Unsupervised neural network based topological learning from point clouds for map building

Yuichiro Toda, Weihong Chin, Naoyuki Kubota

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Topological structure learning methods are expected for the field of data mining for extracting multiscale topological structures from an unknown dataset. In this paper, we introduce the unsupervised neural network method for topological structure learning method from point clouds for map building. We propose Batch Learning GNG (BL-GNG) in order to improve the learning convergence. BL-GNG uses an objective function based on Fuzzy C-means for improving the learning convergence. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other hierarchical approaches, and discuss the effectiveness of our proposed method.

Original languageEnglish
Title of host publicationMHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2018-January
ISBN (Electronic)9781538633144
DOIs
Publication statusPublished - Feb 28 2018
Externally publishedYes
Event28th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2017 - Nagoya, Japan
Duration: Dec 3 2017Dec 6 2017

Other

Other28th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2017
CountryJapan
CityNagoya
Period12/3/1712/6/17

Fingerprint

Data mining
Learning
Neural networks
Experiments
Data Mining

ASJC Scopus subject areas

  • Biotechnology
  • Biomedical Engineering
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Toda, Y., Chin, W., & Kubota, N. (2018). Unsupervised neural network based topological learning from point clouds for map building. In MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science (Vol. 2018-January, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MHS.2017.8305188

Unsupervised neural network based topological learning from point clouds for map building. / Toda, Yuichiro; Chin, Weihong; Kubota, Naoyuki.

MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Toda, Y, Chin, W & Kubota, N 2018, Unsupervised neural network based topological learning from point clouds for map building. in MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 28th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2017, Nagoya, Japan, 12/3/17. https://doi.org/10.1109/MHS.2017.8305188
Toda Y, Chin W, Kubota N. Unsupervised neural network based topological learning from point clouds for map building. In MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/MHS.2017.8305188
Toda, Yuichiro ; Chin, Weihong ; Kubota, Naoyuki. / Unsupervised neural network based topological learning from point clouds for map building. MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{03fd3ad78b524d7da55aac2044c046a1,
title = "Unsupervised neural network based topological learning from point clouds for map building",
abstract = "Topological structure learning methods are expected for the field of data mining for extracting multiscale topological structures from an unknown dataset. In this paper, we introduce the unsupervised neural network method for topological structure learning method from point clouds for map building. We propose Batch Learning GNG (BL-GNG) in order to improve the learning convergence. BL-GNG uses an objective function based on Fuzzy C-means for improving the learning convergence. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other hierarchical approaches, and discuss the effectiveness of our proposed method.",
author = "Yuichiro Toda and Weihong Chin and Naoyuki Kubota",
year = "2018",
month = "2",
day = "28",
doi = "10.1109/MHS.2017.8305188",
language = "English",
volume = "2018-January",
pages = "1--6",
booktitle = "MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Unsupervised neural network based topological learning from point clouds for map building

AU - Toda, Yuichiro

AU - Chin, Weihong

AU - Kubota, Naoyuki

PY - 2018/2/28

Y1 - 2018/2/28

N2 - Topological structure learning methods are expected for the field of data mining for extracting multiscale topological structures from an unknown dataset. In this paper, we introduce the unsupervised neural network method for topological structure learning method from point clouds for map building. We propose Batch Learning GNG (BL-GNG) in order to improve the learning convergence. BL-GNG uses an objective function based on Fuzzy C-means for improving the learning convergence. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other hierarchical approaches, and discuss the effectiveness of our proposed method.

AB - Topological structure learning methods are expected for the field of data mining for extracting multiscale topological structures from an unknown dataset. In this paper, we introduce the unsupervised neural network method for topological structure learning method from point clouds for map building. We propose Batch Learning GNG (BL-GNG) in order to improve the learning convergence. BL-GNG uses an objective function based on Fuzzy C-means for improving the learning convergence. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other hierarchical approaches, and discuss the effectiveness of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85050494122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050494122&partnerID=8YFLogxK

U2 - 10.1109/MHS.2017.8305188

DO - 10.1109/MHS.2017.8305188

M3 - Conference contribution

AN - SCOPUS:85050494122

VL - 2018-January

SP - 1

EP - 6

BT - MHS 2017 - 28th 2017 International Symposium on Micro-NanoMechatronics and Human Science

PB - Institute of Electrical and Electronics Engineers Inc.

ER -