David D'Croz Barón Data Scientist, Ph.D. in Electrical Eng.

H

Integrating machine learning into business and management in the age of artificial intelligence

Humanities and Social Sciences Communications

Mar 2025

Machine learning, with its capacity to leverage computational techniques for experiential learning, has profoundly influenced various disciplines, including business and management. Despite its contributions to the progress of these fields and the advent of artificial intelligence presenting new challenges, there remains ambiguity regarding the specific areas of significant advancement and those with potential for further development. This study addresses three central questions: (1) How is the intellectual landscape of machine learning in business and management research organized and structured? (2) What are the primary applications of machine learning in business administration? And (3) What strategic considerations should companies adop

I

Understanding innovation spaces: a topic modelling approach

International Journal of Entrepreneurship and Innovation Management

Aug 2024

Actors within the triple helix model have increasingly recognised innovation spaces as highly conducive environments for expediting innovative practices. However, the landscape of innovation spaces manifests in diverse typologies, encompassing Makerspaces, Hackerspaces, FabLabs, Innovation Labs, Innovation Centres, Idea Labs, Social Innovation Labs, and STEAM Labs. Hence, we seek to address the question, what do these innovation spaces have in common? Leveraging web scraping, semantic analysis, and topic modelling techniques, we scrutinise the primary content extracted from 181 distinct innovation space websites. These digital repositories harbour valuable information delineating their offerings, communication channels, resources, and objec

I

Recognizing Overarching Themes and Actors in Peacebuilding: A Longitudinal Analysis of Press Content in Latin America

IEEE Colombian Conference on Applications of Computational Intelligence ColCACI

Jul 2024

Various approaches to implementing peacebuilding in practical contexts persist, notwithstanding academia and affiliated organizations' endeavors to broaden the conceptual grasp of this domain. These variations may be amplified by cultural nuances, temporal factors, and geographic distinctions. Consequently, this paper aims to address the following question: What overarching themes emerge when analyzing diverse scenarios related to peacebuilding? To explore this question, a comprehensive statistical topic modeling methodology was employed, focusing on news articles published in prominent newspapers across Colombia, Mexico, Chile, and Peru from 2010 to 2020. The findings reveal six pivotal areas for discourse within the peacebuilding narrativ

T

Spatiotemporal dynamics of EEG in resting-state and sensory tasks with applications to Autism Spectrum Disorder via micr

TTU Electronic Theses and Dissertations

Dec 2020

Electroencephalography (EEG) is a powerful tool to study brain activity under different conditions such as sleep, wakeful rest, and performing cognitive tasks. EEG has been conventionally analyzed in time or time-frequency domains. However, the techniques involved are highly dependent on the reference selected and require many calculations and statistical comparisons. One way to overcome this concern is by applying topographic EEG analysis since different scalp topographies correspond to changes within the brain’s underlying sources. The microstate analysis is an alternative in topographic EEG, where the global variance is explained by a set of few prototypical topographies, which represent the microstate classes. Throughout more than two d

B

Auditory and Visual Tasks Influence the Temporal Dynamics of EEG Microstates During Post-encoding Rest

Brain Topography

Oct 2020

Re-activations of task-dependent patterns of neural activity take place during post-encoding periods of wakeful rest and sleep. However, it is still unclear how the temporal dynamics of brain states change during these periods, which are shaped by prior conscious experiences. Here, we examined the very brief periods of wakeful rest immediately after encoding and recognition of auditory and visual stimuli, by applying the EEG microstate analysis, in which the global variance of the EEG is explained by only a few prototypical topographies. We identified the dominant brain states of sub-second duration during the tasks-dependent periods of rest, finding that the temporal dynamics—represented here by two temporal parameters: the frequency of oc

I

Time-Frequency Analysis of Unimodal Sensory Processing In Autism Spectrum Disorder

ICASSP IEEE International Conference on Acoustics Speech and Signal Processing ICASSP

May 2020

This work summarizes the results of a time-frequency analysis of sensory processing in young adults with Autism Spectrum Disorder via continuous wavelet transform. The sensory tasks consisted of two blocks of unimodal sensory stimuli of the same type (i.e., auditory-auditory or visual-visual). A total of 12 autistic and 15 neurotypical subjects, all between 18-30 years, were analyzed. The 60 electrodes were grouped into 14 regions of interest to identify time-locked elicited brain activity. The power within three selected time-frequency windows for each block was compared between groups, showing significant differences in the first window of the second block of the visual-visual task, with the neurotypicals displaying higher power, suggesti

F

EEG microstates analysis in young adults with Autism Spectrum Disorder during resting-state

Frontiers in Human Neuroscience

Jun 2019

Electroencephalography (EEG) is a useful tool to inspect the brain activity in resting state and allows to characterize spontaneous brain activity that is not detected when a subject is cognitively engaged. Moreover, taking advantage of the high time resolution in EEG, it is possible to perform fast topographical reference-free analysis, since different scalp potential fields correspond to changes in the underlying sources within the brain. In this study, the spontaneous EEG resting state (eyes closed) was compared between 10 young adults ages 18–30 years with autism spectrum disorder (ASD) and 13 neurotypical controls. A microstate analysis was applied, focusing on four temporal parameters: mean duration, the frequency of occurrence, the r

W

A motor imagery BCI experiment using wavelet analysis and spatial patterns feature extraction

Workshop on Engineering Applications

May 2012

A brain computer interface (BCI) is a system that aims to control devices by analyzing brain signals patterns. In this work, a convenient time-frequency representation (TFR) for visualizing ERD/ERS phenomenon (Event related synchronization and desynchronization) based on Hilbert transform and spatial patterns is addressed, and a wavelet based feature extraction method for motor imagery tasks is presented. The feature vectors are constructed with four statistical and energy parameters obtained from wavelet decomposition, based on the sub-band coding algorithm. Experimentation with three classification methods for comparison purposes was carried out using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Support V

C

A BCI motor imagery experiment based on parametric feature extraction and fisher criterion

CONIELECOMP nd International Conference on Electrical Communications and Computers

Feb 2012

An EEG-based classification method in the time domain is proposed to identify left and right hand motor imagery as part of a brain-computer interface (BCI) experiment. The feature vector is formed by sixth order autoregressive coefficients (AR) or sixth order adaptive autoregressive coefficients (AAR) representing EEG signals obtained from C3 and C4 channels, according to the EEG 10-20 standard. The signal is analyzed considering 1 second windows with a 50% overlapping. A feature selection process based on the Fisher Criterion (FC) removes irrelevant or noisy information. A Linear Discriminant Analysis (LDA) is applied to both cases: feature vectors formed with the total number of coefficients, and feature vectors formed with coefficients c

David D'Croz Barón

About

Detail

Timeline

Résumé