Search results

This research presents machine learning models for predicting international tourist arrivals in Indonesia during the COVID-19 pandemic using multisource Internet data.

To develop the prediction models, this research utilizes multisource Internet data from TripAdvisor travel forum and Google Trends. Temporal factors, posts and comments, search queries index and previous tourist arrivals records are set as predictors. Four sets of predictors and three distinct data compositions were utilized for training the machine learning models, namely artificial neural networks (ANNs), support vector regression (SVR) and random forest (RF). To evaluate the models, this research uses three accuracy metrics, namely root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE).

Prediction models trained using multisource Internet data predictors have better accuracy than those trained using single-source Internet data or other predictors. In addition, using more training sets that cover the phenomenon of interest, such as COVID-19, will enhance the prediction model's learning process and accuracy. The experiments show that the RF models have better prediction accuracy than the ANN and SVR models.

First, this study pioneers the practice of a multisource Internet data approach in predicting tourist arrivals amid the unprecedented COVID-19 pandemic. Second, the use of multisource Internet data to improve prediction performance is validated with real empirical data. Finally, this is one of the few papers to provide perspectives on the current dynamics of Indonesia's tourism demand.

This study aims to propose a refined dynamic network slacks-based measure (DNSBM) to evaluate the efficiency of China's regional green innovation system which consists of basic research, applied research and commercialization stages and explore the influencing factors of the stage efficiency.

A two-step procedure is employed. The first step proposes an improved DNSBM model with flexible settings of stages' input or output efficiency and uses second order cone programming (SOCP) to solve the non-linear problem. In the second step, least absolute shrinkage and selection operator (LASSO) and Tobit models are used to explore the influencing factors of the stage efficiency. Global Dynamic Malmquist Productivity Index (GDMPI) and Dagum Gini coefficient decomposition method are introduced for further discussion of the productivity change and regional differences.

On average, Chinese provincial green innovation efficiency should be improved by 24.11% to become efficient. The commercialization stage outperforms the stages of basic research and applied research. Comparisons between the proposed model and input-oriented, output-oriented and non-oriented DNSBM models show that the proposed model is more advanced because it allows some stages to have output-oriented model characteristics while the other stages have input-oriented model characteristics. The examination of the influencing factors reveals that the three stages of the green innovation system have quite diverse influencing factors. Further discussion reveals that Chinese green innovation productivity has increased by 39.85%, which is driven mainly by technology progress, and the increasing tendency of regional differences between northern and southern China should be paid attention to.

This study proposes an improved dynamic three-stage slacks-based measure (SBM) model that allows calculating output efficiency in some stages and input efficiency in the other stages with the application of SOCP approach. In order to capture productivity change, this study develops a GDMPI based on the DNSBM model. In practice, the efficiency of regional green innovation in China and the factors that influence each stage are examined.

In the context of constructing an integrated national strategic system, collaborative innovation among enterprises is the current social focus. Therefore, in order to find the interest relationship between multiple game subjects, to explore the influencing factors of collaborative innovation of civil-military integration enterprises. This paper constructs a collaborative innovation mechanism for military–civilian integration involving four game subjects (military enterprises, private enterprises, local governments, and science and technology intermediaries). It aims to solve and reveal the evolutionary game relationship among the four parties.

To explore the mechanism of military–civilian collaborative innovation involving four players, this study employs game theory and constructs an evolutionary game model for collaborative innovation with the participation of military enterprises, civilian enterprises, local governments, and technology intermediaries. The model reveals the evolutionary game patterns among these four entities, analyzes the impact of various parameters on the evolutionary process of the game system, and numerical simulation is used to show these changes more specifically.

The research findings demonstrate that active government subsidies promote cooperation throughout the system. Moreover, increasing the input-output ratio of research and development (R&D), the rate of technological spillovers, and the R&D investment of civilian enterprises all facilitate the tendency toward cooperation within the system. However, when the government chooses to actively provide subsidies, increasing R&D investment in military enterprises may hinder the tendency toward cooperation. Furthermore, central transfer payments, government punishment from the central government, and an increase in the information conversion rate of technology intermediaries may suppress the rate of cooperation within the system.

Most of the previous studies on the collaborative innovation of military–civilian integration have been tripartite game models between military enterprises, private enterprises, and local governments. In contrast, this study adds science and technology intermediaries on this basis, reveals the evolution mechanism of collaborative innovation of civil-military integration enterprises from the perspective of four-party participation, and analyzes the factors influencing the cooperation of the whole system. The conclusion of this study not only enriches the collaborative innovation evolution mechanism of military–civilian integration enterprises from the perspective of multiple agents but also provides practical guidance for the innovation-driven development of military–civilian integration enterprises.

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.

Using a multilevel model, this study examined how paternalistic leadership behaviors, including authoritarianism, morality and benevolence, influence followers' performance.

A sample of 556 leader–follower dyads from 66 groups in a manufacturing firm in China was collected for analysis. Descriptive statistics and multi-level regression analyses were used to analyze the data.

The results indicated that group efficacy mediates the relationship between authoritarian leadership and followers' performance and that self-efficacy mediates the relationship between benevolent leadership and followers' performance. In addition, the positive relationship between self-efficacy and followers' performance is weaker when followers exhibit higher levels of group efficacy.

The data were collected in a manufacturing firm in China, it is difficult to generalize the results to other settings.

Managers should use their abilities and skills to interpret which paternalistic leadership styles their followers prefer, so as to improve their performance.

This study developed a multilevel model to examine the mediating processes of group efficacy and self-efficacy in the effect of PL behaviors, including authoritarianism, benevolence and morality, on followers' performance.

The purpose of this article is to develop relationships between many major issues relevant to the agriculture supply chain.

With the purpose of gaining an all-encompassing understanding of the agriculture supply chain, this work uses 233 filtered research articles and three bibliometric analysis tools, namely VOSviewer, term frequency-inverse document frequency (TF-IDF) and Person correlation. The collected research publications were also catalogued using Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA).

Using analytic techniques, a total of 12 keywords were obtained. The study found that agri-products are in dire need of digitisation via Internet of things (IoT) and blockchain due to the usage of economic variables and comprehensive management of total food waste throughout transportation, anchoring quality and the predominant variable.

The study was limited to the Scopus and Web of Science (WoS) indexing in order to assess the viability of the linked idea and problem.

This study aims to generate vital knowledge in the field of horticulture-focused agriculture supply chain based on previous justification and relationship formation.

Drawing on the challenge–hindrance stressor framework and the “too-much-of-a-good-thing” principle, this study examined the curvilinear effects of two emic social challenge stressors (guanxi beliefs and participative decision-making (PDM)) and the moderating effect of an etic social hindrance stressor (perceived organizational politics) on Hong Kong and United States nurses’ job satisfaction.

A quantitative survey method was implemented, with the data provided by 355 Hong Kong nurses and 116 United States nurses. Structural equation modeling was used to examine the degree of measurement equivalence across Hong Kong and US nurses. The proposed model and the research questions were tested using nonlinear structural equation modeling analyses.

The results show that while guanxi beliefs only showed an inverted U-shaped relation on Hong Kong nurses’ job satisfaction, PDM had an inverted U-shaped relation with both Hong Kong and United States nurses’ job satisfaction. The authors also found that Hong Kong nurses experienced the highest job satisfaction when their guanxi beliefs and perceived organization politics were both high.

The results add to the comprehension of the nuances of the often-held assumption of linearity in organizational sciences and support the speculation of social stressors-outcomes linkages.

Managers need to recognize that while the nurturing and development of effective relationships with employees via social interaction are important, managers also need to be aware that too much guanxi and PDM may lead employees to feel overwhelmed with expectations of reciprocity and reconciliation to such an extent that they suffer adverse outcomes and become dissatisfied with their jobs.

First, the authors found that influences of guanxi beliefs and PDM are not purely linear and that previous research may have neglected the curvilinear nature of their influences on job satisfaction. Second, the authors echo researchers’ call to consider an organization’s political context to fully understand employees’ attitudes and reactions toward social interactions at work. Third, the authors examine boundary conditions of curvilinear relationships to understand the delicate dynamics.

Flexibility and efficiency are dual attributes of the organizational structure that are crucial for project-driven enterprises to achieve sustainable development in a dynamic environment. However, there is a lack of research on the patterns by which the dual attributes of a project-driven enterprise’s organizational structure affect business model innovation. Employing organizational theory, this study aims to assess the mediating mechanisms and dynamic capabilities through which the dual attributes of the organizational structure influence business model innovation in project-driven enterprises.

Data were collected from 242 employees from four project-driven companies across 26 cities (e.g. Beijing, Tianjin, Guangzhou and Shenzhen) in China. Structural equation modeling revealed the relationship between organizational structure’s dual attributes and business model innovation.

The findings show that the dual attributes (flexibility and efficiency) of the organizational structure have positive impacts on business model innovation. Moreover, dynamic capabilities mediate the relationship between the dual attributes and business model innovation in project-driven enterprises.

This study provides contributions to innovation research in the context of project-driven enterprises by revealing the influence of organizational structure on business model innovation through the firms’ dynamic capabilities. Such knowledge can enable managers of project-driven enterprises to develop effective interventions to promote business model innovation.

The study aims to devise a comprehensive evaluation model (CEM) for evaluating spatial equity in the layout of elderly service facilities (ESFs) to address the inequity in the layout of ESFs within city center communities characterized by limited land resources and a dense elderly population.

The CEM incorporates a suite of analytical tools, including accessibility assessment, Lorenz curve and Gini coefficient evaluations and spatial autocorrelation analysis. Utilizing this model, the study scrutinized the distributional equity of three distinct categories of ESFs in the city center of Xi’an and proposed targeted optimization strategies.

The findings reveal that (1) there are disparities in ESFs’ accessibility among different categories and communities, manifesting a distinct center (high) and periphery (low) distribution pattern; (2) there exists inequality in ESFs distribution, with nearly 50% of older adults accessing only 18% of elderly services, and these inequalities are more pronounced in urban areas with lower accessibility, and (3) approximately 14.7% of communities experience a supply-demand disequilibrium, with demand surpassing supply as a predominant issue in the ongoing development of ESFs.

The CEM formulated in this study offers policymakers, urban planners and service providers a scientific foundation and guidance for decision-making or policy amendment by promptly assessing and pinpointing areas of spatial inequity in ESFs and identifying deficiencies in their development.

Radical changes in consumer habits induced by the coronavirus disease (COVID-19) pandemic suggest that the usual demand forecasting techniques based on historical series are questionable. This is particularly true for hospitality demand, which has been dramatically affected by the pandemic. Accordingly, we investigate the suitability of tourists’ activity on Twitter as a predictor of hospitality demand in the Way of Saint James – an important pilgrimage tourism destination.

This study compares the predictive performance of the seasonal autoregressive integrated moving average (SARIMA) time-series model with that of the SARIMA with an exogenous variables (SARIMAX) model to forecast hotel tourism demand. For this, 110,456 tweets posted on Twitter between January 2018 and September 2022 are used as exogenous variables.

The results confirm that the predictions of traditional time-series models for tourist demand can be significantly improved by including tourist activity on Twitter. Twitter data could be an effective tool for improving the forecasting accuracy of tourism demand in real-time, which has relevant implications for tourism management. This study also provides a better understanding of tourists’ digital footprints in pilgrimage tourism.

This study contributes to the scarce literature on the digitalisation of pilgrimage tourism and forecasting hotel demand using a new methodological framework based on Twitter user-generated content. This can enable hospitality industry practitioners to convert social media data into relevant information for hospitality management.

2019冠狀病毒病引致消費者習慣有根本的改變; 這些改變顯示，根據歷史序列而運作的慣常需求預測技巧未必是正確的。這不確性尤以受到大流行極大影響的酒店服務需求為甚。因此，我們擬探討、若把在推特網站上的旅遊活動視為聖雅各之路 (一個重要的朝聖旅遊聖地) 酒店服務需求的預測器，這會否是合適的呢?

本研究比較 SARIMA 時間序列模型與附有外生變數 (SARIMAX)模型兩者在預測旅遊及酒店服務需求方面的表現。為此，研究人員收集在推特網站上發佈的資訊，作為外生變數進行研究。這個樣本涵蓋於2018年1月至2022年9月期間110,456個發佈資訊。

研究結果確認了傳統的時間序列模型，若涵蓋推特網站上的旅遊活動，則其對旅遊需求方面的預測會得到顯著的改善。推特網站的數據，就改善預測實時旅遊需求的準確度，或許可成為有效的工具; 而這發現對旅遊管理會有一定的意義。本研究亦讓我們進一步瞭解朝聖旅遊方面旅客的數碼足跡。

現存文獻甚少探討朝聖旅遊的數字化，而本研究不但在這方面充實了有關的文獻，還使用了一個根據推特網站上使用者原創內容嶄新的方法框架，進行分析和探討。這會幫助酒店從業人員把社交媒體數據轉變為可供酒店管理之用的合宜資訊。