Wednesday, April 19, 2023

Columbia University – Alfred Lerner Hall

Thank you for your submission to Data Science Day 2023, DSI’s flagship annual event. We look forward to exhibiting your research! Please use this page to search for your project name and find your correlating poster or demo number using the exhibitor map. Please also look at the setup and exhibition timeline to determine when you have been scheduled to drop off your research to the venue. FAQ’s regarding registration, what to bring, and other details are included at the bottom of this page.

Exhibitor Map

Setup & Exhibition Timeline

Check-In Location: Exhibitor Table, Broadway Lobby, Alfred Lerner Hall (2920 Broadway, New York, NY 10027)

8:00 AM – 8:45 AM: SETUP: Part 1

  • ALL Demos must check in at this time
  • Posters P37 – P66 should plan to arrive at this time due to proximity to the stage
  • If you are assigned to one of the above poster numbers and cannot drop your poster off early, we can hold your poster at coat check and you can set up at the end of the stage program (~1:30 PM)

12:00 PM – 1:15 PM: SETUP: Part 2

  • Posters P01 – P36 and P67 – P79 can check in at this time, however, you are encouraged to come earlier!

1:30 PM – 4:00 PM: POSTER AND DEMO SESSION

  • Teams must be stationed by their project during the open session time.

4:00 PM – 5:00 PM: RECEPTION

  • Teams are welcome to continue presenting during the event reception, but this is optional.

5:00 PM – 5:15 PM: BREAKDOWN & EXIT

Table-Based Demos

D01: CPS: Medium: Hybrid Twins for Urban Transportation: From Intersections to Citywide Management

D02: Towards Accessible Sports Broadcasts for Blind and Low-Vision Viewers

D03: Documenting the Development of the Global Gridded Relative Deprivation Index (GRDI), Version 1 (GRDIv1)

D04: Real-Time Automated Diffusion Tensor Imaging Analysis for Pediatric Knee Growth Plate Segmentation and Fiber Tracking

D05: I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors

D06: Machine Learning-Based Eye Disease Screening using Indirect Fundoscopy and iOS device

Posters

P01: Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions

P02: Prophet Inequalities for MNL Assortment Optimization

P03: Diagnosing Model Performance Under Distribution Shift

P04: Identifying and Exploring Key Predictors of Educational Outcomes in Israeli Students Using Tree-Based Machine Learning Algorithms and Receiver Operating Characteristic Area Under the Curve (ROC AUC)

P05: Dynamic Surveying

P06: Reading AI Generated Images to Re-See AI Generated Texts

P07: Data Fusion for the Multi-Store Newsvendor Problem

P08: Detecting AI generated text using GPT-4

P09: On the Statistical Benefits of Temporal Difference Learning

P10: Semi-parametric Clustering of High-dimensional Time Series

P11: Scalable Parametric Signal Detection by Hill Climbing

P12: Extracting representational content in deep learning models through second-order isomorphism-based tools

P13: Speed-based Measures of Signal-to-Noise Ratios

P14: CYsyphus – The Cybersecurity Policy Recommendation Tool

P15: Creating and Enforceable Mechanism for Measuring Security Effort

P16: Thompson Sampling is itself Differentially Private

P17: Intra-Person Fingerprints Are Not Unique

P18: Accelerating the construction of ANN interatomic potentials using surrogate models

P19: Constructing Property-aware Compressed Materials Representations with Information-theory and Autoencoders

P20: Introduction to Machine Learning in the Physical Sciences: A New Hands-on Course at Columbia

P21: MIN-ML: A Machine Learning Approach for Classifying Igneous Minerals

P22: Changing Nature of High-Impact Snowfall Events in the NorthEast

P23: A Foundational CNN Model for Predicting Eye Fixations on OCT Reports

P24: Transferable Energy Storage Bidder

P25: JoinBoost: Grow Trees Over Normalized Data Using Only SQL

P26: Kitana: Efficient Data Augmentation Search

P27: Towards a Real-Time Adaptive Full-Duplex Wireless Radio

P28: Data Analysis of Wireless Communication in a Co-Taught IB Math Classroom

P29: Turning the Block in NYC and Still Getting 5G Coverage? mmWave Around-the-Corner Measurements for Dense Urban Deployment

P30: Network-Level Full-Duplex Wireless in the COSMOS Testbed

P31: Real-time Multi-Camera Analytics for Traffic Information Extraction and Visualization

P32: Text Classifier-Based Indications of Foodborne Illness Events from Yelp Reviews and Median Household Income by New York City Census Tract, 2020

P33: Audio-recording Patient-Nurse Verbal Communication for Proactive Identification of Home Healthcare Patients at Risk of Emergency Department Visit and Hospitalization: A Feasibility Study

P34: An Exploration of Q-Learning for Building Energy System Control

P35: AI-based Modeling Strategies for Rapid Structural Damage Assessment

P36: Expanding a Neighborhood Environmental Vulnerability Index for Childhood

P37: Enhancing Smart City Mobility on Urban Road Networks with Neural Network-Based Map-Matching of GPS Trajectory Data

P38: Parents, Privacy, and Delegation of Trust

P39: Decoding Propaganda: The Effect of Labeling Rhetorical Devices on User Engagement

P40: Creating an Interface for Understanding Changes in Published Text

P41: Open Source Economics – Building Trust and Effective Resource Allocation at Scale

P42: Learned Interactive Visualization Interfaces

P43: Neuro-DBER: A flexible neuroscience- and technology-driven framework for the Scholarship of Teaching & Learning

P44: Time-Varying Latent Dynamics of Teacher-Student Interactions

P45: Education Leadership Data Analytics (ELDA): Applied Data Science in Organizations and Leadership

P46: Saturation Effects in Equitable Demand Response Tariff Design

P47: Iterative Network Pricing for Ridesharing Platforms

P48: Fair Fares for Vehicle Sharing Systems

P49: Balanced Off-Policy Evaluation for Personalized Pricing

P50: Static Pricing for Queueing Systems

P51: Robust Auctions with Support Information

P52: Dynamic Learning in Large Matching Markets

P53: Simulator Is All You Need: Novel Lower Bounds and a Unifying Algorithm for NRM (and more)

P54: Financial Big Data for Data-Driven Financial Reinforcement Learning (FinRL)

P55: Telematics for Risk Scoring Cyber Attacks

P56: EBM-based Malnutrition Risk Factor Visualization Toward Novel Clinical Insights

P57: Clinical-LSTM: Using an Augmented LSTM to predict Myocardial Recovery in VA-ECMO

P58: Towards Personalized Meal Recommendations for Type II Diabetes Self-Management

P59: Using Data Fusion and Multiple Imputation to Correct for Misclassification in Self-reported Substance Use: A Case-Control Study of Cannabis Use and Homicide Victimization

P60: Characterizing E-Cigarette Usage in the New York City Population

P61: Multi-Disciplinary Development and Implementation of a Trial of Void Algorithm to Reduce Indwelling Urethral Catheter Use

P62: Visualizing Social Networks of Caregiver Support Communities for Hispanic and African American Family Caregivers of a Person with Dementia in Twitter

P63: Comparing Emotional Valence Scores of Direct Messages from Human Coding and Machine Learning Algorithms in a Twitter-based Clinical Trial for Hispanic and African American Family Caregivers of Persons with Dementia

P64: Applications of the OnSIDES Adverse Drug Event Database

P65: Functional co-clustering of physical activity patterns among Black and/or Latinx sexual and gender minority adults 

P66: Quantifying and Validating Pace of Aging Using Framingham Heart Study

P67: A Graphical User Interface for Proteomics Analysis

P68: Persistent Homology-based Functional Connectivity and its Association with Cognitive Ability: Life-span Study

P69: Nursing Notes-based Clinical Decision-making through Machine Learning and Natural Language Processing (NLP)

P70: Using Time Series Clustering to Segment and Infer Emergency Department Nursing Shifts from Electronic Health Record Log Files

P71: Noninvasive Glucose Sensing with Light in the Wild

P72: CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks

P73: Incorporating Positional Expert Eye-Tracking Data into Deep Learning Model Training for Glaucoma Detection

P74: Poster 2: Glaucoma Progression Detection and Humphrey Visual Field Prediction Using Discriminative and Generative Vision Transformers

P75: Extracting Decision-Making Features from Unstructured Eye Movements of Clinical Experts on Optical Coherence Tomography Images

P76: Fixation-Order Informed Vision Transformer to Detect Glaucoma in Optical Coherence Tomography Images

P77: Predicting Clinician Fixations on Glaucoma OCT Report via CNN-Based Saliency Prediction Methods

P78: Extracting Novel Features from Eye Movements of Clinical Experts for AI-based Glaucoma Detection

P79: Transfer Learning for Enhanced Phase Recognition in Data-Scarce Surgeries