Toward Automated Tomato Harvesting System: Integration of Haptic Based Piezoresistive Nanocomposite and Machine Learning

Saman Azhari; Takuya Setoguchi; Iwao Sasaki; Arata Nakagawa; Kengo Ikeda; Alin Azhari; Intan Helina Hasan; Mohd Nizar Hamidon; Naoto Fukunaga; Tomohiro Shibata; Hirofumi Tanaka

doi:10.1109/JSEN.2021.3124914

Toward Automated Tomato Harvesting System: Integration of Haptic Based Piezoresistive Nanocomposite and Machine Learning

Saman Azhari^*, Takuya Setoguchi, Iwao Sasaki, Arata Nakagawa, Kengo Ikeda, Alin Azhari, Intan Helina Hasan, Mohd Nizar Hamidon, Naoto Fukunaga, Tomohiro Shibata, Hirofumi Tanaka

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

Carbon nanotubes (CNT)/polydimethylsiloxane (PDMS) have been investigated as potential materials for tomato-harvesting applications. The current-voltage (I-V) and current time (I-t) properties, as well as tomato hardness measurement and support-vector machine learning, were used to determine the performance of the sensor with respect to sensitivity, response time, accuracy, and detection limit of the nanocomposite. The data suggested an accurate (± 5.2%) measurement in a low-weight region of tomato. Narrowing of the I-V hysteresis curve towards a higher weight region was observed as a result of the increase in electron pathways. The fabricated sensor displayed a higher sensitivity (15 mV / mu text{m} ) than the commercial sensor (1 mV / mu text{m} ). In addition, machine learning of the resistance-displacement curve data yielded an average accuracy level of 0.67 when tested using acquired data.

Original language	English
Pages (from-to)	27810-27817
Number of pages	8
Journal	IEEE Sensors Journal
Volume	21
Issue number	24
DOIs	https://doi.org/10.1109/JSEN.2021.3124914
Publication status	Published - 2021 Dec 15
Externally published	Yes

Keywords

CNTs
PDMS
harvesting robot
machine learning
tactile sensor
tomato

ASJC Scopus subject areas

Instrumentation
Electrical and Electronic Engineering

Access to Document

10.1109/JSEN.2021.3124914

Cite this

@article{e6eab8803cf0439aaefc7d7e13d5f1ad,

title = "Toward Automated Tomato Harvesting System: Integration of Haptic Based Piezoresistive Nanocomposite and Machine Learning",

abstract = "Carbon nanotubes (CNT)/polydimethylsiloxane (PDMS) have been investigated as potential materials for tomato-harvesting applications. The current-voltage (I-V) and current time (I-t) properties, as well as tomato hardness measurement and support-vector machine learning, were used to determine the performance of the sensor with respect to sensitivity, response time, accuracy, and detection limit of the nanocomposite. The data suggested an accurate (± 5.2%) measurement in a low-weight region of tomato. Narrowing of the I-V hysteresis curve towards a higher weight region was observed as a result of the increase in electron pathways. The fabricated sensor displayed a higher sensitivity (15 mV / mu text{m} ) than the commercial sensor (1 mV / mu text{m} ). In addition, machine learning of the resistance-displacement curve data yielded an average accuracy level of 0.67 when tested using acquired data.",

keywords = "CNTs, PDMS, harvesting robot, machine learning, tactile sensor, tomato",

author = "Saman Azhari and Takuya Setoguchi and Iwao Sasaki and Arata Nakagawa and Kengo Ikeda and Alin Azhari and Hasan, {Intan Helina} and Hamidon, {Mohd Nizar} and Naoto Fukunaga and Tomohiro Shibata and Hirofumi Tanaka",

note = "Publisher Copyright: {\textcopyright} 2001-2012 IEEE.",

year = "2021",

month = dec,

day = "15",

doi = "10.1109/JSEN.2021.3124914",

language = "English",

volume = "21",

pages = "27810--27817",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "24",

}

TY - JOUR

T1 - Toward Automated Tomato Harvesting System

T2 - Integration of Haptic Based Piezoresistive Nanocomposite and Machine Learning

AU - Azhari, Saman

AU - Setoguchi, Takuya

AU - Sasaki, Iwao

AU - Nakagawa, Arata

AU - Ikeda, Kengo

AU - Azhari, Alin

AU - Hasan, Intan Helina

AU - Hamidon, Mohd Nizar

AU - Fukunaga, Naoto

AU - Shibata, Tomohiro

AU - Tanaka, Hirofumi

PY - 2021/12/15

Y1 - 2021/12/15

N2 - Carbon nanotubes (CNT)/polydimethylsiloxane (PDMS) have been investigated as potential materials for tomato-harvesting applications. The current-voltage (I-V) and current time (I-t) properties, as well as tomato hardness measurement and support-vector machine learning, were used to determine the performance of the sensor with respect to sensitivity, response time, accuracy, and detection limit of the nanocomposite. The data suggested an accurate (± 5.2%) measurement in a low-weight region of tomato. Narrowing of the I-V hysteresis curve towards a higher weight region was observed as a result of the increase in electron pathways. The fabricated sensor displayed a higher sensitivity (15 mV / mu text{m} ) than the commercial sensor (1 mV / mu text{m} ). In addition, machine learning of the resistance-displacement curve data yielded an average accuracy level of 0.67 when tested using acquired data.

AB - Carbon nanotubes (CNT)/polydimethylsiloxane (PDMS) have been investigated as potential materials for tomato-harvesting applications. The current-voltage (I-V) and current time (I-t) properties, as well as tomato hardness measurement and support-vector machine learning, were used to determine the performance of the sensor with respect to sensitivity, response time, accuracy, and detection limit of the nanocomposite. The data suggested an accurate (± 5.2%) measurement in a low-weight region of tomato. Narrowing of the I-V hysteresis curve towards a higher weight region was observed as a result of the increase in electron pathways. The fabricated sensor displayed a higher sensitivity (15 mV / mu text{m} ) than the commercial sensor (1 mV / mu text{m} ). In addition, machine learning of the resistance-displacement curve data yielded an average accuracy level of 0.67 when tested using acquired data.

KW - CNTs

KW - PDMS

KW - harvesting robot

KW - machine learning

KW - tactile sensor

KW - tomato

UR - http://www.scopus.com/inward/record.url?scp=85118629316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85118629316&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2021.3124914

DO - 10.1109/JSEN.2021.3124914

M3 - Article

AN - SCOPUS:85118629316

SN - 1530-437X

VL - 21

SP - 27810

EP - 27817

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

IS - 24

ER -

Toward Automated Tomato Harvesting System: Integration of Haptic Based Piezoresistive Nanocomposite and Machine Learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this