James Sharpnack
YOU?
Author Swipe
View article: Improving lung cancer diagnosis and survival prediction with deep learning and CT imaging
Improving lung cancer diagnosis and survival prediction with deep learning and CT imaging Open
Lung cancer is a major cause of cancer-related deaths, and early diagnosis and treatment are crucial for improving patients’ survival outcomes. In this paper, we propose to employ convolutional neural networks to model the non-linear relat…
View article: BanditCAT and AutoIRT: Machine Learning Approaches to Computerized Adaptive Testing and Item Calibration
BanditCAT and AutoIRT: Machine Learning Approaches to Computerized Adaptive Testing and Item Calibration Open
In this paper, we present a complete framework for quickly calibrating and administering a robust large-scale computerized adaptive test (CAT) with a small number of responses. Calibration - learning item parameters in a test - is done usi…
View article: AutoIRT: Calibrating Item Response Theory Models with Automated Machine Learning
AutoIRT: Calibrating Item Response Theory Models with Automated Machine Learning Open
Item response theory (IRT) is a class of interpretable factor models that are widely used in computerized adaptive tests (CATs), such as language proficiency tests. Traditionally, these are fit using parametric mixed effects models on the …
View article: Improving Lung Cancer Diagnosis and Survival Prediction with Deep Learning and CT Imaging
Improving Lung Cancer Diagnosis and Survival Prediction with Deep Learning and CT Imaging Open
Lung cancer is a major cause of cancer-related deaths, and early diagnosis and treatment are crucial for improving patients' survival outcomes. In this paper, we propose to employ convolutional neural networks to model the non-linear relat…
View article: Exponential family trend filtering on lattices
Exponential family trend filtering on lattices Open
Trend filtering is a modern approach to nonparametric regression that is more adaptive to local smoothness than splines or similar basis procedures. Existing analyses of trend filtering focus on estimating a function corrupted by homoskeda…
View article: Comparative performance analysis of three machine learning algorithms applied to sensor data registered by a leg-attached accelerometer to predict metritis events in dairy cattle
Comparative performance analysis of three machine learning algorithms applied to sensor data registered by a leg-attached accelerometer to predict metritis events in dairy cattle Open
Routinely collected sensor data could be used in metritis predictive modeling but a better understanding of its potential is needed. Our objectives were 1) to compare the performance of k -nearest neighbors ( k -NN), random forest (RF), an…
View article: Impact of sensor data pre-processing strategies and selection of machine learning algorithm on the prediction of metritis events in dairy cattle
Impact of sensor data pre-processing strategies and selection of machine learning algorithm on the prediction of metritis events in dairy cattle Open
With all the sensor data currently generated at high frequency in dairy farms, there is potential for earlier diagnosis of postpartum diseases compared with traditional monitoring methodologies. Our objectives were 1) to compare the impact…
View article: RLSbench: Domain Adaptation Under Relaxed Label Shift
RLSbench: Domain Adaptation Under Relaxed Label Shift Open
Despite the emergence of principled methods for domain adaptation under label shift, their sensitivity to shifts in class conditional distributions is precariously under explored. Meanwhile, popular deep domain adaptation heuristics tend t…
View article: Optimizing machine learning methods to discover strong gravitational lenses in the Deep Lens Survey
Optimizing machine learning methods to discover strong gravitational lenses in the Deep Lens Survey Open
Machine learning models can greatly improve the search for strong gravitational lenses in imaging surveys by reducing the amount of human inspection required. In this work, we test the performance of supervised, semi-supervised, and unsupe…
View article: An Unsupervised Hunt for Gravitational Lenses
An Unsupervised Hunt for Gravitational Lenses Open
Strong gravitational lenses allow us to peer into the farthest reaches of space by bending the light from a background object around a massive object in the foreground. Unfortunately, these lenses are extremely rare, and manually finding t…
View article: Exponential Family Trend Filtering on Lattices
Exponential Family Trend Filtering on Lattices Open
Trend filtering is a modern approach to nonparametric regression that is more adaptive to local smoothness than splines or similar basis procedures. Existing analyses of trend filtering focus on estimating a function corrupted by homoskeda…
View article: Wastewater-Based Epidemiology for COVID-19: Handling qPCR Nondetects and Comparing Spatially Granular Wastewater and Clinical Data Trends
Wastewater-Based Epidemiology for COVID-19: Handling qPCR Nondetects and Comparing Spatially Granular Wastewater and Clinical Data Trends Open
Wastewater-based epidemiology (WBE) is a useful complement to clinical testing for managing COVID-19. While community-scale wastewater and clinical data frequently correlate, less is known about subcommunity relationships between the two d…
View article: The impact of COVID-19 vaccination on California’s return to normalcy
The impact of COVID-19 vaccination on California’s return to normalcy Open
SARS-CoV-2 has infected nearly 3.7 million and killed 61,722 Californians, as of May 22, 2021. Non-pharmaceutical interventions have been instrumental in mitigating the spread of the coronavirus. However, as we ease restrictions, widesprea…
View article: Wastewater surveillance for COVID-19 response at multiple geographic scales: Aligning wastewater and clinical results at the census-block level and addressing pervasiveness of qPCR non-detects
Wastewater surveillance for COVID-19 response at multiple geographic scales: Aligning wastewater and clinical results at the census-block level and addressing pervasiveness of qPCR non-detects Open
Wastewater surveillance is a useful complement to clinical testing for managing COVID-19. While good agreement has been found between community-scale wastewater and clinical data, little is known about sub-community relationships between t…
View article: An open repository of real-time COVID-19 indicators
An open repository of real-time COVID-19 indicators Open
Significance To study the COVID-19 pandemic, its effects on society, and measures for reducing its spread, researchers need detailed data on the course of the pandemic. Standard public health data streams suffer inconsistent reporting and …
View article: Can auxiliary indicators improve COVID-19 forecasting and hotspot prediction?
Can auxiliary indicators improve COVID-19 forecasting and hotspot prediction? Open
Significance Validated forecasting methodology should be a vital element in the public health response to any fast-moving epidemic or pandemic. A widely used model for predicting the future spread of a temporal process is an autoregressive…
View article: Replication Data for: Comparative performance analysis of three machine learning algorithms applied to sensor data in dairy cattle to predict metritis events II. Behaviors measured with a leg-attached accelerometer
Replication Data for: Comparative performance analysis of three machine learning algorithms applied to sensor data in dairy cattle to predict metritis events II. Behaviors measured with a leg-attached accelerometer Open
Dataset containing all the performance metrics (sensitivity, specificity, positive and negative predictive values, accuracy, and F1 score) using a rank-based approach and three different decision thresholds (highest 20%, 30%, and 40% class…
View article: An Open Repository of Real-Time COVID-19 Indicators
An Open Repository of Real-Time COVID-19 Indicators Open
The COVID-19 pandemic presented enormous data challenges in the United States. Policy makers, epidemiological modelers, and health researchers all require up-to-date data on the pandemic and relevant public behavior, ideally at fine spatia…
View article: Can Auxiliary Indicators Improve COVID-19 Forecasting and Hotspot Prediction?
Can Auxiliary Indicators Improve COVID-19 Forecasting and Hotspot Prediction? Open
Short-term forecasts of traditional streams from public health reporting (such as cases, hospitalizations, and deaths) are a key input to public health decision-making during a pandemic. Since early 2020, our research group has worked with…
View article: Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks
Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks Open
Stochastic linear contextual bandit algorithms have substantial applications in practice, such as recommender systems, online advertising, clinical trials, etc. Recent works show that optimal bandit algorithms are vulnerable to adversarial…
View article: Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms
Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms Open
The stochastic contextual bandit problem, which models the trade-off between exploration and exploitation, has many real applications, including recommender systems, online advertising and clinical trials. As many other machine learning al…
View article: The Impact of COVID-19 Vaccination on California’s Return to <i>Normalcy</i>
The Impact of COVID-19 Vaccination on California’s Return to <i>Normalcy</i> Open
SARS-CoV-2 has infected nearly 3.7 million and killed 61,722 Californians, as of May 22, 2021. Non-pharmaceutical interventions have been instrumental in mitigating the spread of the coronavirus. How- ever, as we ease restrictions, widespr…
View article: COVID-19 vaccination in California: Are we equitable yet?
COVID-19 vaccination in California: Are we equitable yet? Open
Background By March 2021, California had one of the least equitable COVID-19 vaccine distribution programs in the US. To rectify this, Governor Newsom ordered 4 million vaccine doses be reserved for the census tracts in the lowest quartile…
View article: Comparative performance analysis of three machine learning algorithms applied to sensor data in dairy cattle to predict metritis events I. Behaviors measured with an ear-tag accelerometer.
Comparative performance analysis of three machine learning algorithms applied to sensor data in dairy cattle to predict metritis events I. Behaviors measured with an ear-tag accelerometer. Open
Dairy cattle behavioral data measured by an ear-tag accelerometer during the first 21 days postpartum was used to build predictive models for metritis events. Three machine learning classifiers were used to compare performance in terms of …
View article: SSE-PT: Sequential Recommendation Via Personalized Transformer
SSE-PT: Sequential Recommendation Via Personalized Transformer Open
Temporal information is crucial for recommendation problems because user preferences are naturally dynamic in the real world. Recent advances in deep learning, especially the discovery of various attention mechanisms and newer architecture…
View article: An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling
An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling Open
We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on fi…
View article: Multiscale Non-stationary Stochastic Bandits
Multiscale Non-stationary Stochastic Bandits Open
Classic contextual bandit algorithms for linear models, such as LinUCB, assume that the reward distribution for an arm is modeled by a stationary linear regression. When the linear regression model is non-stationary over time, the regret o…
View article: Unsupervised Object Segmentation with Explicit Localization Module
Unsupervised Object Segmentation with Explicit Localization Module Open
In this paper, we propose a novel architecture that iteratively discovers and segments out the objects of a scene based on the image reconstruction quality. Different from other approaches, our model uses an explicit localization module th…
View article: Adaptive nonparametric regression with the K-nearest neighbour fused lasso
Adaptive nonparametric regression with the K-nearest neighbour fused lasso Open
Summary The fused lasso, also known as total-variation denoising, is a locally adaptive function estimator over a regular grid of design points. In this article, we extend the fused lasso to settings in which the points do not occur on a r…
View article: Fused Density Estimation: Theory and Methods
Fused Density Estimation: Theory and Methods Open
Summary We introduce a method for non-parametric density estimation on geometric networks. We define fused density estimators as solutions to a total variation regularized maximum likelihood density estimation problem. We provide theoretic…