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
최근 사회의 고령화에 따라 노인을 돌보기 위한 가정에서의 인간의 활동을 인식하기 위한 다양한 연구가 활발히 진행되고 있다. 활동 인식을 위해 여러 센서가 사용됩니다. 그러나 이러한 센서를 사용할 때는 개인 정보 보호를 고려해야 합니다. 프라이버시를 지켜주는 센서 후보 중 하나가 바로 사운드 센서다. MFCC(Mel-Frequency Cepstral Coefficient)는 음성인식을 위한 특징 추출 알고리즘으로 널리 사용됩니다. 그러나 일상생활의 소리에 의한 활동인식에 기존의 MFCC를 적용하는 것은 적합하지 않다. 본 논문에서는 간단히 “생활의 소리”를 “생활의 소리”로 표기한다. 그 이유는 기존의 MFCC는 고주파수에서 나타나는 생활음의 여러 특징을 잘 추출하지 못하기 때문이다. 본 논문에서는 개선된 MFCC를 제안하고, 개선된 MFCC에서 추출된 특징을 이용하여 머신러닝 SVM(Support Vector Machine)을 통한 활동 인식 평가 결과를 보고한다.
João Filipe PAPEL
Tokai University -- Takanawa Campus
Tatsuji MUNAKA
Tokai University -- Takanawa Campus
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
João Filipe PAPEL, Tatsuji MUNAKA, "Home Activity Recognition by Sounds of Daily Life Using Improved Feature Extraction Method" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 4, pp. 450-458, April 2023, doi: 10.1587/transinf.2022IIP0004.
Abstract: In recent years, with the aging of society, many kinds of research have been actively conducted to recognize human activity in a home to watch over the elderly. Multiple sensors for activity recognition are used. However, we need to consider privacy when using these sensors. One of the candidates of the sensors that keep privacy is a sound sensor. MFCC (Mel-Frequency Cepstral Coefficient) is widely used as a feature extraction algorithm for voice recognition. However, it is not suitable to apply conventional MFCC to activity recognition by sounds of daily life. We denote “sounds of daily life” as “life sounds” simply in this paper. The reason is that conventional MFCC does not extract well several features of life sounds that appear at high frequencies. This paper proposes the improved MFCC and reports the evaluation results of activity recognition by machine learning SVM (Support Vector Machine) using features extracted by improved MFCC.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022IIP0004/_p
부
@ARTICLE{e106-d_4_450,
author={João Filipe PAPEL, Tatsuji MUNAKA, },
journal={IEICE TRANSACTIONS on Information},
title={Home Activity Recognition by Sounds of Daily Life Using Improved Feature Extraction Method},
year={2023},
volume={E106-D},
number={4},
pages={450-458},
abstract={In recent years, with the aging of society, many kinds of research have been actively conducted to recognize human activity in a home to watch over the elderly. Multiple sensors for activity recognition are used. However, we need to consider privacy when using these sensors. One of the candidates of the sensors that keep privacy is a sound sensor. MFCC (Mel-Frequency Cepstral Coefficient) is widely used as a feature extraction algorithm for voice recognition. However, it is not suitable to apply conventional MFCC to activity recognition by sounds of daily life. We denote “sounds of daily life” as “life sounds” simply in this paper. The reason is that conventional MFCC does not extract well several features of life sounds that appear at high frequencies. This paper proposes the improved MFCC and reports the evaluation results of activity recognition by machine learning SVM (Support Vector Machine) using features extracted by improved MFCC.},
keywords={},
doi={10.1587/transinf.2022IIP0004},
ISSN={1745-1361},
month={April},}
부
TY - JOUR
TI - Home Activity Recognition by Sounds of Daily Life Using Improved Feature Extraction Method
T2 - IEICE TRANSACTIONS on Information
SP - 450
EP - 458
AU - João Filipe PAPEL
AU - Tatsuji MUNAKA
PY - 2023
DO - 10.1587/transinf.2022IIP0004
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2023
AB - In recent years, with the aging of society, many kinds of research have been actively conducted to recognize human activity in a home to watch over the elderly. Multiple sensors for activity recognition are used. However, we need to consider privacy when using these sensors. One of the candidates of the sensors that keep privacy is a sound sensor. MFCC (Mel-Frequency Cepstral Coefficient) is widely used as a feature extraction algorithm for voice recognition. However, it is not suitable to apply conventional MFCC to activity recognition by sounds of daily life. We denote “sounds of daily life” as “life sounds” simply in this paper. The reason is that conventional MFCC does not extract well several features of life sounds that appear at high frequencies. This paper proposes the improved MFCC and reports the evaluation results of activity recognition by machine learning SVM (Support Vector Machine) using features extracted by improved MFCC.
ER -