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.

169,341 papers · 148 categories

Trend · papers per month

6.3%12.5%18.8%25.0% · Oct 199319922001200920182026
48 results for Pen Stroke Analysis

PENs learn summary statistics for ABC using invariant neural architectures.

problem Learning summary statistics for approximate Bayesian computation (ABC).
method Partially exchangeable networks (PENs) that are invariant to block-switch transformations.
result PENs provide more reliable posterior samples with less training data.

Study uses machine learning to predict stroke risk in China with improved accuracy.

problem Predicting stroke risk in China using machine learning.
method Combines VAR and GNN for causal inference, compares multiple classification algorithms, uses SMOTE undersampling.
result Gradient Boosting model shows highest performance and stability in predicting stroke risk.

Bayesian CNN improves MRI stroke diagnosis accuracy and uncertainty quantification.

problem Uncertainty quantification in automated image analysis for medical decision-making.
method Bayesian Convolutional Neural Network (CNN) with aggregation methods for patient-level diagnoses.
result Bayesian CNN achieved 95.33% accuracy on 511 patients, 2% higher than non-Bayesian.

New model predicts stroke risk with high accuracy and interpretability.

problem Developing accurate and understandable models for stroke risk prediction.
method Bayesian Rule Lists: a generative model that produces interpretable decision lists.
result Bayesian Rule Lists achieves predictive accuracy comparable to top machine learning algorithms and is more accurate than existing models.

We show that the equivalence problem for three-dimensional Lorentzian manifolds requires at most the fifth covariant derivative of the curvature tensor. We prove that this bound is sharp by exhibiting a class of 3D Lorentzian manifolds which realize this bound. The analysis is based on a three-dimensional analogue of t…

2012-10-25abs ↗pdf ↗

DeepWriterID uses deep CNN and DropSegment for efficient writer identification.

problem Insufficient data and difficulty in designing good features for writer identification.
method End-to-end system with deep CNN and DropSegment for data augmentation and improved feature representation.
result Achieved new state-of-the-art identification rates of 95.72% for Chinese text and 98.51% for English text.

Study uses reinforcement learning to optimize metachronal paddling at low Reynolds number.

problem Optimizing metachronal paddling strategies for efficient swimming at low Reynolds numbers.
method Applied reinforcement learning to a swimmer model with varying paddle spacings.
result The reinforcement learning algorithm selects a back-to-front metachronal wave-like stroke as the most efficient, regardless of the number of paddles.

Deep learning identifies functional primitives in stroke rehabilitation.

problem Measuring the necessary dose of rehabilitation training for stroke recovery.
method Automatic identification of functional primitives using IMUs and deep learning.
result Convolutional neural network achieved 70% accuracy in primitive classification.

Automated GMA using accelerometers detects abnormal infant movements with human-level accuracy.

problem Undetected perinatal stroke leads to lifelong disability.
method Wearable accelerometers and Discriminative Pattern Discovery (DPD) for automated GMA.
result Automated method correctly identifies abnormal movements with human-level accuracy.

This paper uses CNNs to automatically segment ischaemic stroke lesions from MRI sequences.

problem Automatically segmenting ischaemic stroke lesions from MRI sequences is challenging.
method Adversarial training of CNNs on multi-sequence MRI data.
result The method achieves high Dice scores for core and penumbra segmentation.

RATE metrics evaluate treatment prioritization rules, subsuming existing methods.

problem Comparing and testing the quality of treatment prioritization rules.
method Rank-weighted average treatment effect (RATE) metrics.
result RATE metrics enable asymptotically exact inference in various study settings.

New method predicts aphasia severity with narrower uncertainty intervals.

problem Predicting aphasia severity in stroke patients using neuroimages.
method Sparse heteroscedastic Bayesian high-dimensional regression with H-PROBE algorithm.
result H-PROBE provides narrower prediction intervals for aphasia severity.

Automatically identifies geometric flat outputs for robotic systems.

problem Lack of systematic and practical means to identify flat outputs for arbitrary robotic systems.
method Casts the search for a globally valid, equivariant flat output as an optimization problem using Riemannian geometry, Lie group theory, and differential forms.
result Approximate transcription of continuum formulation to a quadratic program achieves precise agreement with known closed-form flat outputs.

Deep neural networks map brain lesions to deficits for better brain function understanding.

problem Mapping the functional brain organization from pathological lesions.
method Deep generative neural network architectures, specifically variational convolutional volumetric auto-encoders.
result Our model outperforms established methods in lesion-deficit inference across various scenarios.

Causal ML methods failed to validate their personalized treatment effects in two large trials.

problem Validating causal machine learning methods for personalized treatment effects in precision medicine.
method Assessed 17 mainstream causal heterogeneity ML methods using two large randomized controlled trials.
result None of the ML methods reliably validated their performance, internal or external, showing significant discrepancies between training and test data.

Paper proposes MSSDDPG for better financial trading strategies.

problem Extracting accurate features from noisy, non-stationary financial time series.
method Multi-scale stroke deep deterministic policy gradient reinforcement learning model (MSSDDPG).
result MSSDDPG outperforms other strategies in China's CSI 300 and SSE Composite.

Model uses unsupervised learning to classify medical reports with less labeled data.

problem Lack of labeled data for fine-grained disease classification in medical reports.
method Developed a pipeline combining an unsupervised encoder-language model and a supervised classifier model.
result Improved classification accuracy with less labeled data compared to previous methods.

We suggest an original physical approach to describe the mechanism of market pricing. The core of our approach is to consider pricing at different time scales separately, using independent equations of motion. Such an approach leads to a pricing model that not only allows estimating the volatility of future market pric…

2014-06-22abs ↗pdf ↗

Framework tests CATE homogeneity across trials and evaluates confounding.

problem Assessing treatment effect consistency across randomized and observational studies.
method Leverages multiple randomized trials to test CATE homogeneity and compares with observational data.
result Identifies potential confounding and effect heterogeneity in treatment effects.

Generative Neuro-Symbolic model learns from raw data with rich conceptual representations.

problem Learning rich, general-purpose conceptual representations from raw perceptual inputs.
method Generative Neuro-Symbolic (GNS) model combining symbolic and neural network approaches.
result Model learns from raw data and generalizes to 4 unique tasks.

Bayesian meta-learning improves health prediction models across similar diseases.

problem Inter- and intra-task variability in healthcare predictions due to disease heterogeneity and patient differences.
method Bayesian meta-learning approach that models task similarity to mitigate negative transfer and improve generalizability.
result Significant generalizability improvements in stroke prediction tasks using electronic health record data.

The paper proposes a new algorithm to select subsets of training data for better accuracy and explainability.

problem Tackles the challenge of balancing accuracy and explainability in pattern recognition.
method Identifies multiple subsets with simple local patterns by clustering similar instances.
result The sub-setting algorithm outperformed traditional decision trees by 15% on the international stroke dataset.

Machine learning detects and characterizes whistler radio waves for real-time monitoring of the plasmasphere.

problem Detect and characterise whistler radio waves generated by lightning strokes for real-time monitoring of the plasmasphere.
method Developed a machine learning model using image classification and localisation on spectrogram data to identify and localise whistlers.
result The proposed detectors achieve a misdetection and false alarm rate of less than 15% on Marion's dataset.

Bayesian Supervised Causal Clustering identifies patient subgroups for personalized decision-making.

problem Finding patient subgroups with similar characteristics for personalized decision-making.
method Bayesian Supervised Causal Clustering (BSCC) that identifies homogenous subgroups based on treatment effects.
result BSCC identifies subgroups with similar covariate profiles and treatment effects.

Method condenses brain signal components into clusters based on within-trial dynamics.

problem Variability in optimized spatial filters due to temporal dynamics and hyperparameters.
method Condensing oscillatory brain signal components into clusters based on within-trial envelope dynamics.
result Subject-specific distinct temporal envelope dynamics of components.