IoT Based Biometrics Implementation on ECG

Published on . Written by

IoT Based Biometrics Implementation on ECG
The conventional authentication technologies like RFID tags and authentication cards has a lot of weakness, biometric method of authentication is a prompt replacement for this. Biometrics such as fingerprints, voices and ECG signals are unique human characters that cannot be tampered or replicated. This facilitates real time system implementations. And it is also proven to be more accurate with less than 2 seconds of processing time, facilitating the authentication system to be faster and reliable.

Read more..
Finger print based authentication is the most widely used ones when it comes to biometric. But our finger prints could easily be taken from the glasses, doors, tables that we touched. For this, biometric authentication based on ECG (Electrocardiogram) provides an intelligent solution.


Skyfi Labs Projects
For many years, ECG is used for diagnosing and monitoring of heart condition of individuals. And it is still the most effective way to identify the heart problems. The ECG signal has a unique morphological shape due to the anatomical structure of the heart and physiological conditions. The ECG morphology consists of P, R, and T wave amplitudes, the slope information and temporal distance between wave boundaries provides the individuality for the user. ECG signal is valid to be used as a strong biometric authentication process for the following reasons.

  1. The ECG is a non-invasive test and can be easily measured by placing 2 fingers on the sensory plates
  2. Although the ECG for all the persons has the same P, R, and T waves, the size, position, thickness of heart varies from person to person. So a unique ECG signal will be produced from each person.
  3. ECG-based authentication systems need limited computational processing power for recognizing individuals
The proposed project is an IoT based real time authentication system that is based on the RR Discrete Cosine Transform (DCT). The analysing process of this system depends on using the DCT coefficients which is extracted from a single measured ECG beat. The system uses Raspberry Pi as the IOT sensory note to send the measured data for verification process using the TCP/IP protocol.

Project Description:

  1. Raspberry Pi Architecture: The Raspberry Pi is a series of credit card sized single board computers that can perform the actions of a fully capable computer. It is an open source hardware technology combined with a programming language and an Integrated Development Environment (IDE). The Raspberry Pi has four distinct power modes,
    • The run mode: The quality of the scanned finger print image is the decisive factor for the identification purpose. This can be achieved by using a high-definition finger print scanner which can tolerate the skin types, colours, damages and dryness factors.
    • The standby mode: The main course clocks are shut down i.e. the parts of the CPU that process instructions are no longer running in this mode. But the power circuits on the core will be still active. The core can be quickly woken up by a process generating a special call to the CPU called an interrupt.
    • The shutdown mode: The board will be in a complete shutdown with no power
    • The dormant mode: The core will be powered down and all the caches are left powered ON
  2. Raspbian OS: Raspbian OS is the operating system that is available for Raspberry Pi. Raspbian is based upon the Debian Wheezy Linux operating system and has been optimized for its usage with Raspberry Pi.
  3. Python: Python is the programming language that is used to operate the Raspberry Pi. It is considered as one of the powerful programming languages out there to operate a microcontroller. Basically, Python programming language is used as a scripting language for Linux. Generally Python program contains a series of commands and the program will be executed by the computer from top to bottom.

Project Implementation:

  1. There are 2 major parts to the system. It consists of a remote or a mobile side and a fixed (server) side. This facilitates to combine multiple nodes with a single server and this structure in turn increases the capability of the system and also reduces the cost.
  2. The mobile side contains the ECG module for acquiring an ECG signal, a 16-bit high precision ADC and Raspberry Pi. And the server side contains a web server that manages the system database, which is actually the SQLite database.
  3. The main concept of this system is to compare the features that are extracted from the DCT coefficients for the first RR interval, which has been already stored in the database hosted in the server side
  4. If the correlated result is more than 95% for all the durations than the person is evaluated to be the one who has the authorization. The entire process will take 10 seconds and then the whole process will restart.
  5. MIT-BIH database for normal and abnormal records is used beside the real-time data acquired for system validation and evaluation
  6. The pre-processing stages, RR detection and feature extraction are done by using the DCT performed with the help of Raspberry Pi as the remote side and the web-based database & SQL management application are hosted on the server side.
Programming language: Python Programming

Kit required to develop IoT Based Biometrics Implementation on ECG:
Technologies you will learn by working on IoT Based Biometrics Implementation on ECG:


Any Questions?


Subscribe for more project ideas