Search results

This paper aims to address the limitations of current deep learning algorithms for sound source localization (SSL), which focus on a single feature and frequency scale, neglecting the integration of multi-scale information. The method developed in this study enhances localization accuracy by effectively using the spatial information and spectral diversity provided by microphone arrays.

The method is based on a multi-scale cross-short-time Fourier transform (STFT) complex-valued convolutional neural network (CCNN). It uses cross-STFT spectra at different scales to capture detailed acoustic information across various frequencies. The effectiveness of the algorithm was validated through both simulations and experimental studies.

Experimental results demonstrate that the proposed multi-scale cross-STFT CCNN not only outperforms the single-scale cross-STFT model but also delivers superior localization performance compared to other advanced methods, achieving consistently higher accuracy. The method shows excellent robustness across various signal-to-noise ratio (SNR) conditions and performs well even on imbalanced datasets, confirming its strong generalization capabilities.

This paper introduces a novel approach to SSL that integrates multi-scale information, addressing a key limitation of existing methods. The findings offer significant value to researchers and practitioners in the field of acoustic signal processing, particularly those focused on deep learning-based localization techniques.

Unlike previous research that primarily utilized structural equation modelling (SEM) to evaluate safety hazards in subway projects, this research aims to utilize a hybrid approach to investigate and scrutinize the key indicators of safety hazards leading to accidents, thereby hindering the progress of subway projects in China, taking into cognizance the multiple stakeholder’s perspective.

By administering a survey questionnaire to 373 highly involved stakeholders in subway projects spanning Changsha, Beijing and Qingdao, China, our approach incorporated a four-staged composite amalgamation of exploratory factor analysis (EFA), confirmatory factor analysis (CFA), covariance-based structural equation modelling (CB-SEM) and artificial neural network (ANN) to develop an optimized model that determines the causal relationships and interactions among safety hazards in subway construction projects.

The optimized model delineated the influence of individual safety hazards on subway projects. The feasibility and applicability of the model developed was demonstrated on an actual subway project under construction in Changsha city. The outcomes revealed that the progress of subway projects is significantly influenced by risks associated with project management, environmental factors, subterranean conditions and technical hazards. In contrast, risks related to construction and human factors did not exhibit a significant impact on subway construction progress.

While our study provides valuable insights, it is important to acknowledge the limitation of relying on theoretical approaches without empirical validation from experiments or the field. In future research, we plan to address this limitation by assessing the SEM using empirical data. This will involve a comprehensive comparison of outcomes derived from CB-SEM with those obtained through SEM-ANN methods. Such an empirical validation process is crucial for enhancing the overall efficiency and robustness of the proposed methodologies.

The established hybrid model revealed complex non-linear connections among indicators in the intricate project, enabling the recognition of primary hazards and offering direction to improve management of safety in the construction of subways.

The research on sustainable campus is related to environmental protection and the realization of global sustainable development goals (SDGs). Because the sustainable campus development in China and Japan is carried out around buildings, this paper takes Kitakyushu Science and Research Park as a case to study the characteristics and typical model of sustainable campus in Japan by combined with the characteristics of Chinese sustainable campus.

This study compares the evaluation standards of green buildings between China and Japan, then compares the assessment results of the same typical green building case and finally summarizes the development mode and main realization path by discussing the implications of green buildings on campus sustainability.

The results show that (1) the sustainable campus evaluation in Japan mainly pays attention to the indoor environment, energy utilization and environmental problems. (2) Buildings mainly affect the sustainability of the campus in three aspects: construction, transportation and local. (3) The sustainable campus development model of Science and Research Park can be summarized as follows: taking green building as the core; SDGs as the goals; education as the guarantee; and the integration of industry, education and research as the characteristics.

It mainly provides construction experience for other campuses around the world to coordinate the contradictions between campus buildings and the environment based on sustainable principles in their own construction. It proposes a new sustainable campus construction path of “building–region–environment” integrated development.

This study provides theoretical framework for the development of sustainable campuses that includes long-term construction ideas and current technological support greatly improving the operability of practical applications. It not only enriches the sample cases of global sustainable campuses but also provides new ideas and perspectives for the sustainable development research of the overall campus through quantitative evaluation of building and environmental impacts.

Purpose: The sharing economy epitomises a paradigm shift by advocating for sustainable consumption practices and resource optimisation. This study investigates the critical factors influencing the burgeoning sharing economy.

Methodology: Logical analysis and synthesis methods to glean insights from the existing scholarly literature on the sharing economy and the factors impacting its development. The author establish a comprehensive set of indicators categorised into four key domains: technological infrastructure, political and regulatory landscape, economic context, and socio-cultural environment.

Findings: A framework of quantifiable indicators encompassing the critical factors necessary for the sharing economy’s development. Indicators encompass a comprehensive spectrum, reflecting the influence of technological advancements, economic conditions, socio-cultural factors, and the prevailing political and regulatory environment.

Implications: This evaluation considers the principal factors influencing the development and enables comparative analysis between countries based on the conditions fostering the sharing economy.

Limitations: This study relies on a literature review, which may not encompass all factors affecting the sharing economy, with a possibility that additional factors not addressed in this study could influence the development of the sharing economy. The indicator framework could be expanded or revised in the future based on new research findings.

Future Research: Incorporating dynamic analysis would reveal how fluctuations in identified factors affect the sharing economy over time. Expanding the research to more countries could provide a broader understanding of the global sharing economy landscape, potentially investigating regional or city-level factors for contextual insights. Future research could weight indicators based on their relative importance.

This study aims to explore how communication visibility affects employees’ work engagement from the negative perspective of employees’ perceived overload in the context of enterprise social media (ESM) and the role of ESM policies in the relationship between communication visibility and perceived overload.

This study examines how communication visibility (i.e. message transparency and network translucence) affects employees’ perceived overload (i.e. information overload and social overload), which in turn affects employees’ work engagement, and how ESM policies moderate the relationship between communication visibility and perceived overload. Partial least squares (PLS) analysis was conducted on data gathered from 224 ESM users in workplaces.

Communication visibility has significant positive impacts on perceived overload, perceived overload has significant negative impacts on work engagement and ESM policies negatively moderate the relationships between communication visibility and perceived overload, except for the relationship between message transparency and social overload.

The findings provide new insights for organizational managers to formulate ESM policies to mitigate perceived overload and guidance for ESM developers to improve ESM functions to alleviate perceived overload.

This study provides empirical evidence to explain the role of communication visibility and perceived overload in employees’ work engagement, which contributes to the existing literature on the negative impacts of communication visibility.

Ball grid array (BGA) package is prone to failure issues in a thermal vibration-coupled environment, such as deformation and fracture of solder joints. To predict the minimum equivalent stress of solder joints more accurately and optimize the solder joint structure, this paper aims to compare the machine learning method with response surface methodology (RSM).

This paper introduced a machine learning algorithm using Grey Wolf Optimization (GWO) Support Vector Regression (SVR) to optimize solder joint parameters. The solder joint height, spacing, solder pad diameter and thickness were the design variables, and minimizing the equivalent stress of solder joint was the optimization objective. The three dimensional finite element model of the printed circuit board assembly was verified by a modal experiment, and simulations were conducted for 25 groups of models with different parameter combinations. The simulation results were employed to train GWO-SVR to build a mathematical model and were analyzed using RSM to obtain a regression equation. Finally, GWO optimized these two methods.

The results show that the optimization results of GWO-SVR are closer to the simulation results than those of RSM. The minimum equivalent stress is decreased by 8.528% that of the original solution.

This study demonstrates that GWO-SVR is more precise and effective than RSM in optimizing the design of solder joints.

This study aims to develop a robust long short-term memory (LSTM)-based forecasting model for daily international tourist arrivals at Incheon International Airport (ICN), incorporating multiple predictors including exchange rates, West Texas Intermediate (WTI) oil prices, Korea composite stock price index data and new COVID-19 cases. By leveraging deep learning techniques and diverse data sets, the research seeks to enhance the accuracy and reliability of tourism demand predictions, contributing significantly to both theoretical implications and practical applications in the field of hospitality and tourism.

This study introduces an innovative approach to forecasting international tourist arrivals by leveraging LSTM networks. This advanced methodology addresses complex managerial issues in tourism management by providing more accurate forecasts. The methodology comprises four key steps: collecting data sets; preprocessing the data; training the LSTM network; and forecasting future international tourist arrivals. The rest of this study is structured as follows: the subsequent sections detail the proposed LSTM model, present the empirical results and discuss the findings, conclusions and the theoretical and practical implications of the study in the field of hospitality and tourism.

This research pioneers the simultaneous use of big data encompassing five factors – international tourist arrivals, exchange rates, WTI oil prices, KOSPI data and new COVID-19 cases – for daily forecasting. The study reveals that integrating exchange rates, oil prices, stock market data and COVID-19 cases significantly enhances LSTM network forecasting precision. It addresses the narrow scope of existing research on predicting international tourist arrivals at ICN with these factors. Moreover, the study demonstrates LSTM networks’ capability to effectively handle multivariable time series prediction problems, providing a robust basis for their application in hospitality and tourism management.

This research pioneers the integration of international tourist arrivals, exchange rates, WTI oil prices, KOSPI data and new COVID-19 cases for forecasting daily international tourist arrivals. It bridges the gap in existing literature by proposing a comprehensive approach that considers multiple predictors simultaneously. Furthermore, it demonstrates the effectiveness of LSTM networks in handling multivariable time series forecasting problems, offering practical insights for enhancing tourism demand predictions. By addressing these critical factors and leveraging advanced deep learning techniques, this study contributes significantly to the advancement of forecasting methodologies in the tourism industry, aiding decision-makers in effective planning and resource allocation.

本研究旨在开发一种基于LSTM的强大预测模型, 用于预测仁川国际机场的日常国际游客抵达量, 结合多种预测因素, 包括汇率、WTI原油价格、韩国综合股价指数 (KOSPI) 数据和新冠疫情病例。通过利用深度学习技术和多样化数据集, 研究旨在提升旅游需求预测的准确性和可靠性, 对酒店与旅游领域的理论和实际应用有重要贡献。

本研究通过利用长短期记忆（LSTM）网络引入创新方法, 预测国际游客抵达量。这一先进方法解决了旅游管理中的复杂管理问题, 提供了更精确的预测。方法论包括四个关键步骤: (1) 收集数据集; (2) 数据预处理; (3) 训练LSTM网络; 以及 (4) 预测未来的国际游客抵达量。本文的其余部分结构如下：后续部分详细介绍了提出的LSTM模型, 呈现了实证结果, 并讨论了研究的发现、结论以及在酒店与旅游领域的理论和实际意义。

本研究首次同时使用包括国际游客抵达量、汇率、原油价格、股市数据和新冠疫情病例在内的大数据进行日常预测。研究显示, 整合汇率、原油价格、股市数据和新冠疫情病例显著增强了LSTM网络的预测精度。研究填补了现有研究在使用这些因素预测仁川国际机场国际游客抵达量的狭窄范围。此外, 研究证明了LSTM网络在处理多变量时间序列预测问题上的能力, 为其在酒店与旅游管理中的应用提供了坚实基础。

本研究首次将国际游客抵达量、汇率、WTI原油价格、KOSPI数据和新冠疫情病例整合到日常国际游客抵达量的预测中。它通过提出同时考虑多个预测因素的全面方法, 弥合了现有文献的差距。此外, 研究展示了LSTM网络在处理多变量时间序列预测问题方面的有效性, 为增强旅游需求预测提供了实用见解。通过处理这些关键因素并利用先进的深度学习技术, 本研究在旅游业预测方法的进步中做出了重要贡献, 帮助决策者进行有效的规划和资源配置。

This study aims to examine the impact of peer-to-peer (P2P) accommodation platforms’ green marketing on consumers’ pro-environmental behavioural intention through the mediation of consumer trust and engagement, following the social influence theory and the stimulus–organism–response model.

A questionnaire survey was designed to collect data from American P2P accommodation consumers. Data collection was conducted through an outsourced survey company. Partial least squares structural equation modelling was used to analyse the data.

The study reveals that P2P accommodation platforms’ green marketing orientation was positively associated with consumer trust in the platform and consumer engagement with the platform. Both consumer trust and consumer engagement positively enhanced consumers’ pro-environmental behavioural intention in the P2P accommodation consumption, serving as effective mediators between consumers’ perceptions of green marketing orientation and pro-environmental behavioural intention.

The study offers practical insights for P2P accommodation platforms and operators in engaging in green marketing and fostering consumers’ pro-environmental consumption behaviours in P2P accommodations.

The study addresses the grand question of whether business operators’ responsible production behaviour can possibly lead to consumers’ responsible consumption behaviour in the P2P accommodation sector. It contributes to the literature on P2P accommodation by providing evidence to show green marketing practices of P2P accommodation platforms can lead to consumers’ pro-environmental behavioural intention. It provides both theoretical value for knowledge advancement and practical value to guide more sustainable industry practices.

This study aims to propose a cloud platform architecture considering information sharing based on blockchain to realize the security and convenience of enterprise information sharing in the automotive supply chain.

A bilateral matching model considering enterprises information contribution stimulates information sharing and improves the efficiency and quality of supply and demand matching. Three smart contracts are used to complete the information sharing process and match supply and demand in the automotive supply chain.

The system is tested on the local Ganache private chain, and the decentralized web page is designed based on the architecture prototype.

Solve the problem of information island in automobile supply chain.

The purpose of this paper is to analyze the impact of the off-office audit of natural resource assets on the prevention and control of water pollution against a background of big data using a differences-in-differences model.

This study constructs a differences-in-differences model to evaluate the policy effects of off-office audit based on panel data from 11 cities in Anhui Province, China, from 2011 to 2017, and analyzes the dynamic effect of the audit and intermediary effect of industrial structure.

The implementation of the audit system can effectively reduce water pollution. Dynamic effect analysis showed that the audit policy can not only improve the quality of water resources but can also have a cumulative effect over time. That is, the prevention and control effect on water pollution is getting stronger and stronger. The results of the robustness test verified the effectiveness of water pollution prevention and control. However, the results of the influence mechanism analysis showed that the mediating effect of the industrial structure was not obvious in the short term.

These findings shed light on the effect of the off-office audit of natural resource assets on the prevention and control of water pollution, and provide a theoretical basis for the formulation of relevant environmental policies. Furthermore, these findings show that the implementation of the audit system can effectively reduce water pollution, which has practical significance for the sustainable development of China's economy against the background of big data.

This study quantitatively analyzes the policy effect of off-office auditing from the perspective of water resources based on a big data background, which differs from the existing research that mainly focuses on basic theoretical analysis.