Topic
Greedy algorithm
About: Greedy algorithm is a research topic. Over the lifetime, 15347 publications have been published within this topic receiving 393945 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: In this paper, the problem of scheduling in single-hop wireless networks with real-time traffic is studied, where every packet arrival has an associated deadline and a minimum fraction of packets must be transmitted before the end of the deadline.
Abstract: This paper studies the problem of scheduling in single-hop wireless networks with real-time traffic, where every packet arrival has an associated deadline and a minimum fraction of packets must be transmitted before the end of the deadline. Using optimization and stochastic network theory we study the problem of scheduling to meet quality of service (QoS) requirements under heterogeneous delay constraints and time-varying channel conditions. Our analysis results in an optimal scheduling algorithm which fairly allocates data rates to all flows while meeting long-term delay demands. We also prove that under a simplified scenario our solution translates into a greedy strategy that makes optimal decisions with low complexity.
90 citations
TL;DR: This paper augments activity and data detection for frame-based multi-user uplink scenarios where users are (in)-active for the duration of a frame, namely, the frame-wise joint sparsity model.
Abstract: Grant-free non-orthogonal multiple access has recently gained significant attention for reducing signaling overhead in machine-type communications. In this context, compressed sensing (CS) has been identified as a good candidate for joint activity and data detection due to the inherent sparsity nature of user activity. This paper augments activity and data detection for frame-based multi-user uplink scenarios where users are (in)-active for the duration of a frame, namely, the frame-wise joint sparsity model. First, we formulate the block CS (BCS)-based sparse signal recovery framework, by fully extracting and exploiting the underlying frame-wise joint sparsity of the user activity. Then, to make explicit use of the block sparsity inherent in the equivalent block-sparse model and considering the user sparsity level to be unknown for multiuser detection, two enhanced BCS-based greedy algorithms are developed, i.e., threshold aided block sparsity adaptive subspace pursuit (TA-BSASP) and cross-validation aided block sparsity adaptive subspace pursuit (CVA-BSASP). Specifically, the proposed TA-BSASP algorithm can approach the oracle least squares (LS) performance by reasonably setting the threshold based on the additive white Gaussian noise floor. Moreover, the proposed CVA-BSASP algorithm is a highly practical algorithm design that adopts the statistical and machine learning mechanism cross-validation to determine the stopping condition of the algorithm and this does not require prior knowledge. Furthermore, the convergence and the computational complexity of the proposed algorithms are derived and the superior performance of the proposed algorithms is demonstrated by numerical experiments.
90 citations
01 May 1990
TL;DR: The algorithm is a generalization of an algorithm for graph optimal isomorphism, and its potential for engineering application is demonstrated by a simple structural pattern recognition problem and a plant allocation and distribution problem.
Abstract: An algorithm for finding the optimal monomorphism between two attributed graphs is proposed. The problem is formulated as a tree search problem. To guide the search the branch-and-bound heuristic approach is adopted, using an efficient consistent lower bounded estimate for the evaluation function of the cost associated with the optimal solution path in the search tree. The algorithm is a generalization of an algorithm for graph optimal isomorphism. The algorithm's potential for engineering application is demonstrated by a simple structural pattern recognition problem and a plant allocation and distribution problem. >
90 citations
TL;DR: This paper considers the problem of calculating near-optimal routes for MAs that incrementally aggregate the data as they visit the nodes in a distributed sensor network and follows a greedy-like approach always selecting the next node to be included in an itinerary in such a way that the cost of the so far formed itineraries is kept minimum at each step.
Abstract: A key feature of wireless sensor networks (WSNs) is the collaborative processing, where the correlation existing over the local data of sensor nodes (SNs) is exploited so that the total data volume can be reduced (data aggregation). The use of Mobile Agents (MAs), i.e., software entities able of migrating among nodes and resuming execution naturally, fits in this scenario; the local data of an SN can be combined with the data collected by an MA from other SNs in a way that depends on the specific program code of the MA. In this paper, we consider the problem of calculating near-optimal routes for MAs that incrementally aggregate the data as they visit the nodes in a distributed sensor network. Our algorithm follows a greedy-like approach always selecting the next node to be included in an itinerary in such a way that the cost of the so far formed itineraries is kept minimum at each step. Simulation results confirm the high effectiveness of the proposed algorithm as well as its performance gain over alternative approaches. Also, with the use of proper data structures, the computational complexity of the algorithm is kept low as it is formally proved in the paper.
90 citations
TL;DR: A greedy heuristic and a fix-and-optimize heuristic based on simulated annealing and exact methods are proposed to solve the budget-constrained dynamic facility location–network design problem (DUFLNDP).
90 citations