and the mediating role of green attitude in this relationship.

An online survey was conducted on large Facebook groups and by an international tour operator in March 2022. Through convenience sampling, 600 responses were collected from local and international tourists. Partial least squares structural equation modeling was performed to validate the research model.

The results reveal that tourists' intention to stay at green hotels is positively affected by their green AMO through indirect and direct channels. Specifically, green AMO indirectly effects tourists' intention to stay at green hotels by raising their green attitude. The results also indicate that the direct effect is moderated by environmental concern.

The findings demonstrate the importance of facilitating tourists' access to environmental information on social media platforms, which enhances green attitude and intention to stay at green hotels. This study also proposes practical solutions that managers of green hotels can employ to target green-oriented customers and conduct environmental campaigns on digital platforms.

The research is the first to investigate the effects of tourists' green AMO on their intention to stay at green hotels. It is also the first to explore the roles of environmental concern and green attitude in this relationship.

Data from different countries suggest a higher prevalence of anxiety, depression and suicides among manual and trade workers in the construction industry than in the general population. The present review examines the causes and effects of poor mental health and the effectiveness of interventions to improve manual and trade workers' mental health in the construction industry. It also identifies gaps in research and makes several suggestions for practice and future research.

A systematic literature review was conducted to examine and consolidate evidence reported in 54 relevant journal articles published between 2010 and 2021 on the mental health of manual and trade workers.

Three major themes emerged in the review of the 54 journal articles: causes of poor mental health, effects of poor mental health and interventions to improve mental health. The leading causes of poor mental health among construction manual and trade workers are poor work-life balance, high job demand, poor cultural norms and mental health stigma, chronic bodily pain, lack of social support, workplace injustice and job insecurity. The prominent effects of poor mental health are suicidality, drug and alcohol addiction, poor workplace safety and poor work performance. Moreover, the study found that some of the strategies recently implemented in the construction industry to improve mental health are deemed ineffective, or their effectiveness remains inconclusive.

The review's scope is limited to research on manual and trade workers, and it did not investigate the mental health of construction professionals and construction management students.

The review provides valuable insights into the causes and effects of poor mental health among manual and trade workers and the effectiveness of mental health interventions in the construction industry.

The purpose of this qualitative, single-case study was to explore the development of Jamaica’s maritime education and training (MET) curriculum within the local education context. In this research, the story of the development and sustainability of the local MET curriculum in its 40-year journey from 1980 to present (post 2020), as communicated by various maritime stakeholders and archival documents, is chronicled.

The study utilized a qualitative orientation and was an embedded single-case study in its design. The entire local MET institution community and those legislatively and operationally allied to its sustained viability constituted the general population of this study. Non-probability sampling techniques were used to arrive at a maximum variation sample. Three sources of data were used in this study: individual interviews, focus group discussions and documents.

The Jamaican (local) MET curriculum was the brainchild of local perspicacity that was empowered by international benevolence. It was developed to satisfy market demands that existed at the time of its inception. These market requirements of the maritime industry are what impacted the development of the local MET curriculum over four decades. Several other factors led to the sustained viability of the local MET curriculum. These included the ability of the local MET curriculum to meet direct market needs and maintain its fitness for purpose.

It is the view of the researcher that the findings of this study were limited by the fact that the voices of current students and employers from the four decades of the curriculum's existence are not represented in this initial study. The perspectives from these two sources would have broadened the description presented in this study.

This research has shown that specialized higher education (HE) institutions are better served in their business when they maintain a symbiotic relationship with the industry for which they are producing graduates.

The treatment of HE as a service industry has gained traction globally. This would suggest that ‘product placement' in specialized HE is important to the growth, development and longevity of that course of study within the society in which it exists.

There is a dearth of national research on Jamaica's four-decades-old MET curriculum and the elements that lend to the sustained viability of same. This discussion of sustainability of the MET curriculum will benefit maritime educators and policymakers, who must continue to hone this curriculum so that it is fit for purpose. The study will also identify some of the elements of a sustainable, specialized HE curriculum. The elements identified herein can serve as exemplars and conceptual starting points for other contexts where the discussion of the sustainability of curriculum needs to be had.

This chapter employs critical discourse analysis (CDA) to examine three key policy documents related to international education in New Zealand: The International Student Wellbeing Strategy (ISW), The New Zealand’s International Education Strategy 2018–2020 (IES), and The New Zealand’s Strategic Recovery Plan (SRP) for the International Education Sector. It asks, “How are discourses of international student wellbeing deployed in New Zealand’s international education policy documents?” The findings suggest that the actual targets of wellbeing in New Zealand international education policies were less the international students than New Zealand itself. I argue that discourses of international student wellbeing are instrumentalized in policy discourses to position New Zealand as a progressive and inclusive society and feed the competitive market dynamics driving the global international education market.

Session-based recommendation aims to predict the user's next preference based on the user's recent activities. Although most existing studies consider the global characteristics of items, they only learn the global characteristics of items based on a single connection relationship, which cannot fully capture the complex transformation relationship between items. We believe that multiple relationships between items in learning sessions can improve the performance of session recommendation tasks and the scalability of recommendation models. At the same time, high-quality global features of the item help to explore the potential common preferences of users.

This work proposes a session-based recommendation method with a multi-relation global context–enhanced network to capture this global transition relationship. Specifically, we construct a multi-relation global item graph based on a group of sessions, use a graded attention mechanism to learn different types of connection relations independently and obtain the global feature of the item according to the multi-relation weight.

We did related experiments on three benchmark datasets. The experimental results show that our proposed model is superior to the existing state-of-the-art methods, which verifies the effectiveness of our model.

First, we construct a multi-relation global item graph to learn the complex transition relations of the global context of the item and effectively mine the potential association of items between different sessions. Second, our model effectively improves the scalability of the model by obtaining high-quality item global features and enables some previously unconsidered items to make it onto the candidate list.

South Asia is a region urgently seeking development, although it has failed in regional integration. It is the second least integrated region regarding the number of Free Trade Agreements (FTAs) and can thus be recognised as a missing bloc in the global multilateral system. This study aims to focus on South Asian FTAs and explores the problems of the inter-relations and compatibility between the systemic and regional trade systems.

The study proposes a framework to benchmark the compatibility of South Asian FTAs with WTO rules. Primary data from 2000 to 2020, including descriptive analyses of reports, legal text of the FTAs, official documents and factual presentations, have been collected and analysed through thematic analysis using the proposed framework.

The study finds that, although South Asian FTAs meet most of the WTO requirements, they are not progressing toward facilitating and promoting trade. Data from 2000 to 2020 show us that South Asian FTAs have not significantly impacted trade between themselves. The study argues that, although South Asian FTAs fulfil some benchmarks, they show only a lukewarm interest in contributing to the international trading system as building blocs. It is therefore recommended that the case of South Asian trade liberalisation must be understood contextually and be given careful and exclusive attention by the WTO.

As such, this study is the first to claim that South Asian FTAs are not fully compatible with the WTO rules. They remain a missing regional bloc in the multilateral system, rather than a building bloc or a stumbling bloc, delaying the region’s opportunity to develop as a region and within the larger system.

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.

This work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.