The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
비침습적 인식은 당뇨병 인식에 있어 중요한 추세입니다. 불행하게도 기존의 비침습적 인식 방법은 정확도가 낮습니다. 본 논문에서는 발바닥 압력 영상과 개선된 캡슐 네트워크(DNR-CapsNet)를 통한 새로운 당뇨병 비침습적 인식 방법을 제안합니다. 제안된 방법의 입력은 발바닥 압력 이미지이고 출력은 건강 또는 당뇨병 가능성에 대한 인식 결과입니다. ResNet18은 제안된 DNR-CapsNet에서 픽셀 강도를 로컬 기능으로 변환하기 위해 컨벌루션 레이어의 백본으로 사용됩니다. 그런 다음, PrimaryCaps 층, 보조캡 레이어 및 당뇨병캡스 당뇨병 인식을 달성하기 위해 레이어가 개발되었습니다. 의미론적 융합과 지역성이 제한된 동적 라우팅도 우리 방법의 인식 정확도를 더욱 향상시키기 위해 개발되었습니다. 실험 결과는 제안된 방법이 기존 방법보다 당뇨병 비침습적 인식에 있어 더 좋은 성능을 가짐을 보여준다.
Cunlei WANG
Tianjin University,Tianjin Vocational College of Mechanics and Electricity
Donghui LI
Tianjin University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Cunlei WANG, Donghui LI, "Diabetes Noninvasive Recognition via Improved Capsule Network" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 8, pp. 1464-1471, August 2022, doi: 10.1587/transinf.2022EDP7037.
Abstract: Noninvasive recognition is an important trend in diabetes recognition. Unfortunately, the accuracy obtained from the conventional noninvasive recognition methods is low. This paper proposes a novel Diabetes Noninvasive Recognition method via the plantar pressure image and improved Capsule Network (DNR-CapsNet). The input of the proposed method is a plantar pressure image, and the output is the recognition result: healthy or possibly diabetes. The ResNet18 is used as the backbone of the convolutional layers to convert pixel intensities to local features in the proposed DNR-CapsNet. Then, the PrimaryCaps layer, SecondaryCaps layer, and DiabetesCaps layer are developed to achieve the diabetes recognition. The semantic fusion and locality-constrained dynamic routing are also developed to further improve the recognition accuracy in our method. The experimental results indicate that the proposed method has a better performance on diabetes noninvasive recognition than the state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7037/_p
부
@ARTICLE{e105-d_8_1464,
author={Cunlei WANG, Donghui LI, },
journal={IEICE TRANSACTIONS on Information},
title={Diabetes Noninvasive Recognition via Improved Capsule Network},
year={2022},
volume={E105-D},
number={8},
pages={1464-1471},
abstract={Noninvasive recognition is an important trend in diabetes recognition. Unfortunately, the accuracy obtained from the conventional noninvasive recognition methods is low. This paper proposes a novel Diabetes Noninvasive Recognition method via the plantar pressure image and improved Capsule Network (DNR-CapsNet). The input of the proposed method is a plantar pressure image, and the output is the recognition result: healthy or possibly diabetes. The ResNet18 is used as the backbone of the convolutional layers to convert pixel intensities to local features in the proposed DNR-CapsNet. Then, the PrimaryCaps layer, SecondaryCaps layer, and DiabetesCaps layer are developed to achieve the diabetes recognition. The semantic fusion and locality-constrained dynamic routing are also developed to further improve the recognition accuracy in our method. The experimental results indicate that the proposed method has a better performance on diabetes noninvasive recognition than the state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2022EDP7037},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Diabetes Noninvasive Recognition via Improved Capsule Network
T2 - IEICE TRANSACTIONS on Information
SP - 1464
EP - 1471
AU - Cunlei WANG
AU - Donghui LI
PY - 2022
DO - 10.1587/transinf.2022EDP7037
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2022
AB - Noninvasive recognition is an important trend in diabetes recognition. Unfortunately, the accuracy obtained from the conventional noninvasive recognition methods is low. This paper proposes a novel Diabetes Noninvasive Recognition method via the plantar pressure image and improved Capsule Network (DNR-CapsNet). The input of the proposed method is a plantar pressure image, and the output is the recognition result: healthy or possibly diabetes. The ResNet18 is used as the backbone of the convolutional layers to convert pixel intensities to local features in the proposed DNR-CapsNet. Then, the PrimaryCaps layer, SecondaryCaps layer, and DiabetesCaps layer are developed to achieve the diabetes recognition. The semantic fusion and locality-constrained dynamic routing are also developed to further improve the recognition accuracy in our method. The experimental results indicate that the proposed method has a better performance on diabetes noninvasive recognition than the state-of-the-art methods.
ER -