Human activity recognition from mobile inertial sensors using recurrence plots

Inertial sensors are present in most mobile devices nowadays and such devices are used by people during most of their daily activities. In this paper, we present an approach for human activity recognition based on inertial sensors by employing recurrence plots (RP) and visual descriptors. The pipeline of the proposed approach is the following: compute RPs from sensor data, compute visual features from RPs and use them in a machine learning protocol. As RPs generate texture visual patterns, we transform the problem of sensor data classification to a problem of texture classification. Experiments for classifying human activities based on accelerometer data showed that the proposed approach obtains the highest accuracies, outperforming time- and frequency-domain features directly extracted from sensor data. The best results are obtained when using RGB RPs, in which each RGB channel corresponds to the RP of an independent accelerometer axis.

• Publication year

  2017

• Venue

  arXiv.org

• Publication date

  2017-12-05

• Fields of study

  Computer Science, Engineering

• Identifiers
  arXiv 1712.01429
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Fusion of time series representations for plant recognition in phenology studies

  2016influential reference
• A Survey of Online Activity Recognition Using Mobile Phones

  2015influential reference
• Wearable Inertial Sensors: Applications, Challenges, and Public Test Benches

  2015cited by this paper
• R: A language and environment for statistical computing.

  2014cited by this paper
• Visual word spatial arrangement for image retrieval and classification

  2014cited by this paper
• Are gait variability and stability measures influenced by directional changes?

  2014influential reference
• Extracting Texture Features for Time Series Classification

  2014influential reference
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

  2013influential reference
• Recurrence quantification analysis features for environmental sound recognition

  2013influential reference
• Human Activity Recognition: Using Wearable Sensors and Smartphones

  2013cited by this paper
• Recurrence quantification analysis of gait in normal and hypovestibular subjects.

  2012influential reference
• Convulsive seizure detection using a wrist‐worn electrodermal activity and accelerometry biosensor

  2012influential reference
• Recurrence textures for human activity recognition from compressive cameras

  2012influential reference
• Modelling techniques for analysis of human activity patterns

  2012influential reference
• Exploring Alternative Spatial and Temporal Dense Representations for Action Recognition

  2011cited by this paper
• A survey on vision-based human action recognition

  2010cited by this paper
• Visual Word Ambiguity

  2010cited by this paper
• Evaluating Color Descriptors for Object and Scene Recognition

  2010cited by this paper
• Learning mid-level features for recognition

  2010cited by this paper
• Comparison of recurrence plot features of swallowing and breath sounds

  2008influential reference
• A Dynamical Systems Analysis of Spontaneous Movements in Newborn Infants

  2007cited by this paper
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006cited by this paper
• Histograms of oriented gradients for human detection

  2005influential reference
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• SASI: a generic texture descriptor for image retrieval

  2003cited by this paper
• A compact and efficient image retrieval approach based on border/interior pixel classification

  2002cited by this paper
• Texture Recognition and Image Retrieval Using Gradient Indexing

  2000cited by this paper
• Nonlinear time series analysis of normal and pathological human walking.

  2000cited by this paper
• Use of recurrence plots in analysis of time-series data

  1992cited by this paper
• Recurrence Plots of Dynamical Systems

  1987influential reference

• WavI2I: Wavelet-Driven Inertial Imaging for Robust Industrial Human Activity Recognition

  2025cites this paper
• GeXSe (Generative Explanatory Sensor System): A Deep Generative Method for Human Activity Recognition of Smart Spaces IOT

  2025cites this paper
• Data Reconstruction Methods in Multi-Feature Fusion CNN Model for Enhanced Human Activity Recognition

  2025cites this paper
• GeXSe (Generative Explanatory Sensor System): An Interpretable Deep Generative Model for Human Activity Recognition in Smart Spaces

  2023cites this paper
• GeXSe (Generative Explanatory Sensor System): An Interpretable Deep Generative Model for Human Activity Recognition in Smart Spaces

  2023cites this paper
• Predicting Human Motion Signals Using Modern Deep Learning Techniques and Smartphone Sensors

  2021cites this paper
• Reliability of Recurrence Quantification Analysis Measures for Sit-to-Stand and Stand-to-Sit Activities in Healthy Older Adults Using Wearable Sensors

  2021cites this paper
• Recurrence Quantification Analysis for Human Activity Recognition

  2020cites this paper
• Lagged encoding for image‐based time series classification using convolutional neural networks

  2020cites this paper
• GestureKeeper: Gesture Recognition for Controlling Devices in IoT Environments

  2019cites this paper
• Fusion of Multiple Representations Extracted from a Single Sensor’s Data for Activity Recognition Using CNNs

  2019cites this paper
• Activity Recognition from Mobile Phone using Deep CNN

  2019cites this paper
• Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition

  2018cites this paper
• Human Activity Recognition Based on Transfer Learning

  2018cites this paper
• Design of Novel Deep Learning Models for Real-time Human Activity Recognition with Mobile Phones

  2018cites this paper
• Classification of Recurrence Plots' Distance Matrices with a Convolutional Neural Network for Activity Recognition

  2018cites this paper