arrow
返回

Seq2Dense U-Net: Analyzing Sequential Inertial Sensor Data for Human Activity Recognition Using Dense Segmentation Model

delete2023-09-15
delete9
PRE
AI
T
Tanushree Meena
K
Kishor Sarawadekar *
DOI:10.1109/JSEN.2023.3301187delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
In this article, we have demonstrated a novel, generalized Seq2Dense U-Net model for classifying different activities (time-series data obtained from an accelerometer and gyroscope) and sampling them by considering individual sampling points. For training and classifying activities, the triaxial data from the smart devices are mapped as a linear set of sampling points via the sliding window technique and fed to the model. Our proposed model overcame the challenge of a multiclass window that incorrectly labels different classes of sampling points within a window as a class, as reported by previous studies. The comparative study shows that our method can recognize pixel-level function from corresponding time-series data of human activities. To validate and consolidate the effectiveness of the model, an ablation study has been performed on the components of the classification block. Furthermore, the network depth analysis provides the optimum depth with respect to the number of parameters. We have performed extensive studies on the Sanitation, UCI, and UCI HAPT datasets and calculated various performance metrices to assess the performance of our proposed model. Our proposed model performed significantly better on every individual dataset compared to other models as illustrated in the comparative study and provided the best results on the UCI dataset. For the UCI HAR dataset, our model gives an accuracy score of 0.954781, precision of 0.941473, recall of 0.940618, F1 score of 0.940699 followed by Matthew's correlation coefficient (MCC), and kappa score of 0.948767 and 0.948630, on test data, respectively.
Keyword:
Deep learning (DL)
human activity recognition (HAR)
sequential data analysis
time-series analysis
wearable sensor data

期刊

IEEE Sensors Journal 封面图
IEEE Sensors Journal
IF:
4.5
论文数:
2.2W
被引数:
7.3W

机构

I
indian institute of technology system (iit system)
学者数:
9.5W
论文数: 9.9W
被引数: 93
引用论文

引用论文

err分享
err收藏
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV
err2015-01-01
err0
PREAI
errC. Perréard; Y. Ladner; F. d'Orlyé; S. Descroix; V. Taniga; A. Varenne; F. Kanoufi; C. Slim; S. Griveau; F. Bedioui
err分享
err收藏
Endoscopic Gold Fiducial Marker Placement into the Bladder Wall to Optimize Radiotherapy Targeting for Bladder-Preserving Management of Muscle-Invasive Bladder Cancer: Feasibility and Initial Outcomes
err2014-03-03
err0
errOAAI
errMaurice M. Garcia; Alexander R. Gottschalk; Jonathan Brajtbord; Badrinath R. Konety; Maxwell V. Meng; Mack Roach; Peter R. Carroll
err分享
err收藏
err分享
err收藏
Role of District Heating in Systems with a High Share of Renewables: Case Study for the City of Osijek
err2016-09-01
err0
errOAAI
errTomislav Novosel; Tomislav Pukšec; Goran Krajačić; Neven Duić
err分享
err收藏
Online Learning of Wearable Sensing for Human Activity Recognition
err2022-12-01
err8
PREAI
errZhang, Yiwei; Gao, Bin; Yang, Daili; Woo, Wai Lok; Wen, Houlai
err分享
err收藏
Efficient dense labelling of human activity sequences from wearables using fully convolutional networks
err2018-06-01
err76
PREAI
errYao, Rui; Lin, Guosheng; Shi, Qinfeng; Ranasinghe, Damith C.
err分享
err收藏
On the Personalization of Classification Models for Human Activity Recognition
err2020-01-01
err97
errOAAI
errFerrari, Anna; Micucci, Daniela; Mobilio, Marco; Napoletano, Paolo
err分享
err收藏
Deep learning for sensor-based activity recognition: A survey
err2019-03-01
err1.1K
errOAAI
errWang, Jindong; Chen, Yiqiang; Hao, Shuji; Peng, Xiaohui; Hu, Lisha
err分享
err收藏
学者 查看更多内容