Activities of Daily Living Classification using Recurrent Neural Networks

被引：0

作者：

Jurca, Roxana ^{[1
]}

Cioara, Tudor ^{[1
]}

Anghel, Ionut ^{[1
]}

Antal, Marcel ^{[1
]}

Pop, Claudia ^{[1
]}

Moldovan, Dorin ^{[1
]}

机构：

[1] Tech Univ Cluj Napoca, Dept Comp Sci, Fac Automat & Comp Sci, Cluj Napoca, Romania

来源：

2018 17TH ROEDUNET IEEE INTERNATIONAL CONFERENCE: NETWORKING IN EDUCATION AND RESEARCH (ROEDUNET) | 2018年

基金：

欧盟地平线“2020”;

关键词：

Daily Living Activities; Recurrent Neural Networks; Long Short Term Memory; Machine Learning;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we address the problem of classifying the daily life activities of a person out of sensor based monitored data. We propose the use of recurrent neural networks to track of successive sensor data inputs and Long Short-Term Memory cells to address the issues regarding the long-time dependencies in activities' monitored data. The recurrent neural network model was implemented using TensorFlow library. The results are promising showing a mean accuracy of 82.5 using basic cross validation respectively 87.16% using leave one subject out method. Our results are comparable with the ones reported in the state of the art being slightly better in case of the leave one person out validation approach.

引用

页数：4

共 7 条

[1]

[Anonymous], DEEP CONVOLUTIONAL N

[2]

[Anonymous], LECT NOTES COMPUTER

[3] Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions [J].

Ermes, Miikka ;

Parkka, Juha ;

Mantyjarvi, Jani ;

Korhonen, Ilkka .

IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2008, 12 (01) :20-26

[4]

Hanlon J., WHY IS SO MUCH MEMOR

[5] Hierarchical, Multi-Sensor Based Classification of Daily Life Activities: Comparison with State-of-the-Art Algorithms Using a Benchmark Dataset [J].

Leutheuser, Heike ;

Schuldhaus, Dominik ;

Eskofier, Bjoern M. .

PLOS ONE, 2013, 8 (10)

[6]

Ordonez F. J., 2016, DEEP CONVOLUTIONAL L

[7]

Reiss A., 2013, Towards robust activity recognition for everyday life: Methods and evaluation

← 1 →