skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Exploring the Effects of Segmentation on Semi-Structured Interview Data with Epistemic Network Analysis
Quantitative ethnographic models are typically constructed using qualitative data that has been segmented and coded. While there exist methodological studies that have investigated the effects of changes in coding on model features, the effects of segmentation have received less attention. Our aim was to examine, using a dataset comprised of narratives from semi-structured interviews, the effects of different segmentation decisions on population- and individual-level model features via epistemic network analysis. We found that while segmentation choices may not affect model features overall, the effects on some individual networks can be substantial. This study demonstrates a novel method for exploring and quantifying the impact of segmentation choices on model features.  more » « less
Award ID(s):
1661036
PAR ID:
10248631
Author(s) / Creator(s):
; ;
Editor(s):
Ruis, Andrew R.; Lee, Seung B.
Date Published:
Journal Name:
Advances in Quantitative Ethnography: Second International Conference, ICQE 2020, Malibu, CA, USA, February 1-3, 2021, Proceedings
Page Range / eLocation ID:
78 - 90
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; (, Journal of Computing and Information Science in Engineering)
    Network-based analyses have effectively understood customer preferences through interactions between customers and products, particularly for tailored product design. However, research applying this analysis to diverse customers with varied preferences is limited. This paper introduces a market-segmented network modeling approach, guided by customer preference, to explore heterogeneity in customers’ two-stage decision-making process: consideration-then-choice. In heterogeneous markets, customers with similar characteristics or purchasing similar products can exhibit different decision-making processes. Therefore, this method segments customers based on preferences rather than just characteristics, allowing for more accurate choice modeling. Using joint correspondence analysis, we identify associations between customer attributes and preferred products, characterizing market segments through clustering. We then build individual bipartite customer–product networks and apply the exponential random graph model to compare the product features influencing customer considerations and choices in various market segments. Using a US household vacuum cleaner survey, our method detected different customer preferences for the same product attribute at different decision-making stages. The market-segmentation model outperforms the non-segmented benchmark in prediction, highlighting its accuracy in predicting varied customer behaviors. This study underscores the vital role of preference-guided segmentation in product design, illustrating how understanding customer preferences at different decision stages can inform and refine design strategies, ensuring products align with diverse market needs. 
    more » « less
  2. ; ; (, Frontiers in Neuroscience)
    Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance. 
    more » « less
  3. ; ; ; (, Applied Sciences)
    This paper studied the changing pattern of knee cartilage using 3D knee magnetic resonance (MR) images over a 12-month period. As a pilot study, we focused on the medial tibia compartment of the knee joint. To quantify the thickness of cartilage in this compartment, we utilized two methods: one was measurement through manual segmentation of cartilage on each slice of the 3D MR sequence; the other was measurement through cartilage damage index (CDI), which quantified the thickness on a few informative locations on cartilage. We employed the artificial neural networks (ANNs) to model the changing pattern of cartilage thickness. The input feature space was composed of the thickness information at a cartilage location as well as its neighborhood from baseline year data. The output categories were ‘changed’ and ‘no-change’, based on the thickness difference at the same location between the baseline year and the 12-month follow-up data. Different ANN models were trained by using CDI features and manual segmentation features. Further, for each type of feature, individual models were trained at different subregions of the medial tibia compartment, i.e., the bottom part, the middle part, the upper part, and the whole. Based on the experiment results, we found that CDI features generated better prediction performance than manual segmentation, on both whole medial tibia compartment and any subregion. For CDI, the best performance in term of AUC was obtained using the central CDI locations (AUC = 0.766), while the best performance for manual segmentation was obtained using all slices of the 3D MR sequence (AUC = 0.656). As experiment results showed, the CDI method demonstrated a stronger pattern of cartilage change than the manual segmentation method, which required up to 6-hour manual delineation of all MRI slices. The result should be further validated by extending the experiment to other compartments. 
    more » « less
  4. (, International Conference on Medical Image Computing and Computer-Assisted Intervention)
    null (Ed.)
    Vessel segmentation is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a small sample size. On the contrary, unsupervised methods rely on handcrafted features to detect tube-like structures such as vessels. However, those methods require complex pipelines involving several hyper-parameters and design choices rendering the procedure sensitive, dataset-specific, and not generalizable. We propose a self-supervised method with a limited number of hyper-parameters that is generalizable across modalities. Our method uses tube-like structure properties, such as connectivity, profile consistency, and bifurcation, to introduce inductive bias into a learning algorithm. To model those properties, we generate a vector field that we refer to as a flow. Our experiments on various public datasets in 2D and 3D show that our method performs better than unsupervised methods while learning useful transferable features from unlabeled data. Unlike generic self-supervised methods, the learned features learn vessel-relevant features that are transferable for supervised approaches, which is essential when the number of annotated data is limited. 
    more » « less
  5. ; (, Journal of educational data mining)
    In this paper, we describe our solution to predict student STEM career choices during the 2017 ASSISTments Datamining Competition. We built a machine learning system that automatically reformats the data set, generates new features and prunes redundant ones, and performs model and feature selection. We designed the system to automatically find a model that optimizes prediction performance, yet the final model is a simple logistic regression that allows researchers to discover important features and study their effects on STEM career choices. We also compared our method to other methods, which revealed that the key to good prediction is proper feature enrichment in the beginning stage of the data analysis, while feature selection in a later stage allows a simpler final model. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email