GithubHelp home page GithubHelp logo

shophine / gaitauth Goto Github PK

View Code? Open in Web Editor NEW

This project forked from thanghoang/gaitauth

0.0 0.0 0.0 47.52 MB

Implementation of Authentication Scheme using Gait Signals Captured from Accelerometer

Home Page: https://arxiv.org/abs/1602.03199

License: MIT License

MATLAB 100.00%

gaitauth's Introduction

GaitAuth

Implementation of Authentication Scheme using Gait Signals Captured from Accelerometer. The full paper is available at http://ieeexplore.ieee.org/abstract/document/7518029/ (free version: https://arxiv.org/abs/1602.03199).

Prerequistite Library

  1. libSVM (download link: https://www.csie.ntu.edu.tw/~cjlin/libsvm/)

Usage

The main functions are located in mainAuthentication.m (for authentication scheme) and mainRecognition.m (for recognition scheme)

Dataset

IMPORTANT NOTE: The dataset is only used for academic or research purposes. The authors do not allow anyone to use this dataset for any commercial purposes.

The dataset is located in DATASET folder, which contain gait signals of 38 users and is collected according to the following configurations

  • Device: Google Nexus One Mobile Phone (specs: http://en.wikipedia.org/wiki/Nexus_One)
  • Platform: Android 2.3
  • Physical sensors used: Accelerometer , Magnetometer
  • Sampling rate: 27 Hz with the configuration of SENSOR_DELAY_FASTEST in Android SDK
  • Number of Participants: 38

Data in each walking session is recorded and saved in separate files which are named according to following pattern: UserID_Gender_SessionID_[DeviceName]DataType_SessionSequence.txt.

For example:

ID26_M_173358_[NexusOne]BMA 150 3-axis Accelerometer_10.txt

contains the raw acceleration data of user #26 who is Male, recorded in the session #173358 with Sequence #10.

There are three types of data in this dataset:

  1. BMA 150 3-axis Accelerometer: raw acceleration data which also capture the influence of gravity. Each line consists of 4 components separated by a comma (,) including (i) the timestamp, (ii) the x-dimensional value a_x, (iii) y-dimensional value a_y, and (iv) z-dimensional value a_z. Those values are in g unit (i.e. 1g = 9.8 m/s2).

  2. Linear Acceleration Sensor: acceleration data in which the influence of gravity is completely removed. Each line consists of 4 components separated by a comma (,) including (i) the timestamp, (ii) the x-dimensional value a_x, (iii) y-dimensional value a_y, and (iv) z-dimensional value a_z. Those values are in g unit (i.e. 1g = 9.8 m/s2).

  3. Rotation Matrix: contains 9 elements in the 3x3 rotation matrix as presented in the paper.

Citing

Any use of this implementation and dataset should cite our paper according to the following format:

Hoang, T., Choi, D. and Nguyen, T., On the instability of sensor orientation in gait verification on mobile phone. In 12th IEE E International Joint Conference on e-Business and Telecommunications (ICETE), 4 (2015): 148-159.

Bibtex format

@inproceedings{hoang2015instability, title={On the instability of sensor orientation in gait verification on mobile phone}, author={Hoang, Thang and Choi, Deokjai and Nguyen, Thuc}, booktitle={e-Business and Telecommunications (ICETE), 2015 12th International Joint Conference on}, volume={4}, pages={148--159}, year={2015}, organization={IEEE} }

Further Information

For any inquiries, bugs, and assistance regarding using the code, please contact Thang Hoang ([email protected]).

gaitauth's People

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.