Timely daily activity recognition from headmost sensor events

被引：57

作者：

Liu, Yaqing ^{[1
,2
,3
]}

Wang, Xiangxin ^{[1
]}

Zhai, Zhengguo ^{[1
]}

Chen, Rong ^{[1
]}

Zhang, Bin ^{[4
]}

Jiang, Yu ^{[2
]}

机构：

[1] Dalian Maritime Univ, Sch Informat Sci & Technol, Dalian 116026, Peoples R China

[2] Jilin Univ, Coll Comp Sci & Technol, Changchun 130012, Jilin, Peoples R China

[3] Sichuan Univ Sci & Engn, Artificial Intelligence Key Lab Sichuan Prov, Zigong 643000, Peoples R China

[4] Shandong Technol & Business Univ, Coll Comp Sci & Technol, Yantai 264005, Peoples R China

来源：

ISA TRANSACTIONS | 2019年 / 94卷

基金：

中国国家自然科学基金;

关键词：

Smart homes; Daily activity recognition; Sensor events; Real-time; SMART HOMES; ONTOLOGY; SEGMENTATION; STATE; PATTERN; ART;

D O I：

10.1016/j.isatra.2019.04.026

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Smart homes are designed to promote safe and comfortable living for inhabitants without any manual intervention. The performance of approaches for daily activity recognition is therefore crucial, but current real-time approaches have to wait until a daily activity ends before performing recognition. We present an approach for timely daily activity recognition from an incomplete stream of sensor events, by which the recognition process can start as soon as a daily activity begins. Activity features are generated from several headmost sensor events rather than from all sensor events that a daily activity activated. A public dataset was utilized to evaluate the presented method. Experimental findings show its effectiveness for timely daily activity recognition in terms of precision, recall, average saved time, and saved time proportion. (C) 2019 ISA. Published by Elsevier Ltd. All rights reserved.

引用

页码：379 / 390

页数：12

共 50 条

[1] A Transferred Daily Activity Recognition Method Based on Sensor Sequences
Jinghuan Guo
Jianxun Ren
Haoming Chen
Shuo Han
Shaoxi Li
[J]. Neural Processing Letters, 2023, 55 : 1001 - 1028
[2] A Transferred Daily Activity Recognition Method Based on Sensor Sequences
Guo, Jinghuan
Ren, Jianxun
Chen, Haoming
Han, Shuo
Li, Shaoxi
[J]. NEURAL PROCESSING LETTERS, 2023, 55 (02) : 1001 - 1028
[3] A daily activity feature extraction approach based on time series of sensor events
Liu, Yong
Yang, Hong
Gong, Shanshan
Liu, Yaqing
Xiong, Xingzhong
[J]. MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2020, 17 (05) : 5173 - 5189
[4] Human Daily and Sport Activity Recognition Using a Wearable inertial Sensor Network
Hsu, Yu-Liang
Yang, Shih-Chin
Chang, Hsing-Cheng
Lai, Hung-Che
[J]. IEEE ACCESS, 2018, 6 : 31715 - 31728
[5] Human Daily Activity and Fall Recognition Using a Smartphone's Acceleration Sensor
Chatzaki, Charikleia
Pediaditis, Matthew
Vavoulas, George
Tsiknakis, Manolis
[J]. INFORMATION AND COMMUNICATION TECHNOLOGIES FOR AGEING WELL AND E-HEALTH, ICT4AWE 2016, 2017, 736 : 100 - 118
[6] From action to activity: Sensor-based activity recognition
Liu, Ye
Nie, Liqiang
Liu, Li
Rosenblum, David S.
[J]. NEUROCOMPUTING, 2016, 181 : 108 - 115
[7] A Multi-Sensor Deep Learning Approach for Complex Daily Living Activity Recognition
Woodward, Kieran
Kanjo, Eiman
Taylor, Kyle
Hunt, John A.
[J]. PROCEEDINGS OF THE 2022 EMERGING DEVICES FOR DIGITAL BIOMARKERS, DIGIBIOM 2022, 2022, : 13 - 17
[8] Discovering Daily Activity Patterns from Sensor Data Sequences and Activity Sequences
Maucec, Mirjam Sepesy
Donaj, Gregor
[J]. SENSORS, 2021, 21 (20)
[9] Sensor Fusion for Recognition of Activities of Daily Living
Wu, Jiaxuan
Feng, Yunfei
Sun, Peng
[J]. SENSORS, 2018, 18 (11)
[10] Daily Activity Recognition based on Meta-classification of Low-level Audio Events
Giannakopoulos, Theodoros
Konstantopoulos, Stasinos
[J]. PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES FOR AGEING WELL AND E-HEALTH (ICT4AWE), VOL 1, 2017, : 220 - 227

← 1 2 3 4 5 →