I'm implementing an accelerometer-based pedometer, and I was wondering if there was any known algorithms to handle that.
-
1Do you have some data? Can you deduce what a step looks like? Now ask how to find features of that kind in the time series. – dmckee --- ex-moderator kitten Jun 16 '11 at 16:49
-
no data,, but I think there has to be some ready thought algorithms – Bassel Alkhateeb Jun 18 '11 at 07:53
-
There is some data in the paper that Ali linked. The thing is that the details will depend on the sensitivity, sample rate, and noisiness of the device that you have. So at some point you are going to need some data. Instrumentation problems are like that. – dmckee --- ex-moderator kitten Jun 18 '11 at 16:09
3 Answers
You have probably found this:
Enhancing the Performance of Pedometers Using a Single Accelerometer
Anyhow, I am also interested in finding a good algorithm, I am curios what other answers you will get. :)

- 56,466
- 29
- 168
- 265
There's an interesting paper (with source code) here that may be of help: http://www.analog.com/static/imported-files/application_notes/47076299220991AN_900.pdf.
The charts are interesting. If I were to do this myself I would probably sample the data at a fairly high frequency, convert to frequency domain with a FFT, apply a digital band-pass filter to cut off all frequencies outside the expected minimum/maximum walking speeds (including any DC offset), do a reverse-FFT to reconstruct the now-filtered signal and then run the resulting data through an edge-detector with a Hysteresis function. This is all pure speculation of course but looking at those charts I think it would work, it would be relatively fast to code up and well within the processing power of a mobile phone.

- 15,731
- 3
- 31
- 58
-
1There's another paper here with an very simple algorithm explained in detail: http://www.enggjournals.com/ijcse/doc/IJCSE12-04-05-266.pdf – Mark Feldman Dec 06 '13 at 02:53
-
Also there's over 2GB of raw data at this site of accelerometer data for people engaged in various activities: http://architecture.mit.edu/house_n/data/Accelerometer/BaoIntilleData04.htm – Mark Feldman Dec 06 '13 at 02:57
-
@MarkFelman - The data isn't there anymore. Do you know where it might be found? – Omnifarious Jan 25 '17 at 20:25
There is an app called Sensor data that you can uses to gather experimental data so you can then analyze it and try to find an algorithm.
Its going to be quite tricky to find a very good algorithm especially for the iPhone since its accelerometer is quite noisy

- 595
- 1
- 7
- 18