Learning Human Identity From Motion Patterns

Neverova, Natalia; Wolf, Christian; Lacey, Griffin; Fridman, Lex; Chandra, Deepak; Barbello, Brandon; Taylor, Graham W.

doi:10.1109/access.2016.2557846

Cited by 156 publications

(116 citation statements)

References 32 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…We take a different approach and propose to use convolutional neural networks in order to obtain deep embeddings of the motion signals recorded by the accelerometer and the gyroscope. It is important to note that Neverova et al [17,21] used convolutional neural networks as baselines, showing better results with their recurrent neural networks. While Neverova et al [17] used the discrete temporal signals as input for their baseline CNNs, we propose o novel approach to convert the temporal signals into a 2D gray-scale image representation to be used as input for our CNN.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images

Benegui

Ionescu

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a deep learning approach for smartphone user identification based on analyzing motion signals recorded by the accelerometer and the gyroscope, during a single tap gesture performed by the user on the screen. We transform the discrete 3-axis signals from the motion sensors into a gray-scale image representation which is provided as input to a convolutional neural network (CNN) that is pre-trained for multiclass user classification. In the pre-training stage, we benefit from different users and multiple samples per user. After pre-training, we use our CNN as feature extractor, generating an embedding associated to each single tap on the screen. The resulting embeddings are used to train a Support Vector Machines (SVM) model in a few-shot user identification setting, i.e. requiring only 20 taps on the screen during the registration phase. We compare our identification system based on CNN features with two baseline systems, one that employs handcrafted features and another that employs recurrent neural network (RNN) features. All systems are based on the same classifier, namely SVM. To pre-train the CNN and the RNN models for multi-class user classification, we use a different set of users than the set used for few-shot user identification, ensuring a realistic scenario. The empirical results demonstrate that our CNN model yields a top accuracy of 89.75% in multi-class user classification and a top accuracy of 96.72% in few-shot user identification. In conclusion, we believe that our system is ready for practical use, having a better generalization capacity than both baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We conduct experiments in order to compare our user identification system based on CNN features with two baselines, one that is based on handcrafted features [18] and one that is based on recurrent neural network (RNN) features [17]. All models are evaluated in a few-shot user identification context using the same classifier, namely SVM.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images

Benegui

Ionescu

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Neverova et al [16] propose an optimized shiftinvariant dense convolutional mechanism (DCWRNN) to extract features. GMM is used for the recognition task.…”

Section: Related Workmentioning

confidence: 99%

Multi-Channels LSTM Networks for Fence Activity Classification

Zheng

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe propose a novel neural networks model based on LSTM which is used to solve the task of classifying inertial sensor data attached to a fence with the goal of detecting security relevant incidents. To evaluate it we deployed an experimental fence surveillance system. By comparing experimental data of different approaches we find out that the neural network outperforms the baseline approach.

show abstract

“…undesired) inferences that a user might wish to keep private, such as discovering smoking habits [4] or revealing personal attributes such as age and gender [5]. Some patterns in raw sensor data may also enable user re-identification [6].…”

Section: Introductionmentioning

confidence: 99%

Privacy and utility preserving sensor-data transformations

Malekzadeh

Clegg

Cavallaro

et al. 2020

Pervasive and Mobile Computing

View full text Add to dashboard Cite

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. These transformations aim at eliminating patterns that can be used for user reidentification or for inferring potentially sensitive activities, while introducing a minor utility loss for the target application (or task). We show that, on gesture and activity recognition tasks, we can prevent inference of potentially sensitive activities while keeping the reduction in recognition accuracy of non-sensitive activities to less than 5 percentage points. We also show that we can reduce the accuracy of user re-identification and of the potential inference of gender to the level of a random guess, while keeping the accuracy of activity recognition comparable to that obtained on the original data.

show abstract

Learning Human Identity From Motion Patterns

Cited by 156 publications

References 32 publications

Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images

Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images

Multi-Channels LSTM Networks for Fence Activity Classification

Privacy and utility preserving sensor-data transformations

Contact Info

Product

Resources

About