Anibal Sólon Heinsfeld
A5024812055- Functional Brain Connectivity Studies
- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- African history and culture analysis
- Biomedical and Engineering Education
- Cell Image Analysis Techniques
- Data Stream Mining Techniques
- Health, Environment, Cognitive Aging
- Genomics and Rare Diseases
- EEG and Brain-Computer Interfaces
- Autism Spectrum Disorder Research
- Health and Medical Research Impacts
- Advanced Biosensing Techniques and Applications
- Ethics in Clinical Research
- Neural and Behavioral Psychology Studies
- Time Series Analysis and Forecasting
- Evolutionary Algorithms and Applications
- Human-Automation Interaction and Safety
- Research Data Management Practices
- Glioma Diagnosis and Treatment
- Statistical Methods and Inference
- Advanced Fluorescence Microscopy Techniques
- Data Visualization and Analytics
- Reinforcement Learning in Robotics
- Multi-Agent Systems and Negotiation
The University of Texas at Austin
2020-2024
Institut des Sciences Cognitives Marc Jeannerod
2021
Child Mind Institute
2018-2020
Pontifícia Universidade Católica do Rio Grande do Sul
2016-2017
The goal of the present study was to apply deep learning algorithms identify autism spectrum disorder (ASD) patients from large brain imaging dataset, based solely on activation patterns. We investigated ASD data a world-wide multi-site database known as ABIDE (Autism Brain Imaging Data Exchange). is brain-based characterized by social deficits and repetitive behaviors. According recent Centers for Disease Control data, affects one in 68 children United States. patterns functional...
Neuroscience is advancing standardization and tool development to support rigor transparency. Consequently, data pipeline complexity has increased, hindering FAIR (findable, accessible, interoperable reusable) access. brainlife.io was developed democratize neuroimaging research. The platform provides standardization, management, visualization processing automatically tracks the provenance history of thousands objects. Here, described evaluated for validity, reliability, reproducibility,...
Data standardization promotes a common framework through which researchers can utilize others' data and is one of the leading methods neuroimaging use to share replicate findings. As today, standardizing datasets requires technical expertise such as coding knowledge file formats. We present ezBIDS, tool for converting associated metadata Brain Imaging Structure (BIDS) standard. ezBIDS contains four major features: (1) No installation or programming requirements. (2) Handling both imaging...
Abstract When fields lack consensus standard methods and accessible ground truths, reproducibility can be more of an ideal than a reality. Such has been the case for functional neuroimaging, where there exists sprawling space tools processing pipelines. We provide critical evaluation impact differences across five independently developed minimal preprocessing pipelines MRI. show that even when handling identical data, inter-pipeline agreement was only moderate, critically shedding light on...
Increasing the reproducibility of neuroimaging measurement addresses a central impediment to advancement human neuroscience and its clinical applications. Recent efforts demonstrating variance in functional brain organization within between individuals shows need for improving parcellations without long scan times. We apply bootstrap aggregation, or bagging, problem parcellation. use two large datasets demonstrate that compared standard clustering framework, bagging improves test-retest...
The sparse group lasso is a high-dimensional regression technique that useful for problems whose predictors have naturally grouped structure and where sparsity encouraged at both the individual predictor level.In this paper we discuss new R package computing such regularized models.The intention to provide highly optimized solution routines enabling analysis of very large datasets, especially in context design matrices.
Brainhack is an innovative meeting format that promotes scientific collaboration and education in open inclusive environment. Departing from the formats of typical workshops, these events are based on grassroots projects training, foster reproducible practices. We describe here multifaceted, lasting benefits Brainhacks for individual participants, particularly early career researchers. further highlight unique contributions can make to research community, contributing progress by...
Abstract Although neuroimaging provides powerful tools for assessing brain structure and function, their utility elucidating mechanisms underlying neuropsychiatric disorders is limited by sensitivity to head motion. Several publications have shown that standard retrospective motion correction arduous quality assessment are insufficient fully remove the deleterious impacts of on functional (fMRI) structural (sMRI) data. These residual errors tend be correlated with age clinical diagnosis,...
OHBM Brainhack 2022 took place in June 2022. The first hybrid hackathon, it had an in-person component taking Glasgow and three hubs around the globe to improve inclusivity fit as many timezones possible. In buzzing setting of Queen Margaret Union virtual platform, 23 projects were presented after development. Following are reports 14 those, well a recapitulation organisation event.
Abstract Increasing the reproducibility of neuroimaging measurement addresses a central impediment to advancement human neuroscience and its clinical applications. Recent efforts demonstrating variance in functional brain organization within between individuals shows need for improving parcellations without long scan times. We apply bootstrap aggregation, or bagging, problem parcellation. use two large datasets demonstrate that compared standard clustering framework, bagging improves...
Ants are essentially social insects, and their organizational depen dency reflects directly on survival. Due to nature, ant society provides a rich model for analysing properties of multiagent systems such as col laboration effectiveness collective action. Modelling natural behaviour ants can help understand actions, well studying better forms co operation competition other models. In this paper, we an within stochastic environment in which is gen erated using reinforcement learning generate...
JASON is an AGENTSPEAK interpreter for multi-agent system devel opment, in which agents are described the language. There fore, we only have to describe agent behavior, but environment does not follow this style, it requires a Java description of how actions and percep tions operate. This choice implementation guarantees that even complex envi ronments can be created JASON, knowledge about both JASON’s Application Programming Interface (API). In paper aim fill gap between languages with...
Data standardization has become one of the leading methods neuroimaging researchers rely on for data sharing and reproducibility. promotes a common framework through which can utilize others' data. Yet, as today, formatting datasets that adhere to community best practices requires technical expertise involving coding considerable knowledge file formats standards. We describe ezBIDS, tool converting associated metadata Brain Imaging Structure (BIDS) standard. ezBIDS provides four unique...