Piezoelectric and Machine Learning Based Keystroke Dynamics for Highly Secure User Authentication

Tang, Chenyu; Cui, Ziang; Chu, Meng; Lü, Yanwu; Zhou, Fuqiang; Gao, Shuo

doi:10.1109/jsen.2022.3141872

Cited by 8 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) This sample size is consistent with the literature in the field of biometric authentication. Within the field of biometric authentication, smaller sample sizes have been used for the preliminary testing of model performance in authenticating device users (e.g., 5-10 participants) [16][17][18][19][20]. (3) The machine learning models used in this study are trained to predict the child user at the 1-s level (i.e., with a high degree of granularity); therefore, the amount of data points per subject is large (see Table S4).…”

Section: Methodsmentioning

confidence: 99%

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Finnegan,

Weaver,

Yang

et al. 2024

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F1 score, accuracy, precision, and recall. Model performance was high, with F1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments.

show abstract

Section: Methodsmentioning

confidence: 99%

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Finnegan,

Weaver,

Yang

et al. 2024

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…Additionally, fine-tuning the training parameters may considerably increase ML performance, particularly when utilizing an ANN or DNN. Tang et al [24] completed an initial investigation on a polyvinylidene fluoride (PVDF) based piezoelectric touch screen that can learn specific force touch behaviors of consumers. The research introduced a Support Vector Machine (SVM) method and experimented with frequency domain features to obtain 98.3% more authentication accuracy than typical time domain features.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Piezoelectric Tile Performance in Flat and Mountainous Terrains Through Deep Neural Network

Adhikari,

Singh,

Sagar

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

Piezoelectric tiles harvest mechanical vibrations and convert them into electrical energy, making them an attractive energy‐harvesting technology. However, their performance is heavily influenced by the terrain where they are installed. Traditional experimental methods for predicting their performance on different terrains are time‐consuming, so a computational approach is necessary to improve efficiency. To address this, a machine learning‐based approach is proposed using Artificial Neural network (ANN) and Deep neural network (DNN) with the Tanh activation function to predict piezoelectric tile performance in diverse terrains. The models are trained on an experimental dataset consisting of four terrains, including Flat terrain (FT) and Hilly Terrain (HT) 1, 2, 3 with road angles of 0, 3, 6, and 10 degrees. A finite element model is also established to optimize the piezoelectric tile and estimate the suitable parameter range to prevent damage to the tile during experiments. The results indicate that the DNN model performs better than the ANN model, achieving high accuracy in predicting piezoelectric tile performance on different terrains. These findings suggest that machine learning can provide a time and cost‐effective way for predicting the performance of piezoelectric tiles in varied terrains, thereby facilitating betters installation and maintenance decisions for piezoelectric tile systems.

show abstract

Reading between the lines: Automatic inference of self-assessed personality traits from dyadic social chats

Buker,

Vinciarelli

2023

Computers in Human Behavior: Artificial Humans

View full text Add to dashboard Cite

Piezoelectric and Machine Learning Based Keystroke Dynamics for Highly Secure User Authentication

Cited by 8 publications

References 38 publications

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Prediction of Piezoelectric Tile Performance in Flat and Mountainous Terrains Through Deep Neural Network

Reading between the lines: Automatic inference of self-assessed personality traits from dyadic social chats

Contact Info

Product

Resources

About