projets:plim:20142015:gr9
Différences
Ci-dessous, les différences entre deux révisions de la page.
| Les deux révisions précédentesRévision précédenteProchaine révision | Révision précédente | ||
| projets:plim:20142015:gr9 [2014/11/23 15:06] – palma | projets:plim:20142015:gr9 [2014/11/23 18:08] (Version actuelle) – palma | ||
|---|---|---|---|
| Ligne 13: | Ligne 13: | ||
| === Content of the Project === | === Content of the Project === | ||
| - | |||
| - | == Introduction == | ||
| - | |||
| - | Current mobile devices now incorporates a wide range of powerful sensors such as GPS, accelerometer, | ||
| - | Several methodologies have been used to monitor user activity from mobile phones embedded sensors. The widely used sensor for that purpose is the single [2] [3]… or multiple [17] tri-axis accelerometer sensor(s) used to either measure the user steps count [14] (pedometer) or, to accurately classify activities like walking, running and so on [1] [3] [4]… | ||
| - | |||
| - | In this project, we combine the data from a single tri-axis accelerometer sensor data with GPS sensor data in order to help distinguishing between different activities like walking, running and so on. Except [16] none of the selected related works uses GPS sensor data. | ||
| - | According to [1] and [15] the data gathered from sensors have to go through two different processes before the activities are able to be recognized. The first process is the features extraction and the second process is the classification. Some of the related works uses supervised classification algorithms [1] [5] [15] [17] whereas we used, in this paper, an unsupervised activity classification algorithm (k-means clustering). Indeed, we want to find hidden structure of unlabeled data leading the use of unsupervised learning. Also, according to [18] unsupervised learning is well suited to cluster sensor data into categories mapping onto meaningful label. | ||
| == Activities == | == Activities == | ||
| Ligne 30: | Ligne 22: | ||
| The sensors data have been gathered on a HTC Windows phone 8S from an application developed with the Windows Phone SDK 8.0. | The sensors data have been gathered on a HTC Windows phone 8S from an application developed with the Windows Phone SDK 8.0. | ||
| Sensors data are gathered during a 6s measurement windows. Accelerometer sampling period is set to 35ms by default, which gives up to 171 measures per axis per measurement window. GPS latitude and longitude are measured each second during the measurement window only if the user moved by more than 10m within this period of time. | Sensors data are gathered during a 6s measurement windows. Accelerometer sampling period is set to 35ms by default, which gives up to 171 measures per axis per measurement window. GPS latitude and longitude are measured each second during the measurement window only if the user moved by more than 10m within this period of time. | ||
| + | |||
| + | __We have used the following namespaces for measuring the sensors data:__ | ||
| + | - Windows.Devices.Sensors ([[http:// | ||
| + | - Windows.Devices.Geolocation ([[http:// | ||
| == Data filtering == | == Data filtering == | ||
| - | In order to remove the high frequency noise occurring on the accelerometer axis measurements in the real conditions, we implemented a Butterworth | + | In order to remove the high frequency noise occurring on the accelerometer axis measurements in the real conditions, we implemented a [[http:// |
| - | Also, walking and running activities generates a periodic pattern on the accelerometer axis data within a frequency range from 2Hz to 6Hz while resting and driving a car activities do not match any periodic pattern data on the accelerometer axis. The periodic pattern frequency feature cannot be measured in the time domain hence the use of a Fast Fourier Transform (FFT) applied on the accelerometer sensor raw (or filtered) in order to extract the pattern frequency feature. | + | Also, walking and running activities generates a periodic pattern on the accelerometer axis data within a frequency range from 2Hz to 6Hz while resting and driving a car activities do not match any periodic pattern data on the accelerometer axis. The periodic pattern frequency feature cannot be measured in the time domain hence the use of a [[http:// |
| == Features extraction == | == Features extraction == | ||
| Ligne 55: | Ligne 51: | ||
| == Classification == | == Classification == | ||
| - | The k-means unsupervised classification algorithm has been used to cluster features into categories mapping onto user activities. It is well suited for our purpose since it is fast and we know upfront the amount of clusters which corresponds to the user activities we want to track (resting, walking, running and driving a car). | + | The [[http:// |
| The k-means clustering algorithm computes the mean value of a ten dimension vector (the ten features defined earlier) and computes the Euclidian distance in between this value and the values of each cluster mean value (cluster’s centroid). The vector is assigned to the nearest cluster (with the lowest Euclidian distance). Then, the nearest cluster’s centroid is updated to take into account the new vector it has been assigned to. | The k-means clustering algorithm computes the mean value of a ten dimension vector (the ten features defined earlier) and computes the Euclidian distance in between this value and the values of each cluster mean value (cluster’s centroid). The vector is assigned to the nearest cluster (with the lowest Euclidian distance). Then, the nearest cluster’s centroid is updated to take into account the new vector it has been assigned to. | ||
| Ligne 66: | Ligne 62: | ||
| == Requirements == | == Requirements == | ||
| - | - Windows 8/8.1 Professionnal. | + | - Windows 8/8.1 Professional. |
| - Visual Studio 2013 SP2 update 3. | - Visual Studio 2013 SP2 update 3. | ||
| - Windows Phone SDK 8.0 | - Windows Phone SDK 8.0 | ||
| Ligne 72: | Ligne 68: | ||
| == Project zip file == | == Project zip file == | ||
| + | [[https:// | ||
| == Installation == | == Installation == | ||
| Ligne 107: | Ligne 104: | ||
| Once started, you will get the following user interface: | Once started, you will get the following user interface: | ||
| + | |||
| + | * [[https:// | ||
| + | |||
| + | This interface is mainly designed for a debug purpose. It displays real time data gathered for each measurement window on both accelerometer and GPS. Some sliders are also made available to modify some parameters (although we do not recommend to modify these parameters). | ||
| + | The GPS sensor status is also given by a LED (RED : GPS sensor not ready, GREEN : GPS sensor ready). | ||
| You have nothing to do. Just take the cell phone and rest, walk, run or drive a car to get sensors data gathered. | You have nothing to do. Just take the cell phone and rest, walk, run or drive a car to get sensors data gathered. | ||
| - | At the end of the day, you can open-up the statistics window to get a status about your daily activities: | ||
| + | Finally, the " | ||
| + | So, at the end of the day, you can open-up the statistics window to get a status about your daily activities: | ||
| + | |||
| + | * [[https:// | ||
| + | |||
| + | |||
| === RESULTS | === RESULTS | ||
| Ligne 117: | Ligne 124: | ||
| === CONCLUSION AND FUTURE WORK === | === CONCLUSION AND FUTURE WORK === | ||
| - | We have developed a methodology based on mobile phone accelerometer and GPS sensors to measure user activity. First results are very encouraging despite some instabilities noticed on the GPS measurements leading to wrong cluster mapping. This phenomena is aggravated by the fact that resting to walking and walking to running vectors are close (from a user speed standpoint of view) and very sensitive to speed (then GPS) measurement accuracy. On the other hand, GPS measures are key when dealing with driving activity. So, we could improve by disregarding the speed measurements that are below 15km/h (set to 0km/h) and rely only on the periodic pattern of each axis of the accelerometer to classify resting, walking and running activities. | + | We have developed a methodology based on mobile phone accelerometer and GPS sensors to measure user activity. First results are very encouraging despite some instabilities noticed on the GPS measurements leading to wrong cluster mapping. This phenomena is aggravated by the fact that resting to walking and walking to running vectors are close (from a user speed standpoint of view) and very sensitive to speed (then GPS) measurement accuracy. On the other hand, GPS measures are key when dealing with driving activity. So, we could improve |
| Also, the amount of dimensions used in the k-means vector is quite important making hard to ensure data globularity which is a requirement for the k-means algorithm to properly work [19]. The amount of dimension necessary might be refined by additional experiments. | Also, the amount of dimensions used in the k-means vector is quite important making hard to ensure data globularity which is a requirement for the k-means algorithm to properly work [19]. The amount of dimension necessary might be refined by additional experiments. | ||
| === PUBLICATION ==== | === PUBLICATION ==== | ||
| - | A preliminary publication of this study can be found here after. This publication would still need to be updated with real sensors results gathered from the cell phone. | + | A preliminary publication of this study can be found here after. This publication would still need to be updated with real sensors results gathered from the cell phone. |
| [[https:// | [[https:// | ||
projets/plim/20142015/gr9.1416755215.txt.gz · Dernière modification : 2014/11/23 15:06 de palma