Fernando García-Torres

Mr. Fernando García-Torres

CVBLab, Polytechnic University of Valencia, Valencia, Spain
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
27 May 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Sofía IranzoSofía Iranzo
Sofía Iranzo
APAlicia Piedrabuena
Alicia Piedrabuena
FGFernando García-Torres
Fernando García-Torres
JMJose L. Martinez-de-Juan
Jose L. Martinez-de-Juan
GPGema Prats-Boluda
Gema Prats-Boluda
Juan Manuel Belda LoisJuan Manuel Belda Lois
Juan Manuel Belda Lois
Manual material handling tasks in industry cause work-related musculoskeletal disorders. Exoskeletons are being introduced to reduce the risk of musculoskeletal injuries. This study investigated the effect of using a passive lumbar exoskeleton in terms of moderate ergonomic risk. Eight participants were monitored by electromyogram (EMG) and motion capture (MoCap) while performing tasks with and without the lumbar exoskeleton. The results showed a significant reduction in the root mean square (VRMS) for all muscles tracked: erector spinae (8%), semitendinosus (14%), gluteus (5%), and quadriceps (10.2%). The classic fatigue parameters showed a significant reduction in the case of the semitendinosus: 1.7% zero-crossing rate, 0.9% mean frequency, and 1.12% median frequency. In addition, the logarithm of the normalized Dimitrov’s index showed reductions of 11.5, 8, and 14% in erector spinae, semitendinosus, and gluteus, respectively. The calculation of range of motion in the relevant joints demonstrated significant differences, but in almost all cases, the differences were smaller than 10%. The findings of the study indicate that the passive exoskeleton reduces muscle activity and introduces some changes of strategies for motion. Thus, EMG and MoCap appear to be appropriate measurements for designing an exoskeleton assessment procedure.

5 April 2022 in Preprints.org
Verified
Preprint
Open access
PDF file
Sofía IranzoSofía Iranzo
Sofía Iranzo
APAlicia Piedrabuena
Alicia Piedrabuena
FGFernando García-Torres
Fernando García-Torres
JMJose L. Martinez-de-Juan
Jose L. Martinez-de-Juan
GPGema Prats-Boluda
Gema Prats-Boluda
Juan Manuel Belda LoisJuan Manuel Belda Lois
Juan Manuel Belda Lois
Manual material handling tasks in industry cause work-related musculoskeletal disorders. Exoskeletons are being introduced to reduce the risk of musculoskeletal injuries. This study investigated the effect of using a passive lumbar exoskeleton in terms of moderate ergonomic risk. Eight participants were monitored by electromyogram (EMG) and motion capture (MoCap) while performing tasks with and without the lumbar exoskeleton. The results showed a significant reduction in the root mean square (VRMS) for all muscles tracked: erector spinae (8%), semitendinosus (14%), gluteus (5%), and quadriceps (10.2%). The classic fatigue parameters showed a significant reduction in the case of the semitendinosus: 1.7% zero-crossing rate, 0.9% mean frequency, and 1.12% median frequency. In addition, the logarithm of the normalized Dimitrov’s index showed reductions of 11.5, 8, and 14% in erector spinae, semitendinosus, and gluteus, respectively. The calculation of range of motion in the relevant joints demonstrated significant differences, but in almost all cases, the differences were smaller than 10. The findings of the study indicate that the passive exoskeleton reduces muscle activity and introduces a minor change of strategies for motion. Thus, EMG and MoCap appear to be appropriate measurements for designing an exoskeleton assessment procedure.

14 November 2024
Verified
Book Chapter
Closed access
PDF file
FGFernando García-Torres
Fernando García-Torres
RARocío del Amor
Rocío del Amor
SMSandra Morales-Martínez
Sandra Morales-Martínez
ÁBÁlvaro Barroso
Álvaro Barroso
BKBjörn Kemper
Björn Kemper
VNValery Naranjo
Valery Naranjo

25 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
FGFernando García-Torres
Fernando García-Torres
RARocio del Amor
Rocio del Amor
SMSandra Morales
Sandra Morales
APAlvaro Barroso Pena
Alvaro Barroso Pena
PHPeter Heiduschka
Peter Heiduschka
VNValery Naranjo
Valery Naranjo
Background and Objective: Generating realistic medical images along with anatomically accurate segmentation masks is a promising approach to address the shortage of annotated data in medical imaging, particularly in optical coherence tomography (OCT) of mouse eyes, where manual retinal layer delineation is very labour-intensive due to tiny structures and demands on expert knowledge, resulting in scarce available datasets. While diffusion models have shown strong performance in medical image synthesis, joint image-mask generation has primarily relied on U-Net-based denoisers, leaving diffusion transformers largely unexplored in this context.Methods: We propose a conditional dual-output Diffusion Transformer (DualDiT) for the simultaneous synthesis of OCT B-scans and segmentation masks of the upper retinal cell layers (URCL) of ex vivo mouse retina. DualDiT encodes both modalities into a shared latent space via a pretrained variational auto-encoder, concatenates their latent representations, and performs conditional diffusion over the resulting joint tensor. We compared DualDiT against two adapted denoising diffusion baselines: a pixel-space conditional model (DDPM) and a latent-space conditional model (LDM). Generative quality was assessed using distribution similarity metrics (Fréchet Inception Distance, FID; spatial FID, sFID), practical utility was evaluated through synthetic data augmentation for downstream U-Net segmentation, and perceptual realism was assessed by a panel of three domain experts.Results: DualDiT achieved the best generative quality, obtaining a FID of 56.14 and sFID of 114.35, outperformingDDPM(FID 164.55, sFID 254.52) andLDM(FID 102.21, sFID 150.66). In the expert evaluation, panels incorrectly classified, on average, 46% of synthetic samples as real and 42% of real samples as synthetic. The additional use of DualDiT-generated images and masks increases Dice and IoU scores, as evaluated on a held-out test set of the segmentation model.Conclusions: DualDiT demonstrates that transformer-based diffusion models can effectively learn the joint distribution of OCT images and segmentation masks, surpassing conventional DDPM- and LDM-based baselines in generative fidelity, downstream segmentation utility, and perceptual realism, highlighting its potential as a data augmentation strategy for annotation-scarce medical imaging applications.