A5007053668- Neural Networks and Applications
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Face and Expression Recognition
- Domain Adaptation and Few-Shot Learning
- ECG Monitoring and Analysis
- Tunneling and Rock Mechanics
- Anomaly Detection Techniques and Applications
- Machine Learning and ELM
- Non-Invasive Vital Sign Monitoring
- Heart Rate Variability and Autonomic Control
- Hemodynamic Monitoring and Therapy
- Image and Signal Denoising Methods
- Intracerebral and Subarachnoid Hemorrhage Research
- Brain Tumor Detection and Classification
- Rock Mechanics and Modeling
- Image Retrieval and Classification Techniques
- Medical Imaging and Analysis
- Medical Image Segmentation Techniques
- Neural and Behavioral Psychology Studies
- Motor Control and Adaptation
- Landslides and related hazards
- Geotechnical Engineering and Analysis
- Image and Video Stabilization
Federico Santa María Technical University
2005-2024
University of Talca
2022-2024
University of Valparaíso
2017-2023
Institut national de recherche en informatique et en automatique
2019
Laboratoire Lorrain de Recherche en Informatique et ses Applications
2019
Centre National de la Recherche Scientifique
2019
Université de Lorraine
2019
Valparaiso University
2016
Universidad Técnica Federico Santa María
2007
Deep learning models are part of the family artificial neural networks and, as such, they suffer catastrophic interference when sequentially. In addition, greater number these have a rigid architecture which prevents incremental new classes. To overcome drawbacks, we propose Self-Improving Generative Artificial Neural Network (SIGANN), an end-to-end deep network system can ease forgetting problem this method, introduce novel detection model that automatically detects samples classes, and...
Medical image quality is crucial to obtaining reliable diagnostics. Most controls rely on routine tests using phantoms, which do not reflect closely the reality of images obtained patients and directly perceived by radiologists. The purpose this work develop a method that classifies radiologists in MR images. focus was set lumbar as they are widely used with different challenges. Three neuroradiologists evaluated dataset included T1-weighting axial sagittal orientation, T2-weighting. In...
Based on similarity measures in the wavelet domain under a multichannel EEG setting, two new methods are developed for single-trial event-related potential (ERP) detection. The first method, named “multichannel thresholding by similarity” (METS), simultaneously denoises all of information recorded channels. second approach, “semblance-based ERP window selection” (SEWS), presents versions to automatically localize time each subject reduce be analysed removing useless features. We empirically...
We propose an efficient computational method to obtain the fractional derivative of a digital signal. The proposal consists new interpretation Grünwald–Letnikov differintegral operator where we have introduced finite Cauchy convolution with dynamic kernel. can be applied any signal without knowing its analytical form. In experiments, compared proposed Riemman–Louville approach for two well-known functions. simulations exhibit similar results both methods; however, outperforms other in...
Cardiovascular diseases represent the leading cause of death worldwide. Thus, cardiovascular rehabilitation programs are crucial to mitigate deaths caused by this condition each year, mainly in patients with coronary artery disease. COVID-19 was not only a challenge area but also an opportunity open remote or hybrid versions these programs, potentially reducing number who leave due geographical/time barriers. This paper presents method for building prediction model using retrospective and...
The handstand is an uncommon posture, highly demanding in terms of muscle and joint stability, used sporting artistic practices a variety disciplines. Despite its becoming increasingly widespread, there no specific way to perform handstand, the neuromuscular organizational mechanisms involved are unknown. objective this study was determine synergy four postures through semblance analysis based on wavelets electromyographic signals upper limbs experienced circus performers between 18- 35-year...
Deep learning models are part of the family artificial neural networks and, as such, it suffers catastrophic interference when they learn sequentially. In addition, most these have a rigid architecture which prevents incremental new classes. To overcome drawbacks, in this article we propose Self-Improving Generative Artificial Neural Network (SIGANN), type end-to-end system is able to ease forgetting problem leaning method, introduce novelty detection model automatically detect samples...
Electroencephalographic signals are usually contaminated by noise and artifacts making difficult to detect Event-Related Potential (ERP), specially in single trials. Wavelet denoising has been successfully applied ERP detection, but works using channels information independently. This paper presents a new adaptive approach denoise taking into account correlation the wavelet domain. Moreover, we combine phase amplitude domain automatically select temporal window which increases class...
This study introduces a novel measure for evaluating attribute relevance, specifically designed to accurately identify attributes that are intrinsically related phenomenon, while being sensitive the asymmetry of those relationships and noise conditions. Traditional variable selection techniques, such as filter wrapper methods, often fall short in capturing these complexities. Our methodology, grounded decision trees but extendable other machine learning models, was rigorously evaluated...