Difference between revisions of "Functional data analysis for BCI and biomedical signals"
| Line 4: | Line 4: | ||
<!-- My research focuses on the problems of model selection in Machine Learning. It explores methods of Applied Mathematics and Computer Science. The central issue is to select the most accurate, robust, and simplest model. This model forecasts spatial time series, and measurements in medicine, biology, and physics. The practical applications are brain-computer interfaces, health monitoring with wearable devices, human behavior analysis, and classification of human motions in sports and computer games. | <!-- My research focuses on the problems of model selection in Machine Learning. It explores methods of Applied Mathematics and Computer Science. The central issue is to select the most accurate, robust, and simplest model. This model forecasts spatial time series, and measurements in medicine, biology, and physics. The practical applications are brain-computer interfaces, health monitoring with wearable devices, human behavior analysis, and classification of human motions in sports and computer games. | ||
--> | --> | ||
| − | == Brain | + | == Brain signals and dimensionality reduction == |
| + | |||
| + | Intracranial electroencephalography (iEEG) signals are tensors or time-related tensor fields. They have several indexes for physical space, time, and frequency. The multi-index structure of time series causes redundancy of space features and multi-correlation. It turns out to increase the complexity of the model and obtain unstable forecasts. I address the dimensionality reduction problem for high-dimensional data. The essential methods are tensor decomposition and high-order singular value decomposition. To reveal hidden dependencies in data, we proposed a feature selection method. It minimizes multi-correlation in the source space and maximizes the relation between source and target spaces. This solution shrinks the number of model parameters tenfold and stabilizes the forecast. | ||
== Biomedical signal decoding and multi-modeling == | == Biomedical signal decoding and multi-modeling == | ||
Revision as of 21:17, 12 October 2022
Vadim, 2023
Functional data analysis for BCI and biomedical signals
Brain-computer interfaces require a sophisticated forecasting model. This model fits heterogeneous data. The signals come from ECoG, ECG, fMRI, hand and eye movements, and audio-video sources. The model must reveal hidden dependencies in these signals and establish relations between brain signals and limb motions. My research focuses on the constriction of BCI forecasting models. The main challenges of the research are phase space construction, dimensionality reduction, manifold learning, heterogeneous modeling, and knowledge transfer. Since the measured data are stochastic and contain errors, I actively use and develop Bayesian model selection methods. These methods infer criteria to optimize model structure and parameters. They aim to select an accurate and robust BCI model.
Brain signals and dimensionality reduction
Intracranial electroencephalography (iEEG) signals are tensors or time-related tensor fields. They have several indexes for physical space, time, and frequency. The multi-index structure of time series causes redundancy of space features and multi-correlation. It turns out to increase the complexity of the model and obtain unstable forecasts. I address the dimensionality reduction problem for high-dimensional data. The essential methods are tensor decomposition and high-order singular value decomposition. To reveal hidden dependencies in data, we proposed a feature selection method. It minimizes multi-correlation in the source space and maximizes the relation between source and target spaces. This solution shrinks the number of model parameters tenfold and stabilizes the forecast.