Bladimir Serna

Dr. Bladimir Serna

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 July 2025 in Brain Sciences
Verified
Journal Article
Open access
PDF file
BSBladimir Serna
Bladimir Serna
RSRicardo Salazar
Ricardo Salazar
GAGustavo Adolfo Alonso-Silverio
Gustavo Adolfo Alonso-Silverio
RBRosario NACIONAL Baltazar
Rosario NACIONAL Baltazar
EVElías Jesús Ventura-Molina
Elías Jesús Ventura-Molina
AAAntonio Alarcón-Paredes
Antonio Alarcón-Paredes
Background/Objectives: Fear detection through EEG signals has gained increasing attention due to its applications in affective computing, mental health monitoring, and intelligent safety systems. This systematic review aimed to identify the most effective methods, algorithms, and configurations reported in the literature for detecting fear from EEG signals using artificial intelligence (AI). Methods: Following the PRISMA 2020 methodology, a structured search was conducted using the string (“fear detection” AND “artificial intelligence” OR “machine learning” AND NOT “fnirs OR mri OR ct OR pet OR image”). After applying inclusion and exclusion criteria, 11 relevant studies were selected. Results: The review examined key methodological aspects such as algorithms (e.g., SVM, CNN, Decision Trees), EEG devices (Emotiv, Biosemi), experimental paradigms (videos, interactive games), dominant brainwave bands (beta, gamma, alpha), and electrode placement. Non-linear models, particularly when combined with immersive stimulation, achieved the highest classification accuracy (up to 92%). Beta and gamma frequencies were consistently associated with fear states, while frontotemporal electrode positioning and proprietary datasets further enhanced model performance. Conclusions: EEG-based fear detection using AI demonstrates high potential and rapid growth, offering significant interdisciplinary applications in healthcare, safety systems, and affective computing.

20 June 2019
Verified
Book Chapter
Closed access
PDF file
BSBladimir Serna
Bladimir Serna
RBRosario NACIONAL Baltazar
Rosario NACIONAL Baltazar
PCPedro Cruz-Parada
Pedro Cruz-Parada
JMJorge Meza
Jorge Meza
JMJuan Manríquez
Juan Manríquez
VZVíctor Zamudio
Víctor Zamudio

20 June 2019
Verified
Book Chapter
Closed access
PDF file
BSBladimir Serna
Bladimir Serna
RBRosario NACIONAL Baltazar
Rosario NACIONAL Baltazar
MCMiguel Casillas
Miguel Casillas
YSYesica Saavedra
Yesica Saavedra
AAArnulfo Alanis
Arnulfo Alanis
AMAntonio Meza
Antonio Meza

8 October 2026 in Sensors
Verified
Journal Article
Open access
PDF file
BSBladimir Serna
Bladimir Serna
RSRicardo Salazar
Ricardo Salazar
GAGustavo Adolfo Alonso-Silverio
Gustavo Adolfo Alonso-Silverio
RBRosario NACIONAL Baltazar
Rosario NACIONAL Baltazar
EVElías Jesús Ventura-Molina
Elías Jesús Ventura-Molina
AAAntonio Alarcón-Paredes
Antonio Alarcón-Paredes
Electroencephalography (EEG) and artificial intelligence (AI) are central tools in affective computing, yet fear-related inference remains constrained by a gap between experimental performance and deployable evidence: high accuracy on controlled datasets guarantees neither neurobiological specificity, nor robustness across users, nor traceable inference. EEG does not measure fear directly; it captures cortical dynamics compatible with threat processing, arousal or vigilance. This paper introduces the Fear-EEG-AIFramework, a technology-independent architecture for designing, validating and deploying EEG–AI systems targeting fear-compatible neurophysiological states. Building on a prior systematic review, it organizes development into three hierarchical levels—neurobiological foundation, neuroelectric correlates and computational modeling—governed by six cross-cutting principles, and makes them evaluable through eight observable dimensions, the Fear-EEG-AI Alignment Index (FAI) and five validation evidence levels. Applied to the eight eligible studies of that corpus by two raters who had not drafted the instrument, with adjudication by a third, the rubric reached 67.2% exact agreement (quadratic-weighted κ=0.741; ICC(2,1) =0.744). Under 10,000 admissible weightings the equal-weight ordering survived in 10.1% of draws, and one of 56 ordered pairs met a stability criterion fixed before the pairwise results were tabulated. The index is therefore reported as a descriptor of methodological documentation and not as a ranking of implementations.