Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality

Jojo Blanza; Lawrence Materum; Takuichi Hirano; Takuichi HIRANO

doi:10.30534/IJETER/2020/37872020

Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality

Translated title of the contribution: Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality

Jojo Blanza, Lawrence Materum, Takuichi Hirano, Takuichi HIRANO

Department of Electrical,Electronic and Communication Engineering

Research output: Contribution to journal › Article

Abstract

Deep divergence-based clustering (DDC) is used to cluster COST 2100 channel model (C2CM) wireless propagation multipaths. The dataset is taken from the IEEE DataPort. DDC solves the membership of the clusters. DDC builds on information theoretic divergence measures and geometric regularization in order to determine the membership of the clusters. The cluster count is then computed through the cluster-wise Jaccard index of the membership of the multipaths to their clusters. The performance of DDC is evaluated using the Jaccard index by comparing the reference multipathdatasets from IEEE DataPort with the calculated multipath clusters obtained by DDC. Results show that DDC can be used as an alternative clustering approach in the field of channel modeling.

Translated title of the contribution	Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality
Original language	Japanese
Pages (from-to)	3104 - 3110
Journal	International Journal of Emerging Trends in Engineering Research
Volume	8
Issue number	7
DOIs	https://doi.org/10.30534/IJETER/2020/37872020
State	Published - 2020

Access to Document

10.30534/IJETER/2020/37872020

Cite this

@article{51830a9dde134985b432fe6bdd1281ee,

title = "Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality",

abstract = "Deep divergence-based clustering (DDC) is used to cluster COST 2100 channel model (C2CM) wireless propagation multipaths. The dataset is taken from the IEEE DataPort. DDC solves the membership of the clusters. DDC builds on information theoretic divergence measures and geometric regularization in order to determine the membership of the clusters. The cluster count is then computed through the cluster-wise Jaccard index of the membership of the multipaths to their clusters. The performance of DDC is evaluated using the Jaccard index by comparing the reference multipathdatasets from IEEE DataPort with the calculated multipath clusters obtained by DDC. Results show that DDC can be used as an alternative clustering approach in the field of channel modeling.",

author = "\{Jojo Blanza\} and \{Lawrence Materum\} and \{Takuichi Hirano\} and Takuichi HIRANO",

year = "2020",

doi = "10.30534/IJETER/2020/37872020",

language = "Japanese",

volume = "8",

pages = "3104 -- 3110",

journal = "International Journal of Emerging Trends in Engineering Research",

issn = "2347-3983",

publisher = "World Academy of Research in Science and Engineering",

number = "7",

}

TY - JOUR

T1 - Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality

AU - Jojo Blanza, null

AU - Lawrence Materum, null

AU - Takuichi Hirano, null

AU - HIRANO, Takuichi

PY - 2020

Y1 - 2020

N2 - Deep divergence-based clustering (DDC) is used to cluster COST 2100 channel model (C2CM) wireless propagation multipaths. The dataset is taken from the IEEE DataPort. DDC solves the membership of the clusters. DDC builds on information theoretic divergence measures and geometric regularization in order to determine the membership of the clusters. The cluster count is then computed through the cluster-wise Jaccard index of the membership of the multipaths to their clusters. The performance of DDC is evaluated using the Jaccard index by comparing the reference multipathdatasets from IEEE DataPort with the calculated multipath clusters obtained by DDC. Results show that DDC can be used as an alternative clustering approach in the field of channel modeling.

AB - Deep divergence-based clustering (DDC) is used to cluster COST 2100 channel model (C2CM) wireless propagation multipaths. The dataset is taken from the IEEE DataPort. DDC solves the membership of the clusters. DDC builds on information theoretic divergence measures and geometric regularization in order to determine the membership of the clusters. The cluster count is then computed through the cluster-wise Jaccard index of the membership of the multipaths to their clusters. The performance of DDC is evaluated using the Jaccard index by comparing the reference multipathdatasets from IEEE DataPort with the calculated multipath clusters obtained by DDC. Results show that DDC can be used as an alternative clustering approach in the field of channel modeling.

U2 - 10.30534/IJETER/2020/37872020

DO - 10.30534/IJETER/2020/37872020

M3 - 記事

SN - 2347-3983

VL - 8

SP - 3104

EP - 3110

JO - International Journal of Emerging Trends in Engineering Research

JF - International Journal of Emerging Trends in Engineering Research

IS - 7

ER -

Deep divergence-based clustering of wireless multipaths for simultaneously addressing the grouping and the cardinality

Abstract

Access to Document

Fingerprint

Cite this