Adam or Eve? Automatic users’ gender classification via gestures analysis on touch devices

Abstract

Gender classification of mobile devices’ users has drawn a great deal of attention for its applications in healthcare, smart spaces, biometric-based access control systems and customization of user interface (UI). Previous works have shown that authentication systems can be more effective when considering soft biometric traits such as the gender, while others highlighted the significance of this trait for enhancing UIs. This paper presents a novel machine learning-based approach to gender classification leveraging the only touch gestures information derived from smartphones’ APIs. To identify the most useful gesture and combination thereof for gender classification, we have considered two strategies: single-view learning, analyzing, one at a time, datasets relating to a single type of gesture, and multi-view learning, analyzing together datasets describing different types of gestures. This is one of the first works to apply such a strategy for gender recognition via gestures analysis on mobile devices. The methods have been evaluated on a large dataset of gestures collected through a mobile application, which includes not only scrolls, swipes, and taps but also pinch-to-zooms and drag-and-drops which are mostly overlooked in the literature. Conversely to the previous literature, we have also provided experiments of the solution in different scenarios, thus proposing a more comprehensive evaluation. The experimental results show that scroll down is the most useful gesture and random forest is the most convenient classifier for gender classification. Based on the (combination of) gestures taken into account, we have obtained F1-score up to 0.89 in validation and 0.85 in testing phase. Furthermore, the multi-view approach is recommended when dealing with unknown devices and combinations of gestures can be effectively adopted, building on the requirements of the system our solution is built-into. Solutions proposed turn out to be both an opportunity for gender-aware technologies and a potential risk deriving from unwanted gender classification.

Classification of Drivers’ Mental Workload Levels: Comparison of Machine Learning Methods Based on ECG and Infrared Thermal Signals

“…Of note and with reference to the state of the art in ML and deep learning, in this work a specific typology of multimodal approach has been used. Indeed, referring to the recent work of Guarino et al, together with the unimodal approach defined by the authors also single-view learning, a single typology of multimodal procedure was adopted in the present study, referred to by the authors as the intermediate integration multi-view approach [ 65 ]. This particular multi-view approach has been chosen since there was the necessity of having a feature selection step (i.e., wrapper method) in the analysis pipeline, prior to the concatenation of IR and HRV features.…”

Machine learning in project analytics: a data-driven framework and case study

“…In addition to the three feature selection methods, multiview can be adopted when applying the proposed framework to the case study. Multi-view learning is another direction in machine learning that considers learning with multiple views of the existing data with the aim to improve predictive performance 81,82 . Similarly, although we considered five performance measures, there are other potential candidates.…”

“In the Wild” Video Content as a Special Case of User Generated Content and a System for Its Recognition

“…The other approaches available for cross-validation are leave-one-out cross-validation (LOO-CV) and leave-one-user-out cross-validation (LOUO-CV). These approaches were clearly described in [ 22 ]. We chose the k-fold method instead of the other two on the basis of the size of the database.…”