Show simple item record

dc.contributor.authorComiter, Marcus
dc.contributor.authorCrouse, Michael
dc.contributor.authorKung, H.
dc.date.accessioned2019-09-13T16:41:54Z
dc.date.issued2017-05-30
dc.identifier.citationComiter, Marcus Z., Michael B. Crouse, and H.T. Kung. 2017. International Journal of Computer Networks and Communications (IJCNC) 9, no. 3 (May): 21-39.en_US
dc.identifier.issn0975-2293en_US
dc.identifier.issn0974-9322en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:41364823*
dc.description.abstractNext-generation wireless networks such as 5G and 802.11ad networks will use millimeter waves operating at 28GHz, 38GHz, or higher frequencies to deliver unprecedentedly high data rates, e.g., 10 gigabits per second. However, millimeter waves must be used directionally with narrow beams in order to overcome the large attenuation due to their higher frequency. To achieve high data rates in a mobile setting, communicating nodes need to align their beams dynamically, quickly, and in high resolution. We propose a data-driven, deep neural network (DNN) approach to provide robust localization for beam alignment, using a lower frequency spectrum (e.g., 2.4 GHz). The proposed DNN-based localization methods use the angle of arrival derived from phase differences in the signal received at multiple antenna arrays to infer the location of a mobile node. Our methods differ from others that use DNNs as a black box in that the structure of our neural network model is tailored to address difficulties associated with the domain, such as collinearity of the mobile node with antenna arrays, fading and multipath. We show that training our models requires a small number of sample locations, such as 30 or fewer, making the proposed methods practical. Our specific contributions are: (1) a structured DNN approach where the neural network topology reflects the placement of antenna arrays, (2) a simulation platform for generating training and evaluation data sets under multiple noise models, and (3) demonstration that our structured DNN approach improves localization under noise by up to 25% over traditional off-the-shelf DNNs, and can achieve sub-meter accuracy in a real-world experiment.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.language.isoen_USen_US
dc.publisherAcademy and Industry Research Collaboration Center (AIRCC)en_US
dash.licenseMETA_ONLY
dc.subjectmillimeter waveen_US
dc.subject5Gen_US
dc.subject802.11aden_US
dc.subjectlocalizationen_US
dc.subjectmobile networksen_US
dc.subjectmachine learningen_US
dc.subjectdeep neural networksen_US
dc.titleA Structured Deep Neural Network for Data Driven Localization in High Frequency Wireless Networksen_US
dc.typeJournal Articleen_US
dc.description.versionVersion of Recorden_US
dc.relation.journalInternation Journal of Computer Networks and Communications (IJCNC)en_US
dash.depositing.authorKung, H.
dc.date.available2019-09-13T16:41:54Z
dash.workflow.commentsFAR2017en_US
dash.funder.nameIntel Corporationen_US
dash.funder.nameNaval Supply Systems Commanden_US
dash.funder.awardN00244-15-0050en_US
dash.funder.awardN00244-16-1-0018en_US
dc.identifier.doi10.5121/ijcnc.2017.9302
dc.source.journalIJCNC
dash.source.volume9;3
dash.source.page21-39
dash.contributor.affiliatedComiter, Marcus
dash.contributor.affiliatedKung, H.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record