Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO Article Swipe
Hosein Zarini
,
Mohammad Robat Mili
,
Mehdi Rasti
,
Sergey Andreev
,
Pedro H. J. Nardelli
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.05830
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.05830
In this paper, we propose an intelligent analog beam selection strategy in a terahertz (THz) band beamspace multiple-input multiple-output (MIMO) system. First inspired by transfer learning, we fine-tune the pre-trained off-the-shelf GoogleNet classifier, to learn analog beam selection as a multi-class mapping problem. Simulation results show 83% accuracy for the analog beam selection, which subsequently results in 12% spectral efficiency (SE) gain, upon the existing counterparts. Towards a more accurate classifier, we replace the conventional rectified linear unit (ReLU) activation function of the GoogleNet with the recently proposed Swish and retrain the fine-tuned GoogleNet to learn analog beam selection. It is numerically indicated that the fine-tuned Swish-driven GoogleNet achieves 86% accuracy, as well as 18% improvement in achievable SE, upon the similar schemes. Eventually, a strong ensembled classifier is developed to learn analog beam selection by sequentially training multiple fine-tuned Swish-driven GoogleNet classifiers. According to the simulations, the strong ensembled model is 90% accurate and yields 27% gain in achievable SE, in comparison with prior methods.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2110.05830
- https://arxiv.org/pdf/2110.05830
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4286905945
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4286905945Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2110.05830Digital Object Identifier
- Title
-
Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMOWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-10-12Full publication date if available
- Authors
-
Hosein Zarini, Mohammad Robat Mili, Mehdi Rasti, Sergey Andreev, Pedro H. J. NardelliList of authors in order
- Landing page
-
https://arxiv.org/abs/2110.05830Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2110.05830Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2110.05830Direct OA link when available
- Concepts
-
Classifier (UML), Terahertz radiation, Selection (genetic algorithm), Computer science, MIMO, Artificial intelligence, Beam (structure), Pattern recognition (psychology), Machine learning, Physics, Telecommunications, Optics, BeamformingTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4286905945 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2110.05830 |
| ids.doi | https://doi.org/10.48550/arxiv.2110.05830 |
| ids.openalex | https://openalex.org/W4286905945 |
| fwci | |
| type | preprint |
| title | Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10936 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9958999752998352 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2208 |
| topics[0].subfield.display_name | Electrical and Electronic Engineering |
| topics[0].display_name | Millimeter-Wave Propagation and Modeling |
| topics[1].id | https://openalex.org/T10752 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9930999875068665 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Terahertz technology and applications |
| topics[2].id | https://openalex.org/T10262 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9929999709129333 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Microwave Engineering and Waveguides |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C95623464 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7080901861190796 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[0].display_name | Classifier (UML) |
| concepts[1].id | https://openalex.org/C107816215 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7070662379264832 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q647887 |
| concepts[1].display_name | Terahertz radiation |
| concepts[2].id | https://openalex.org/C81917197 |
| concepts[2].level | 2 |
| concepts[2].score | 0.567928671836853 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q628760 |
| concepts[2].display_name | Selection (genetic algorithm) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5441731810569763 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C207987634 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5224539041519165 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q176862 |
| concepts[4].display_name | MIMO |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.505908191204071 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C168834538 |
| concepts[6].level | 2 |
| concepts[6].score | 0.43081605434417725 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3705329 |
| concepts[6].display_name | Beam (structure) |
| concepts[7].id | https://openalex.org/C153180895 |
| concepts[7].level | 2 |
| concepts[7].score | 0.3725491166114807 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[7].display_name | Pattern recognition (psychology) |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33387133479118347 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C121332964 |
| concepts[9].level | 0 |
| concepts[9].score | 0.1574362814426422 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[9].display_name | Physics |
| concepts[10].id | https://openalex.org/C76155785 |
| concepts[10].level | 1 |
| concepts[10].score | 0.13257762789726257 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[10].display_name | Telecommunications |
| concepts[11].id | https://openalex.org/C120665830 |
| concepts[11].level | 1 |
| concepts[11].score | 0.11555111408233643 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[11].display_name | Optics |
| concepts[12].id | https://openalex.org/C54197355 |
| concepts[12].level | 2 |
| concepts[12].score | 0.07286608219146729 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q5782992 |
| concepts[12].display_name | Beamforming |
| keywords[0].id | https://openalex.org/keywords/classifier |
| keywords[0].score | 0.7080901861190796 |
| keywords[0].display_name | Classifier (UML) |
| keywords[1].id | https://openalex.org/keywords/terahertz-radiation |
| keywords[1].score | 0.7070662379264832 |
| keywords[1].display_name | Terahertz radiation |
| keywords[2].id | https://openalex.org/keywords/selection |
| keywords[2].score | 0.567928671836853 |
| keywords[2].display_name | Selection (genetic algorithm) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5441731810569763 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/mimo |
| keywords[4].score | 0.5224539041519165 |
| keywords[4].display_name | MIMO |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.505908191204071 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/beam |
| keywords[6].score | 0.43081605434417725 |
| keywords[6].display_name | Beam (structure) |
| keywords[7].id | https://openalex.org/keywords/pattern-recognition |
| keywords[7].score | 0.3725491166114807 |
| keywords[7].display_name | Pattern recognition (psychology) |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.33387133479118347 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/physics |
| keywords[9].score | 0.1574362814426422 |
| keywords[9].display_name | Physics |
| keywords[10].id | https://openalex.org/keywords/telecommunications |
| keywords[10].score | 0.13257762789726257 |
| keywords[10].display_name | Telecommunications |
| keywords[11].id | https://openalex.org/keywords/optics |
| keywords[11].score | 0.11555111408233643 |
| keywords[11].display_name | Optics |
| keywords[12].id | https://openalex.org/keywords/beamforming |
| keywords[12].score | 0.07286608219146729 |
| keywords[12].display_name | Beamforming |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2110.05830 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | public-domain |
| locations[0].pdf_url | https://arxiv.org/pdf/2110.05830 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/public-domain |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2110.05830 |
| locations[1].id | doi:10.48550/arxiv.2110.05830 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | public-domain |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/public-domain |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2110.05830 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5078312436 |
| authorships[0].author.orcid | https://orcid.org/0009-0003-4049-3997 |
| authorships[0].author.display_name | Hosein Zarini |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zarini, Hosein |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5066654506 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4120-1872 |
| authorships[1].author.display_name | Mohammad Robat Mili |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mili, Mohammad Robat |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5028985499 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2081-0102 |
| authorships[2].author.display_name | Mehdi Rasti |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Rasti, Mehdi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5049711982 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8223-3665 |
| authorships[3].author.display_name | Sergey Andreev |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Andreev, Sergey |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5058989730 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-7398-1802 |
| authorships[4].author.display_name | Pedro H. J. Nardelli |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Nardelli, Pedro H. J. |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2110.05830 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10936 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9958999752998352 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2208 |
| primary_topic.subfield.display_name | Electrical and Electronic Engineering |
| primary_topic.display_name | Millimeter-Wave Propagation and Modeling |
| related_works | https://openalex.org/W2033952283, https://openalex.org/W2762687161, https://openalex.org/W2353254830, https://openalex.org/W2351210568, https://openalex.org/W2028421553, https://openalex.org/W2890072373, https://openalex.org/W3000002614, https://openalex.org/W2800192479, https://openalex.org/W3040184894, https://openalex.org/W2105973023 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2110.05830 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | public-domain |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2110.05830 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/public-domain |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2110.05830 |
| primary_location.id | pmh:oai:arXiv.org:2110.05830 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | public-domain |
| primary_location.pdf_url | https://arxiv.org/pdf/2110.05830 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/public-domain |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2110.05830 |
| publication_date | 2021-10-12 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 12, 39, 67, 124 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.It | 99 |
| abstract_inverted_index.an | 5 |
| abstract_inverted_index.as | 38, 111, 113 |
| abstract_inverted_index.by | 23, 135 |
| abstract_inverted_index.in | 11, 56, 116, 158, 161 |
| abstract_inverted_index.is | 100, 128, 151 |
| abstract_inverted_index.of | 81 |
| abstract_inverted_index.to | 33, 94, 130, 144 |
| abstract_inverted_index.we | 3, 26, 71 |
| abstract_inverted_index.12% | 57 |
| abstract_inverted_index.18% | 114 |
| abstract_inverted_index.27% | 156 |
| abstract_inverted_index.83% | 46 |
| abstract_inverted_index.86% | 109 |
| abstract_inverted_index.90% | 152 |
| abstract_inverted_index.SE, | 118, 160 |
| abstract_inverted_index.and | 89, 154 |
| abstract_inverted_index.for | 48 |
| abstract_inverted_index.the | 28, 49, 63, 73, 82, 85, 91, 104, 120, 145, 147 |
| abstract_inverted_index.(SE) | 60 |
| abstract_inverted_index.band | 15 |
| abstract_inverted_index.beam | 8, 36, 51, 97, 133 |
| abstract_inverted_index.gain | 157 |
| abstract_inverted_index.more | 68 |
| abstract_inverted_index.show | 45 |
| abstract_inverted_index.that | 103 |
| abstract_inverted_index.this | 1 |
| abstract_inverted_index.unit | 77 |
| abstract_inverted_index.upon | 62, 119 |
| abstract_inverted_index.well | 112 |
| abstract_inverted_index.with | 84, 163 |
| abstract_inverted_index.(THz) | 14 |
| abstract_inverted_index.First | 21 |
| abstract_inverted_index.Swish | 88 |
| abstract_inverted_index.gain, | 61 |
| abstract_inverted_index.learn | 34, 95, 131 |
| abstract_inverted_index.model | 150 |
| abstract_inverted_index.prior | 164 |
| abstract_inverted_index.which | 53 |
| abstract_inverted_index.(MIMO) | 19 |
| abstract_inverted_index.(ReLU) | 78 |
| abstract_inverted_index.analog | 7, 35, 50, 96, 132 |
| abstract_inverted_index.linear | 76 |
| abstract_inverted_index.paper, | 2 |
| abstract_inverted_index.strong | 125, 148 |
| abstract_inverted_index.yields | 155 |
| abstract_inverted_index.Towards | 66 |
| abstract_inverted_index.mapping | 41 |
| abstract_inverted_index.propose | 4 |
| abstract_inverted_index.replace | 72 |
| abstract_inverted_index.results | 44, 55 |
| abstract_inverted_index.retrain | 90 |
| abstract_inverted_index.similar | 121 |
| abstract_inverted_index.system. | 20 |
| abstract_inverted_index.accuracy | 47 |
| abstract_inverted_index.accurate | 69, 153 |
| abstract_inverted_index.achieves | 108 |
| abstract_inverted_index.existing | 64 |
| abstract_inverted_index.function | 80 |
| abstract_inverted_index.inspired | 22 |
| abstract_inverted_index.methods. | 165 |
| abstract_inverted_index.multiple | 138 |
| abstract_inverted_index.problem. | 42 |
| abstract_inverted_index.proposed | 87 |
| abstract_inverted_index.recently | 86 |
| abstract_inverted_index.schemes. | 122 |
| abstract_inverted_index.spectral | 58 |
| abstract_inverted_index.strategy | 10 |
| abstract_inverted_index.training | 137 |
| abstract_inverted_index.transfer | 24 |
| abstract_inverted_index.According | 143 |
| abstract_inverted_index.GoogleNet | 31, 83, 93, 107, 141 |
| abstract_inverted_index.accuracy, | 110 |
| abstract_inverted_index.beamspace | 16 |
| abstract_inverted_index.developed | 129 |
| abstract_inverted_index.ensembled | 126, 149 |
| abstract_inverted_index.fine-tune | 27 |
| abstract_inverted_index.indicated | 102 |
| abstract_inverted_index.learning, | 25 |
| abstract_inverted_index.rectified | 75 |
| abstract_inverted_index.selection | 9, 37, 134 |
| abstract_inverted_index.terahertz | 13 |
| abstract_inverted_index.Simulation | 43 |
| abstract_inverted_index.achievable | 117, 159 |
| abstract_inverted_index.activation | 79 |
| abstract_inverted_index.classifier | 127 |
| abstract_inverted_index.comparison | 162 |
| abstract_inverted_index.efficiency | 59 |
| abstract_inverted_index.fine-tuned | 92, 105, 139 |
| abstract_inverted_index.selection, | 52 |
| abstract_inverted_index.selection. | 98 |
| abstract_inverted_index.Eventually, | 123 |
| abstract_inverted_index.classifier, | 32, 70 |
| abstract_inverted_index.improvement | 115 |
| abstract_inverted_index.intelligent | 6 |
| abstract_inverted_index.multi-class | 40 |
| abstract_inverted_index.numerically | 101 |
| abstract_inverted_index.pre-trained | 29 |
| abstract_inverted_index.Swish-driven | 106, 140 |
| abstract_inverted_index.classifiers. | 142 |
| abstract_inverted_index.conventional | 74 |
| abstract_inverted_index.sequentially | 136 |
| abstract_inverted_index.simulations, | 146 |
| abstract_inverted_index.subsequently | 54 |
| abstract_inverted_index.counterparts. | 65 |
| abstract_inverted_index.off-the-shelf | 30 |
| abstract_inverted_index.multiple-input | 17 |
| abstract_inverted_index.multiple-output | 18 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |