Because of the wide range of backgrounds of your peers, you can only use the methods discussed in the book in Chapters 1 through 6 of the ISLR book. Any use of any other methods will automatically disqualify your submission.
\n\n
All the available data may be used. However, you may not use the minor `flaw` in the data collection design: the order of activities was not randomized across participants, and so certain activities tend to occur after other activities. You may not make an external data file that includes both the provided and new features and use that in your entire script. All data merging should be done inside your R script.
\n\n\nYou work in teams of 2 or (at most) 3 members. Each team submits their work as a team. For this competition each team can enter 2 submissions. (You will be able to indicate which two submissions have to be used.)
\n\nThere are two deadlines: One for the first submission and one for the second submission. Both submissions will be graded.
\n\nTake advantage of the first round of submissions to improve your teams position on the leaderboard. That is, learn from the other teams scripts and 'steal' their good ideas! (Make sure to give credit where credit is due!)
\n\n\ndplyr with pipes (%>%) where possible (this generalizes much more easily to large data bases such as SQL data bases, makes it much easier to understand processing steps)\nThe data are stored in a zip file. The zip file contains\n
Both Train and Test folder contains text files with raw sensor signals. The Train folder also contains a file names labels_train.txt that specifies which segments of the signals correspond to which activities.
\n\nThe dataset consists of\n=================\n\n- Files with Inertial sensor data: Raw triaxial signals from the accelerometer and gyroscope of all the trials with with participants. \n- A file with labels of all the performed activities.\n \n\nThe dataset includes the following files:\n=========================================\n\n- 'README.txt'\n\n- 'RawData/Train/acc_expXX_userYY.txt': The raw triaxial acceleration signal for the experiment number XX and associated to the user number YY. Every row is one acceleration sample (three axis) captured at a frequency of 50Hz. \n\n- 'RawData/Train/gyro_expXX_userYY.txt': The raw triaxial angular speed signal for the experiment number XX and associated to the user number YY. Every row is one angular velocity sample (three axis) captured at a frequency of 50Hz. \n\n- 'RawData/labels.txt': include all the activity labels available for the dataset (1 per row). \n Column 1: experiment number ID, \n Column 2: user number ID, \n Column 3: activity number ID \n Column 4: Label start point (in number of signal log samples (recorded at 50Hz))\n Column 5: Label end point (in number of signal log samples)\n\n\n\nNotes: \n======\n\n- The units used for the accelerations (total and body) are 'g's (gravity of earth -> 9.80665 m/seg2).\n- The gyroscope units are rad/seg.\n- A video of the experiment including an example of the 6 recorded activities with one of the participants can be seen in the following link: http://www.youtube.com/watch?v=XOEN9W05_4A\n\n\nLicense:\n========\nUse of this dataset in publications must be acknowledged by referencing the following publications\n\n- Jorge-L. Reyes-Ortiz, Luca Oneto, Albert Sam‡, Xavier Parra, Davide Anguita. Transition-Aware Human Activity Recognition Using Smartphones. Neurocomputing. Springer 2015.\n\nThis dataset is distributed AS-IS and no responsibility implied or explicit can be addressed to the authors or their institutions for its use or misuse. Any commercial use is prohibited.\n\n\nOther Related Publications:\n===========================\n\n- Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra and Jorge L. Reyes-Ortiz. A Public Domain Dataset for Human Activity Recognition Using Smartphones. 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013. Bruges, Belgium 24-26 April 2013. \n\n- Jorge-Luis Reyes-Ortiz, Luca Oneto, Alessandro Ghio, Albert Sam·, Davide Anguita and Xavier Parra. Human Activity Recognition on Smartphones With Awareness of Basic Activities and Postural Transitions. Artificial Neural Networks and Machine Learning ñ ICANN 2014. Lecture Notes in Computer Science. Springer. 2014.\n\n- Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, Jorge L. Reyes-Ortiz. Energy Efficient Smartphone-Based Activity Recognition using Fixed-Point Arithmetic. Journal of Universal Computer Science. Special Issue in Ambient Assisted Living: Home Care. Volume 19, Issue 9. May 2013\n\n- Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra and Jorge L. Reyes-Ortiz. Human Activity Recognition on Smartphones using a Multiclass Hardware-Friendly Support Vector Machine. 4th International Workshop of Ambient Assited Living, IWAAL 2012, Vitoria-Gasteiz, Spain, December 3-5, 2012. Proceedings. Lecture Notes in Computer Science 2012, pp 216-223. \n\n- Jorge Luis Reyes-Ortiz, Alessandro Ghio, Xavier Parra-Llanas, Davide Anguita, Joan Cabestany, Andreu Catal‡. Human Activity and Motion Disorder Recognition: Towards Smarter Interactive Cognitive Environments. 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013. Bruges, Belgium 24-26 April 2013. \n\n---------------------\n\nJorge L. Reyes-Ortiz, Alessandro Ghio, Luca Oneto, Davide Anguita and Xavier Parra. July 2015.\n\nAdapted Aug 2018 for BDA, University of Amsterdam\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "\nThis competition involves building a classifier that recognizes different types of physical activity from signals measured by the accelerometer and gyroscope in your smartphone, which both measure aspects of movement and orientation. The data for this competition were collected in a lab using a basic smartphone in experiments with human participants carrying out various daily activities in set order.
\n\n\nThe experiments were carried out with a group of 30 volunteers within an age bracket of 19-48 years. They performed a protocol of activities composed of six basic activities: three static postures (standing, sitting, lying) and three dynamic activities (walking, walking downstairs and walking upstairs). The experiment also included postural transitions that occurred between the static postures. These are: stand-to-sit, sit-to-stand, sit-to-lie, lie-to-sit, stand-to-lie, and lie-to-stand. All the participants were wearing a smartphone (Samsung Galaxy S II) on the waist during the experiment execution. We captured 3-axial linear acceleration and 3-axial angular velocity at a constant rate of 50Hz using the embedded accelerometer and gyroscope of the device. The experiments were video-recorded to label the data manually. The obtained dataset was randomly partitioned into two sets, where 70% of the volunteers was selected for generating the training data and 30% the test data. \n
\nA video of the an experimental run can be viewed here\n
\n\nThe dataset consists of\n
The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:
\nThe evaluation metric for this competition is Accuracy. It is computed as \n
\nmean(Predicted == Observed)\n\n\n
For every experimental run of each participant you should predict the activity in the 128 samples time window specified in the sample submission file. The submission file should be a .csv file that contains two columns: Id and Predicted. Predicted should only contain the labels specified in the activity_labels.txt file (WALKING, STAYING, etc.). The labels should be exactly as in that file (yes, in upper case). The Id column must identify the participant id (userXX), the experimental run id (expYY) and the sample number of the start of the window. They should be joined in one string with _ as seperator.
The file should contain a header and have the following format:
\nId,Predicted\nuser02_exp03_0,STANDING\nuser02_exp03_128,STANDING\nuser02_exp03_256,STANDING\nuser02_exp03_384,STANDING\nuser02_exp03_512,STANDING\nuser02_exp03_640,STANDING\n⋮\nuser24_exp49_18048,WALKING\nuser24_exp49_18176,WALKING\n\n
A sample submission file can be downloaded here
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }