Compressed sensing technology is one of the effective techniques to effectively reduce the amount of data transmission in wireless sensor networks. Compressed sensing technology can reduce the amount of data that a node undertakes from n to m, where m n, but we still hope to further reduce the amount of data that the node bears to improve network lifetime. In this paper, a Compressive Sensing based Clustering Joint Annular Routing Data Gathering (CS-CARDG) scheme is proposed to improve the network life. The key technology adopted by CS-CARDG scheme is: data is collected by cluster. The network first forms a cluster, and each node in the cluster sends the data packet to the cluster head. Each cluster forms mdimensional data according to the requirements of the compressed sensing technology to ensure that the data can be recovered. When the cluster head node routes the m-dimensional data to the sink, the CS-CARDG scheme adopts a two-stage routing scheme with the same ring routing and shortest path that is completely different from the previous scheme. The same ring routing means that the cluster heads with the same number of sink hops are routed around the ring for one week to route the compressed sensing data of the same ring to a node in the ring. In this way, each sub-dimension data in the same ring is routed to the corresponding node of each ring through the same-loop route, and then the shortest-circuit strategy of the second phase is started. That is, from the outermost ring, the same fractal data is sequentially compressed from the outside to the inside, and is routed to the sink by the shortest path. In this round of data collection, the number of data packets that the nodes in the near-sink one-hop range bears is only m, and the nodes in the near-sink region directly send data to the sink node, thereby reducing the amount of data that the node bears to m k + 1, where k is the number of nodes within the node's broadcast radius.. In this paper, the compressed sensing strategies proposed in the past are compared by detailed theoretical analysis. The theoretical analysis results show that the CS-CARDG strategy proposed in this paper can effectively reduce the amount of data carried by nodes. This scheme reduces the amount of data in the network from 1Reduced the amount of data by at least 20%. In the network with R = 480 m, the energy utilization rate can reach more than 90%.INDEX TERMS Wireless sensor networks, annular routing, compressed sensing, clustering, energy utilization.The associate editor coordinating the review of this article and approving it for publication was Yuyu Yin. according Ref. [5]. The current sensing-based devices have far exceeded the number of humans, and are growing at a rapid rate. With the development of microprocessor technology [6], the computing and storage capabilities of these sensing-based devices have been greatly
Reinforcement Learning (RL) based machine trading attracts a rich profusion of interest. However, in the existing research, RL in the day-trade task suffers from the noisy financial movement in the short time scale, difficulty in order settlement, and expensive action search in a continuous-value space. This paper introduced an end-to-end RL intraday trading agent, namely QF-TraderNet, based on the quantum finance theory (QFT) and deep reinforcement learning. We proposed a novel design for the intraday RL trader’s action space, inspired by the Quantum Price Levels (QPLs). Our action space design also brings the model a learnable profit-and-loss control strategy. QF-TraderNet composes two neural networks: 1) A long short term memory networks for the feature learning of financial time series; 2) a policy generator network (PGN) for generating the distribution of actions. The profitability and robustness of QF-TraderNet have been verified in multi-type financial datasets, including FOREX, metals, crude oil, and financial indices. The experimental results demonstrate that QF-TraderNet outperforms other baselines in terms of cumulative price returns and Sharpe Ratio, and the robustness in the acceidential market shift.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.