Search results

The use of aviation incident data to carry out aviation risk prediction is of great significance for improving the initiative of accident prevention and reducing the occurrence of accidents. Because of the nonlinearity and periodicity of incident data, it is challenging to achieve accurate predictions. Therefore, this paper aims to provide a new method for aviation risk prediction with high accuracy.

This paper proposes a hybrid prediction model incorporating Prophet and long short-term memory (LSTM) network. The flight incident data are decomposed using Prophet to extract the feature components. Taking the decomposed time series as input, LSTM is employed for prediction and its output is used as the final prediction result.

The data of Chinese civil aviation incidents from 2002 to 2021 are used for validation, and Prophet, LSTM and two other typical prediction models are selected for comparison. The experimental results demonstrate that the Prophet–LSTM model is more stable, with higher prediction accuracy and better applicability.

This study can provide a new idea for aviation risk prediction and a scientific basis for aviation safety management.

The innovation of this work comes from combining Prophet and LSTM to capture the periodic features and temporal dependencies of incidents, effectively improving prediction accuracy.

The purpose of this paper is to assess the risk of controlled flight into terrain (CFIT) for airlines and to develop a practical method for evaluating and predicting CFIT risk to ensure safe and efficient airline operations.

In accordance with the monitoring project specification issued by the Flight Standards Department of the Civil Aviation Administration of China (CAAC), a preliminary draft of evaluation indicators for CFIT risk was developed based on the literature review and semi-structured interviews. Fifteen aviation experts were then selected and invited to participate in a Delphi method to revise the draft. Analytic hierarchy process (AHP) and entropy weight method were used to determine the combined weight of the indicators. The variable fuzzy set model and quick access recorder (QAR) data were applied to evaluate the CFIT risk of an airline from 2007 to 2018, and the classification results were compared with actual operational data.

The research findings reveal that the six most significant monitoring items affecting CFIT risk are incorrect configuration settings during landing, loss of altitude during climbing, ground proximity warning, G/S deviation, flap extension delay during landing and incorrect takeoff configuration. The CFIT risk of airlines has shown an increasing trend since 2015. The values in 2010, 2017 and 2018 were greater than 2 and less than 2.5, indicating that the CFIT risk is at Level 2, close to Level 3, and the risk is low but approaching medium.

Using the combination weight determined by AHP and entropy weight method to rank the weight of 15 monitoring items, airlines can take necessary measures (simulator training, knowledge training) to reduce the occurrence of monitoring items with high weight to reduce CFIT risk. This risk assessment method can quantitatively evaluate the CFIT risk of airlines and provide theoretical guidance and technical support for airlines to formulate safety management measures and flight training programs, enabling the interconnection between QAR data and flight quality.

The proposed method in this study differs from traditional approaches by offering a quantitative assessment of CFIT risk for airlines and enabling the interconnection between QAR data and flight quality.

The purpose of this paper is to identify the key influencing factors of aviation accidents and to predict the aviation accidents caused by the factors.

This paper proposes an improved gray correlation analysis (IGCA) theory to make the relational analysis of aviation accidents and influencing factors and find out the critical causes of aviation accidents. The optimal varying weight combination model (OVW-CM) is constructed based on gradient boosted regression tree (GBRT), extreme gradient boosting (XGBoost) and support vector regression (SVR) to predict aviation accidents due to critical factors.

The global aviation accident data from 1919 to 2020 is selected as the experimental data. The airplane, takeoff/landing and unexpected results are the leading causes of the aviation accidents based on IGCA. Then GBRT, XGBoost, SVR, equal-weight combination model (EQ-CM), variance-covariance combination model (VCW-CM) and OVW-CM are used to predict aviation accidents caused by airplane, takeoff/landing and unexpected results, respectively. The experimental results show that OVW-CM has a better prediction effect, and the prediction accuracy and stability are higher than other models.

Unlike the traditional gray correlation analysis (GCA), IGCA weights the sample by distance analysis to more objectively reflect the degree of influence of different factors on aviation accidents. OVW-CM is built by minimizing the combined prediction error at sample points and assigns different weights to different individual models at different moments, which can make full use of the advantages of each model and has higher prediction accuracy. And the model parameters of GBRT, XGBoost and SVR are optimized by the particle swarm algorithm. The study can guide the analysis and prediction of aviation accidents and provide a scientific basis for aviation safety management.

The purpose of this study is to investigate the influence of brand equity on corporate financial performance across various institutional factors in China, encompassing macro (regional economic development and product market development), meso (industry uncertainty), and micro (CEO overseas experience) levels.

Using archival data related to Chinese listed companies, this study employs standard error combined with fixed effect regression for model estimation to empirically evaluate the impact of brand equity on financial performance (Tobin’s q) and its boundary effects.

This study reveals that in China, the influence of brand equity on Tobin’s q isn’t significant. However, when considering institutional factors across various levels, its impact becomes significant. Specifically, the positive effect of brand equity on Tobin’s q in China is more pronounced in regions with higher economic or product market development, industries with high uncertainty, or when the CEO has overseas experience.

This study enriches the brand-related marketing literature in China and highlights the potential underperformance of brand equity within this context. Furthermore, this study advances the integration of resource-based view with institutional theory by combining brand equity with institutional factors at the macro-, meso-, and micro-level in China.

This study focuses on brand performance in China, the largest emerging market, emphasizing the importance of integrating brand equity with diverse institutional factors to amplify its beneficial influence on financial performance.

This paper aims to analyze and provide insight on the algorithms for the optimization of construction site layout planning (CSLP). It resolves problems, such as the selection of suitable algorithms, considering the optimality, optimization objectives and representation of layout solutions. The approaches for the better utilization of optimization algorithms are also presented.

To achieve the above, existing records (results = 200) were selected from three databases: Web of Science, ScienceDirect and Scopus. By implementing a systematic protocol, the articles related to the optimization algorithms for the CLSP (results = 75) were identified. Moreover, various related themes were collated and analyzed according to a coding structure.

The results indicate the consistent and increasing interest on the optimization algorithms for the CLSP, revealing that the trend in shifting to smart approaches in the construction industry is significant. Moreover, the interest in metaheuristic algorithms is dominant because 65.3% of the selected articles focus on these algorithms. The optimality, optimization objectives and solution representations are also important in algorithm selection. With the employment of other algorithms, self-developed applications and commercial software, optimization algorithms can be better utilized for solving CSLP problems. The findings also identify the gaps and directions for future research.

The selection of articles in this review does not consider the industrial perspective and practical applications of commercial software. Further comparative analyses of major algorithms are necessary because this review only focuses on algorithm types.

This paper presents a comprehensive systematic review of articles published in the recent decade. It significantly contributes to the demonstration of the status and selection of CLSP algorithms and the benefit of using these algorithms. It also identifies the research gaps in knowledge and reveals potential improvements for future research.

The current studies on remaining useful life (RUL) prediction mainly rely on convolutional neural networks (CNNs) and long short-term memories (LSTMs) and do not take full advantage of the attention mechanism, resulting in lack of prediction accuracy. To further improve the performance of the above models, this study aims to propose a novel end-to-end RUL prediction framework, called convolutional recurrent attention network (CRAN) to achieve high accuracy.

The proposed CRAN is a CNN-LSTM-based model that effectively combines the powerful feature extraction ability of CNN and sequential processing capability of LSTM. The channel attention mechanism, spatial attention mechanism and LSTM attention mechanism are incorporated in CRAN, assigning different attention coefficients to CNN and LSTM. First, features of the bearing vibration data are extracted from both time and frequency domain. Next, the training and testing set are constructed. Then, the CRAN is trained offline using the training set. Finally, online RUL estimation is performed by applying data from the testing set to the trained CRAN.

CNN-LSTM-based models have higher RUL prediction accuracy than CNN-based and LSTM-based models. Using a combination of max pooling and average pooling can reduce the loss of feature information, and in addition, the structure of the serial attention mechanism is superior to the parallel attention structure. Comparing the proposed CRAN with six different state-of-the-art methods, for the predicted results of two testing bearings, the proposed CRAN has an average reduction in the root mean square error of 57.07/80.25%, an average reduction in the mean absolute error of 62.27/85.87% and an average improvement in score of 12.65/6.57%.

This article provides a novel end-to-end rolling bearing RUL prediction framework, which can provide a reference for the formulation of bearing maintenance programs in the industry.

It is unclear what constitutes the tourism live streaming (TLS) servicescape and how it affects users' travel intention (TI). The study aims to explore the composition of the TLS servicescape, the influence mechanism of the TLS servicescape on users' TI and the formation of users' TI.

Based on stimulus organism response theory (SOR), we develop a mediation model to explore the influence of TLS servicescape on users' TI. This study collected data from 432 Chinese TLS users through an online questionnaire, and we used the structural equation model and the SPSS PROCESS macro to test the proposed model. In addition, we tested the variable relationships using fuzzy-set qualitative comparative analysis (fsQCA).

TLS servicescape is a second-order variable that can be categorized into physical element (PE), social element (SOE), symbolic element (SYE) and natural element (NE). TLS servicescape influences TI by affecting social presence (SP) and customer engagement (CE). The fsQCA reveals seven combinations of PE, SOE, SYE, NE, SP and CE that form a high TI for TLS users.

Using multiple data analysis methods, the study emphasizes the significance of the TLS servicescape for TLS. It explores how to evoke users' TI in TLS and provides a reference for TLS marketing.

The purpose of this paper is to provide scientific guidance for the integration of industrialization and information (TIOII). In recent years, TIOII has promoted the development of intelligent manufacturing in China. However, many enterprises blindly invest in TIOII, which affects their normal production and operation.

This study establishes an efficiency evaluation model for TIOII. In this paper, entropy analytic hierarchy process (AHP) constraint cone and cross-efficiency are added based on traditional data envelopment analysis (DEA) model, and entropy AHP–cross-efficiency DEA model is proposed. Then, statistical analysis is carried out on the integration efficiency of enterprises in Guangzhou using cross-sectional data, and the traditional DEA model and entropy AHP–cross-efficiency DEA model are used to analyze the integration efficiency of enterprises.

The data show that the efficiency of enterprise integration is at a medium level in Guangzhou. The efficiency of enterprise integration has no significant relationship with enterprise size and production type but has a low negative correlation with the development level of enterprise integration. In addition, the improved DEA model can better reflect the real integration efficiency of enterprises and obtain complete ranking results.

By adding the entropy AHP constraint cone and cross-efficiency, the traditional DEA model is improved. The improved DEA model can better reflect the real efficiency of TIOII and obtain complete ranking results.

Knowledge transfer which refers to the communication of knowledge from a source so that it is learned and applied by a recipient has long been a challenge for knowledge management. The purpose of this study is to understand influencing factors of transactive memory system (TMS) and knowledge transfer.

Drawing on the theories of communication visibility, social distance and flow, this study develops a research model. Then, data are collected from users of the social media mobile App. Partial least squares-structural equation modeling (PLS-SEM) is employed to analyze data.

TMS is a valid second-order construct in the social media mobile app context, which is more reflected by credibility. Meanwhile, communication visibility and social distance each have positive effects on TMS which further has a positive effect on knowledge transfer. Flow has a positive effect on knowledge transfer.

Developers of the mobile App should carefully consider the role of information and communication technology (ICT) in supporting TMS and knowledge transfer. They should consider recommendation algorithm so that the benefit of communication visibility can be retained. They should design the feature to classify users based on similarity so as to stimulate users' feeling of close social distance. They should keep on improving features based on users' holistic experience.

This study incorporates the perspectives of communication visibility, social distance and flow to understand TMS and knowledge transfer, presenting a new lens for research.

The purpose of this study is to discover the uniqueness of China's online livestreaming industry and to make preliminary predictions about its future.

Providing a panoramic description of China's online livestreaming industry and a comparative analysis with other countries' online livestreaming industries.

China's online livestreaming industry is world leader in general. In terms of user size and age structure, although China has a high proportion of online livestreaming users, the proportion of anchors is not high, while the age structure of users in both China and other countries shows the characteristics of younger users. In terms of policy, the difference between China and foreign support in online livestreaming is small, but developed countries have stricter regulations.

The research in this paper has great significance in gaining an in-depth understanding of the development status and trends of China's online livestreaming industry and in designing accurate support policies.