Matches in SemOpenAlex for { <https://semopenalex.org/work/W2735961282> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2735961282 abstract "As one of the most recognized models in machine learning, the conditional random fields (CRF) has been widely used in many applications. As the parameter estimation of CRF is highly time-consuming, how to improve the performance of CRF has received significant attention, in particular in the big data environment. To deal with large-scale data, CPU-based or GPU-based parallelization solutions have been proposed to improve performance. However, the problem is an ongoing one. In this paper, we focus on the big data environment and propose a distributed CRF on a heterogeneous CPU-GPU cluster called DHCRF. Our approach differs from previous work. Specifically, it leverages a three-stage heterogeneous Map and Reduce operation to improve the performance, making full use of CPU-GPU collaborative computing capabilities in a big data environment. Furthermore, by combining elastic data partition and intermediate results multiplexing method, the distributed CRF is optimized. Elastic data partition is performed to keep the load balanced, and the intermediate results multiplexing method is adopted to reduce data communication. Experimental results show that the DHCRF outperforms the baseline CRF algorithm and the CPU-based parallel CRF algorithm with notable performance improvement while maintaining competitive correctness at the same time." @default.
- W2735961282 created "2017-07-21" @default.
- W2735961282 creator A5011482738 @default.
- W2735961282 creator A5031690201 @default.
- W2735961282 creator A5062903694 @default.
- W2735961282 creator A5078793726 @default.
- W2735961282 creator A5087894632 @default.
- W2735961282 date "2017-06-01" @default.
- W2735961282 modified "2023-09-23" @default.
- W2735961282 title "DHCRF: A Distributed Conditional Random Field Algorithm on a Heterogeneous CPU-GPU Cluster for Big Data" @default.
- W2735961282 cites W1997187731 @default.
- W2735961282 cites W2005228904 @default.
- W2735961282 cites W2034164729 @default.
- W2735961282 cites W2036343664 @default.
- W2735961282 cites W2057383669 @default.
- W2735961282 cites W2114361266 @default.
- W2735961282 cites W2129232371 @default.
- W2735961282 cites W2147880316 @default.
- W2735961282 cites W2159329043 @default.
- W2735961282 cites W2523064693 @default.
- W2735961282 cites W588342568 @default.
- W2735961282 doi "https://doi.org/10.1109/icdcs.2017.66" @default.
- W2735961282 hasPublicationYear "2017" @default.
- W2735961282 type Work @default.
- W2735961282 sameAs 2735961282 @default.
- W2735961282 citedByCount "3" @default.
- W2735961282 countsByYear W27359612822019 @default.
- W2735961282 countsByYear W27359612822021 @default.
- W2735961282 crossrefType "proceedings-article" @default.
- W2735961282 hasAuthorship W2735961282A5011482738 @default.
- W2735961282 hasAuthorship W2735961282A5031690201 @default.
- W2735961282 hasAuthorship W2735961282A5062903694 @default.
- W2735961282 hasAuthorship W2735961282A5078793726 @default.
- W2735961282 hasAuthorship W2735961282A5087894632 @default.
- W2735961282 hasConcept C11413529 @default.
- W2735961282 hasConcept C114614502 @default.
- W2735961282 hasConcept C119857082 @default.
- W2735961282 hasConcept C120314980 @default.
- W2735961282 hasConcept C124101348 @default.
- W2735961282 hasConcept C152565575 @default.
- W2735961282 hasConcept C154945302 @default.
- W2735961282 hasConcept C173608175 @default.
- W2735961282 hasConcept C19275194 @default.
- W2735961282 hasConcept C33923547 @default.
- W2735961282 hasConcept C41008148 @default.
- W2735961282 hasConcept C42812 @default.
- W2735961282 hasConcept C49154492 @default.
- W2735961282 hasConcept C55439883 @default.
- W2735961282 hasConcept C73555534 @default.
- W2735961282 hasConcept C75684735 @default.
- W2735961282 hasConcept C76155785 @default.
- W2735961282 hasConcept C9390403 @default.
- W2735961282 hasConceptScore W2735961282C11413529 @default.
- W2735961282 hasConceptScore W2735961282C114614502 @default.
- W2735961282 hasConceptScore W2735961282C119857082 @default.
- W2735961282 hasConceptScore W2735961282C120314980 @default.
- W2735961282 hasConceptScore W2735961282C124101348 @default.
- W2735961282 hasConceptScore W2735961282C152565575 @default.
- W2735961282 hasConceptScore W2735961282C154945302 @default.
- W2735961282 hasConceptScore W2735961282C173608175 @default.
- W2735961282 hasConceptScore W2735961282C19275194 @default.
- W2735961282 hasConceptScore W2735961282C33923547 @default.
- W2735961282 hasConceptScore W2735961282C41008148 @default.
- W2735961282 hasConceptScore W2735961282C42812 @default.
- W2735961282 hasConceptScore W2735961282C49154492 @default.
- W2735961282 hasConceptScore W2735961282C55439883 @default.
- W2735961282 hasConceptScore W2735961282C73555534 @default.
- W2735961282 hasConceptScore W2735961282C75684735 @default.
- W2735961282 hasConceptScore W2735961282C76155785 @default.
- W2735961282 hasConceptScore W2735961282C9390403 @default.
- W2735961282 hasLocation W27359612821 @default.
- W2735961282 hasOpenAccess W2735961282 @default.
- W2735961282 hasPrimaryLocation W27359612821 @default.
- W2735961282 hasRelatedWork W2047086434 @default.
- W2735961282 hasRelatedWork W2145361639 @default.
- W2735961282 hasRelatedWork W2483136543 @default.
- W2735961282 hasRelatedWork W2495231312 @default.
- W2735961282 hasRelatedWork W2539422249 @default.
- W2735961282 hasRelatedWork W2767167788 @default.
- W2735961282 hasRelatedWork W2783000183 @default.
- W2735961282 hasRelatedWork W2805253785 @default.
- W2735961282 hasRelatedWork W2907991499 @default.
- W2735961282 hasRelatedWork W2939089006 @default.
- W2735961282 hasRelatedWork W2975343232 @default.
- W2735961282 hasRelatedWork W3010790835 @default.
- W2735961282 hasRelatedWork W3015677374 @default.
- W2735961282 hasRelatedWork W3017114573 @default.
- W2735961282 hasRelatedWork W3017445852 @default.
- W2735961282 hasRelatedWork W3018696818 @default.
- W2735961282 hasRelatedWork W3038407585 @default.
- W2735961282 hasRelatedWork W3101434632 @default.
- W2735961282 hasRelatedWork W3167254314 @default.
- W2735961282 hasRelatedWork W3177073825 @default.
- W2735961282 isParatext "false" @default.
- W2735961282 isRetracted "false" @default.
- W2735961282 magId "2735961282" @default.
- W2735961282 workType "article" @default.