You are on page 1of 4

TOTAL BODY ANALYSIS OF A SOLDIER USING ECG SIGNAL

The steps in this project can be broadly classified as ECG data


acquisition, Pre-processing (Denoising), Heart Beat detection(R-wave
detection), Feature extraction of various physical actions, Training and
Classification of actions.
The Primary step in this process is Pre-processing, removing various
noises from the raw ECG data that is obtained from the sensors.
Secondary step is R-wave Detection. Many R-wave detection algorithms
have been proposed by researchers for the past several decades. These
detection algorithms can be divided into the following mathematical
algorithms including [5]
Time domain detection algorithms. Considering that R-wave is
characterized by of high amplitude and the ECG signal is changing
quickly, these algorithms directly detect R-wave in time domain by using
detecting threshold of ECG signal with first-order or second-order
derivative. Time domain algorithms are often good enough for real-time
application but they are sensitive to interference. Thus such existing
algorithms are suitable for the ECG signal without changing quickly
sometimes.
Frequency domain detection algorithms. Firstly, obtain transformation
of ECG signal by linear or nonlinear transform, in which SNR is higher
than original ECG signal. Then apply appropriate threshold detection
rules. The representative transform includes wavelet transform, Hilbert
transform, etc. Transform domain algorithms often have high detection
rate and good robustness to interference but sometimes need more
detection time.
Other algorithms include template matching and morphologic filtering
algorithms, gene-based design, morphology-based design, zero-crossing
design and filter bank design.
Feature Extraction:
The Features extracted should reflect the various actions of the soldier.
Many research papers have been studied and found that the following
features might be effective for the purpose of the various physical actions.

Using HR(Heart Rate) and HRV(Heart Rate Variability),GSR:[1]


[2]
Normal HR= 60-100
Identification of state of a person using HR, HRV
Physical Stress level
i)
Anaerobic : HR=150-180 (weightlifting)
ii)
Aerobic : HR=120-150 (Yoga)
Mental Stress level: Increased HR and decreased HRV.

(a) RR interval data of a subject

(b) Skin conductance of a subject

Another idea is to prepare a model that maps an ECG signal to


different human emotions which can determine various physical
actions of a soldier.

1) The proposed methodology [3] for ECG feature extraction is based on


Empirical Mode Decomposition (EMD) which uses the fast fourier
transform to remove the noise from the ECG signal and uses the HilbertHaung Transform for extracting the features from the ECG signal.

2) In this work [4], the six basic emotional states (Happiness, sadness, fear,
surprise, disgust and neutral) were identified from the QRS complex of
electrocardiogram (ECG) signals. We focus specifically on the nonlinear
feature Hurst exponent computed using two methods namely rescaled
range statistics (RRS) and finite variance scaling (FVS). The non-linear

feature Hurst was computed using Rescaled Range Statistics (RRS) and
Finite Variance Scaling (FVS) methods. New Hurst features were proposed
by combining the existing RRS and FVS methods with Higher Order
Statistics (HOS). The features were then classified using four classifiers
Bayesian Classifier, Regression Tree, K- nearest neighbor and Fuzzy Knearest neighbour. Seventy percent of the features were used for training and
thirty percent for testing the algorithm. The Hurst computed using FVS and
HOS yields better results of 92.87% and 76.45% for random and subject
independent validation respectively using FKNN classifier.

[1] Activity-aware Mental Stress Detection Using Physiological Sensors


[2] hrv background
[3] Emotion Detection in Human Beings Using ECG Signals
[4] Emotion detection from QRS complex of ECG signals using Hurst Exponent
for different age groups
[5] The Application of Time-Frequency Analysis on Biomedical ECG Signals

You might also like