ABSTRACT
As a promising paradigm, mobile crowdsensing (MCS) takes advantage of sensing abilities and cooperates with multi-agent reinforcement learning technologies to provide services for users in large sensing areas, such as smart transportation, environment monitoring, etc. In most cases, strategy training for multi-agent reinforcement learning requires substantial interaction with the sensing environment, which results in unaffordable costs. Thus, environment reconstruction via extraction of the causal effect model from past data is an effective way to smoothly accomplish environment monitoring. However, the sensing environment is often so complex that the observable and unobservable data collected are sparse and heterogeneous, affecting the accuracy of the reconstruction. In this paper, we focus on developing a robust multi-agent environment monitoring framework, called self-interested coalitional crowdsensing for multi-agent interactive environment monitoring (SCC-MIE), including environment reconstruction and worker selection. In SCC-MIE, we start from a multi-agent generative adversarial imitation learning framework to introduce a new self-interested coalitional learning strategy, which forges cooperation between a reconstructor and a discriminator to learn the sensing environment together with the hidden confounder while providing interpretability on the results of environment monitoring. Based on this, we utilize the secretary problem to select suitable workers to collect data for accurate environment monitoring in a real-time manner. It is shown that SCC-MIE realizes a significant performance improvement in environment monitoring compared to the existing models.
ABSTRACT
Sulforaphane (SFN) is a natural isothiocyanate derived from cruciferous vegetables such as broccoli, Brussels sprouts, and cabbage. SFN plays a crucial role in maintaining redox homeostasis by interacting with the active cysteine residues of Keap1, leading to the dissociation and activation of NRF2 in various diseases. In this study, our objective was to investigate the impact of SFN on oxidative stress and pyroptosis in Mycobacterium tuberculosis (Mtb)-infected macrophages. Our findings demonstrated that Mtb infection significantly increased the production of iNOS and ROS, indicating the induction of oxidative stress in macrophages. However, treatment with SFN effectively suppressed the expression of iNOS and COX-2 and reduced MDA and ROS levels, while enhancing GSH content as well as upregulating NRF2, HO-1, and NQO-1 expression in Mtb-infected RAW264.7 macrophages and primary peritoneal macrophages from WT mice. These results suggest that SFN mitigates oxidative stress by activating the NRF2 signaling pathway in Mtb-infected macrophages. Furthermore, excessive ROS production activates the NLRP3 signaling pathway, thereby promoting pyroptosis onset. Further investigations revealed that SFN effectively suppressed the expression of NLRP3, Caspase-1, and GSDMD, IL-1ß, and IL-18 levels, as well as the production of LDH, suggesting that it may exhibit anti-pyroptotic effects through activation of the NRF2 signaling pathway and reductions in ROS production during Mtb infection. Moreover, we observed that SFN also inhibited the expression of NLRP3, ASC, Caspase1, and IL-1ß along with LDH production in Mtb-infected primary peritoneal macrophages from NFR2-/- mice. This indicates that SFN can directly suppress NLRP3 activation and possibly inhibit pyroptosis initiation in an NRF2-independent manner. In summary, our findings demonstrate that SFN exerts its inhibitory effects on oxidative stress by activating the NRF2 signaling pathway in Mtb-infected macrophages, while it may simultaneously exert anti-pyroptotic properties through both NRF2-dependent and independent mechanisms targeting the NLRP3 signaling pathway.