Real-Time Human Physical Activity Recognition with Low Latency Prediction Feedback Using Raw IMU Data

In the realm of Human Activity Recognition (HAR), supervised machine learning and deep learning are commonly used. Their training is done using time and frequency features extracted from raw data (inertial and gyroscopic). Nevertheless, raw data are seldom employed. In this paper, a dataset of able-bodied participants is recorded using 3 custom wireless motion sensors providing embedded IMU and sEMG detection and processing and a base station (a Raspberry Pi 3) running a classification algorithm. A Support Vector Machine with Radius Basis Function Kernel (RBF-SVM) is augmented using Spherical Normalization to achieve a motion classification accuracy of 97.35% between 8 body motions. The proposed classifier allows for real-time prediction callback with low latency output.

• Publication year

  2018

• Venue

  Annual International Conference of the IEEE Engineering in Medicine and Biology Society

• Publication date

  2018-07-01

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1109/EMBC.2018.8512252PMID 30440382
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• A multimodal adaptive wireless control interface for people with upper-body disabilities

  2017cited by this paper
• Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks

  2015cited by this paper
• Physical Human Activity Recognition Using Wearable Sensors

  2015cited by this paper
• Cost-Effective Activity Recognition on Mobile Devices

  2013cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Accelerometer Placement for Posture Recognition and Fall Detection

  2011cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• A Mobile Context Sharing System Using Activity and Emotion Recognition with Bayesian Networks

  2010cited by this paper
• On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation

  2010cited by this paper
• Activity identification using body-mounted sensors—a review of classification techniques

  2009cited by this paper
• Speaker verification using sequence discriminant support vector machines

  2005cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper

• IMU-based recognition of ergonomically unsafe postures in construction work using image encoding and Vision Mamba

  2026cites this paper
• Artificial Intelligence for automatic movement recognition: a network-based approach

  2025cites this paper
• Dual-Stage Attention-Based Model for Rehabilitation Activity Recognition Using Data From Wearable Sensors

  2025cites this paper
• A Low-Cost Inertial Measurement Unit Motion Capture System for Operation Posture Collection and Recognition

  2024cites this paper
• Design of an Energy Efficient Sensor Node for Wearable Applications

  2024cites this paper
• Vector-based Inertial Poser: Human pose estimation with high gain observer and deep learning using sparse IMU sensors

  2024cites this paper
• Activity Recognition Using a High Gain Observer and Spectrograms

  2023cites this paper
• Activity recognition using a combination of high gain observer and deep learning computer vision algorithms

  2023cites this paper
• Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction

  2023influential citation
• Real-Time Sensor-Embedded Neural Network for Human Activity Recognition

  2023cites this paper
• Real-Time Human Activity Recognition with IMU and Encoder Sensors in Wearable Exoskeleton Robot via Deep Learning Networks

  2022cites this paper
• Human climbing detection algorithm based on multi-level HRNET and LSTM network

  2022cites this paper
• New Sensor Data Structuring for Deeper Feature Extraction in Human Activity Recognition †

  2021cites this paper
• Real-Time Walking Gait Estimation for Construction Workers using a Single Wearable Inertial Measurement Unit (IMU)

  2021cites this paper
• Deep Learning for Classifying Physical Activities from Accelerometer Data

  2021cites this paper
• Real-time recognition of human lower-limb locomotion based on exponential coordinates of relative rotations

  2021influential citation
• Control of a Telepresence Robot Using Force data

  2020cites this paper
• Toward a robot swarm protecting a group of migrants

  2020cites this paper
• Balancing Timing and Accuracy Requirements in Human Activity Recognition Mobile Applications

  2019cites this paper
• IoT-FAR: A multi-sensor fusion approach for IoT-based firefighting activity recognition

  year unknowncites this paper