A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition

Prudhvi Tej Chinimilli, Sangram Redkar, Thomas Sugar

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The current state-of-the-art methods utilize multiple sensors and derive numerous features to perform human locomotion recognition. The use of multiple sensors causes discomfort to the users. Also, the derivation of numerous features for multiple sensors poses real-time processing issues. This paper presents a real-time human locomotion recognition system using a single inertial measurement unit placed on the human thigh to capture thigh angular data. Two features, amplitude ( A ) and omega ( omega ), are derived from the adaptive time window of thigh angular data. An adaptive time window is built using two consecutive peaks in the thigh angle signal. The machine learning algorithms, such as linear support vector machine and k -nearest neighbors, are employed on the A - omega feature space to perform the classification. A total number of six periodic activities are considered in this paper that includes level walking, stair ascent, stair descent, uphill, downhill, jogging, and running. The experiments are performed on six healthy subjects in controlled (motion capture laboratory) and uncontrolled (outdoor) environmental conditions to evaluate the efficacy of the algorithm. The A - omega feature-based method achieved a significant classification accuracy of 98.1% and 93.3% for controlled and uncontrolled experiments, respectively. Also, it reported a fast mean activity recognition time of 80 ms.

Original languageEnglish (US)
Article number8626125
Pages (from-to)4271-4282
Number of pages12
JournalIEEE Sensors Journal
Volume19
Issue number11
DOIs
StatePublished - Jun 1 2019
Externally publishedYes

Fingerprint

locomotion
thigh
Stairs
Sensors
Units of measurement
sensors
Learning algorithms
Support vector machines
Learning systems
Experiments
machine learning
walking
ascent
descent
Processing
derivation
causes

Keywords

  • gait recognition
  • Human activity classification
  • patient monitoring
  • wearable robots
  • wearable sensors

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition. / Chinimilli, Prudhvi Tej; Redkar, Sangram; Sugar, Thomas.

In: IEEE Sensors Journal, Vol. 19, No. 11, 8626125, 01.06.2019, p. 4271-4282.

Research output: Contribution to journalArticle

@article{f0fb0590e9504892ac7c8d20c74c452c,
title = "A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition",
abstract = "The current state-of-the-art methods utilize multiple sensors and derive numerous features to perform human locomotion recognition. The use of multiple sensors causes discomfort to the users. Also, the derivation of numerous features for multiple sensors poses real-time processing issues. This paper presents a real-time human locomotion recognition system using a single inertial measurement unit placed on the human thigh to capture thigh angular data. Two features, amplitude ( A ) and omega ( omega ), are derived from the adaptive time window of thigh angular data. An adaptive time window is built using two consecutive peaks in the thigh angle signal. The machine learning algorithms, such as linear support vector machine and k -nearest neighbors, are employed on the A - omega feature space to perform the classification. A total number of six periodic activities are considered in this paper that includes level walking, stair ascent, stair descent, uphill, downhill, jogging, and running. The experiments are performed on six healthy subjects in controlled (motion capture laboratory) and uncontrolled (outdoor) environmental conditions to evaluate the efficacy of the algorithm. The A - omega feature-based method achieved a significant classification accuracy of 98.1{\%} and 93.3{\%} for controlled and uncontrolled experiments, respectively. Also, it reported a fast mean activity recognition time of 80 ms.",
keywords = "gait recognition, Human activity classification, patient monitoring, wearable robots, wearable sensors",
author = "Chinimilli, {Prudhvi Tej} and Sangram Redkar and Thomas Sugar",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/JSEN.2019.2895289",
language = "English (US)",
volume = "19",
pages = "4271--4282",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition

AU - Chinimilli, Prudhvi Tej

AU - Redkar, Sangram

AU - Sugar, Thomas

PY - 2019/6/1

Y1 - 2019/6/1

N2 - The current state-of-the-art methods utilize multiple sensors and derive numerous features to perform human locomotion recognition. The use of multiple sensors causes discomfort to the users. Also, the derivation of numerous features for multiple sensors poses real-time processing issues. This paper presents a real-time human locomotion recognition system using a single inertial measurement unit placed on the human thigh to capture thigh angular data. Two features, amplitude ( A ) and omega ( omega ), are derived from the adaptive time window of thigh angular data. An adaptive time window is built using two consecutive peaks in the thigh angle signal. The machine learning algorithms, such as linear support vector machine and k -nearest neighbors, are employed on the A - omega feature space to perform the classification. A total number of six periodic activities are considered in this paper that includes level walking, stair ascent, stair descent, uphill, downhill, jogging, and running. The experiments are performed on six healthy subjects in controlled (motion capture laboratory) and uncontrolled (outdoor) environmental conditions to evaluate the efficacy of the algorithm. The A - omega feature-based method achieved a significant classification accuracy of 98.1% and 93.3% for controlled and uncontrolled experiments, respectively. Also, it reported a fast mean activity recognition time of 80 ms.

AB - The current state-of-the-art methods utilize multiple sensors and derive numerous features to perform human locomotion recognition. The use of multiple sensors causes discomfort to the users. Also, the derivation of numerous features for multiple sensors poses real-time processing issues. This paper presents a real-time human locomotion recognition system using a single inertial measurement unit placed on the human thigh to capture thigh angular data. Two features, amplitude ( A ) and omega ( omega ), are derived from the adaptive time window of thigh angular data. An adaptive time window is built using two consecutive peaks in the thigh angle signal. The machine learning algorithms, such as linear support vector machine and k -nearest neighbors, are employed on the A - omega feature space to perform the classification. A total number of six periodic activities are considered in this paper that includes level walking, stair ascent, stair descent, uphill, downhill, jogging, and running. The experiments are performed on six healthy subjects in controlled (motion capture laboratory) and uncontrolled (outdoor) environmental conditions to evaluate the efficacy of the algorithm. The A - omega feature-based method achieved a significant classification accuracy of 98.1% and 93.3% for controlled and uncontrolled experiments, respectively. Also, it reported a fast mean activity recognition time of 80 ms.

KW - gait recognition

KW - Human activity classification

KW - patient monitoring

KW - wearable robots

KW - wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=85065450860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065450860&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2019.2895289

DO - 10.1109/JSEN.2019.2895289

M3 - Article

VL - 19

SP - 4271

EP - 4282

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 11

M1 - 8626125

ER -