Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

326496128 · Jun 202019922001200920182026
48 results for Long QT syndrome

Machine learning improves detection of Brugada Syndrome from ECGs.

problem Detecting Brugada Syndrome (BrS) from ECGs is challenging due to limited diagnostic criteria.
method Pipeline that reads and processes scanned ECG images, uses LSTM classifier to diagnose.
result The proposed pipeline distinguishes between ECG types and diagnoses BrS with high accuracy.

Syndromic surveillance detects and monitors individual and population health indicators through sources such as emergency department records. Automated classification of these records can improve outbreak detection speed and diagnosis accuracy. Current syndromic systems rely on hand-coded keyword-based methods to parse…

2018-05-19abs ↗pdf ↗

AlphaStock uses deep learning to select winning stocks and avoid losers, balancing risk and return.

problem Balancing risk and return in stock selection, avoiding extreme losses, and making strategies interpretable.
method Integrates deep attention networks with a Sharpe ratio-oriented reinforcement learning framework, modeling asset interrelationships.
result AlphaStock selects stocks with high long-term growth, low volatility, and undervaluation, outperforming other strategies.

QTNet uses deep reinforcement learning to automate trading strategies.

problem Handling noisy and high-frequency financial data, balancing exploration and exploitation.
method QTNet employs deep reinforcement learning (DRL) with imitative learning to autonomously formulate trading strategies.
result QTNet demonstrates proficiency in extracting robust market features and adaptability to diverse conditions.

QT improves inference in complex PGMs with hidden variables.

problem Intractable learning and prediction errors in undirected PGMs with hidden variables.
method Query training (QT) learns a worse model to improve marginal inference.
result QT produces better marginals for a given inference algorithm than the original model.

Clusters of ACS patients identified for better therapeutic stratification.

problem Data-driven classification and subtyping of ACS patients for improved treatment.
method Outcome-driven clustering using a multi-task neural network with attention.
result Seven patient clusters with distinct characteristics and risk profiles identified.

Improved logistic regression for multi-omics data improves prediction and variable selection.

problem Predicting binary class labels from multi-omics datasets with varying characteristics.
method Two-step penalized logistic regression with separate variable selection for each data layer.
result Our approach selects more relevant predictors and achieves comparable prediction performance.

Study builds machine learning models to predict ICU patients' one-year mortality.

problem Improving mortality prediction accuracy in ICU patients with heart disease.
method Developed and evaluated various machine learning models using MIMIC-III database.
result Best models achieved 85.12% prediction accuracy and AUC of 0.901.

Quantum time evolution exhibits rich physics, attributable to the interplay between the density and phase of a wave function. However, unlike classical heat diffusion, the wave nature of quantum mechanics has not yet been extensively explored in modern data analysis. We propose that the Laplace transform of quantum tra…

2017-11-14abs ↗pdf ↗

Study uses LCA to identify ARDS sub-phenotypes improving predictive models.

problem Complex and heterogeneous nature of ARDS makes early recognition difficult.
method Applied latent class analysis to identify sub-groups, then built predictive models.
result Significantly improved prediction performance for two sub-phenotypes of ARDS.

The paper prices a new life insurance policy for couples, considering various contingent benefits.

problem Valuation of life insurance policies for dependent coupled lives.
method Employed the QPQP-rule combining real-world and risk-neutral measures for pricing.
result Explicit pricing expressions for the new insurance policy were derived and analyzed.

Every torus knot can be represented as a Fourier-(1,1,2) knot which is the simplest possible Fourier representation for such a knot. This answers a question of Kauffman and confirms the conjecture made by Boocher, Daigle, Hoste and Zheng. In particular, the torus knot T(p,q) can be parameterized as x(t)=cos(pt), y(t)=c…

2007-08-27abs ↗pdf ↗

Safe-FinRL uses DRL for high-frequency stock trading, reducing bias and variance.

problem Challenges in applying DRL to high-frequency stock trading, especially bias and variance issues.
method Safe-FinRL separates financial time series into near-stationary short environments and uses Trace-SAC with a general retrace operator.
result Safe-FinRL reduces bias and variance significantly in near-stationary financial environments.

Enhanced mortality prediction model using EHR and free-text data.

problem Predicting one-year mortality in AMI patients.
method Used deep learning models with word embedding features from free-text discharge summaries.
result Significant improvement in model performance (92.89% accuracy, 0.928 F-measure).

This paper automates mining of COVID-19 scholarly articles using machine learning.

problem Time-consuming and impractical manual extraction of relevant COVID-19 research articles.
method Used machine learning approaches, specifically clustering and parallel one-class support vector machines (OCSVMs), on the CORD-19 dataset.
result Parallel OCSVMs outperform other methods for both original and reduced feature space.

DSM improves visual quality of fetoscopic videos by mosaicking.

problem Challenges in identifying all vascular connections during fetoscopy due to low visual quality and drift.
method Proposes a Deep Sequential Mosaicking (DSM) framework using deep learning techniques to handle visual variations and reduce drift.
result DSM framework reduces accumulated drift and improves visual quality of fetoscopic videos.

Develops a novel approach for estimating optimal DTRs with multicategory treatments and censored data.

problem Estimating optimal treatment regimes for chronic diseases with censored data.
method Angle-based multicategory classification algorithm for maximizing conditional survival function.
result The proposed method outperforms existing approaches in maximizing conditional survival function.

ECG-DelNet uses neural networks to accurately delineate ECGs, even with low-quality data.

problem Lack of model explainability and small databases limit deep learning applicability in ECG detection.
method Adapted U-Net architecture for 1D data, used PhysioNet's QT database, applied data augmentation and regularization techniques.
result Best configuration achieved high precision and recall for P, QRS, and T waves.

The study explores vector flows on manifolds, focusing on polynomial constraints and equivalence relations.

problem Understanding vector flows on compact manifolds with constraints on tangency patterns.
method Introduces equivalence relations (quasitopy) and computes spaces of polynomials with constrained divisors.
result Quasitopy classes stabilize as the degree of polynomials increases.

Develops a risk score to assist ECMO planning for critically ill patients with viral or unspecified pneumonia.

problem Lack of a risk score to guide ECMO planning for critically ill patients.
method Leverages machine learning to develop the PEER score.
result PEER score predicts mortality and decompensation in patients eligible for ECMO.

Study uses machine learning to identify posturographic features in Parkinson's patients who fall.

problem Identifying patients at risk of falling in Parkinson's syndrome.
method Employed ts-AUC, a non-parametric multivariate two-sample test, to analyze posturographic features.
result Significant differences in antero-posterior movements and posturographic area between fallers and non-fallers identified.

A point in the (N,q)(N,q)-torus knot in R3\mathbb{R}^3 goes qq times along a vertical circle while this circle rotates NN times around the vertical axis. In the Lissajous-toric knot K(N,q,p)K(N,q,p), the point goes along a vertical Lissajous curve (parametrized by t(sin(qt+φ),cos(pt+ψ)))t\mapsto(\sin(qt+φ),\cos(pt+ψ))) while this curve rotates $N…

2016-10-14abs ↗pdf ↗

AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.

problem Difficulty in maximizing over large action spaces in Q-learning.
method Replace expensive maximization over all actions with a maximization over a small subset sampled from a learned proposal distribution.
result AQL outperforms existing methods on continuous control tasks with up to 21 dimensional actions.

Deep learning system tracks stool consistency for GI disease assessment.

problem Lack of objective stool consistency measurements in chronic GI disease.
method Computer vision and deep convolutional neural networks (CNN).
result Developed a stool detection and tracking system.

The paper proposes a method to predict the performance of data-driven algorithms using surrogate models.

problem Improving the performance prediction of data-driven knowledge discovery algorithms.
method Surrogate-assisted performance prediction using evolutionary modeling of clinical pathways.
result The proposed approach provides interpretable prediction of algorithm performance and quality.