Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207643999> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3207643999 endingPage "140211" @default.
- W3207643999 startingPage "140199" @default.
- W3207643999 abstract "In the last decade, deep neural network (DNN)-based object detection technologies have received significant attention as a promising solution to implement a variety of image understanding and video analysis applications on mobile edge devices. However, the execution of computationally intensive DNN-based object detection workloads in mobile edge devices is insufficient in fulfilling the object detection requirements with high accuracy and low latency, owing to the limited computation capacity. In this paper, we implement and evaluate a DNN-based object detection offloading framework to improve the object detection performance of mobile edge devices by offloading computation-intensive workloads to a remote edge server. However, preliminary experimental results have shown that offloading all object detection workloads of mobile edge devices may lead to worse performance than executing the workloads locally. This degradation is obtained from the inefficient resource utilization in the edge computing architectures, both for the edge server and mobile edge devices. To resolve the aforementioned problem with degradation, we devise a device-aware DNN offloading decision algorithm that is aimed to maximize resource utilization in the edge computing architecture. The proposed algorithm decides whether or not to offload the object detection workloads of edge devices by considering their computing power and network bandwidth, and therefore maximizing their average object detection processing frames per second. Through various experiments conducted in a real-life wireless local area network (WLAN) environment, we verified the effectiveness of the proposed DNN-based object detection offloading framework." @default.
- W3207643999 created "2021-10-25" @default.
- W3207643999 creator A5016663241 @default.
- W3207643999 creator A5048006664 @default.
- W3207643999 creator A5048334346 @default.
- W3207643999 creator A5079549367 @default.
- W3207643999 creator A5087010497 @default.
- W3207643999 date "2021-01-01" @default.
- W3207643999 modified "2023-10-05" @default.
- W3207643999 title "Implementing Practical DNN-Based Object Detection Offloading Decision for Maximizing Detection Performance of Mobile Edge Devices" @default.
- W3207643999 cites W2486687030 @default.
- W3207643999 cites W2761862361 @default.
- W3207643999 cites W2769686021 @default.
- W3207643999 cites W2770532911 @default.
- W3207643999 cites W2792220137 @default.
- W3207643999 cites W2884367402 @default.
- W3207643999 cites W2904994737 @default.
- W3207643999 cites W2918891759 @default.
- W3207643999 cites W2950865323 @default.
- W3207643999 cites W2960447515 @default.
- W3207643999 cites W2960833983 @default.
- W3207643999 cites W2965289829 @default.
- W3207643999 cites W2972006294 @default.
- W3207643999 cites W2979596121 @default.
- W3207643999 cites W2980856918 @default.
- W3207643999 cites W3008867028 @default.
- W3207643999 cites W3011134162 @default.
- W3207643999 cites W3036641478 @default.
- W3207643999 cites W3047122373 @default.
- W3207643999 cites W3094144275 @default.
- W3207643999 cites W3171617040 @default.
- W3207643999 doi "https://doi.org/10.1109/access.2021.3118731" @default.
- W3207643999 hasPublicationYear "2021" @default.
- W3207643999 type Work @default.
- W3207643999 sameAs 3207643999 @default.
- W3207643999 citedByCount "5" @default.
- W3207643999 countsByYear W32076439992022 @default.
- W3207643999 countsByYear W32076439992023 @default.
- W3207643999 crossrefType "journal-article" @default.
- W3207643999 hasAuthorship W3207643999A5016663241 @default.
- W3207643999 hasAuthorship W3207643999A5048006664 @default.
- W3207643999 hasAuthorship W3207643999A5048334346 @default.
- W3207643999 hasAuthorship W3207643999A5079549367 @default.
- W3207643999 hasAuthorship W3207643999A5087010497 @default.
- W3207643999 hasBestOaLocation W32076439991 @default.
- W3207643999 hasConcept C111919701 @default.
- W3207643999 hasConcept C138236772 @default.
- W3207643999 hasConcept C149635348 @default.
- W3207643999 hasConcept C153180895 @default.
- W3207643999 hasConcept C154945302 @default.
- W3207643999 hasConcept C162307627 @default.
- W3207643999 hasConcept C186967261 @default.
- W3207643999 hasConcept C2776061582 @default.
- W3207643999 hasConcept C2776151529 @default.
- W3207643999 hasConcept C2778456923 @default.
- W3207643999 hasConcept C41008148 @default.
- W3207643999 hasConcept C79403827 @default.
- W3207643999 hasConcept C79974875 @default.
- W3207643999 hasConceptScore W3207643999C111919701 @default.
- W3207643999 hasConceptScore W3207643999C138236772 @default.
- W3207643999 hasConceptScore W3207643999C149635348 @default.
- W3207643999 hasConceptScore W3207643999C153180895 @default.
- W3207643999 hasConceptScore W3207643999C154945302 @default.
- W3207643999 hasConceptScore W3207643999C162307627 @default.
- W3207643999 hasConceptScore W3207643999C186967261 @default.
- W3207643999 hasConceptScore W3207643999C2776061582 @default.
- W3207643999 hasConceptScore W3207643999C2776151529 @default.
- W3207643999 hasConceptScore W3207643999C2778456923 @default.
- W3207643999 hasConceptScore W3207643999C41008148 @default.
- W3207643999 hasConceptScore W3207643999C79403827 @default.
- W3207643999 hasConceptScore W3207643999C79974875 @default.
- W3207643999 hasLocation W32076439991 @default.
- W3207643999 hasLocation W32076439992 @default.
- W3207643999 hasOpenAccess W3207643999 @default.
- W3207643999 hasPrimaryLocation W32076439991 @default.
- W3207643999 hasRelatedWork W2917288403 @default.
- W3207643999 hasRelatedWork W3046070740 @default.
- W3207643999 hasRelatedWork W3157901373 @default.
- W3207643999 hasRelatedWork W3174690704 @default.
- W3207643999 hasRelatedWork W4224133481 @default.
- W3207643999 hasRelatedWork W4282943865 @default.
- W3207643999 hasRelatedWork W4287703675 @default.
- W3207643999 hasRelatedWork W4292862198 @default.
- W3207643999 hasRelatedWork W4312540714 @default.
- W3207643999 hasRelatedWork W4322494604 @default.
- W3207643999 hasVolume "9" @default.
- W3207643999 isParatext "false" @default.
- W3207643999 isRetracted "false" @default.
- W3207643999 magId "3207643999" @default.
- W3207643999 workType "article" @default.