Search results

Previous research mainly uses graph neural networks on syntactic dependency graphs, often neglecting emotional cues in sarcasm detection and failing to integrate image features for multimodal information effectively. To address these limitations, this study proposes a novel multimodal sarcasm detection model based on the directed graph isomorphism network with sentiment enhancement and multimodal fusion (DGIN-SE-MF).

The approach extracts image and text features through vision transformer and BERT, respectively. To deeply integrate the extracted features, the author develops a text-guided multi-head attention fusion mechanism module. Subsequently, a directed graph is constructed through SE and the multimodal factorized bilinear pooling method to integrate image features into the graph. The DGIN then fuses the image and text features, using a weighted attention mechanism to generate the final representation.

The model is validated on three datasets: English, Chinese and an Indonesian–English dataset. The results demonstrate that the proposed model consistently outperforms other baseline models, particularly on the Chinese and English sarcasm datasets, achieving F1 scores of 88.75 % and 83.10 %, respectively.

The proposed model addresses the inadequacies of previous methods by effectively integrating emotional cues and image features into sarcasm detection. To the best of the authors’ knowledge, this is the first work to leverage a DGIN-SE-MF for this task, leading to significant improvements in detection performance across different languages.

The suppliers of experimental resources required in megaprojects are driven by short-term interests, presuming that participation in the digital platform would only increase their inputs and fail to rapidly expand their revenue, resulting in their insufficient motivation to participate. This paper aims to design effective incentives for these suppliers exhibiting the aforementioned behaviour to drive them to participate and actively share their resources on the platform.

This paper develops incentives for applying the digital platform for experimental resource sharing by using a reverse induction approach to model and solve an incomplete information game. It compares the traditional experiment management mode and the new mode of applying the digital platform, taking the degree of sharing experimental resources on the platform as the variable and constructing three incentive models. By analysing these different degrees of sharing and the different experimental and informatisation capabilities of the suppliers, it could obtain the optimal incentive scheme for changes in sharing behaviour.

The results show that the designed incentives could increase the participation of suppliers in the platform and the number of their shared resources and make the benefits of both the supplier and the demand side reach the optimal state of a win-win situation. However, a higher degree of sharing by suppliers does not yield better results. In addition, the incentive coefficients for this degree should be set based on the suppliers’ different experimental and informatisation capabilities and the ratio of input cost-sharing, so as to avoid blind inputs from both supply and demand.

This study fills the research gap regarding incentives of the digital platform of experimental resource-sharing for megaprojects; it contributes to the body of knowledge by providing a quantitative perspective of understanding the experimental resource-sharing behaviour that motivates the usage of the digital platform. Furthermore, it reveals the incentive mechanism for application in different scenarios, and quantitative analysis is conducted to provide practical insights into promoting the new experiment management mode in megaprojects for more effective incentivisation.

The purpose of this paper is to investigate the impact of various decision-making approaches and government subsidies on supply chain performance, aiming to enhance the profits of disposal firms and retailers as well as to improve social welfare.

In this paper, a two-echelon biomass supply chain composed of a disposal firm and a retailer is developed. Firstly, considering the effects of government subsidies, we analyze biofuels prices, corporate social responsibility levels, social welfare and supply chain profitability under centralized and decentralized decision-making scenarios, respectively. Furthermore, we assess how subsidies influence pricing, market participation, profitability and social welfare. Secondly, we propose a revenue sharing–cost sharing contract to enhance the profits of the disposal firm and retailer. Thirdly, we extend the supply chain to a disposal firm and two retailers and explore the impact of competition intensity on corporate decision-making behavior. Finally, numerical analysis is conducted by taking one biomass energy firm as an example to support the results.

Our research finds that (1) Equilibrium strategies under the centralized decision-making scenario are greater than those under the decentralized decision-making scenario. Centralized decision-making can increase market demand and consumer surplus. (2) Government subsidies can promote corporate social responsibility levels, despite causing a slight increase in retail price for biofuels. When market competition intensifies, companies usually reduce their investment in CSR, and this trend is particularly pronounced in the absence of subsidies. (3) In both the decentralized and the centralized decision-making scenarios, increasing conversion rates and the CSR coefficient can significantly increase the overall profitability and social welfare.

A three-echelon biomass supply chain involving collection station, disposal firm and retailer can be studied in the future.

By examining the effects of subsidies on CSR engagement and market outcomes, our study contributes valuable insights into policy design for promoting sustainable practices in biomass industries.

This paper aims to study the joint decision making of advance selling and service cancelation for service provides with limited capacity when consumers are overconfident.

For the case in which consumers encounter uncertainties about product valuation and consumption states in the advance period and are overconfident about the probability of a good state, we study how the service provider chooses the optimal sales strategy among the non-advance selling strategy, the advance selling and disallowing cancelation strategy, and the advance selling and allowing cancelation strategy. We also discuss how overconfidence influences the service provider’s decision making.

The results show that when service capacity is sufficient, the service provider should adopt advance selling and disallow cancelation; when service capacity is insufficient, the service provider should still implement advance selling but allow cancelation; and when service capacity is extremely insufficient, the service provider should offer spot sales. Moreover, overconfidence weakens the necessity to allow cancelation under sufficient service capacity and enhances it under insufficient service capacity but is always advantageous to advance selling.

The obtained results provide managerial insights for service providers to make advance selling decisions.

This paper is among the first to explore the effect of consumers’ overconfidence on the joint decision of advance selling and service cancelation under capacity constraints.

This paper addresses the issue of internal spatial environmental pollution in non-blasting tunnel construction by proposing a comprehensive evaluation model. The model aims to provide a scientific basis for environmental pollution prevention in non-blasting tunnel construction, thereby facilitating green tunnel construction and sustainable development management.

The study firstly refines and constructs the evaluation index system from the perspective of pollution sources. A novel weight calculation method is introduced by integrating the analytic hierarchy process (AHP) with the ordered weighted averaging (OWA) operator, and a comprehensive evaluation model for internal environmental pollution in non-blasting tunnels is established by incorporating the grey clustering evaluation method. Finally, an empirical study is conducted using the Erbaoshan Tunnel as a case study to verify the feasibility and effectiveness of the model.

The study develops an evaluation system for internal environmental pollution in non-blasting tunnels and applies it to the Erbaoshan Tunnel. The results classify the pollution level as “general pollution,” confirming the rationality and applicability of the evaluation system and model while also identifying the primary pollution factors.

This study first developed a comprehensive evaluation system for environmental pollution in non-blasting tunnel construction from the pollution source perspective, making the system more comprehensive. Additionally, it innovatively combined AHP–OWA and gray clustering methods to scientifically assess pollution levels, providing valuable scientific guidance for the evaluation and management of non-blasting tunnels and similar underground projects.

Incorporating dynamic spatial effects exhibits considerable potential in improving the accuracy of forecasting tourism demands. This study aims to propose an innovative deep learning model for capturing dynamic spatial effects.

A novel deep learning model founded on the transformer architecture, called the spatiotemporal transformer network, is presented. This model has three components: the temporal transformer, spatial transformer and spatiotemporal fusion modules. The dynamic temporal dependencies of each attraction are extracted efficiently by the temporal transformer module. The dynamic spatial correlations between attractions are extracted efficiently by the spatial transformer module. The extracted dynamic temporal and spatial features are fused in a learnable manner in the spatiotemporal fusion module. Convolutional operations are implemented to generate the final forecasts.

The results indicate that the proposed model performs better in forecasting accuracy than some popular benchmark models, demonstrating its significant forecasting performance. Incorporating dynamic spatiotemporal features is an effective strategy for improving forecasting. It can provide an important reference to related studies.

The proposed model leverages high-frequency data to achieve accurate predictions at the micro level by incorporating dynamic spatial effects. Destination managers should fully consider the dynamic spatial effects of attractions when planning and marketing to promote tourism resources.

This study incorporates dynamic spatial effects into tourism demand forecasting models by using a transformer neural network. It advances the development of methodologies in related fields.

纳入动态空间效应在提高旅游需求预测的准确性方面具有相当大的潜力。本研究提出了一种捕捉动态空间效应的创新型深度学习模型。

本研究提出了一种基于变压器架构的新型深度学习模型, 称为时空变压器网络。该模型由三个部分组成：时空转换器、空间转换器和时空融合模块。时空转换器模块可有效提取每个景点的动态时间依赖关系。空间转换器模块可有效提取景点之间的动态空间相关性。提取的动态时间和空间特征在时空融合模块中以可学习的方式进行融合。通过卷积运算生成最终预测结果。

结果表明, 与一些流行的基准模型相比, 所提出的模型在预测准确性方面表现更好, 证明了其显著的预测性能。纳入动态时空特征是改进预测的有效策略。它可为相关研究提供重要参考。

所提出的模型利用高频数据, 通过纳入动态空间效应, 在微观层面上实现了准确预测。旅游目的地管理者在规划和营销推广旅游资源时, 应充分考虑景点的动态空间效应。

本研究通过使用变压器神经网络, 将动态空间效应纳入旅游需求预测模型。它推动了相关领域方法论的发展。

La incorporación de efectos espaciales dinámicos ofrece un considerable potencial para mejorar la precisión de la previsión de la demanda turística. Este estudio propone un modelo innovador de aprendizaje profundo para capturar los efectos espaciales dinámicos.

Se presenta un novedoso modelo de aprendizaje profundo basado en la arquitectura transformadora, denominado red de transformador espaciotemporal. Este modelo tiene tres componentes: el transformador temporal, el transformador espacial y los módulos de fusión espaciotemporal. El módulo transformador temporal extrae de manera eficiente las dependencias temporales dinámicas de cada atracción. El módulo transformador espacial extrae eficientemente las correlaciones espaciales dinámicas entre las atracciones. Las características dinámicas temporales y espaciales extraídas se fusionan de manera que se puede aprender en el módulo de fusión espaciotemporal. Se aplican operaciones convolucionales para generar las previsiones finales.

Los resultados indican que el modelo propuesto obtiene mejores resultados en la precisión de las previsiones que algunos modelos de referencia conocidos, lo que demuestra su importante capacidad de previsión. La incorporación de características espaciotemporales dinámicas supone una estrategia eficaz para mejorar las previsiones. Esto puede proporcionar una referencia importante para estudios afines.

El modelo propuesto aprovecha los datos de alta frecuencia para lograr predicciones precisas a nivel micro incorporando efectos espaciales dinámicos. Los gestores de destinos deberían tener plenamente en cuenta los efectos espaciales dinámicos de las atracciones en la planificación y marketing para la promoción de los recursos turísticos.

Este estudio incorpora efectos espaciales dinámicos a los modelos de previsión de la demanda turística mediante el empleo de una red neuronal transformadora. Supone un avance en el desarrollo de metodologías en campos afines.

To help supervisors understand the positions of workers in real-time, provide safety guidance for workers and reduce the occurrence of accidents. This study proposes a real-time positioning algorithm based on multi-source information coupling, aiming to solve the problem of workers’ autonomous positioning in signal-blind areas.

The proposed algorithm utilizes the visual SLAM and IMU sensors to perceive the environment, construct three-dimensional images, improve the accuracy of corner point matching, pre-integrate the raw IMU data, and adopt the tightly coupled method to couple the visual and inertial navigation data, thereby establishing a binocular visual SLAM and IMU coupling real-time positioning model.

The real-time positioning technology based on the coupling of visual SLAM and IMU shows good positioning effect and calculation speed in indoor sites, has good adaptability and accuracy in different building construction scenarios, and the positioning error can be controlled within 3%.

The successful construction of the real-time positioning method effectively alleviates the problem of inaccurate positioning caused by signal blind areas in the existing positioning management system, helps protect the lives and safety of construction site workers and improves the management efficiency of construction site supervisors.

It is a complex and dynamic process to provide high-quality rural infrastructure. However, there lacks a holistic performance evaluation method for rural infrastructure provision that reflects changing rural social needs and takes a village as a whole. This study aims to develop a holistic and dynamic performance evaluation model for rural infrastructure in Mainland China.

This study established an evaluation index system by combining the lifecycle theory and the economy, efficiency, effectiveness and equity (4E) theory. This study developed an evaluation model by using the analytic network process (ANP) and matter-element analysis theory (MEAT). The model was validated by two representative villages in Mainland China.

The developed model can reflect dynamic social needs and effectively evaluate the overall infrastructure provision performance of a village. The weight of indicators reflects the changes in Mainland China’s contemporary rural social needs, with particular emphasis on the impact and output performance. The evaluation result shows that the overall performance of the representative villages was excellent but had a tendency toward good. Although the output performance was excellent, different input, process and impact performances resulted in different downgrade trends.

This study provides a theoretical basis for disaggregating the complex issue of the performance of rural infrastructure provision. The results can be used by relevant authorities to make a holistic and dynamic evaluation of the performance of rural infrastructure provision and timely revise planning and management policies.

Through the scientific and reasonable evaluation of the site selection of the emergency material reserve, the optimal site selection scheme is found, which provides reference for the future emergency decision-making research.

In this paper, we have chosen three primary indicators and twelve secondary indicators to construct an assessment framework for the determination of suitable locations for storing emergency material reserves. By mean of the improved entropy weight-order relationship weight determination method, the evaluation model of kullback leibler-technique for order preference by similarity to an ideal solution (KL-TOPSIS) emergency material reserve location based on relative entropy is established. On this basis, 10 regional storage sites in Beijing are selected for evaluation.

The results show that the evaluation model of the location of emergency material reserve not only respects the objective knowledge, but also considers the subjective information of the experts, which makes the ranking result of the location of the emergency material reserve more accurate and reliable.

Firstly, the modification factor is added to the calculation formula of traditional entropy weight method to complete the improvement of entropy weight method. Secondly, the order relation analysis method is used to assign subjective weights to the indicators. The principle of minimum information entropy is introduced to determine the comprehensive weight of the index. Finally, KL distance and TOPSIS method are combined to determine the relative entropy and proximity degree of alternative solutions and positive and negative ideal solutions, and the scientific and effective of the method is proved by case study.

This paper aims to highlight the factors affecting health and safety (H&S) and the SMART Technologies (ST) used to mitigate them in the construction industry through a range of selected papers to encourage readers and potential audiences to consider the need for intelligent technologies to minimize the risks of injuries, illnesses and severe harm in the construction industry.

This paper adopts a double systematic literature review (SLR) to analyse studies investigating the factors affecting H&S and the ST in the construction industry using databases such as Google Scholar, Scopus, Science Direct and Emerald Insight publication.

The SLR identified “fatal or focus five factors” that include objects Fall from heights (FFH) and trapped between objects; Falls, Trips and slips (FTS); Machinery/Equipment Malfunction and Moving Equipment; Pollutants: Chemicals, Airborne Dust, Asbestos; and Electrocution. The ST includes Safety Boots/SMART Glasses/SMART Helmet/SMART Vests/SMART PPE/SMART Watch, Mobile Apps, Building Information Modelling (BIM), Virtual Reality/Augmented Reality (VR/AR), Drones/Unmanned Aerial Vehicles and Wearable Technology/Mobile Sensors help mitigate the risk posed by “Fatal five”. However, other factors within the scope of ST, such as Weather Conditions, Vibrations, Violence, Disease and illness, Fire and Explosion and Over Exertion, are yet to be adopted in the field.

SLR methodology limitations of not obtaining the most updated field knowledge are critical and are offset by choosing 72% of H&S and 92% of SM review literature post-2017. Limitations to capturing articles because of the restriction of database access: only English language search and journals that are not a part of the databases selected are acknowledged. However, key database search that recognizes rigorous peer-reviewed articles offset these limitations. The researcher’s Bias is acknowledged.

This paper unravels the construction H&S factors and their interlinks with ST, which would aid industry understanding and focus on mitigating associated risks. The paper highlights the Fatal five and trivial 15, which would help better understand the causes of the H&S risks. Further, the paper discusses ST’s connectivity, which would aid the organization’s overall H&S management. The practical and theoretical implications include a better understanding of all factors that affect H&S and ST available to help mitigate concerns. The operating managers could use the ST to reduce H&S risks at every construction process stage. This paper on H&S and ST and relationships can theorize that the construction industry is more likely to identify clear root causes of H&S and ST usage than previously. The theoretical implications include enhanced understanding for academics on H&S factors, ST and gaps in ST concerning H&S, which can be expanded to provide new insights into existing knowledge.

This paper highlights all factors affecting H&S and ST that help mitigate associated risks and identifies the “Fatal five” factors. The paper is the first to highlight the factors affecting H&S combined with ST in use and their interactions. The paper also identified factors within the ST scope that are yet to be explored.