Abstract | ||
---|---|---|
This paper presents an human sensing (HS) system based on Hidden Markov Models (HMMs) for classifying physical activities: walking, walking-upstairs, walking-downstairs, sitting, standing and lying down. The system includes a feature extractor (developed by the authors and presented in a previous work), an HMMs training module and an HAR module. All experiments have been done using a publicly available dataset named UCI Human Activity Recognition Using Smartphones. The final results using HMMs obtain comparable results to other recognition methods. Some improvements have been obtained when considering a discriminative HMM training procedure. The best result obtains an activity recognition error rate (ARER) of 2.5%. This work is focused on independent activity recognition and extends other works from the same authors focused on activity segmentation and feature extraction. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/MIM.2016.7777649 | IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE |
Keywords | Field | DocType |
Hidden Markov models,Training,Feature extraction,Error analysis,Computational modeling,Human factors | Feature extraction,Artificial intelligence,Ubiquitous computing,Engineering,Hidden Markov model,Machine learning,Government | Journal |
Volume | Issue | ISSN |
19 | 6 | 1094-6969 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rubén San-Segundo-Hernández | 1 | 15 | 2.36 |
Julián D. Echeverry-Correa | 2 | 10 | 2.35 |
Christian Salamea Palacios | 3 | 10 | 1.63 |
José Manuel Pardo | 4 | 152 | 30.36 |