Joon Lee

dblp:64/4749 · DBLP profile ↗
← Back
9ranked-venue papers
1as first author
4since 2021 · last 2023
—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 3 · 1 first-authorApplied, interdisciplinary, general and emerging computing · 3 · 2 since 2021Theory of computation · 2 · 2 since 2021Human-computer interaction and ubiquitous computing · 1
YearPublicationVenuePosition
2023 The Full Rank Condition for Sparse Random Matrices
abstract
We derive a sufficient condition for a sparse random matrix with given numbers of non-zero entries in the rows and columns having full row rank. The result covers both matrices over finite fields with independent non-zero entries and $\{0,1\}$-matrices over the rationals. The sufficient condition is generally necessary as well.
Amin Coja-Oghlan, Jane Gao, Max Hahn-Klimroth, Joon Lee, Noëla Müller, Maurice Rolvien
APPROX/RANDOM4
2022 The Sparse Parity Matrix
abstract
The last decade witnessed several pivotal results on random inference problems where the aim is to learn a hidden ground truth from indirect randomised observations; much of this research has been guided by statistical physics intuition. Prominent examples include the stochastic block model, low-density parity check codes or compressed sensing. In all random inference problems studied so far the posterior distribution of the ground truth given the observations appears to enjoy a key property called “strong replica symmetry”. This means that the overlap of the posterior distribution with the ground truth (basically the number of bits that can be learned correctly) concentrates on a deterministic value. Whether this is generally true has been an open question. In this paper we discover an example of an inference problem based on a very simple random matrix over that fails to exhibit strong replica symmetry. Beyond its impact on random inference problems, the random matrix model, reminiscent of the binomial Erdős-Rényi random graph, gives rise to a natural random constraint satisfaction problem related to the intensely studied random k-XORSAT problem.
Amin Coja-Oghlan, Oliver Cooley, Mihyun Kang, Joon Lee, Jean Bernoulli Ravelomanana
SODA4
2021 Natural language processing to measure the frequency and mode of communication between healthcare professionals and family members of critically ill patients
abstract
OBJECTIVE: To apply natural language processing (NLP) techniques to identify individual events and modes of communication between healthcare professionals and families of critically ill patients from electronic medical records (EMR). MATERIALS AND METHODS: Retrospective cohort study of 280 randomly selected adult patients admitted to 1 of 15 intensive care units (ICU) in Alberta, Canada from June 19, 2012 to June 11, 2018. Individual events and modes of communication were independently abstracted using NLP and manual chart review (reference standard). Preprocessing techniques and 2 NLP approaches (rule-based and machine learning) were evaluated using sensitivity, specificity, and area under the receiver operating characteristic curves (AUROC). RESULTS: Over 2700 combinations of NLP methods and hyperparameters were evaluated for each mode of communication using a holdout subset. The rule-based approach had the highest AUROC in 65 datasets compared to the machine learning approach in 21 datasets. Both approaches had similar performance in 17 datasets. The rule-based AUROC for the grouped categories of patient documented to have family or friends (0.972, 95% CI 0.934-1.000), visit by family/friend (0.882 95% CI 0.820-0.943) and phone call with family/friend (0.975, 95% CI: 0.952-0.998) were high. DISCUSSION: We report an automated method to quantify communication between healthcare professionals and family members of adult patients from free-text EMRs. A rule-based NLP approach had better overall operating characteristics than a machine learning approach. CONCLUSION: NLP can automatically and accurately measure frequency and mode of documented family visitation and communication from unstructured free-text EMRs, to support patient- and family-centered care initiatives.
Filipe R. Lucini, Karla D. Krewulak, Kirsten M. Fiest, Sean M. Bagshaw, Danny J. Zuege, Joon Lee, Henry T. Stelfox
J. Am. Medical Informatics Assoc.6
2021 Predicting Discharge Destination of Critically Ill Patients Using Machine Learning
abstract
Decision making about discharge destination for critically ill patients is a highly subjective and multidisciplinary process, heavily reliant on the ICU care team, patients and their caregivers' preferences, resource demand, staffing, and bed capacity. Timely identification of discharge disposition can be useful in care planning, and as a surrogate for functional status outcomes following critical illness. Although prior research has proposed methods to predict discharge destination in a critical care setting, they are limited in scope and in the generalizability of their findings. We proposed and implemented different machine learning architectures to determine the efficacy of the Acute Physiology and Chronic Health Evaluation (APACHE) IV score as well as the patient characteristics that comprise it to predict the discharge destination for critically ill patients within 24 hours of ICU admission. We conducted a retrospective study of ICU admissions within the eICU Collaborative Research Database (eICU-CRD) populated with de-identified clinical data from adult patients admitted to an ICU between 2014 and 2015. Machine learning models were developed to predict four discharge categories: death, home, nursing facility, and rehabilitation. These models were trained and tested on 115,248 unique ICU admissions. To mitigate class imbalance, we used synthetic minority over-sampling techniques. Hierarchical and ensemble classifiers were used to further study the impact of imbalanced testing set on the performance of our predictive models. Amongst all of the tested models, XGBoost provided the best discrimination performance with an area under the receiver operating characteristic curve of 90% (recall: 71%, F1: 70%). Our findings indicate that the variables used in the APACHE IV model for estimating patient severity of illness are better predictors of hospital discharge destination than the APACHE IV score alone. Incorporating these models into clinical decision support systems may assist patients, caregivers, and the ICU team to begin disposition planning as early as possible during the hospitalization.
Zahra Shakeri Hossein Abad, David M. Maslove, Joon Lee
IEEE J. Biomed. Health Informatics3
2017 Video Highlight Prediction Using Audience Chat Reactions
abstract
Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis.We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese.We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tvchannels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model architectures.
Cheng-Yang Fu, Joon Lee, Mohit Bansal, Alexander C. Berg
EMNLP2
2012 Risk Stratification of ICU Patients Using Topic Models Inferred from Unstructured Progress Notes
Li-Wei H. Lehman, Mohammed Saeed 0001, William J. Long, Joon Lee, Roger G. Mark
AMIA4
2011 Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals
Joon Lee, Catriona M. Steele, Tom Chau
Artif. Intell. Medicine1
2010 Continuous Time Bayesian Network Reasoning and Learning Engine
Christian R. Shelton, Yu Fan 0002, William Lam, Joon Lee, Jing Xu 0009
J. Mach. Learn. Res.4
2006 Design of User Authentication System based on WPKI
abstract
In this paper we challenge the user authentication using KerberosV5 authentication protocol in WPKI environment. This paper is the security structure that defined in a WAP forum and security and watches all kinds of password related technology related to the existing authentication system. It looks up weakness point on security with a problem on the design that uses wireless public key based structure and transmission hierarchical security back of a WAP forum, and a server client holds for user authentication of an application layer all and all, and it provides one counterproposal. Therefore, we offer authentication way solution that connected X.509 V3 with using WIM for complement an authentication protocol KerberosV5 and its disadvantages
Cheol-seung Lee, Hyeong-Gyun Kim, Joon Lee
CSCWD3