Toward Fear Detection using Affect Recognition

Miranda, José Ángel Portal; Canabal, Manuel F.; Lanza-Gutiérrez, José M.; Portela-García, M.; López-Ongil, C.

doi:10.1109/dcis201949030.2019.8959852

Cited by 11 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another possible approach to deal with this problem is based on the application of data augmentation techniques or weighted classes. Some of these techniques have been already used in [ 30 ] by the authors. Conversely, in the case of V7, the system showed 40.00% positive class information, which translates into a better SVM performance.…”

Section: Resultsmentioning

confidence: 99%

“…Another step commonly implemented after feature extraction is the application of feature selection techniques to reduce the redundant information and the dimensionality of the problem. In this regard, previous results obtained in [30], in which the model performance was compromised, led the authors of this work not to include this step in the current study.…”

Section: Feature Extractionmentioning

confidence: 96%

“…The most common are MIT [24], DEAP [25], MAHNOB [8], DECAF [26], ASCERTAIN [27], and WESAD [28]. In [29,30], the authors performed a detailed analysis of some of these databases and provided conclusions about their methodologies and emotional recognition approaches. These open databases provide a solid benchmark for current and future emotion recognition systems based on physiological signals.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Miranda

Canabal

Gutiérrez-Martín

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Emotion recognition is benefitting from the latest research into physiological monitoring and wireless communications, among other remarkable achievements. These technologies can indeed provide solutions to protect vulnerable people in scenarios such as personal assaults, the abuse of children or the elderly, gender violence or sexual aggression. Cyberphysical systems using smart sensors, artificial intelligence and wearable and inconspicuous devices can serve as bodyguards to detect these risky situations (through fear-related emotion detection) and automatically trigger a protection protocol. As expected, these systems should be trained and customized for each user to ensure the best possible performance, which undoubtedly requires a gender perspective. This paper presents a specialized fear recognition system for women based on a reduced set of physiological signals. The architecture proposed is characterized by the usage of three physiological sensors, lightweight binary classification and the conjunction of linear (temporal and frequency) and non-linear features. Moreover, a binary fear mapping strategy between dimensional and discrete emotional information based on emotional self-report data is implemented to avoid emotional bias. The architecture is evaluated using a public multi-modal physiological dataset with two approaches (subject-dependent and subject-independent models) focusing on the female participants. As a result, the proposal outperforms the state-of-the-art in fear recognition, achieving a recognition rate of up to 96.33% for the subject-dependent model.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 96%

mentioning

confidence: 99%

See 1 more Smart Citation

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Miranda

Canabal

Gutiérrez-Martín

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The study described in [ 31 ] presents a binary fear recognition system (fear was considered as a low valence and high arousal emotion) based on 20 PPG and GSR features extracted from the DEAP dataset, using the subject-independent modality. The best results—concerning the values of accuracy, specificity and sensitivity—were obtained by applying the SVM algorithm, a dimensionality reduction technique based on Fisher’s Criterion and the SMOTE method for dealing with the class imbalance problem (there were 979 negative observations and 301 positive observations).…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Methods for Fear Classification Based on Physiological Features

Petrescu

Oprea

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.

show abstract

“…to train the algorithms that could classify, in real time and automatically, the emotion experienced by the person. In this sense, Bindi system is proposed by the UC3M4Safety team to detect and prevent violent aggressions against women, by detecting fear or panic emotions, through the voice and the physiological responses [ 17 , 18 , 19 ]. However, specific databases are required to create these artificial intelligence-based algorithms in detecting fear or panic emotions and considering the users will be women.…”

Section: Introductionmentioning

confidence: 99%

Emotion Elicitation Under Audiovisual Stimuli Reception: Should Artificial Intelligence Consider the Gender Perspective?

Blanco-Ruiz

Sainz-de-Baranda

Gutiérrez-Martín

et al. 2020

IJERPH

View full text Add to dashboard Cite

Identification of emotions triggered by different sourced stimuli can be applied to automatic systems that help, relieve or protect vulnerable groups of population. The selection of the best stimuli allows to train these artificial intelligence-based systems in a more efficient and precise manner in order to discern different risky situations, characterized either by panic or fear emotions, in a clear and accurate way. The presented research study has produced a dataset of audiovisual stimuli (UC3M4Safety database) that triggers a complete range of emotions, with a high level of agreement and with a discrete emotional categorization, as well as quantitative categorization in the Pleasure-Arousal-Dominance Affective space. This database is adequate for the machine learning algorithms contained in these automatic systems. Furthermore, this work analyses the effects of gender in the emotion elicitation under audiovisual stimuli, which can help to better design the final solution. Particularly, the focus is set on emotional responses to audiovisual stimuli reproducing situations experienced by women, such as gender-based violence. A statistical study of gender differences in emotional response was carried out on 1332 participants (811 women and 521 men). The average responses per video is around 84 (SD = 22). Data analysis was carried out with RStudio®.

show abstract

Toward Fear Detection using Affect Recognition

Cited by 11 publications

References 13 publications

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Machine Learning Methods for Fear Classification Based on Physiological Features

Emotion Elicitation Under Audiovisual Stimuli Reception: Should Artificial Intelligence Consider the Gender Perspective?

Contact Info

Product

Resources

About