Search results

Parkinson's disease (PD) is a well-known complex neurodegenerative disease. Typically, its identification is based on motor disorders, while the computer estimation of its main symptoms with computational machine learning (ML) has a high exposure which is supported by researches conducted. Nevertheless, ML approaches required first to refine their parameters and then to work with the best model generated. This process often requires an expert user to oversee the performance of the algorithm. Therefore, an attention is required towards new approaches for better forecasting accuracy.

To provide an available identification model for Parkinson disease as an auxiliary function for clinicians, the authors suggest a new evolutionary classification model. The core of the prediction model is a fast learning network (FLN) optimized by a genetic algorithm (GA). To get a better subset of features and parameters, a new coding architecture is introduced to improve GA for obtaining an optimal FLN model.

The proposed model is intensively evaluated through a series of experiments based on Speech and HandPD benchmark datasets. The very popular wrappers induction models such as support vector machine (SVM), K-nearest neighbors (KNN) have been tested in the same condition. The results support that the proposed model can achieve the best performances in terms of accuracy and g-mean.

A novel efficient PD detection model is proposed, which is called A-W-FLN. The A-W-FLN utilizes FLN as the base classifier; in order to take its higher generalization ability, and identification capability is also embedded to discover the most suitable feature model in the detection process. Moreover, the proposed method automatically optimizes the FLN's architecture to a smaller number of hidden nodes and solid connecting weights. This helps the network to train on complex PD datasets with non-linear features and yields superior result.

This research investigates the link between corporate social responsibility (CSR) activities and bank risk-taking in Vietnam and introduces the constraint factor to see whether this link alters with different levels of constraint.

Using a sample of commercial banks in Vietnam from 2008 to 2017, this study employs two-step system generalized method of moments (Sys GMM) with a finite sample correction mechanism to estimate the models.

The results suggest that CSR activities reduce bank risk-taking, and this relationship is only present in the case of financially constrained banks. Unconstrained banks, on the other hand, are more likely to invest in unnecessary CSR, thus reducing bank performance and increasing bank risk-taking.

The first implication from this study is that CSR activities might be considered as a risk-mitigating tool and should be invested in that respect. Secondly, regulatory units and investors should be more cautious about CSR expenditures since this type of spending could increase default risk, especially for banks with easy access to external financing. One particular limitation of this study is the low number of observations available for banks in Vietnam. Future studies could use texture analysis to expand the sample or consider macro-level governance characteristics to examine which factors might modify the relationship between CSR and bank risk.

Very limited studies discussed the link between corporate social responsibility and bank performance and bank risk. There are even fewer papers examining the relationship between CSR and risk, and most of these papers deal with advanced economies. Furthermore, no studies investigate the interaction effect of CSR and financial constraint, which should be prevalent in developing countries on bank risk. As a consequence, the current study seeks to verify the impact of financial constraints on the link between CSR and bank risk.

This research investigated whether corporate social responsibility (CSR) can alleviate the negative effect of non-performing loans (NPLs) on bank performance.

The research employed a sample of European banks over the 2008–2017 period. To resolve endogeneity and heterogeneity problems, the system generalized method of moments (SGMM) model was employed.

First, bank NPLs were negatively and significantly associated with bank performance as measured by the Q-Tobin ratio and the return on assets (ROA). Second, CSR scores exerted a negative and significant effect on the level of NPLs. Finally, the results indicated that bank performance could benefit from the interactional effect of CSR and NPLs.

This study fills the gap in the debate over the mediating role of CSR in the NPLs – bank performance interrelation. In addition, our SGMM analysis yielded more robust and efficient results while resolving endogeneity and heterogeneity problems concerning CSR and bank performance or risk in corporate finance.

CSR practices can play an essential mediating role in the NPLs–bank performance relationship. CSR activities in the European context may reduce the level of NPLs and increase bank performance.

To the best of the authors’ knowledge, studies of the implications of CSR activities on the banking sector are very limited. Indeed, this paper shows that CSR mediates the relationship between CSR practices and NPLs. The results suggest that bank performance could benefit from the interactional effect of CSR and NPLs.