Performance Analysis of Data Parallelism Technique in Machine Learning for Human Activity Recognition Using LSTM

2019 ◽  
Author(s):  
Tri D.T. Nguyen ◽  
Eui-Nam Huh ◽  
Jae Ho Park ◽  
Md Imtiaz Hossain ◽  
Md Delowar Hossain ◽  
...  
Keyword(s):  
Machine Learning ◽  
Performance Analysis ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Data Parallelism

Machine Learning approach applied to Human Activity Recognition – An application to the VanKasteren dataset

2021 ◽  
Vol 191 ◽  
pp. 367-372
Author(s):  
Ariza-Colpas Paola ◽  
Oñate-Bowen Alvaro Agustín ◽  
Suarez-Brieva Eydy del Carmen ◽  
Oviedo-Carrascal Ana ◽  
Urina Triana Miguel ◽  
...  
Keyword(s):  
Machine Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Learning Approach ◽  
Machine Learning Approach

scholarly journals A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5770 ◽  
Author(s):  
Keshav Thapa ◽  
Zubaer Md. Abdullah Al ◽  
Barsha Lamichhane ◽  
Sung-Hyun Yang
Keyword(s):  
Machine Learning ◽  
Random Field ◽  
Activity Recognition ◽  
Human Activity ◽  
Short Term Memory ◽  
Conditional Random Field ◽  
Human Activity Recognition ◽  
Second Phase ◽  
Complex Activity ◽  
Two Phase

Human activity recognition has become an important research topic within the field of pervasive computing, ambient assistive living (AAL), robotics, health-care monitoring, and many more. Techniques for recognizing simple and single activities are typical for now, but recognizing complex activities such as concurrent and interleaving activity is still a major challenging issue. In this paper, we propose a two-phase hybrid deep machine learning approach using bi-directional Long-Short Term Memory (BiLSTM) and Skip-Chain Conditional random field (SCCRF) to recognize the complex activity. BiLSTM is a sequential generative deep learning inherited from Recurrent Neural Network (RNN). SCCRFs is a distinctive feature of conditional random field (CRF) that can represent long term dependencies. In the first phase of the proposed approach, we recognized the concurrent activities using the BiLSTM technique, and in the second phase, SCCRF identifies the interleaved activity. Accuracy of the proposed framework against the counterpart state-of-art methods using the publicly available datasets in a smart home environment is analyzed. Our experiment’s result surpasses the previously proposed approaches with an average accuracy of more than 93%.

Sign in / Sign up

Export Citation Format

Share Document