Search results

Twin support vector machine (TSVM) is an effective machine learning technique. However, the TSVM model does not consider the influence of different data samples on the optimal hyperplane, which results in its sensitivity to noise. To solve this problem, this study proposes a twin support vector machine model based on fuzzy systems (FSTSVM).

This study designs an effective fuzzy membership assignment strategy based on fuzzy systems. It describes the relationship between the three inputs and the fuzzy membership of the sample by defining fuzzy inference rules and then exports the fuzzy membership of the sample. Combining this strategy with TSVM, the FSTSVM is proposed. Moreover, to speed up the model training, this study employs a coordinate descent strategy with shrinking by active set. To evaluate the performance of FSTSVM, this study conducts experiments designed on artificial data sets and UCI data sets.

The experimental results affirm the effectiveness of FSTSVM in addressing binary classification problems with noise, demonstrating its superior robustness and generalization performance compared to existing learning models. This can be attributed to the proposed fuzzy membership assignment strategy based on fuzzy systems, which effectively mitigates the adverse effects of noise.

This study designs a fuzzy membership assignment strategy based on fuzzy systems that effectively reduces the negative impact caused by noise and then proposes the noise-robust FSTSVM model. Moreover, the model employs a coordinate descent strategy with shrinking by active set to accelerate the training speed of the model.

We examine how superstition shapes corporate tax avoidance and do so by taking a risk perspective and focusing on the zodiac-year belief prevalent in China.

We adopt a difference-in-differences research design to compare the degree of corporate tax avoidance in the CEOs’ zodiac year with that in the adjacent years. We do propensity-score matching to form a sample of Chinese listed firms for the regression analysis.

We find causal evidence that firms exhibit a greater magnitude of tax avoidance in the CEOs’ zodiac years, a result attributable to relatively weak tax enforcement in the Chinese context. We also find that the zodiac-year effect on corporate tax avoidance is more pronounced for firms with tight financial constraints, firms with high business risk, firms headquartered in regions with a high degree of superstition and non-state-owned firms.

This study is the first to show that superstition is a determinant factor of tax avoidance and contributes to the tax literature by shedding light on the behavioral risk factors that shape corporate tax avoidance. We take the perspective of CEOs’ risk appetite to analyze how tax avoidance is influenced by the CEOs’ trade-off between the costs and benefits of avoiding taxes. Our results suggest that, when CEOs are more risk-averse, they attach more importance to financial risk than the risk of reputational losses and litigation associated with corporate tax avoidance. The findings imply that tax avoidance can be curbed by increasing (or decreasing) the tax (financial) risk confronting the CEOs.

To improve power system peak dispatching ability, connecting energy-storage device such as electric vehicle (EV) and regenerative electric heater (REH) to power grid is a good choice.

This paper establishes a multi-energy combined peak dispatching system MCPDS which includes EV, REH and wind power. The matter-element extension model based on improved variable weight theory is applied to evaluate MCPDS synthetic benefit.

The research shows that the MCPDS established in this paper performs excellently in security benefit, economic benefit, social benefit and environmental benefit.

With the assistance of energy storage devices such as EV and REH, the electrical system peak dispatching ability and power system operation efficiency has improved. More devices with energy-storage ability should be introduced into electrical power system to improve its synthetic benefit.

The aim of this paper is to review the current situation and existing problem, establish investment benefits evaluation indicator system and introduce synthetic approach degree containing Hamming approach degree, Euclid approach degree and gray correlation degree to improve the shortage of Euclidean distance in traditional TOPSIS method, and the evaluation result is strengthened by multiplication rule. This paper aims to solve the distribution network investment decision-making problem and construct a comprehensive distribution network investment benefit indicator system, which is more suitable for China distribution network characteristics.

This study develops improved TOPSIS methods for decision maker in the power distribution network market and uses an example to prove its effectiveness and superiority in practice which can realize the combination of theory and practice.

The research shows that the investment evaluation indicator system built in present paper covers more investment benefit influencing factors (such as qualified rate of trunk cross-section, pass rate of N-1 lines), and the evaluation result obtained by improved TOPSIS method is more efficient and persuasive.

The study can help investors evaluate distribution network project more efficient, and make contribution to the choice of distribution cases with similar investment benefits.

This study aims to investigate the process of developing loyalty in the Chinese mobile health community from the information seeking perspective.

A covariance-based structural equation model was developed to explore the mobile health community loyalty development process from information seeking perspective and tested with LISREL 9.30 for the 191 mobile health platform user samples.

The empirical results demonstrate that the information seeking perspective offers an interesting explanation for the mobile health community loyalty development process. All hypotheses in the proposed research model are supported except the relationship between privacy and trust. The two types of mobile health community loyalty—attitudal loyalty and behavioral loyalty are explained with 58 and 37% variance.

This paper has brought out the information seeking perspective in the loyalty formation process in mobile health community and identified several important constructs for this perspective for the loyalty formation process including information quality, communication with doctors and communication with patients.

The landscape of health information acquisition has shifted from offline to online, and online question-and-answer (Q&A) communities have emerged as prominent sources of health information; however, it is unclear how users identify satisfactory health information. This paper identifies factors that influence users’ adoption of health information in the context of online Q&A communities.

Based on the elaboration likelihood model (ELM) and opinion leader theory, we construct a research model to examine how information quality (complexity, image structure and emotional change) and source credibility (authentication status, follower number) affect health information adoption behavior. We verify the hypotheses by Poisson regression and zero-inflation Poisson regression using the data collected from an online Q&A community.

The empirical results indicate that both information quality and source credibility positively affect users’ adoption of health information.

This research can assist designers and managers of online Q&A communities to better comprehend users’ health information needs and their preferences for adoption. This enhanced understanding can facilitate the provision of superior online health information.

There are thousands of areas excluded from using electrical energy in China. It is mainly because that these places, which are away from towns, have the characteristics of scattered living and low-power consumption and are difficult to construct the power grid. The utilization of energy in remote areas could improve the level of education and quality of life for people living in there, which has great social significance. However, how to choose the optimal power generation model quantitatively according to local energy advantages is a difficult problem.

To carry out a better assessment of the energy benefits of Chinese rural areas to assist the decision-making of energy utilization project, this paper takes Sunan Yugu Autonomous County in Gansu Province as an example. Four feasible energy utilization scenarios are proposed by analyzing its geographical conditions and re-source advantage, respectively, are photovoltaic power generation, biomass power generation, wind power generation and power grid extension. Based on the above scenarios, the evaluation index system of comprehensive utilization of energy in remote areas is constructed, and the comprehensive benefit of each model is evaluated by adopting entropy-based fuzzy comprehensive evaluation model.

Evaluation results show that the comprehensive benefits of photovoltaic power generation is the best, followed by power grid extension. Thus, preference should be given to the two models in the energy utilization in Sunan County. This evaluation model can provide a scientific reference for the selection decision-making of energy utilization project, which is helpful to provide the feasibility and efficiency of the construction of energy utilization project.

The authors construct the comprehensive benefit evaluation index system and evaluate the comprehensive benefits of different scenarios are by using entropy - fuzzy comprehensive evaluation model. Then the qualitative problem can be analyzed quantitatively. The purpose of this study is to support the decision-making of energy investment. Simultaneously, the paper also has some practical significance in improving the credibility of the government and the quality of local people’s life.

To combine the forecasting by single method using influence information fully, other than regular combined methods only focusing on historical forecasting errors.

To combine the single methods based on the analysis of improved gray correlation, with more related information being considered to enhance the price forecasting precision, such as the trend of the prices, the historical forecasting errors, and the temporal influence factors on prices.

A case of PJM market of USA shows that the proposed method has better performance than any other combined methods, and all single models as well.

The combined performance depends on the forecasting precision of single methods, and the correlation between the single methods, as well as the number of single method that to be combined.

It is a novel idea for combined method to forecasting the time series data, such as electricity prices, electric power loads.

The proposed method considers all the following factors: the similarity between the trends of the single forecasting, the errors of the single models and the temporal influence.

Since stock return and volatility matters to investors, this study proposes to incorporate the textual sentiment of annual reports in stock price crash risk prediction.

Specific sentences gathered from management discussions and their subsequent analyses are tokenized and transformed into numeric vectors using textual mining techniques, and then the Naïve Bayes method is applied to score the sentiment, which is used as an input variable for crash risk prediction. The results are compared between a collection of predictive models, including linear regression (LR) and machine learning techniques.

The experimental results find that those predictive models that incorporate textual sentiment significantly outperform the baseline models with only accounting and market variables included. These conclusions hold when crash risk is proxied by either the negative skewness of the return distribution or down-to-up volatility (DUVOL).

It should be noted that the authors' study focuses on examining the predictive power of textual sentiment in crash risk prediction, while other dimensions of textual features such as readability and thematic contents are not considered. More analysis is needed to explore the predictive power of textual features from various dimensions, with the most recent sample data included in future studies.

The authors' study provides implications for the information value of textual data in financial analysis and risk management. It suggests that the soft information contained within annual reports may prove informative in crash risk prediction, and the incorporation of textual sentiment provides an incremental improvement in overall predictive performance.

With the popularity of the internet, access to health-related information has become more convenient. However, the easy acquisition of e-health information could lead to unfavorable consequences, such as health anxiety. The purpose of this paper is to explore a set of important influencing factors that lead to health anxiety.

Based on the stimulus–organism–response (S-O-R) framework, we propose a theoretical model of health anxiety, with metacognitive beliefs and catastrophic misinterpretation as the mediators between stimulus factors and health anxiety. Using 218 self-reported data points, the authors empirically examine the research model and hypotheses.

The study results show that anxiety sensitivity positively affects metacognitive beliefs. The severity of physical symptoms has a significant positive impact on catastrophic misinterpretation. Metacognitive beliefs and catastrophic misinterpretation have significant positive impacts on health anxiety.

Based on the S-O-R model, this paper develops a comprehensive model to explain health anxiety and verifies the model using firsthand data.