Predicting public opinion trends during major infectious disease outbreaks is critical for guiding effective public health responses. However, predicting public opinion remains challenging because it is influenced by socio-economic, psychological, and media factors. This paper presents a novel framework for predicting public opinion trends related to significant infectious diseases, with a focus on COVID-19 as a case study. The proposed framework identifies the key factors influencing public opinion development and enables both point and interval predictions. The framework uses information ecology theory and applies the NSGA-II algorithm to select the features that best drive public opinion trends. By incorporating this framework, accurate point forecasts are produced alongside prediction intervals, effectively quantifying the uncertainty inherent in public opinion dynamics. This approach minimizes the quality-driven loss function to generate precise prediction intervals, providing decision-makers with critical insights into public opinion fluctuations during epidemics. The results offer valuable, real-time public sentiment warnings, supporting timely and effective interventions in epidemic prevention and control efforts.

To address the limitations of traditional product and service models and meet consumers’ demands for personalized, intelligent, and seamless experiences, the Smart Product Service Ecosystem (SPSE) has recently garnered increasing attention as a new business model. Ensuring its stable operation is crucial to maintain competitiveness and achieve long-term sustainability. The stability of the SPSE is conceptualized as the outcome of the interconnectedness and co-evolution of multiple factors. Therefore, identifying key factors affecting stability and implementing targeted measures are key to maintaining stable system operation and continuous optimization. In this study, through a comprehensive literature review and analysis of the system’s operating logic, 36 factors affecting the stability of the SPSE are identified based on the dimensions of structure, function, mechanism and benefit. Given the strengths of the ORESTE method and its traditional model’s limitations in fully leveraging decision-making information, this paper proposes a CN-PF-ORESTE model to rank these stability factors. Complex network (CN) captures the correlation among factors and objectively measures the relative importance of factors through the centrality index. Pythagorean fuzzy sets (PF) can deal with the ambiguity of attribute evaluation information. The improved ORESTE model takes into account both the subjective analysis of the expert’s empirical judgment and the objective analysis of the information structure. Finally, the implementation process of the method is illustrated with an example of Smart Home Product Service Ecosystem (SHSE), and the comparative analysis and discussions are conducted to demonstrate its rationality and flexibility.

Traffic accidents are unexpected incidents where one or multiple vehicles collide and damage properties, dying or injuring many individuals. It causes significant social burdens, including loss of life, serious injuries, and economic suppression from medical costs, property damages, and productivity losses. This kind of incident brings a miserable situation for the affected people. Many factors, including infrastructure, weather, vehicles, or driver-related issues, contribute to happening traffic accidents. This work explores an innovative approach by investigating contributing factors to ensure road safety. In this study, an ensemble machine learning model, namely Weighted Fusion-Based Feature Selection (WFFS), was proposed to identify different significant features to reduce the effects of traffic accidents. A large amount of traffic accident records from the United Kingdom (UK) were gathered and split into several folds, which were cleaned and balanced using different techniques such as removing percentages, Synthetic Minority Oversampling Technique (SMOTE), and random oversampling. Then, WFFS were employed in each fold and identified the most significant features to predict traffic accident severity more accurately. Different classifiers, such as tree-based, bagging, boosting, and voting classifiers, were implemented into WFFS-generated feature subsets and performed better than primary data and other feature subsets. In this case, the random tree-based bagging method provided the highest accuracy of 97.28% to predict accident severity for the WFFS subset, where its number of features is 18. However, different classifiers achieved better accuracies for 6 out of 11 times using WFFS. This method is highly recommended for policymakers and transportation engineers to identify potentially hazardous locations and take appropriate measures to diminish the effects of traffic accidents.

In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect classifier performance. Traditional data balancing methods can lead to overfitting and underfitting, making it difficult to identify potential health risks accurately. Early prediction of heart attacks is of paramount importance, and researchers have developed ML-based systems to address this problem. However, much of the existing ML research is based on a single dataset, often ignoring performance evaluation across multiple datasets. As the demand for interpretable ML models grows, model interpretability becomes central to revealing insights and feature effects within predictive models. To address these challenges, we present a novel data balancing technique that uses a divide-and-conquer strategy with the K-Means clustering algorithm to segment the dataset. The performance of our approach is highlighted through comparisons with established techniques, which demonstrate the superiority of our proposed method. To address the challenge of inter-dataset discrepancies, we use two different datasets. Our holistic pipeline, strengthened by the innovative balancing technique, effectively addresses performance discrepancies, culminating in a significant improvement from 81% to 90%. Furthermore, through advanced statistical analysis, it has been determined that the 95% confidence interval for the AUC metric of our method ranges from 0.8187 to 0.8411. This observation serves to underscore the consistency and reliability of our approach, demonstrating its ability to achieve high performance across a range of scenarios. Incorporating Explainable AI (XAI), we examine the feature rankings and their contributions within the best performing Random Forest model. While the domain expert feedback is consistent with the explanatory power of XAI, some differences remain. Nevertheless, a remarkable convergence in feature ranking and weighting is observed, bridging the insights from XAI tools and domain expert perspectives.

The proliferation of multimodal data provides a valuable repository of information for financial distress prediction. However, the use of multimodal data faces critical challenges, such as heterogeneity within and among modalities and difficulties in discriminating complementary and redundant information among modalities. To this end, we propose an attentive and regularized deep learning method for predicting financial distress using multimodal data, including financial indicators, current reports, and interfirm networks. Specifically, considering heterogeneity within and among modalities, we design three modality-specific attentions, i.e., ratio-aware, report-aware, and neighbor-aware attentions, for adaptively extracting key information from financial indicators, current reports, and interfirm networks, respectively. Considering difficulties in discriminating complementary and redundant information among modalities, we design a conditional entropy-based regularization to guide the method focusing on complementary information while discarding redundant information during modality fusion. We also propose the use of focal loss to address the class imbalance problem. Empirical evaluation shows that the proposed method significantly outperformed all benchmarked methods in terms of predictive and representation performance. We also provide key findings and implications for stakeholders.

Carbon emissions trading has become an increasingly hot topic nowadays, due to the fact that how to reduce carbon emissions has been a common effort of different countries. However, traditional methods are plagued by issues, such as inadequate privacy protection mechanisms and the challenge of representing data assets in a comprehensive form using blockchain data models. In this article, we propose carbon emissions trading scheme (CETS), a secure carbon emissions trading system using blockchain combined with digital assets transactions. The proposed CETS scheme enhances the performance of models for carbon emissions trading by prioritizing the efficiency, privacy, and traceability of carbon emissions trading. Simultaneously, it improves the consistency of digital asset trading throughout the chain. First, we propose a dual-blockchain-based method for storing and tracing carbon emission data, which ensures the privacy of the data. Next, we propose algorithms for transaction of digital assets in carbon emission trading scheme, which include digital asset uniqueness algorithm, serializable mechanism, and cross-chain algorithm of digital assets. Finally, we propose an automated machine learning pipeline approach based on the carbon trading price forecasting model construction method, which can provide efficient, automatic price forecasting model construction and training. The experimental results prove that our proposed carbon emission trading system can provide an efficient and stable carbon emission trading solution.

In this article, we aim to design an architecture for privacy-preserved credit data and model sharing to guarantee the secure storage and sharing of credit information in a distributed environment. The proposed architecture optimizes the data privacy by sharing the data model instead of revealing the actual data. This article also proposes an efficient credit data storage mechanism combined with a deletable Bloom filter to guarantee a uniform consensus for the training and computation process. In addition, we propose authority control contract and credit verification contract for the secure certification of credit sharing model results under federated learning. Extensive experimental results and security analysis demonstrate that our proposed credit model sharing system based on federated learning and blockchain is of high accuracy, efficiency, as well as stability. In particular, the findings of this article could alleviate the potential credit crisis under financial pressure that assist to economic recovery after the global COVID-19 pandemic. Our approach has further boosted up the demand for efficient, secure credit models for Industry 4.0.