I
Inma Mohino-Herranz
Researcher at University of Alcalá
Publications - 20
Citations - 131
Inma Mohino-Herranz is an academic researcher from University of Alcalá. The author has contributed to research in topics: Feature extraction & Mel-frequency cepstrum. The author has an hindex of 5, co-authored 20 publications receiving 102 citations.
Papers
More filters
Journal ArticleDOI
Assessment of Mental, Emotional and Physical Stress through Analysis of Physiological Signals Using Smartphones.
Inma Mohino-Herranz,Roberto Gil-Pita,Javier Ferreira,Manuel Rosa-Zurera,Fernando Seoane,Fernando Seoane +5 more
TL;DR: In this paper, the authors used genetic algorithms to select a reduced set of features from the raw time measurements of the EKG and thoracic electrical bioimpedance (TEB) signals.
Journal ArticleDOI
Activity Recognition Using Wearable Physiological Measurements: Selection of Features from a Comprehensive Literature Study.
TL;DR: A deep analysis of features proposed to extract information from the electrocardiogram, thoracic electrical bioimpedance, and electrodermal activity signals is carried out, determining the best number of features to obtain a good error probability avoiding over-fitting, and the best subset of features among those proposed in the literature.
Journal ArticleDOI
Energy-Efficient Acoustic Violence Detector for Smart Cities
Marta Bautista-Durán,Joaquín García-Gómez,Roberto Gil-Pita,Inma Mohino-Herranz,Manuel Rosa-Zurera +4 more
TL;DR: Results demonstrate the viability of the system, thanks to the low cost that some violence features require, making feasible the implementation of the proposed method in a nowadays low power microprocessor.
Book ChapterDOI
Violence Detection in Real Environments for Smart Cities
Joaquín García-Gómez,Marta Bautista-Durán,Roberto Gil-Pita,Inma Mohino-Herranz,Manuel Rosa-Zurera +4 more
TL;DR: Results derived from the experiments show that MFCCs are the best features for violence detection, and others like pitch or short time energy have also a good performance, in other words, features that can distinguish between voiced and unvoiced frames seem to be a good election for violence Detection in real environments.
Journal ArticleDOI
A Wrapper Feature Selection Algorithm: An Emotional Assessment Using Physiological Recordings from Wearable Sensors.
Inma Mohino-Herranz,Roberto Gil-Pita,Joaquín García-Gómez,Manuel Rosa-Zurera,Fernando Seoane +4 more
TL;DR: The proposed k-fold approach outperforms the conventional method with 4% hit success rate improvement, and the proposed selection criterion method allows the classifier to produce the best performance using a lower number of features at lower computational cost.