Smartphone Activity Dataset

This dataset contains data from 82 participants, collected in two settings: in the lab, and at home. 25 participants completed trials both at home and in the lab. The participants ranged in age from 18 to 32 and 48 to 74.

The data collected at home consists of multiple sessions performed over several weeks. During those sessions, participants were asked to interact with their smartphones in different body postures and movements. The dataset includes sensor data such as accelerometer and gyroscope readings with timestamps.

The data collected in the lab consists of data collection trials divided in two sessions, spaced by about one-week on average. (Three users, which are not accounted for in this average, performed their session several months apart due to restrictions associated with COVID-19.) Sessions were divided in 24 sixty-second trials evenly split across 4 body posture/activity combinations, i.e., sit and swipe, sit and type, walk and swipe, walk and type.

This dataset is a reorganized and cleaned version of the originally published dataset from 2023. The new data structure is organized by data collection location, then by user id. For lab data, the directories are then split by the unique sessions 1 and 2, after which it is split by experiment and modality type. Inside of those modality and authentication method directories, will be trials named after the date and time they were completed, and will contain at a minimum accelerometer.csv, gyroscope.csv keystroke_data.csv or swiping_data.csv, and motion_capture_data__*.csv; some trials may also include face_tracking_data.csv, but not all trials recorded this. For the home data, the directories are split by authentication method swiping or typing, inside of each will contain directories of trials named for the date and time the trial was completed. Inside of each trial directory it will contain at a minimum accelerometer.csv, gyroscope.csv keystroke_data.csv or swiping_data.csv, and user_properties.csv; some trials may also include face_tracking_data.csv, but not all trials recorded this.

The dataset provides a valuable resource for understanding the relationship between body posture, movements, and mobile authentication performance. It can be used by researchers to explore the impact of different body postures and movements on mobile device security, and to develop more effective mobile authentication methods. By sharing this dataset, we hope to contribute to the wider research community and promote further investigation into this important topic.

All data was collected using an iPhone XR. Each participant completed an average of 25 sessions. During each session, subjects were asked to perform simple tasks, such as reading, writing, and image comparison. At the end of each reading and image comparison task, they were asked 3-5 questions about the task. In each session, users were not required to perform the tasks in a specific body position.

Data was collected with the approval NYIT IRB approval.

The dataset used in our work can be downloaded from this link

Dataset SHA-256: dc727ab5a39ebda810021d11a21250593156d32424cbba2dbafb31d6206770ad.

Last updated: September 12, 2024.


Terms

The New York Institute of Technology hereby grants to You a non-exclusive, non-transferable, revocable license to use the Dataset solely for Your non-commercial, educational, and research purposes only, but without any right to copy or reproduce, publish or otherwise make available to the public or communicate to the public, sell, rent or lend the whole or any constituent part of the Dataset thereof. The Dataset shall not be redistributed without the express written prior approval of The New York Institute of Technology You agree to respect the privacy of those human subjects whose smartphone usage behavior data are included in the Dataset. Do not attempt to reverse the anonymization process to identify specific identifiers including, without limitation, names, postal address information, telephone numbers, e-mail addresses, social security numbers, and biometric identifiers. You agree not to reverse engineer, separate or otherwise tamper with the Dataset so that data can be extracted and used outside the scope of that permitted in this Agreement.

You agree to acknowledge the source of the Dataset in all of Your publications and presentations based wholly or in part on the Dataset. You agree to provide a disclaimer in any publication or presentation to the effect that The New York Institute of Technology does not bear any responsibility for Your analysis or interpretation of Dataset.

You agree and acknowledge that The New York Institute of Technology may hold, process, and store any personal data submitted by You for validation and statistical purposes and for the purposes of the administration and management of Dataset. You agree that any personal data submitted by You is accurate to the best of his or her knowledge.

The New York Institute of Technology provides the Dataset “AS IS,” without any warranty or promise of technical support, and disclaims any liability of any kind for any damages whatsoever resulting from use of the Dataset.

The New York Institute of Technology makes no warranties, express or implied with respect to the Dataset, including any implied warranty of merchantability or fitness for a particular purpose, which are hereby expressly disclaimed.

Your acceptance and use of the Dataset binds you to the terms and conditions of this License as stated herein.