Data Streams create new challenges for fuzzy clustering algorithms, specifically Interval Type-2 Fuzzy C-Means (IT2FCM). One problem associated with IT2FCM is that it tends to be sensitive to initialization conditions and therefore, fails to return global optima. This problem has been addressed by optimizing IT2FCM using Ant Colony Optimization approach. However, IT2FCM-ACO obtain clusters for the whole dataset which is not suitable for clustering large streaming datasets that may be coming continuously and evolves with time. Thus, the clusters generated will also evolve with time. Additionally, the incoming data may not be available in memory all at once because of its size. Therefore, to encounter the challenges of a large data stream environment we propose improvising IT2FCM-ACO to generate clusters incrementally. The proposed algorithm produces clusters by determining appropriate cluster centers on a certain percentage of available datasets and then the obtained cluster centroids are combined with new incoming data points to generate another set of cluster centers. The process continues until all the data are scanned. The previous data points are released from memory which reduces time and space complexity. Thus, the proposed incremental method produces data partitions comparable to IT2FCM-ACO. The performance of the proposed method is evaluated on large real-life datasets. The results obtained from several fuzzy cluster validity index measures show the enhanced performance of the proposed method over other clustering algorithms. The proposed algorithm also improves upon the run time and produces excellent speed-ups for all datasets.
Growing concerns regarding climate change and the necessity to shift towards a low-carbon economy have resulted in a significant rise in the worth of green finance for developing energy technology. This growing emphasis on green finance underscores the urgency for a nuanced exploration of the asymmetric nexus between green investment and energy innovation in Europe. The present article investigates the asymmetric relationship between green investment and energy innovation in the top ten European nations with the highest green investment (France, Netherlands, Germany, Italy, Spain, Denmark, Austria, Finland, the UK, and Sweden). Formerly, panel data methodologies were employed to observe the link between green investment and energy innovation despite the absence of an exclusive connection in certain economies. On the other hand, this study uses 'Quantile-on-Quantile' approach for econometric estimation using the annual data from 2007 to 2022. This unique methodology enables a detailed and specific analysis of time-series interdependence in every economy, providing valuable perceptions of the nuanced relationship between these variables. Investment in renewable energy is employed as a proxy for green investment, while energy-related patents represent energy innovation. The study employs a quantile cointegration test to assess the variables long-run relationship. The results indicate a positive correlation between green investment and energy innovation in many countries at certain data points. Additionally, the analysis demonstrates that the extent of asymmetry between these variables varies across countries, stressing policymakers' need to closely monitor fluctuations in green investment and energy innovation.
This study examines the role of a private standard on corporate social responsibility (CSR) compliance in the Pakistani mango industry and how this compliance affects rural workers' motivation. Pakistan is the fifth largest mango producer in the world and the fourth largest exporter in global mango trade; also, mango is the biggest fruit crop within the country. Mango trade is subject to trade terms, where buyers decide the conditions of trade agreements by means of codes of conduct. The key dimensions of the codes involved in agrofood trade are food safety, traceability, worker welfare, and environmental consideration, issues which are all connected with CSR. Private standards ensure compliance with these codes of conduct. This study draws on interviews and a questionnaire survey with certified mango producers and farm workers in Pakistan. The mango industry also involves other stakeholders such as government institutes and NGOs; interviews were also conducted with their representatives. Given that this study is an impact assessment research, the researcher designed a theoretical framework using a mixed method approach to investigate the rationale behind acquiring the standard by the mango growers in Pakistan and what impact (if any) this shift has generated with regard to the farm workers' job satisfaction and motivation. This study is the first to empirically examine good agricultural practices in Pakistan and evaluate their impact. This study shows that private standards play a significant role in ensuring compliance, and CSR practices implemented through them were found to be positively related to the rural workers' job satisfaction and motivation. Furthermore, this study has made separate contributions to theory, methodology, and practice. The production of the synergistic model for improving compliance is among the key highlights of the study. The findings of this study can extend to other agriculture and primary production industry workers in Pakistan and even beyond to other developing countries' rural agriculture workers.
E-shopping is a rapidly growing phenomenon among different individuals who intend to shop online. However, a trust deficit in the E-shopping environment has always been a critical issue in the brick-and-click mode of shopping, being one of the main reasons for E-cart abandonment in E-commerce. This empirical study is aimed at investigating the perceived effect of website trust on E-shopping intentions and behaviour, drawing upon the theory of planned behaviour (TPB). Data were collected through self-administered questionnaires from working adults who shop for garments online. Structural equation modelling was used to evaluate the model fit and assumptions. Our findings suggest that website trust and E-shopping attitude play substantial roles in building E-shopping intentions and actual behaviours. Both are the significant predictors of the behaviour mediated by E-shopping intentions. However, E-shopping intentions did not mediate between subjective norms and E-shopping behaviour, when working adults decide to purchase garments online.
Air pollution is the existence of atmospheric chemicals damaging the health of human beings and other living organisms or damaging the environment or resources. Rarely any common contaminants are smog, nicotine, mold, yeast, biogas, or carbon dioxide. The paper will primarily observe, visualize and anticipate pollution levels. In particular, three algorithms of Artificial Intelligence were used to create good forecasting models and a predictive AQI model for 4 distinct gases: carbon dioxide, sulphur dioxide, nitrogen dioxide, and atmospheric particulate matter. Thus, in this paper, the Air Qualification Index is developed utilizing Linear Regression, Support Vector Regression, and the Gradient Boosted Decision Tree GBDT Ensembles model over the next 5 h and analyzes air qualities using various sensors. The hypothesized artificial intelligence models are evaluated to the Root Mean Squares Error, Mean Squared Error and Mean absolute error, depending upon the performance measurements and a lower error value model is chosen. Based on the algorithm of the Artificial Intelligent System, the level of 5 air pollutants like CO2, SO2, NO2, PM 2.5 and PM10 can be predicted immediately by integrating the observations with errors. It may be used to detect air quality from distance in large cities and can assist lower the degree of environmental pollution.
Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community's behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency-inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques.