Search results

Music sentiment analysis helps to promote the diversification of music information retrieval methods. Traditional music emotion classification tasks suffer from high manual workload and low classification accuracy caused by difficulty in feature extraction and inaccurate manual determination of hyperparameter. In this paper, the authors propose an optimized convolution neural network-random forest (CNN-RF) model for music sentiment classification which is capable of optimizing the manually selected hyperparameters to improve the accuracy of music sentiment classification and reduce labor costs and human classification errors.

A CNN-RF music sentiment classification model is designed based on quantum particle swarm optimization (QPSO). First, the audio data are transformed into a Mel spectrogram, and feature extraction is conducted by a CNN. Second, the music features extracted are processed by RF algorithm to complete a preliminary emotion classification. Finally, to select the suitable hyperparameters for a CNN, the QPSO algorithm is adopted to extract the best hyperparameters and obtain the final classification results.

The model has gone through experimental validations and achieved a classification accuracy of 97 per cent for different sentiment categories with shortened training time. The proposed method with QPSO achieved 1.2 and 1.6 per cent higher accuracy than that with particle swarm optimization and genetic algorithm, respectively. The proposed model had great potential for music sentiment classification.

The dual contribution of this work comprises the proposed model which integrated two deep learning models and the introduction of a QPSO into model optimization. With these two innovations, the efficiency and accuracy of music emotion recognition and classification have been significantly improved.

With the change in climate and increased pollution, there has been a need to reduce environmental carbon emissions. This research aims to develop a framework for reducing environmental carbon footprints to improve business performance.

This study uses Scientific Procedures and Rationales for the Systematic Literature Reviews (SPAR-4-SLR) approach. Articles are searched in the Scopus database using various keywords and their combinations. It resulted in 651 articles initially. After applying different screening criteria, 61 articles were considered for the final study.

This study provided four themes and sub-themes within each category. This research also used theories, methodologies and context (TMC) framework to provide future research questions. This study used the antecedents, decisions and outcomes (ADO) framework for synthesising the findings. The ADO framework will help to achieve carbon neutrality and improve firms' supply chain (SC) performance.

This study provides theoretical implications by highlighting the various theories that can be used in future research. This study also states the practical implications for the achievement of carbon neutrality by the firms.

This study contributes to the literature linking carbon neutrality with business performance.

In the digital economy, digital capability has become an important dynamic capability of enterprises and plays an essential role in enhancing firm resilience. This study aims to investigate the relationships among digital capability, knowledge search, coopetition behavior and firm resilience based on knowledge-based view and resource-based view.

This study uses the hierarchical regression and bootstrapping methods to test the theoretical framework and research hypotheses. The survey data were collected from 241 Chinese enterprises.

Digital capability has significantly positive effects on knowledge search and firm resilience. Knowledge search positively affects firm resilience and partially mediates the relationship between digital capability and firm resilience. Coopetition behavior weakens the relationship between digital capability and knowledge search, and the mediating effect of knowledge search in the relationship between digital capability and firm resilience. The moderating effect of coopetition behavior on the relationship between digital capability and firm resilience is insignificant.

This study clarifies the effect of digital capability on firm resilience and uncovers the “black box” from digital capability to firm resilience. In addition, this research enriches the literature on digital capability and firm resilience and expands the application of knowledge-based view and resource-based view in the digital context.

Users often struggle to select choosing among similar online services. To help them make informed decisions, it is important to establish a service reputation measurement mechanism. User-provided feedback ratings serve as a primary source of information for this mechanism, and ensuring the credibility of user feedback is crucial for a reliable reputation measurement. Most of the previous studies use passive detection to identify false feedback without creating incentives for honest reporting. Therefore, this study aims to develop a reputation measure for online services that can provide incentives for users to report honestly.

In this paper, the authors present a method that uses a peer prediction mechanism to evaluate user credibility, which evaluates users’ credibility with their reports by applying the strictly proper scoring rule. Considering the heterogeneity among users, the authors measure user similarity, identify similar users as peers to assess credibility and calculate service reputation using an improved expectation-maximization algorithm based on user credibility.

Theoretical analysis and experimental results verify that the proposed method motivates truthful reporting, effectively identifies malicious users and achieves high service rating accuracy.

The proposed method has significant practical value in evaluating the authenticity of user feedback and promoting honest reporting.

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

Although blockchain technology holds significant promise in influencing supply chain resilience (SCR), its effectiveness depends on a variety of factors. However, given that blockchain adoption in SCR is still in its infancy, there is a lack of empirical research to reveal the critical success factors maximizing its efficacy. This study aims to apply an organizational information processing theory (OIPT) perspective to explore how transformational supply chain leadership (TSCL) can facilitate the deployment and connection of blockchain technology to meet the imperatives of enhancing SCR.

This study used a two-wave survey method to gather data from 317 Chinese manufacturers to empirically examine the hypothesized relationships.

The findings suggest that the adoption of blockchain technology enhances both the proactive and reactive dimensions of SCR, and these effects can be realized through the mediating role of TSCL. Furthermore, the positive effect of blockchain technology on TSCL is strengthened in the context of dysfunctional competition.

These findings suggest that companies can only enhance the benefits of disruptive technologies, such as blockchain, by fully integrating them into the operational and supply chain processes.

This research offers novel insights into the specific processes of how blockchain technology can be used to enhance SCR. It also deepens our comprehension of how digital technology can be optimally harnessed within the framework of OIPT, thus providing a contribution to the literature on emerging technologies and SCR.

This study aims to explore how relationship trust and different types of influence strategy (i.e., non-coercive and coercive influence strategy) impact green customer integration (GCI), while investigating the moderating mechanisms of big data development and social capital.

Following hierarchical linear regression analysis, the authors examine hypothesized relationships by combining survey data from 206 Chinese manufacturers with secondary data.

The results show that relationship trust positively affects non-coercive influence strategy, while its impact on coercive influence strategy is insignificant. Non-coercive influence strategy has an inverted U-shaped impact on GCI. Furthermore, big data development flattens the inverted U-shaped relationship between non-coercive influence strategy and GCI. Conversely, social capital steepens the inverted U-shaped relationship between non-coercive influence strategy and GCI.

This study sheds light on managers on how to involve customers in GCI through friendly strategies that favor the involvement of customers and the willingness to develop environmentally friendly initiatives.

Although GCI has received widespread attention, how it can be enhanced remains unclear. These findings provide novel insights into the emerging GCI literature and complement social exchange theory.

The elderly service industry is emerging in China. The Chinese government introduced a series of policies to guide elderly service enterprises to improve their service quality. This study explores novel differentiated subsidy strategies that not only promote the improvement of service quality in elderly service enterprises but also alleviate the financial burden on the government.

Evolutionary game and Hotelling models are employed to investigate this issue. First, a Hotelling model that considers consumer word-of-mouth preferences is established. Subsequently, an evolutionary game model between local governments and enterprises is constructed, and the evolutionary stable strategies of both parties are analyzed. Finally, simulation experiments are conducted.

The findings indicate that local government decisions have a significant influence on the behavior of elderly service enterprises. Increasing the proportion of local governments opting for subsidy strategies helps incentivize elderly service enterprises to improve their service quality. Furthermore, providing differentiated subsidies based on the preferences of the customer base of elderly service enterprises can encourage service quality improvement while reducing government expenditure. The findings offer valuable insights into the design of government subsidy policies.

Compared with previous research, this study examines the role of consumer preferences in a differentiated subsidy policy. This enriches the authors’ understanding of the field by incorporating neglected aspects of consumer preferences in the context of the emerging elderly service industry.

Motivated by empirical features that characterize cryptocurrency volatility data, the authors develop a forecasting strategy that can account for both model uncertainty and heteroskedasticity of unknown form. The theoretical investigation establishes the asymptotic optimality of the proposed heteroskedastic model averaging heterogeneous autoregressive (H-MAHAR) estimator under mild conditions. The authors additionally examine the convergence rate of the estimated weights of the proposed H-MAHAR estimator. This analysis sheds new light on the asymptotic properties of the least squares model averaging estimator under alternative complicated data generating processes (DGPs). To examine the performance of the H-MAHAR estimator, the authors conduct an out-of-sample forecasting application involving 22 different cryptocurrency assets. The results emphasize the importance of accounting for both model uncertainty and heteroskedasticity in practice.

This paper aims to examine the effects of bonding temperature, bonding time, bonding pressure and the presence of a Pt catalyst on the bonding strength of Cu/SB/P-Cu/SB/Cu joints by transient liquid phase bonding (TLPB).

TLPB is promising to assemble die-attaching packaging for power devices. In this study, porous Cu (P-Cu) foil with a distinctive porous structure and Sn-58Bi solder (SB) serve as the bonding materials for TLPB under a formic acid atmosphere (FA). The high surface area of P-Cu enables efficient diffusion of the liquid phase of SB, stimulating the wetting, spreading and formation of intermetallic compounds (IMCs).

The higher bonding temperature decreased strength due to the coarsening of IMCs. The longer bonding time reduced the bonding strength owing to the coarsened Bi and thickened IMC. Applying optimal bonding pressure improved bonding strength, whereas excessive pressure caused damage. The presence of a Pt catalyst enhanced bonding efficiency and strength by facilitating reduction–oxidation reactions and oxide film removal.

Overall, this study demonstrates the feasibility of low-temperature TLPB for Cu/SB/P-Cu/SB/Cu joints and provides insights into optimizing bonding strength for the interconnecting materials in the applications of power devices.