Search

Semi-supervised anomaly detection for sensor signals is critical in ensuring system reliability in smart manufacturing. However, existing methods rely heavily on data correlation, neglecting causality and leading to potential misinterpretations due to confounding factors. Moreover, while current reinforcement learning-based methods can effectively identify known and unknown anomalies with limited labeled samples, these methods still face several challenges, such as under-utilization of priori knowledge, lack of model flexibility, and deficient reward feedback during environmental interactions. To address the above problems, this paper innovatively constructs a counterfactual causal reinforcement learning model, termed Triple-Assisted Causal Reinforcement Learning Anomaly Detector (Tri-CRLAD). The model leverages causal inference to extract the intrinsic causal feature in data, enhancing the agent's utilization of prior knowledge and improving its generalization capability. In addition, Tri-CRLAD features a triple decision support mechanism, including a sampling strategy based on historical similarity, an adaptive threshold smoothing adjustment strategy, and an adaptive decision reward mechanism. These mechanisms further enhance the flexibility and generalization ability of the model, enabling it to effectively respond to various complex and dynamically changing environments. Experimental results across seven diverse sensor signal datasets demonstrate that Tri-CRLAD outperforms nine state-of-the-art baseline methods. Notably, Tri-CRLAD achieves up to a 23\% improvement in anomaly detection stability with minimal known anomaly samples, highlighting its potential in semi-supervised anomaly detection scenarios. Our code is available at https://github.com/Aoudsung/Tri-CRLAD.

Social insects are ecologically and evolutionarily most successful organisms on earth, which can achieve robust collective behaviors through local interactions among group members. Colony migration has been considered as a leading example of collective decision-making in social insects. In this paper, a piecewise colony migration system with recruitment switching is proposed to explore underlying mechanisms and synergistic effects of colony size and quorum on the outcomes of collective decision. The completed dynamical analysis for the non-smooth system (including the dynamics on subsystems, switching surface, and full system) is performed, and the sufficient conditions significantly related to colony size for the stability of equilibria are provided. The theoretical results suggest that large colonies are more likely to emigrate to a new site. More interesting findings include but not limit to: (a) the system may exhibit oscillation when the colony size is below a critical level; (b) the system may also exhibit a bistable state, and colonies migrate to a new site or the old nest depending on their initial sizes of recruiters. Bifurcation analysis shows that the variations of colony size and quorum threshold greatly impact the dynamics. The results suggest that it is important to distinguish two populations of recruiters in modeling. This work may provide important insights on how simple and local interactions achieve the collective migrating activity in social insects.

Considering feedback of collective actions of cooperation on common resources has vital importance to reach sustainability. But such efforts may have not immediate consequence on the state of environment and it is unclear how they influence the strategic and environmental dynamics with feedbacks. To address this issue, we construct a feedback-evolving game model in which we consider the growth capacity of resources and the punishment efficiency on defectors who do not provide returns to the environment. Importantly, we further assume a delay in adopting the contribution of cooperative individuals to environmental change in our model. We find that when this contribution amount from cooperators' endowment is fixed, the time delay has no particular consequence on the coevolutionary dynamics. However, when the return is proportional to their endowment, then the time delay can induce periodic oscillatory dynamics of cooperation level and environment. Our work reveals the potential effects of time delay of cooperative actions on the coevolutionary dynamics in strategic interactions with environmental feedback.