Agricultural Research Management Information System

Home
Research Summary
Search
About Us
- ARMIS
- Brochure
Contact Us
Report
User Request
Data Input
Help
- Operation Manual
  - PDF
  - Video
- Program Area & Commodity
We have reached 37600 number of research entries at this moment.

- Logout

Research Detail

Home
Research
Detail

Human Walkjng Steps Counting and Distance Measurement for Gravitational Threshold on Smart Phones

Nusrat Jahan
Faculty of Computer Science and Engineering, Patuakhali Science and Technology University

M. A. Masud
Assistant Professor, Department of Computer Science and lnformation Technology, Patuakhali Science and Technology University, Patuakhali , Bangladesh

Nushrat Jahan Bubly
Faculty of Computer Science and Engineering, Patuakhali Science and Technology University

Lopa Khatun
Faculty of Computer Science and Engineering, Patuakhali Science and Technology University

M. K. H. Chowdhury
Assistant Professor, Department of Computer Science and Engineering, Comilia University

Abstract/ Executive Summary:

Nowadays smart phones are becoming more familiar tool which are highly adapted in our everyday life. Most importantly these smart phones are programmable and equipped with various sensors that can be utilized to build up a wide variety of useful applications. In this paper, we present a method for counting the number of steps of a smart phone user, while walking at any variable speed. Hence, the cellular device must be configured with the acceleration and orientation sensor. For this purpose, the steps are detected based on a gravity with respect to time and the calculation of gravity is done from raw data of those sensors. The user 's walking motion is recognized by android sensor (acceleration and orientation) and generated raw data. The walking distance with average step length 2.5 feet is assigned from survey study.

Keywords: Gravity, Raw-data , Sensor, Smartphone, Step length , Threshold-value.

Location: Department of Computer Science and lnformation Technology, Patuakhali Science and Technology University

Start Date: 00-03-2013

End Date: 00-07-2013

Program Area: Knowledge Management

Non-commodity: Database Management

Objectives:

1. To maintain physical fitness every person need effective walking. Therefore, quantitative assessment of activities is important. For researchers interested in quantifying the energy expended in physical activity, measurement of walking behavior is an important concern.

Methodology:

Step counters are becoming popular as an everyday exercise measurer and motivator. Accelerometers are becoming increasingly ubiquitous in commercially sold devices, such as mobile phones like Apple i-Phone or Samsung Galaxy Ace. But not only using the acceleration data the result of detection steps or distance is not so much accurate . If we combine acceleration sensors with orientation sensors the result will be more accurate. Here we propose step detection algorithm that utilizes the accelerometer of a waist-mounted smart phone. Also we calculate distance between starting state and ending state of walking. Modern mobile phones are often equipped with acceleration sensors. Considering the fact a mobile phone can be at any position on the user 's body, with time-varying orientation change, we use the magnitude of 3-axis accelerometer reading instead of its vertical and horizontal components. The Orientation sensor also have three axes. The three axes are azimuth, pitch and roll. Azimuth is used to detect the compass direction , where 0 = North , 90 = East, etc. Pitch is used to track the devices side to side orientation, where vertical is around 0, tilted to the left side on top is around 90, and tilted to the right side on top is around -90. The documentation for pitch says the values range between -180 and 180 The roll represents the degree to wh ich the device is tilled back and forth . A more promising possibility for measuring distances is counting steps based on the readings of the acceleration sensor and orientation sensor. By counting steps, distances cannot be measured exactly, but good estimates can be made. Multi-sensor pedometer application makes acceleration mapped to the gravity direction using orientation sensor, and gains accurate gravity acceleration changes. The steps feature extraction of the single acceleration sensor is to analyze the absolute values of the acceleration to determine the wave crest (wave troughs). The acceleration values were recorded in meters per second squared (rn/s²).

Source of Information: J. Patuakhali Sci and Tech. Univ. 2013, 4 (2) : 105-116; ISSN 1996-4501

Article Link (Online Journal):

Funding Source:

Total Budget (Tk.) :

Achievement/Findings:

The cellular device must be configured with the acceleration and orientation sensor. For this purpose, the steps are detected based on a gravity with respect to time and the calculation of gravity is done from raw data of those sensors. The user 's walking motion is recognized by android sensor (acceleration and orientation) and generated raw data. The walking distance with average step length 2.5 feet is assigned from survey study.

Knowledge Management: Journal