Cited 0 time in webofscience Cited 0 time in scopus

Deep Neural Network Classification of Tactile Materials Explored by Tactile Sensor Array With Various Active-Cell Formations

Title
Deep Neural Network Classification of Tactile Materials Explored by Tactile Sensor Array With Various Active-Cell Formations
Authors
Lim, Sung-HoKim, KyungsooSim, MinkyungShin, KwonsikLee, DoyoungPark, JihoJang, Jae EunChoi, Ji-Woong
DGIST Authors
Jang, Jae EunChoi, Ji-Woong
Issue Date
2020-08
Citation
IEEE/ASME Transactions on Mechatronics, 25(4), 2134-2138
Type
Article
Article Type
Article
Author Keywords
Neural network applicationspattern classificationpiezoelectric devicestactile sensorstactile system
ISSN
1083-4435
Abstract
Reducing the input data of tactile sensory systems brings a large degree of freedom to real-world implementations from the perspectives of bandwidth and computational complexity. For this, in this letter, we suggest efficient active-cell formations with a high classification accuracy of tactile materials. By revealing that averaged Kullback-Leibler-divergence and common frequency component power to variance ratio are proportional to the classification accuracy, we showed that those methods can be useful in estimating valid active-cell formations.
URI
http://hdl.handle.net/20.500.11750/12564
DOI
10.1109/TMECH.2020.3006702
Publisher
Institute of Electrical and Electronics Engineers
Related Researcher
  • Author Jang, Jae Eun Advanced Electronic Devices Research Group(AEDRG) - Jang Lab.
  • Research Interests Nanoelectroinc device; 생체 신호 센싱 시스템 및 생체 모방 디바이스; 나노 통신 디바이스
Files:
There are no files associated with this item.
Collection:
Department of Information and Communication EngineeringAdvanced Electronic Devices Research Group(AEDRG) - Jang Lab.1. Journal Articles
Department of Information and Communication EngineeringCSP(Communication and Signal Processing) Lab1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE