Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/700898

Optimized visual stimuli for BCI with hessenberg decomposition based extreme learning machine

Yayık, A.·Kutlu, Y.·Altan, G.
View original source ↗Export metadata ↓

Abstract

Background and ObjectivesBrain-computer interfaces (BCIs) aim to provide neuroscientific communication platform for human-beings, in particular locked-in patients. In most cases event-related potentials (ERPs), averaged voltage responses to a specific target stimuli over time, have key roles in designing BCIs. With this reason, for the last several decades BCI researchers heavily have focused on signal processing methods to improve quality of ERPs. However, designing visual stimulus with considering their physical properties with regard to rapid and also reliable machine learning algorithms for BCIs remain relatively unexplored. Addressing the issues explained above, in summary the main contributions of this study are as follows: (1) optimizing visual stimulus in terms of size, color and background and, (2) to enhance learning capacity of conventional extreme learning machine (ELM) using advanced linear algebra techniques. MethodsTwo different sized (small and big), three different colored (blue, red and colorful) images with four different backgrounds (white, black and concentric) for each of them were designed and utilized as single object paradigm. Hessenberg decomposition method was proposed for learning process and compared with conventional ELM and multi-layer perceptron in terms of training duration and performance measures. ResultsPerformance measures of small colorful images with orange-concentric background were statistically higher than those of others. Visual stimulus with white background led to relatively higher performance measures than those with black background. Blue colored images had much more impact on improvement of P300 waves than red colored ones had. Hessenberg decomposition method provided 1.5 times shortened training duration than conventional ELM, in addition with comparable performance measures. ConclusionsHerein, a visual stimuli model based on improving quality of ERP responses and machine learning algorithm relies on hessenberg decomposition method are introduced with demonstration of their advantages in the context of BCI. Methods and findings described in this study may pave the way for widespread applications, particularly in clinical health-informatics.

Explore related subjects

neurosciencePreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yayık, A., Kutlu, Y., Altan, G.. 2019-07-14. Optimized visual stimuli for BCI with hessenberg decomposition based extreme learning machine. https://doi.org/10.1101/700898

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

The Unreasonable Effectiveness of Cell Types in Describing Neuronal Physiological Features

Single-cell RNA sequencing (scRNA-seq) captures detailed gene expression profiles at scale, while patch-clamp recordings measure intrinsic neuronal electrophysiological properties. Modeling the relations between these two modalities remains a challenge. Here, we compare how well electrophysiological features can be predicted by traditional transcriptomic cell type classification, representations derived from a foundational model (scGPT) pretrained on large-scale scRNA-seq datasets, ion channel-coding genes, and highly variable genes. Using paired transcriptomic and electrophysiological patch-sequencing data from 495 human neurons from neurosurgical tissue, we find that cluster-level cell type representations consistently outperform highly variable gene selection, ion channel gene selection, and context-enriched scGPT embeddings. Notably, performance varies across model architectures and initializations, and the best results are obtained by combining the outputs of separate cell type and scGPT-based models. Together, these findings suggest that traditional discrete cellular classification is highly effective in predicting physiological features. For maximum performance it can be complemented by pretrained transformer models.

neuroscience↗
bioRxiv2026

A nonlinear inhibition pathway underlying cortical responses to tuned holographic optogenetic perturbations

Optogenetics enables causal manipulation of cortical activity. Perturbation responses can be counterintuitive due to network interactions, making theory essential for predicting them. Existing approaches often rely on linear approximations, which fail for many biologically relevant perturbations. Here we develop a nonlinear theory of responses to holographic perturbations in cell-type-specific recurrent networks with structured connectivity. We fit a nonlinear model to mouse V1 data, which shows cotuned-ensemble suppression: perturbing spatially clustered neurons with similar preferred orientations yields markedly stronger short-range suppression than perturbing untuned ensembles. We show that cotuned-ensemble suppression arises from a feature-tuned, nonlinear inhibition pathway implicating somatostatin-positive (SST) interneurons. The theory predicts that cotuned ensembles suppress parvalbumin-positive (PV) neurons but facilitate SST neurons, and links the degree of cotuned-ensemble suppression or facilitation to the variance of the SST response. This framework identifies mechanisms by which nonlinear inhibition sculpts cortical dynamics and establishes a predictive basis for targeted optogenetic interventions.

neuroscience↗
bioRxiv2026

Proteomic signatures of APOE ε4 across human tissues and cell types in Alzheimers disease

The apolipoprotein E {varepsilon}4 (APOE {varepsilon}4) allele is the strongest genetic risk factor for late-onset Alzheimers disease (AD). However, the underlying molecular mechanisms remain unclear. This study included 1691 participants from the Religious Orders Study and Rush Memory and Aging Project (ROSMAP), 1226 participants from the Accelerating Medicines Partnership - Alzheimers Disease (AMP-AD) Diverse Cohorts Study, and 735 participants from the Alzheimers Disease Neuroimaging Initiative (ADNI). To characterise APOE {varepsilon}4 molecular effects, we analysed proteomic data from plasma, cerebrospinal fluid (CSF), and induced pluripotent stem cell (iPSC)-derived astrocytes and neurons, as well as transcriptomic and proteomic data from multiple brain regions. The association of APOE {varepsilon}4 with AD neuropathology was also examined. APOE {varepsilon}4 carriers shared a plasma proteomic signature enriched for immune processes, irrespective of AD diagnosis. A machine learning classifier trained on this signature discriminated APOE {varepsilon}4 carriers from non-carriers in an independent cohort using CSF proteomics. APOE {varepsilon}4 carriage was associated with higher Braak stages and Consortium to Establish a Registry for Alzheimers Disease (CERAD) score. However, only limited APOE {varepsilon}4-associated transcriptomic and proteomic changes were observed in bulk brain tissue, with poor cross-layer concordance. Proteomic analyses of iPSC-derived astrocytes and neurons further revealed cell-type-specific APOE {varepsilon}4-associated changes. APOE {varepsilon}4 is associated with a consistent proteomic signature across plasma and CSF. Its molecular effects in the brain differ across cell types, brain regions and molecular layers. These findings support the need for cell-type-resolved multi-omic studies to elucidate how APOE {varepsilon}4 confers AD risk.

neuroscience↗