Human beings live in a world full of risks, from minor risks such as colds and fevers to major crises such as economic crises and hurricanes. How to cope with these risks is a constant topic in the evolution of humankind. The impact of various characteristics of risk on the risk-resistance outcomes has been well studied, including the probability, intensity and spread of risks. However, as an additional dimension independent of the above main characteristics, risk-resistance solutions that are appropriate to the risk have not received sufficient attention. We abstract this characteristic as the relative cost-effectiveness between collective solution and individual solution in resisting a risk and name it communality. Taking communality and intensity as the two main characteristics of risk, we propose a risk-resistance model and explore the critical impact of risk communality on the outcomes of risk resistance. Using numerical analysis, we map the state transition of the population on a two-dimensional surface consisting of communality and intensity. Simulation experiments validate the results from numerical analysis and reveal four regions in this surface, each of which corresponds to a governance structure endogenous to the population. The complex impact of population-endogenous governance structures on the risk-resistance outcomes reflects the real-world challenges of risk governance. This article suggests that social governors need to implement different logics in the face of risks with different communalities.

Anomaly detection has emerged as one of the core research topics to support workflow applications across various domains. To differentiate anomalies from underlying normal patterns of workflows, Graph Neural Networks (GNNs) models have been introduced. These models leverage time series data to construct graph structures, in order to explicitly capture task dependencies among industrial Internet of Things (IoT) devices, and thus, to identify deviations from predicted behaviours as anomalies. However, existing forecasting-based anomaly detection methods may not accurately detect certain anomalies, since they have seldom considered valuable information uncovered by historical sensory data, but presented as domain knowledge. To address this limitation, this paper proposes a Knowledge-enhanced graph attention-based Anomaly Detection (KeAD) method. Specifically, a knowledge-enhanced graph structure is constructed by incorporating domain-specific knowledge to represent spatio-temporal dependencies between IoT devices. Based on which, a knowledge-enhanced graph attention-based forecasting network is developed to predict the future behaviours of IoT devices. Anomalies, such as those caused by cyber-attacks in workflows, are detected by analyzing deviations from these predicted behaviours in conjunction with domain-specific knowledge. A case study is presented, along with extensive experiments conducted on publicly available datasets. Evaluation results demonstrate that KeAD outperforms the state-of-the-art techniques in terms of anomaly detection accuracy.

Anomaly detection is a long-standing research topic to support the prompt remedy of potential risks for dependency-aware tasks, where Graph Neural Networks (GNNs) models have been adopted to differentiate anomalies from normal patterns. Generally, GNN models utilize time series data to construct graph structures for capturing task dependencies between Internet of Things (IoT) devices, such that deviations from predicted behaviours are assumed as anomalies. Current forecasting-based anomaly detection methods can hardly detect anomalies, which are uncovered by historical sensory data, but are explicitly specified by domain knowledge. To solve this issue, this paper proposes a Knowledge-enhanced graph attention-based Anomaly Detection (KeAD) method. Specifically, a knowledge-enhanced graph structure is constructed by incorporating domain-specific knowledge to represent spatio-temporal dependencies between IoT devices. Thereafter, a knowledge-enhanced graph attention-based forecasting network is developed to predict future behaviours of IoT devices. Anomalies are detected by analyzing deviations from these predicted behaviours, taking domain-specific knowledge into account. Extensive experiments are conducted based on publicly-available datasets, and evaluation results demonstrate that our KeAD outperform the state-of-the-art techniques in terms of the accuracy of anomaly detection.

Currently, e-commerce is being applied more and more widely in daily life. However, how to give an accurate, real-time and low-cost estimation of online retail sales is still a difficult problem from both academic and industrial aspects. This paper presents an efficient method for the estimation of online retail sales that is characterized by an order detection algorithm embedded in distributed clients to detect transaction amounts of successful orders. The proposed order detection algorithm is a kind of logistic regression classifier based on web semantic features, which divides web pages into three categories: ordinary pages, order placement pages and order confirmation pages. A further 10-fold validation is conducted and proves the algorithm is quite effective.