Support Vector Machines predict gas-liquid flow patterns with 97% accuracy.
problem Predicting gas-liquid flow patterns in multiphase flow systems.
method Support Vector Machine (SVM) applied to a dataset of two-phase flow patterns.
result Achieved 97% correct classification of flow patterns.
Dockless bike sharing systems need effective bike flow prediction models.
problem Imbalanced and dynamic use of bikes leads to mandatory rebalancing operations.
method Divide urban area into regions, model spatio-temporal bike flows, extract traffic patterns, and predict bike flows.
result Interpretable bike flow prediction model provides valuable insights into bike flow analysis.
Study of combinatorial Calabi flow on ideal circle patterns.
problem Finding ideal circle patterns with prescribed curvatures.
method Combinatorial Calabi flow in hyperbolic and Euclidean geometry.
result Flow converges exponentially to ideal circle patterns.
Paper develops models to forecast private equity fund cash flows.
problem Limited literature on illiquid alternative asset cash flow forecasting.
method Develops benchmark model and two novel approaches (direct vs. indirect) using LSTM/GRU models and macroeconomic indicators.
result Direct model performs better and aligns with actual cash flows, but indirect model's performance is less clear.
New matrix completion method for arbitrary sampling patterns using network flows.
problem Matrix completion under arbitrary sampling patterns.
method Network flow approach to matrix completion.
result Minimax optimal estimation for individual entries.
Predicts traffic flow using reinforcement learning and sensor data.
problem Accurately predict expanding and evolving long-term streaming traffic networks.
method Formulates the problem as a continuous reinforcement learning task, where the agent predicts future traffic based on sensor data.
result The approach improves accuracy in predicting traffic flow by updating the agent's state representation over time.
A new model predicts dynamic O-D matrices using graph neural networks and Kalman filters.
problem Predicting dynamic O-D demand matrices from traffic flow data.
method Combines graph neural networks and Kalman filters to recognize spatial and temporal patterns.
result The proposed model outperforms other methods in various prediction scenarios.
Survey of urban flows prediction methods using various datasets.
problem Predicting urban flows influenced by human activities, weather, events, and holidays.
method Analysis of four main factors, preparation of multi-sources spatial-temporal data, detailed comparison of five categories of prediction methods.
result Facilitates researchers to choose suitable methods and datasets for urban flows prediction.
New approach predicts commuters' flow with 90.4% accuracy.
problem Limited ability to predict and reconstruct commuters' networks.
method Machine learning and 22 urban indicators.
result Predictions with 90.4% accuracy and 77.6% variance explained.
The paper extends circle pattern flows to hyperbolic and Euclidean geometry.
problem Extending circle pattern flows to hyperbolic and Euclidean geometry.
method Proving the existence and exponential convergence of combinatorial Calabi flows for ideal circle patterns.
result The solution to combinatorial Calabi flows converges exponentially fast to a flat cone metric.
Proves existence of circle patterns on surfaces with cusps.
problem Existence of circle patterns with prescribed angles on surfaces with cusps.
method Introduced combinatorial Ricci and Calabi flows to prove longtime existence and convergence.
result Existence of generalized circle patterns with prescribed angles on surfaces with cusps.
Motivated by the literature on investment flows and optimal trading, we examine intraday predictability in the cross-section of stock returns. We find a striking pattern of return continuation at half-hour intervals that are exact multiples of a trading day, and this effect lasts for at least 40 trading days. Volume, o…
New method finds ideal circle patterns on spheres.
problem Finding ideal circle patterns on spheres with prescribed curvatures.
method Combinatorial Calabi flow in spherical geometry.
result Existence and convergence of the flow for ideal circle patterns.
Paper resolves spherical curvature flow problem.
problem Existence of ideal circle patterns in spherical background geometry.
method Introduces a combinatorial geodesic curvature flow in spherical background geometry.
result Characterizes sufficient and necessary conditions for flow convergence.
The paper studies the combinatorial p-th Calabi flow for finite and infinite circle patterns.
problem Establishing convergence and long-time existence of the combinatorial p-th Calabi flow.
method Combinatorial p-th Calabi flow for finite and infinite ideal circle patterns.
result Sharp criterion for convergence in finite case and long-time existence in infinite case for p≥2. Paper solves degenerated circle pattern metric problem in spherical geometry.
problem Existence and rigidity of (degenerated) circle pattern metrics with prescribed total geodesic curvatures.
method Defined prescribed combinatorial Ricci flows and studied their convergence.
result First degenerated result for total geodesic curvatures in spherical background geometry.
Paper proposes a neural network to improve traffic flow forecasting.
problem Forecasting future traffic flow distribution in an area.
method Position-aware convolutional neural network integrating data features and position information.
result Our approach outperforms previous methods even with fewer data sources.
Bayesian calibration improves ABMs for predicting travel patterns.
problem Calibrating ABMs for accurate travel pattern predictions.
method Gaussian Process emulator with deep learning dimensionality reduction for high-dimensional, non-stationary data.
result Improved accuracy in predicting travel patterns using traffic flow data.
The paper studies circle patterns on surfaces with specific angles and curvature maps.
problem Investigating circle patterns with obtuse angles on surfaces of finite type.
method Characterizing curvature maps and establishing combinatorial Ricci flow conditions.
result Generalizations of circle pattern theorem and a computational method to find patterns.
MIP framework improves urban flow prediction by adapting to distribution shifts.
problem Distribution shifts in urban flow data make prediction models unreliable.
method Memory-enhanced Invariant Prompt learning with learnable memory bank.
result MIP ensures robust predictions by focusing on invariant features.
Study combinatorial Ricci flow on surfaces with nonpositive Euler characteristic.
problem Addressing convergence issues in Ricci flow on surfaces.
method Investigate combinatorial Ricci flow on surfaces of nonpositive Euler characteristic.
result Observation of convergence despite necessary condition not being valid.
DeepMPC uses neural networks to control complex fluid flows efficiently.
problem Controlling complex fluid flows in real-time is challenging due to high dimensionality and multi-scale dynamics.
method Deep learning, specifically recurrent neural networks (RNNs), embedded in model predictive control (MPC) framework.
result Significant improvements in control performance achieved through online updates to prediction accuracy.
Develops a data-driven model for porous media flow simulations.
problem Capturing flow field and permeability in digital porous media.
method Data-driven approach using Lattice Boltzmann simulation data.
result Accurately predicts flow solutions with reduced computational time.
Paper solves long-standing problem of infinite ideal polyhedra in hyperbolic space.
problem Characterize infinite ideal polyhedra in hyperbolic 3-space.
method Introduced combinatorial Ricci flow for infinite ideal circle patterns.
result Proved characterization of infinite ideal circle patterns under specific conditions.
Safe Pattern Pruning reduces pattern explosion in predictive pattern mining.
problem Exponential growth of patterns in structured data.
method Safe Pattern Pruning (SPP) method.
result Effective model building in practical data analysis.
Machine learning improves ice flow tracking in satellite images.
problem Improving accuracy of ice flow tracking in multi-spectral satellite images.
method Adversarial learning method to predict future ice flow.
result Adversarial learning improves ice flow tracking accuracy.
New neural network predicts traffic flow across different cities.
problem Forecasting traffic flow across different cities is challenging due to spatio-temporal correlations.
method Proposes a local-spacetime neural network (STNN) that captures universal spatio-temporal correlations.
result Improves prediction accuracy by 4% over state-of-the-art methods.
In this paper we propose a new method to predict the final destination of vehicle trips based on their initial partial trajectories. We first review how we obtained clustering of trajectories that describes user behaviour. Then, we explain how we model main traffic flow patterns by a mixture of 2d Gaussian distribution…
New framework predicts arterial blood pressure from MRI data using physics-informed neural networks.
problem Clinical applicability of predictive cardiovascular flow models is hindered by computational cost and tedious pre-processing.
method Physics-informed neural networks constrained by conservation of mass and momentum principles.
result Deep neural networks provide physically consistent predictions for arterial blood pressure without conventional simulators.
Hybrid model combines VAR and neural network for OFI prediction.
problem Accurate prediction of Order Flow Imbalance (OFI) in high frequency trading.
method Combines Vector Auto Regression (VAR) and a simple feedforward neural network (FNN).
result Hybrid model achieves superior predictive accuracy compared to standalone models.
Hybrid model improves traffic flow prediction accuracy.
problem Predicting traffic flow with high accuracy in short-term future.
method A hybrid model combining hidden Markov model and LSTM.
result Significant performance gains over conventional methods.
Physics-guided deep learning improves CFD for bubbly flow simulations.
problem Accurate CFD prediction of two-phase bubbly flow with high computational efficiency.
method Developed a multi-scale framework with Feature Similarity Measurement (FSM) for error estimation and a physics-guided deep feedforward neural network (DFNN) surrogate model.
result Physics-guided deep learning achieves comparable accuracy to fine-mesh simulations with fast-running feature.
In this paper we study predictive pattern mining problems where the goal is to construct a predictive model based on a subset of predictive patterns in the database. Our main contribution is to introduce a novel method called safe pattern pruning (SPP) for a class of predictive pattern mining problems. The SPP method a…
Study infinite combinatorial Ricci flow on spherical surfaces.
problem Investigate infinite combinatorial Ricci flow with spherical background.
method Establish existence and convergence of solution for infinite cellular decompositions.
result Existence and convergence of solution for infinite combinatorial Ricci flow in spherical geometry.
RestoreAI predicts landmine risk from patterns, improving clearance efficiency.
problem Predicting landmine risk from spatial patterns to enhance clearance efficiency.
method RestoreAI uses landmine patterns for risk prediction, implementing three deminers: linear, curved, and Bayesian.
result RestoreAI significantly boosts clearance efficiency, achieving a 14.37 percentage point increase in cleared landmines per timestep.
DISTANA predicts and denoises spatial wave dynamics.
problem Identifying causality in spatially distributed, non-linear dynamical processes.
method Generative, recurrent graph convolution neural network architecture (DISTANA).
result DISTANA outperforms alternative approaches in denoising and predicting complex spatial wave propagation.
Model predicts Bitcoin's future movements using multimodal pattern matching.
problem Challenges in predicting Bitcoin's volatile future movements.
method Ranking similar past chart patterns given current chart information.
result Improves directional prediction of Bitcoin's future movements.
KINN integrates expert knowledge into neural networks to improve performance.
problem Lack of expert knowledge in neural networks, especially in time-series domains.
method Integrates expert knowledge through a residual knowledge incorporation scheme.
result Significantly improved performance on real-world traffic flow prediction.
A deep neural network for spatial time series forecasting.
problem Challenges in forecasting spatial time series with specific patterns and curse of dimensionality.
method Spatial-temporal decomposition, fuzzy clustering, multi-kernel convolution, convolution-LSTM, denoising autoencoder.
result Model outperforms baseline and state-of-the-art models in traffic flow prediction.
Method extracts taint flows to classify Bitcoin mining pools.
problem Understanding pseudonymous Bitcoin actors and their transactions.
method Taint analysis and graph embedding methods applied to taint flows.
result Taint flows from the same period show high similarity.
Study improves cross-modal bike-share and transit demand prediction.
problem Cross-modal ripple effects in urban transportation demand.
method Transfer learning and stacked LSTM models for cross-modal demand prediction.
result Transfer learning models outperform unimodal models in cross-modal demand prediction.
Cryptocurrency patterns stable across market caps, validated by microstructure theory.
problem Stable patterns in cryptocurrency microstructure across different market caps.
method Unified CatBoost modeling pipeline with time-series cross validation, validated by backtests.
result Feature rankings and partial effects are stable across assets despite heterogeneous liquidity and volatility.
Study shows generic surfaces avoid complex flow patterns.
problem Understanding flow patterns of surfaces in 3D space.
method Analyzes mean curvature flow of closed surfaces in R3. result Non-cylindrical self-shrinkers cannot arise generically.
Benford's law states that in data sets from different phenomena leading digits tend to be distributed logarithmically such that the numbers beginning with smaller digits occur more often than those with larger ones. Particularly, the law is known to hold for different types of financial data. The Illicit Financial Flow…
New criteria for ideal circle patterns on surfaces.
problem Determining when a surface supports ideal circle patterns.
method Introducing a character L(D,Φ) and using combinatorial Ricci flows. result Simpler and more easily verifiable criteria for ideal circle patterns.
Predict genetic inheritance patterns using hypergraphs and latent models.
problem Diagnosing inherited diseases requires identifying family genetic patterns.
method Represent family trees as hypergraphs, use latent state space models for causal inference.
result Allows for explainable predictions of patient genotypes based on relatives' phenotypes.
Bayesian classifier predicts journey routes using Markov chains.
problem Predicting the route of ongoing journeys.
method Modeling journey patterns as stochastic processes and updating posterior probabilities with Markov chains.
result High accuracy in route predictions demonstrated on synthetic data.
This work evaluates machine learning-based hotspot detectors on synthesized layout patterns.
problem Evaluating model robustness and generality of machine learning-based hotspot detectors.
method Developed an automatic layout generation tool to synthesize various layout patterns and tested machine learning-based detectors on these synthesized layouts.
result Machine learning-based detectors need continuous study for robustness and generality in DFM flows.