Cluster analysis faces two problems in high dimensions: the "curse of dimensionality" that can lead to overfitting and poor generalization performance and the sheer time taken for conventional algorithms to process large amounts of high-dimensional data. We describe a solution to these problems, designed for the application of spike sorting for next-generation, high-channel-count neural probes. In this problem, only a small subset of features provides information about the cluster membership of any one data vector, but this informative feature subset is not the same for all data points, rendering classical feature selection ineffective. We introduce a "masked EM" algorithm that allows accurate and time-efficient clustering of up to millions of points in thousands of dimensions. We demonstrate its applicability to synthetic data and to real-world high-channel-count spike sorting data.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4298163 | PMC |
| http://dx.doi.org/10.1162/NECO_a_00661 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Screening and identification of evaluation indicators of low phosphorus tolerant germplasm in Gleditsia sinensis Lam.
Sci Rep
December 2024
Institute for Forest Resources and Environment of Guizhou, College of Forestry, Guizhou University, Guiyang, 550025, Guizhou, China.
This study aims to explore the low phosphorus (P) tolerance of saplings from different Gleditsia sinensis Lam. families. It also seeks to screen for Gleditsia sinensis families with strong low P tolerance and identify key indicators for evaluating their tolerance.
View Article and Find Full Text PDFTranscriptomic analysis of + non-small cell lung cancer reveals an upregulation of nucleotide synthesis and cell adhesion pathways.
Front Oncol
December 2024
Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Edegem, Belgium.
Introduction: The transcriptomic characteristics of + non-small cell lung cancer (NSCLC) represent a crucial aspect of its tumor biology. These features provide valuable insights into key dysregulated pathways, potentially leading to the discovery of novel targetable alterations or biomarkers.
Methods: From The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) databases, all available + (n = 10), + (n = 5) and + (n = 5) NSCLC tumor and + cell line (n = 7) RNA-sequencing files were collected.
Spatial variation and associated factors of home delivery among reproductive age group women in Ethiopia, evidence from Performance Monitoring for Action Ethiopia Survey 2019, spatial and multilevel logistic regression analysis.
Front Glob Womens Health
December 2024
Department of Health System and Management, School of Public Health, College of Medicine and Health Sciences, Wollo University, Dessie, Ethiopia.
Introduction: Home birth is described as a delivery that takes place at home without the presence of a skilled birth attendant. In 2017, nearly 295,000 mothers died from various pregnancy and childbirth-related problems, accounting for approximately 810 maternal deaths per day. Therefore, this study aims to investigate the spatial distributions of home birth and associated factors in Ethiopia using the Performance Monitoring for Action Survey (PMAS) 2019) to get information that helps to take geographic-based interventions and can assist health planners and policymakers in developing particular measures to reduce home deliveries.
View Article and Find Full Text PDFImpaired interhemispheric synchrony in patients with iridocyclitis and classification using machine learning: an fMRI study.
Front Immunol
December 2024
Department of ophthalmology, Jiangxi Provincial People's Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, China.
Background: This study examined the interhemispheric integration function pattern in patients with iridocyclitis utilizing the voxel-mirrored homotopic connectivity (VMHC) technique. Additionally, we investigated the ability of VMHC results to distinguish patients with iridocyclitis from healthy controls (HCs), which may contribute to the development of objective biomarkers for early diagnosis and intervention in clinical set.
Methods: Twenty-six patients with iridocyclitis and twenty-six matched HCs, in terms of sex, age, and education level, underwent resting-state functional magnetic resonance imaging (fMRI) examinations.
Oncogene 5'-3' exoribonuclease 2 enhances epidermal growth factor receptor signaling pathway to promote epithelial-mesenchymal transition and metastasis in non-small-cell lung cancer.
Cytojournal
November 2024
Department of Respiratory and Critical Care Medicine, Wuyi County First People's Hospital, Jinhua, Zhejiang, China.
Objective: Epithelial-mesenchymal transition (EMT) and metastasis are the primary causes of mortality in non-small-cell lung cancer (NSCLC). 5'-3' exoribonuclease 2 (XRN2) plays an important role in the process of tumor EMT. Thus, this investigation mainly aimed to clarify the precise molecular pathways through which XRN2 contributes to EMT and metastasis in NSCLC.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!