Farnoush Banaei‐Kashani
A5007232242- Data Management and Algorithms
- Geographic Information Systems Studies
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Advanced Database Systems and Queries
- Peer-to-Peer Network Technologies
- Bioinformatics and Genomic Networks
- Complex Network Analysis Techniques
- Data Stream Mining Techniques
- Data Mining Algorithms and Applications
- Transportation Planning and Optimization
- Automated Road and Building Extraction
- Caching and Content Delivery
- Methane Hydrates and Related Phenomena
- Respiratory Support and Mechanisms
- Opportunistic and Delay-Tolerant Networks
- Gene expression and cancer classification
- Arctic and Antarctic ice dynamics
- Asthma and respiratory diseases
- Transportation and Mobility Innovations
- Digital Mental Health Interventions
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Pulmonary Hypertension Research and Treatments
- Anomaly Detection Techniques and Applications
- Time Series Analysis and Forecasting
- Internet Traffic Analysis and Secure E-voting
University of Colorado Denver
2016-2025
University of Denver
2017-2024
University of Colorado Boulder
2017-2024
Park University
2022
Weatherford College
2021
Flint Institute Of Arts
2021
University of Colorado System
2017-2020
University of Southern California
2005-2014
Southern California University for Professional Studies
2006-2014
Increasing awareness of the prevalence and significance Preserved Ratio Impaired Spirometry (PRISm), alternatively known as restrictive or Global Initiative for Chronic Obstructive Lung Disease (GOLD)-unclassified spirometry, has expanded body knowledge on cross-sectional risk factors. However, longitudinal studies PRISm remain limited.
Geospatial queries (GQ) have been used in a wide variety of applications such as decision support systems, profile-based marketing, bioinformatics and GIS. Most the existing query-answering approaches assume centralized processing on single machine although GQs are intrinsically parallelizable. There some that designed for parallel databases cluster however, these only apply to systems with limited capability, far from cloud-based platforms. In this paper, we study problem geospatial query...
Rationale: The decades-long progression of chronic obstructive pulmonary disease (COPD) renders identifying different trajectories challenging.Objectives: To identify subtypes patients with COPD distinct longitudinal patterns using a novel machine-learning tool called "Subtype and Stage Inference" (SuStaIn) to evaluate the utility SuStaIn for patient stratification in COPD.Methods: We applied cross-sectional computed tomography imaging markers 3,698 Global Initiative Chronic Obstructive Lung...
Cardiovascular disease (CVD) is the most important comorbidity in patients with chronic obstructive pulmonary (COPD). COPD exacerbations not only contribute to progression but may also elevate risk of CVD. This study aimed determine whether increase subsequent CVD events using up 15 years prospective longitudinal follow-up data from COPDGene (Genetic Epidemiology Chronic Obstructive Pulmonary Disease) study.
This paper introduces LIBS, a light-weight and inexpensive wearable sensing system, that can capture electrical activities of human brain, eyes, facial muscles with two pairs custom-built flexible electrodes each which is embedded on an off-the-shelf foam earplug. A supervised non-negative matrix factorization algorithm to adaptively analyze extract these bioelectrical signals from single mixed in-ear channel collected by the sensor also proposed. While LIBS enable wide class low-cost...
Peer-to-peer Data Networks (PDNs) are large-scale, self-organizing, distributed query processing systems. Familiar examples of PDN peer-to-peer file-sharing networks, which support exact-match search queries to locate user-requested files. In this paper, we formalize the more general problem <i>similarity-search</i> in PDNs, and propose a <i>family</i> access methods, termed <i>Small-World Access Methods (SWAM)</i>, for efficient execution various similarity-search queries, namely...
Microsleep, caused by sleep deprivation, apnea, and narcolepsy, costs the U.S.'s economy more than $411 billion/year because of work performance reduction, injuries, traffic accidents. Mitigating microsleep's consequences require an unobtrusive, reliable, socially acceptable microsleep detection solution throughout day, every day. Unfortunately, existing solutions do not meet these requirements.
Multiple studies have demonstrated an increased risk of chronic obstructive pulmonary disease (COPD) in heterozygous carriers the AAT (alpha-1 antitrypsin) Z allele. However, it is not known if MZ subjects with COPD are phenotypically different from noncarriers (MM genotype) COPD.
Chronic obstructive pulmonary disease (COPD) and idiopathic fibrosis (IPF) are characterized by shared exposures clinical features, but distinct genetic pathologic features exist. These have not been well-studied using large-scale gene expression datasets. We hypothesized that there divergent gene, pathway, cellular signatures between COPD IPF.We performed RNA-sequencing on lung tissues from individuals with IPF (n = 231) 377) compared to control 267), defined as normal spirometry. grouped...
Network approaches have successfully been used to help reveal complex mechanisms of diseases including Chronic Obstructive Pulmonary Disease (COPD). However despite recent advances, we remain limited in our ability incorporate protein-protein interaction (PPI) network information with omics data for disease prediction. New deep learning methods convolution Graph Neural (ConvGNN) has shown great potential classification using transcriptomics and known PPI networks from existing databases. In...
Due to enormous complexity of the unstructured peer-to-peer networks as large-scale, self-configure, and dynamic systems, models used characterize these systems are either inaccurate, because oversimplification, or analytically inapplicable, due their high complexity. By recognizing "complex ", we employ statistical before complex for formal analysis efficient design networks. We provide two examples application this modeling approach that demonstrate its power. For instance, using have been...
The problem of point-to-point shortest path computation in spatial networks is extensively studied with many approaches proposed to speed-up the computation. Most existing make simplifying assumption that weights (e.g., travel-time) network edges are constant. However, real-world edge travel-times time-dependent, where arrival-time an determines actual travel-time edge. With this paper, we study applicability algorithms large time-dependent networks. In addition, evaluate importance...
Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of mortality in United States; however, COPD has heterogeneous clinical phenotypes. This first large scale attempt which uses transcriptomics, proteomics, and metabolomics (multi-omics) to determine whether there are molecularly defined clusters with distinct phenotypes that may underlie heterogeneity. Subjects included 3,278 subjects from COPDGene cohort at least one following profiles: whole blood transcriptomes (2,650...
The ability of peripheral blood biomarkers to assess chronic obstructive pulmonary disease (COPD) risk and progression is unknown. Genetics gene expression may capture important aspects COPD-related biology that predict activity.
Annotation of polyadenylation sites from short-read RNA sequencing alone is a challenging computational task. Other algorithms rooted in DNA sequence predict potential sites; however, vivo expression particular site varies based on myriad conditions. Here, we introduce aptardi (alternative transcriptome analysis RNA-Seq data and information), which leverages both machine learning paradigm to expressed sites. Specifically, as input takes nucleotide sequence, genome-aligned data, an initial...
Abstract Background Artificially intelligent (AI) chatbots that deploy natural language processing and machine learning are becoming more common in health care to facilitate patient education outreach; however, generative such as ChatGPT face challenges, they can misinform hallucinate. Health systems increasingly interested using these tools for education, access care, self-management, but need reassurances AI be secure credible. Objective This study aimed build a system people use send SMS...
Multiple -omics (genomics, proteomics, etc.) profiles are commonly generated to gain insight into a disease or physiological system. Constructing multi-omics networks with respect the trait(s) of interest provides an opportunity understand relationships between molecular features but integration is challenging due multiple data sets high dimensionality. One approach use canonical correlation integrate one two omics types and single trait interest. However, these methods may be limited (1)...
Accurate mapping of sea ice is crucial for marine navigation and monitoring climate change. Automating remains challenging due to remotely-sensed signal ambiguity, the dynamic nature ice, limited field measurements. The AutoICE challenge recently introduced a benchmark advance deep learning mapping. Top-performing solutions used U-Net architecture with extra pre/post-processing steps incorporated location features obtain higher metrics. However, model interpretation diagnostics remain...
Sea ice plays a critical role in the global climate system and maritime operations, making timely accurate classification essential. However, traditional manual methods are time-consuming, costly, have inherent biases. Automating sea-ice type addresses these challenges by enabling faster, more consistent, scalable analysis. While both deep-learning approaches been explored, models offer promising direction for improving efficiency consistency classification. absence of standardized benchmark...
The World Wide Web (WWW) is the largest distributed information space and has grown to encompass diverse resources. Although web growing exponentially, individual's capacity read digest content essentially fixed. full economic potential of will not be realized unless enabling technologies are provided facilitate access Currently personalization most promising approach remedy this problem, mining, particularly web-usage considered a crucial component any efficacious web-personalization...
A spatiotemporal network is a spatial (e.g., road network) along with the corresponding time-dependent weight travel time) for each edge of network. The design and analysis policies plans on networks path planning location-based services) require realistic models that accurately represent temporal behavior such networks. In this paper, first time we propose traffic modeling framework enables 1) generating an accurate model from archived data collected (so as to be able publish without having...