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.

Damage to the pipe structure and increased bolt stress in operating tunnels will significantly affect the long-term stability of shield tunnels. However, due to the large number of segments and complex bolt installation methods, it is difficult to directly obtain the conditions of segments and bolts. Convergence deformation, as an important indicator for the health assessment of operating tunnels, is easy to collect and can directly reflect the structural state of tunnel segments and bolts.

Taking the typical sections of Hangzhou Metro Line 1 and Line 3 as an example, the current structural damage is simulated by monitoring tunnel convergence deformation. First, based on the disease data, the relationship between convergence deformation and segment leakage, segment misalignment as well as the longitudinal joint opening between two segments is analyzed statistically. The stress of bolts, steel bars and segments under different convergence deformations is simulated by Midas. Then a reinforcement measure of circumferential internal tension steel rings is proposed.

It is found that when the segment convergence exceeds 85 mm, although the overall force on the segment has not reached the material limit, there are certain safety risks in the structure. After comparison, the reinforcement measure has a relatively significant effect on controlling the lateral deformation of segments.

The results have important guiding significance for the evaluation of structural diseases, early warning and control of structural diseases at different convergence deformations.

This article aims to contribute to the accounting knowledge literature by presenting the framework of shadow accounting functions (SAF) and investigating the effect of stakeholders’ pressure anomie (SPA) on it.

This study adopted a mixed, both inductive and deductive approach to develop an integrated framework, validate its practicability and verify its effectiveness in selected manufacturing firms listed on the Tehran Stock Exchange. In developing the framework and implementation procedure, the study employed an exploratory data collection (qualitative) approach to review the phenomenon of shadow accounting functions. Then, in the second phase, this study tested the research hypothesis through a partial least squares process. The population of the study is made up of all financial managers and heads of the accounting departments of capital market companies in Iran. Presently, there are 185 companies (TSE). From this, a sample of 100 companies was selected, which are all on the Tehran Stock Exchange.

Based on the mixed method of this study, the result in the qualitative part provides the shadow accounting framework of the existence of three categories; there are six components and 37 themes during 12 interviews. In the quantitative section, it was also determined that social pressure anomie has a positive and significant effect on shadow accounting functions.

So far, it is rare to find preceding studies that proposed, validated and practically tested an integrated shadow accounting framework within the context of manufacturing industries. Thus, the authors understand that this is the very first research focused on the development of the framework for manufacturing industries to be competitive and could help managers, institutions, practitioners and academicians in the perception of social values expected by stakeholders.

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.

Emergencies have become a growing concern for organizations, which require flexibility to respond to changes in emergencies based on their contingency, dynamic evolution rapidly and other characteristics. In order to enhance the ability of engineering project organizations to cope with emergencies, this study explores the mechanism of its influence on knowledge innovation under emergencies from the perspective of bricolage theory, and provides a new perspective for the traditional preplanning-based handling of emergencies by improvising to enhance the ability and results of improvisation.

Firstly, a structural equation model of the relationship between bricolage and knowledge innovation was constructed by introducing improvisational behavior and serendipity as mediating and moderating variables of the relationship between bricolage and knowledge innovation based on bricolage theory; secondly, drawing on previous well-established measurement scales about bricolage, improvisational behavior, knowledge innovation and serendipity, a questionnaire survey was conducted with different types of engineering project managers and technicians in Gansu Province as the research subjects, and 238 valid questionnaires were returned; finally, validation factor analysis and correlation analysis were performed, and the hypothesized relationships were verified using AMOS 24.0 software.

The results show that bricolage positively influences improvisational behavior; improvisational behavior positively influences knowledge innovation; bricolage positively influences knowledge innovation; bricolage influences knowledge innovation through the mediating role of improvisational behavior and serendipity positively moderates the impact of resource bricolage on knowledge innovation.

It reveals the mechanism of knowledge innovation of engineering project organizations in response to emergencies and the innovation mechanism of the episodic nature of emergency decision-making, extends the applicable context of bricolage theory and provides a new perspective for engineering project organizations in response to emergencies.

From the perspective of intangible knowledge resources, this paper clarifies the impact of managerial ability on the performance of overseas investment subsidiaries. It explains the dilemma that the rapid growth of overseas investment by enterprises in emerging markets has not brought about the corresponding expected performance.

This paper uses matching data between the parent companies and overseas subsidiaries of Chinese A-share listed companies from 2007 to 2022 to study the impact of managerial ability on the performance of overseas investment subsidiaries and its mechanism.

The results show that there is a significant positive correlation between managerial ability and the performance of overseas subsidiaries. However, the impact of managerial ability exhibits heterogeneous, which is more significant in non-state-owned enterprises, investments in high-income economies and M&A investment. Managerial ability promotes mainly the performance of overseas subsidiaries through R&D knowledge resources, marketing knowledge resources and internationalization experience; managerial ability significantly impacts the performance of overseas subsidiaries in the case of CEO two-job separation, low CEO shareholding level, the executive team with overseas background and female.

This paper introduces managerial ability as a critical intangible knowledge resource in the study of overseas investment performance, enriching and expanding the connotation and theoretical foundation of managerial ability. It clarifies the impact mechanism of managerial ability on overseas investment performance from three dimensions: R&D knowledge resources, marketing knowledge resources and internationalization experience. It provides new empirical evidence and management enlightenment for promoting overseas investment performance and high-quality development in emerging market countries.

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。