Sussex-Huawei Locomotion Challenge
The Sussex-Huawei Locomotion Dataset will be used in an activity recognition challenge with results to be presented at the HASCA Workshop at Ubicomp 2018. The goal of the challenge is to recognize the basic 8 modes of locomotion and transportation (activities) from inertial sensor data. The participants would have to develop an algorithm pipeline that will process the sensor data (time-series), create models and provide recognition of the activities.
Data and Activities
The data is recorded by a Huawei Mate 9 smartphone by a single participant in a period of 4 months. The participant was performing the activities on a daily basis (approximately 5-8 hours) with the phone logging the sensors data and being worn inside the front right pocket (not fixed orientation).
The following sensor data can be used in order to recognize the activities: accelerometer (3 axis), gyroscope (3 channels), magnetometer (3 channels), quaternions (4 channels), ambient pressure (1 channel).
The following 8 activities have to be recognized: Car, Bus, Train, Subway, Walk, Run, Bike, and Still.
The data is cleaned and the NULL activity is removed. That means there will be gaps (NULL class) in the data, which should be appropriately addressed by the algorithm.
The data is divided into two parts: train and test. The train data contains the raw sensors data and the appropriate activity labels (class label). The test data contains only the raw sensors data, the labels are kept for evaluation and scoring. The idea is that the participants use the train data to create their algorithm pipeline and model that will recognize the activities using the sensor data.
We recommend that the participants use sliding window (frame) for processing the sensor data. The size of the window can be arbitrary, but not larger than 1 minute.
The output of your algorithm should be a .txt file containing the timestamp and the recognized activity (labels) for the test data samples. Therefore, the file should contain the same number of rows as the test file.
There will be 2 evaluations: midterm and final evaluation. The midterm evaluation will be done after 2 weeks of the start of the competition and will be informative, i.e., will inform the participants about their ranking. The final evaluation will be at the end of the competition and will reveal the final results and rankings.
F1-score (average over all of the activities) will be used for evaluation.
Explaing training dataset format
Explaing testing dataset format
Submission of test dataset classification
Explain how to submit the test dataset classification results
- Challenge duration: TBA (tentative: 04.06.2018 – 30.06.2018)
- Paper submission: TBA (tentative: 15.07.2018)
- Workshop presentation: TBA (tentative: 08.11.2018)
All inquiries should be directed to: email@example.com
- Dr. Hristijan Gjoreski, University of Sussex (UK) & Ss. Cyril and Methodius University (MK)
- Dr. Lin Wang, University of Sussex (UK)
- Dr. Daniel Roggen, University of Sussex (UK)