Timeline for How to classify accelerometer data?
Current License: CC BY-SA 3.0
31 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 9, 2017 at 16:12 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jun 9, 2017 at 2:23 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| May 9, 2017 at 23:50 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Apr 9, 2017 at 23:43 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Mar 10, 2017 at 23:17 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Feb 8, 2017 at 22:38 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jan 9, 2017 at 20:47 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Dec 10, 2016 at 19:25 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Nov 10, 2016 at 18:27 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Oct 11, 2016 at 17:33 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Sep 11, 2016 at 16:51 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 12, 2016 at 16:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 13, 2016 at 15:53 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jun 13, 2016 at 15:40 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| May 14, 2016 at 15:11 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Nov 16, 2015 at 0:54 | answer | added | Andrea | timeline score: 1 | |
| May 18, 2015 at 17:26 | answer | added | Naveen | timeline score: 1 | |
| Mar 19, 2015 at 13:46 | answer | added | Clayton Pipkin | timeline score: 1 | |
| Aug 20, 2014 at 15:53 | comment | added | Matt L. | OK, if you use the accelerometer data, you could in principle just use the sign of the acceleration (- for braking, + for accelerating). The problem is the noise. Probably you can sufficiently increase the SNR by using a Savitzky Golay filter. | |
| Aug 20, 2014 at 14:42 | comment | added | riik | @MattL. you are right about that. However, the speed signal is just for illustrational purposes (derived form GPS Data). For my project I just want to use the accelerometer data to detect acceleration and braking. | |
| Aug 20, 2014 at 13:46 | comment | added | Matt L. | Maybe I'm missing something but why can't you use the piecewise constant speed signal? It very clearly shows where the acceleration is positive and where it is negative. | |
| Aug 20, 2014 at 13:23 | comment | added | riik | @PaulR thanks for the clarification! I just updated the question accordingly. | |
| Aug 20, 2014 at 13:21 | history | edited | riik | CC BY-SA 3.0 |
deleted 5 characters in body
|
| Aug 20, 2014 at 13:13 | comment | added | Paul R | This will seem pedantic, but in the long run it should help you when you are e.g. using Google to search for relevant material on this subject: it's "brake", not "break" - the verb "to break" means "to make kaput", which is a very different meaning than "to brake", as in to slow a vehicle! ;-) | |
| Aug 20, 2014 at 10:33 | history | tweeted | twitter.com/#!/StackSignals/status/502040727728422912 | ||
| Aug 20, 2014 at 9:53 | comment | added | riik | The blue line only indicates if the car is moving or is not moving at all (full stop). For example between 4000 and 6000 the car was breaking but didn't come to a full stop. But I also want to register these kind of breaks. Can you maybe give an example of such a condition? | |
| Aug 20, 2014 at 8:04 | comment | added | Gilles | Okay it's the number of samples. One way would be getting a sliding window of the size you're suggesting and putting conditions on the mean and variance of the collected samples , if necessary adding conditions on zero crossing intervals. But if you do the analysis without the short-time windows, can't the number of rising edges of the activity signal (blue signal) give you how many times you've accelerated, and falling edges for breaking ? | |
| Aug 20, 2014 at 6:56 | comment | added | riik | The unit of the x axis is time. I sampled with 60 Hz. So the values on the x axis divided by 60 would represent seconds. | |
| Aug 19, 2014 at 22:23 | comment | added | Gilles | What is the unit on the $x-\text{axis}$ ? | |
| Aug 19, 2014 at 20:07 | review | First posts | |||
| Aug 19, 2014 at 20:36 | |||||
| Aug 19, 2014 at 20:03 | history | asked | riik | CC BY-SA 3.0 |