Filters








6 Hits in 4.4 sec

On the Inference of Soft Biometrics from Typing Patterns Collected in a Multi-device Environment [article]

Vishaal Udandarao and Mohit Agrawal and Rajesh Kumar and Rajiv Ratn Shah
2020 arXiv   pre-print
On the other hand, for regression tasks, we evaluated three ML and four DL-based regressors.  ...  The best arrangements achieved accuracies of 96.15%, 93.02%, and 87.80% for typing style, gender, and major/minor, respectively, and mean absolute errors of 1.77 years and 2.65 inches for age and height  ...  Likewise, Li et al. ] analyzed stylometry and keystroke dynamics to predict the gender of the person from 15 minutes of chat with 72% accuracy. Bandeira et al.  ... 
arXiv:2006.09501v1 fatcat:aamsibagmbarzdyhtmc2a5v3pa

Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications [article]

Giorgio Roffo
2017 arXiv   pre-print
For example, in pattern classification tasks, different data representations can complicate and hide the different explanatory factors of variation behind the data.  ...  In such a case feature selection is used, that, by producing ranked lists of features, helps to filter out the unwanted information.  ...  Data needed to analyze keystroke dynamics is obtained by keystroke logging.  ... 
arXiv:1706.05933v1 fatcat:oc4xtmyqkvf4njpqsojewv75qu

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
We propose a candidate ranking model for "this-issue" anaphora resolution that explores different "issue"-specific and general abstract-anaphora features. The model is not restricted to nominal  ...  To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features.  ...  We exploit the latent semantic information among users, topics, and social connections as features for prediction. Our framework is evaluated on real data collected from public domain.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Multimodal Person Recognition using Social Behavioral Biometric [article]

Madeena Sultana, University Of Calgary, University Of Calgary, Marina L. Gavrilova, Svetlana N. Yanushkevich
2018
and spatio-temporal data.  ...  This research identified a set of Social Behavioral Biometric (SBB) features from the online social information and proposed a framework to utilize these features for an automated person recognition for  ...  Keystroke and Low level metrics, Decision Multi- [FSA + 13] mouse dynamics, stylometry behavioral writing sample, web browsing Youssef et al.  ... 
doi:10.11575/prism/31776 fatcat:3zu5enludjga5hw7wou5zb5zey

A Conceptual Framework for Monitoring the Emotional State of Students in VLEs

Lubna Alharbi
2021
that would need to be performed by a system implementing the approach, and we discuss their performances on either available datasets, or, for one of the experiments, a purpose built dataset, which is  ...  We propose a system where technology is supportive of educators rather than replacing them, and is not intrusive or changing the classroom dynamics.  ...  For each anonymised client, the source provides information on age, gender, marital status, any symptoms or condition, as well as some general information on the therapist, such as gender and level of  ... 
doi:10.17638/03118135 fatcat:yjclcfcq45ezhmvsqtmxpaqspa

Artikelsamling - MNT-konferansen 2019

Reidar Lyng
2019 Nordic Journal of STEM Education  
Complete proceedings for the MNT Conference 2019, 28-29 March, 2019, Tromsø.  ...  Excited receives public funding through the Norwegian Agency for International Cooperation and Quality Enhancement in Higher Education (Diku).  ...  ACKNOWLEDGEMENTS The research presented in this paper was conducted by Excited Centre for Excellence in IT Education, https://www.ntnu.edu/excited, which is a collaboration between NTNU and Nord university  ... 
doi:10.5324/njsteme.v3i1.2992 fatcat:ap57jmqj5bh3bmnnsdv37msc4q