![\"Accelerometer](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3524/media/coordinates.png\" "\\"Accelerometer")
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\nKaggle and the competition host have the right to publicly disseminate any entries or models.
\r\n\r\n Winning solutions need to be made available under\r\n a popular OSI-approved license\r\n in order to be eligible for recognition and prize money.\r\n
\r\n\r\n Prizes will be awarded after the winners have posted their solutions to the competition forum.\r\n Winners must post or link to their solutions within seven (7) days of being notified of their winning status.\r\n
\r\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 5 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: 7/23/2013 4:32 PM UTC
\r\nMerger Deadline: 11/20/2013 10:40 PM UTC
\r\nEntry Deadline: None
\r\nEnd Date: 11/22/2013 11:59 PM UTC
\r\n\t\r\nThis competition is subject to the Research Competition Standard Rules.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "Since everyone moves differently and accelerometers are fast becoming ubiquitous, this competition is designed to investigate the feasibility of using accelerometer data as a biometric for identifying users of mobile devices.
\r\nSeal has collected accelerometer data from several hundred users over a period of several months during normal device usage. To collect the data, we published an app on Googles’s Android PlayStore that samples accelerometer data in the background and posts it to a central database for analysis.
\r\nWe have uploaded approximately 60 million unique samples of accelerometer data collected from 387 different devices. These are split into equal sets for training and test. Samples in the training set are labeled with the unique device from which the data was collected. The test set is demarcated into 90k sequences of consecutive samples from one device. A file of test questions is provided in which you are asked to determine whether the accelerometer data came from the proposed device.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "Submissions are judged on area under the ROC curve.
\r\nIn Matlab (using the stats toolbox):
\r\n[~, ~, ~, auc ] = perfcurve(true_labels, predictions, 1);\r\n\r\n
In R (using the verification package):
\r\nauc = roc.area(true_labels, predictions)\r\n\r\n
In python (using the metrics module of scikit-learn):
\r\nfpr, tpr, thresholds = metrics.roc_curve(true_labels, predictions, pos_label=1)\r\nauc = metrics.auc(fpr,tpr)\r\n
Each line of your submission should contain an QuestionId and a prediction, IsTrue. Note that you may submit any real-valued number as a prediction, since AUC is only sensitive to the ranking. sampleSubmission.csv shows a representative valid submission. The format looks like this:
\r\nQuestionId,IsTrue\r\n1,0\r\n2,0.3\r\n3,99999\r\n4,-0.8\r\netc...\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "
Your task is to determine whether the accelerometer recordings in the test set (test.csv) belong to the proposed devices in the question set (questions.csv).
\r\n| \r\n File name \r\n | \r\n\r\n Description \r\n | \r\n
| \r\n train.zip \r\n | \r\n\r\n 30m samples for training, labeled with DeviceId \r\n | \r\n
| \r\n test.zip \r\n | \r\n\r\n 30m samples for test, split into 90k sequences, labeled with SequenceId \r\n | \r\n
| \r\n questions.csv \r\n | \r\n\r\n 90k questions that match test sequences to DeviceId \r\n | \r\n
| \r\n Field name \r\n | \r\n\r\n Description \r\n | \r\n
| \r\n T \r\n | \r\n\r\n Unix time (miliseconds since 1/1/1970) \r\n | \r\n
| \r\n X \r\n | \r\n\r\n Acceleration measured in g on x co-ordinate \r\n | \r\n
| \r\n Y \r\n | \r\n\r\n Acceleration measured in g on y co-ordinate \r\n | \r\n
| \r\n Z \r\n | \r\n\r\n Acceleration measured in g on z co-ordinate \r\n | \r\n
| \r\n DeviceId \r\n | \r\n\r\n Unique Id of the device that generated the samples \r\n | \r\n
| \r\n Field name \r\n | \r\n\r\n Description \r\n | \r\n
| \r\n T \r\n | \r\n\r\n Unix time (miliseconds since 1/1/1970) \r\n | \r\n
| \r\n X \r\n | \r\n\r\n Acceleration measured in g on x co-ordinate \r\n | \r\n
| \r\n Y \r\n | \r\n\r\n Acceleration measured in g on y co-ordinate \r\n | \r\n
| \r\n Z \r\n | \r\n\r\n Acceleration measured in g on z co-ordinate \r\n | \r\n
| \r\n SequenceId \r\n | \r\n\r\n Unique sequence number assigned to each question. Each group of samples is labeled with a unique SequenceId. Each SequenceId is matched to a professed DeviceId in the questions.csv file. \r\n | \r\n
| \r\n Field name \r\n | \r\n\r\n Description \r\n | \r\n
| \r\n QuestionId \r\n | \r\nId of question | \r\n
| \r\n SequenceId \r\n | \r\n\r\n Unique number assigned to each sequence of samples \r\n | \r\n
| \r\n QuizDevice \r\n | \r\n\r\n Professed device that generated the sequence of | \r\n
Figure 1. Coordinate system (relative to a device) that's used by the Android Sensor API.
\r\nIn general, the sensor framework uses a standard 3-axis coordinate system to express data values. For most sensors, the coordinate system is defined relative to the device's screen when the device is held in its default orientation (see figure 1). When a device is held in its default orientation, the X axis is horizontal and points to the right, the Y axis is vertical and points up, and the Z axis points toward the outside of the screen face. In this system, coordinates behind the screen have negative Z values. (Quoted from the Sensor Overview at Android developers site.)
\r\nThe Android system allows developers to specify sampling frequency using one of four sensor delay comstants:
\r\nDevice manufacturers may interpret these values differently. Our background process that collected samples for this contest specified a sample frequency value of SENSOR_DELAY_NORMAL. Other applications running on the device can overide the sampling frequency specified. The mean interval between consecutive samples in this data set is 207 ms.
\r\nThe combined force exerted upon the x,y and z axes of a device is calculated by the distance function: SquareRoot(x^2 + y^2 +z^2). When the device is not accelerating, this function evaluates to the force of gravity (~9.85). This property ensures that when a correctly calibrated device is not in motion,the x,y,z accelerometer readings that it provides, will plot to points on a sphere with radius ~9.85.
\r\n\r\n
![\"Gravity](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3524/media/gravsphere.png\" "\\"Gravity")
Figure 2: 670 sample data points collected from an accelerometer stream during approximately 2 minutes, while the device was held in portrait, landscape and face-up positions.
\r\nNotice that the plotted x,y,z coordinates of each accelerometer event appear as points on the surface of a sphere.
\r\nSee Detecting how you hold your phone for more information.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "About The Sponsor", "content": "Seal Mobile ID is based in Tel Aviv and was incorporated in January 2012.
\r\nThe company filed a US provisional patent application (61/430,549) in January 2011, describing \"Systems methods and media for unobtrusively recognizing an authorized user by a mobile device\". Our PCT application is published at the WIPO site. For additional information about Seal, please see our web site.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "First Place:
\r\nSecond Place:
\r\nThird Place:
\r\nFourth Place:
\r\n