Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet
Wearable devices are gaining recognition for their use as a biosensor platform. Electrical impedance tomography (EIT) is one of the sensing techniques that utilizes wearable sensors as its primary data acquisition system. It measures the impedance or resistance at the peripheral (skin) level and cal...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Multimodal Technologies and Interaction |
Subjects: | |
Online Access: | https://www.mdpi.com/2414-4088/4/3/47 |
id |
doaj-dd2960d74d264d10b8551b5e00229a92 |
---|---|
record_format |
Article |
spelling |
doaj-dd2960d74d264d10b8551b5e00229a922020-11-25T03:09:58ZengMDPI AGMultimodal Technologies and Interaction2414-40882020-08-014474710.3390/mti4030047Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance BraceletGodwin Ponraj Joseph Vedhagiri0Xin Zhi Wang1Kirthika Senthil Kumar2Hongliang Ren3Department of Biomedical Engineering, National University of Singapore, Singapore 117583, SingaporeDepartment of Mechanical Engineering, National University of Singapore, Singapore 117575, SingaporeDepartment of Biomedical Engineering, National University of Singapore, Singapore 117583, SingaporeDepartment of Biomedical Engineering, National University of Singapore, Singapore 117583, SingaporeWearable devices are gaining recognition for their use as a biosensor platform. Electrical impedance tomography (EIT) is one of the sensing techniques that utilizes wearable sensors as its primary data acquisition system. It measures the impedance or resistance at the peripheral (skin) level and calculates the conductivity distribution throughout the body. Even though the technology has existed for several decades, modern-day EIT devices are still costly and bulky. The paper proposes a novel low-cost kirigami-based wearable device that has soft PEDOT: PSS electrodes for sensing skin impedances. Simulation results show that the proposed kirigami structure for the bracelet has a large deformation during actuation while experiencing relatively lower stress. The paper also presents a comparative study on a few machine learning algorithms to classify hand gestures, based on the measured skin impedance. The best classification accuracy (91.49%) was observed from the quadratic support vector machine (SVM) algorithm with 48 principal components.https://www.mdpi.com/2414-4088/4/3/47kirigami wearable devicegesture classificationmachine learningelectrical impedance tomography |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Godwin Ponraj Joseph Vedhagiri Xin Zhi Wang Kirthika Senthil Kumar Hongliang Ren |
spellingShingle |
Godwin Ponraj Joseph Vedhagiri Xin Zhi Wang Kirthika Senthil Kumar Hongliang Ren Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet Multimodal Technologies and Interaction kirigami wearable device gesture classification machine learning electrical impedance tomography |
author_facet |
Godwin Ponraj Joseph Vedhagiri Xin Zhi Wang Kirthika Senthil Kumar Hongliang Ren |
author_sort |
Godwin Ponraj Joseph Vedhagiri |
title |
Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet |
title_short |
Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet |
title_full |
Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet |
title_fullStr |
Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet |
title_full_unstemmed |
Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet |
title_sort |
comparative study of machine learning algorithms to classify hand gestures from deployable and breathable kirigami-based electrical impedance bracelet |
publisher |
MDPI AG |
series |
Multimodal Technologies and Interaction |
issn |
2414-4088 |
publishDate |
2020-08-01 |
description |
Wearable devices are gaining recognition for their use as a biosensor platform. Electrical impedance tomography (EIT) is one of the sensing techniques that utilizes wearable sensors as its primary data acquisition system. It measures the impedance or resistance at the peripheral (skin) level and calculates the conductivity distribution throughout the body. Even though the technology has existed for several decades, modern-day EIT devices are still costly and bulky. The paper proposes a novel low-cost kirigami-based wearable device that has soft PEDOT: PSS electrodes for sensing skin impedances. Simulation results show that the proposed kirigami structure for the bracelet has a large deformation during actuation while experiencing relatively lower stress. The paper also presents a comparative study on a few machine learning algorithms to classify hand gestures, based on the measured skin impedance. The best classification accuracy (91.49%) was observed from the quadratic support vector machine (SVM) algorithm with 48 principal components. |
topic |
kirigami wearable device gesture classification machine learning electrical impedance tomography |
url |
https://www.mdpi.com/2414-4088/4/3/47 |
work_keys_str_mv |
AT godwinponrajjosephvedhagiri comparativestudyofmachinelearningalgorithmstoclassifyhandgesturesfromdeployableandbreathablekirigamibasedelectricalimpedancebracelet AT xinzhiwang comparativestudyofmachinelearningalgorithmstoclassifyhandgesturesfromdeployableandbreathablekirigamibasedelectricalimpedancebracelet AT kirthikasenthilkumar comparativestudyofmachinelearningalgorithmstoclassifyhandgesturesfromdeployableandbreathablekirigamibasedelectricalimpedancebracelet AT hongliangren comparativestudyofmachinelearningalgorithmstoclassifyhandgesturesfromdeployableandbreathablekirigamibasedelectricalimpedancebracelet |
_version_ |
1724661357120323584 |