Identification Issues Associated with the Use of Wearable Accelerometers in Lifelogging

Personal lifelogging builds upon the pervasive and continuous acquisition of sensor measurements and signals in time, and this may expose the subject, and eventually bystanders, to privacy violations. While the issue is easy to understand for image and video data, the risks associated to the use of wearable accelerometers is less clear and may be underestimated. This work addresses the problem of understanding if acceleration measurements collected from the wrist, by subjects performing different types of Activities of Daily Living (ADLs), may release personal details, for example about their gender or age. A positive outcome would motivate the need for de-identification algorithms to be applied to acceleration signals, embedded into wearable devices, in order to limit the unintentional release of personal details and ensure the necessary privacy by design and by default requirements.

[1]  Ahmad Almogren,et al.  Human Activity Recognition from Body Sensor Data using Deep Learning , 2018, Journal of Medical Systems.

[2]  Alex Mihailidis,et al.  Privacy-Aware and Acceptable Lifelogging services for older and frail people: the PAAL project , 2018, 2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin).

[3]  Giancarlo Fortino,et al.  Gait-based identification for elderly users in wearable healthcare systems , 2020, Inf. Fusion.

[4]  Diane J. Cook,et al.  Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data , 2015 .

[5]  Ian Cleland,et al.  Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home , 2019, Pervasive Mob. Comput..

[6]  Shan Lin,et al.  Toothbrushing Monitoring using Wrist Watch , 2016, SenSys.

[7]  Joemon M. Jose,et al.  Analysing privacy in visual lifelogging , 2017, Pervasive Mob. Comput..

[8]  Josef Hallberg,et al.  Collection of a Diverse, Realistic and Annotated Dataset for Wearable Activity Recognition , 2018, 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[9]  U. Nayak,et al.  The effect of age on variability in gait. , 1984, Journal of gerontology.

[10]  Arun Ross,et al.  Biometric recognition by gait: A survey of modalities and features , 2018, Comput. Vis. Image Underst..

[11]  Thingom Bishal Singha,et al.  Person Recognition using Smartphones' Accelerometer Data , 2017, ArXiv.

[12]  Björn Krüger,et al.  One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor , 2015, Sensors.

[13]  Philippe Terrier,et al.  Effect of age on the variability and stability of gait: a cross-sectional treadmill study in healthy individuals between 20 and 69 years of age. , 2014, Gait & posture.

[14]  Nuno M. Garcia,et al.  Identification of activities of daily living through data fusion on motion and magnetic sensors embedded on mobile devices , 2018, Pervasive Mob. Comput..

[15]  Chris D. Nugent,et al.  Improving the Collection and Understanding the Quality of Datasets for the Aim of Human Activity Recognition , 2019, Smart Assisted Living.

[16]  Ted Herman,et al.  Hand hygiene duration and technique recognition using wrist-worn sensors , 2015, IPSN.

[17]  Alex Mihailidis,et al.  A review on video-based active and assisted living technologies for automated lifelogging , 2020, Expert Syst. Appl..

[18]  Pierre Parrend,et al.  Cerberus, an Access Control Scheme for Enforcing Least Privilege in Patient Cohort Study Platforms , 2017, Journal of Medical Systems.

[19]  Vivek Kanhangad,et al.  Gender classification in smartphones using gait information , 2018, Expert Syst. Appl..

[20]  Alessio Vecchio,et al.  Gait-based authentication using a wrist-worn device , 2016, MobiQuitous.

[21]  Hau Lee Tong,et al.  Daily Activities Classification on Human Motion Primitives Detection Dataset , 2019 .

[22]  Wouter Joosen,et al.  A Systematic Comparison of Age and Gender Prediction on IMU Sensor-Based Gait Traces , 2019, Sensors.

[23]  Yingnan Sun,et al.  A Deep Learning Approach on Gender and Age Recognition using a Single Inertial Sensor , 2019, 2019 IEEE 16th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[24]  Faicel Chamroukhi,et al.  Physical Human Activity Recognition Using Wearable Sensors , 2015, Sensors.

[25]  Lisandro Lovisolo,et al.  Person Identification based on Smartphones Inertial Sensors , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).