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.

169,181 papers · 148 categories

Trend · papers per month

0.4%0.8%1.2%1.6% · Dec 199719922001200920182026
48 results for illegal parking

Deep learning improves real-time illegal parking detection.

problem Weak robustness of traditional illegal parking detection methods.
method Used SSD algorithm for vehicle location and classification, optimized default box aspect ratio, and adopted tracking and analysis for movement judgment.
result Achieved 99% accuracy and 25FPS real-time detection with strong robustness in complex environments.

Predicting illegal fishing on Patagonian Shelf using machine learning.

problem Improving detection of illegal fishing to conserve fish stocks.
method Combining vessel tracking data with oceanographic seascapes and machine learning models.
result Machine learning models predict illegal fishing with 69-96% confidence.

Approach detects illegal insider trading proactively from diverse data sources.

problem Detecting illegal insider trading in the stock market.
method Deep-learning and discrete signal processing on time series data, combined with tree-based visualization.
result Approach has a good success rate in detecting illegal insider trading patterns.

SHARE predicts city-wide parking availability using a hierarchical graph neural network.

problem Predicting city-wide parking availability is challenging due to spatial and temporal autocorrelation.
method SHARE uses a hierarchical graph convolution structure with contextual and soft clustering blocks, a recurrent neural network, and a parking availability approximation module.
result SHARE outperforms state-of-the-art baselines in predicting city-wide parking availability.

Generative classifier derived from any discriminative classifier rejects illegal inputs.

problem Detecting and rejecting illegal inputs like adversarial examples and out-of-distribution samples.
method SDIM-logit: learns generative classifier from logits of any discriminative classifier, imposing statistical constraints.
result SDIM-logit inherits performance of base classifier without loss and can reject illegal inputs.

Study detects illegal discrimination by employers using correspondence experiments.

problem Detecting illegal discrimination by individual employers based on protected characteristics.
method Correspondence experiments, bounding higher moments of causal effects, decision rules for investigation.
result 85% of jobs contacting both white and black applicants are likely to discriminate.

Study models parking duration using machine learning and interpretable methods.

problem Parking issues in developing countries like India.
method Artificial neural networks (ANNs) for capturing relationships; Garson algorithm and LIME for model interpretation.
result LIME shows higher prediction accuracy and can be universally adopted.

This study predicts parking availability using multi-source data and a self-supervised learning enhanced transformer.

problem Accurate parking availability prediction to support urban planning and management.
method Proposes SST-iTransformer, a self-supervised learning enhanced spatio-temporal inverted transformer, integrating multi-source data.
result SST-iTransformer achieves state-of-the-art performance in parking availability prediction.

In this paper, first we consider the existence and non-existence of Einstein metrics on the topological 4-manifolds $3\mathbb{CP}^2 # k \bar{\mathbb{CP}}^2$ (for k11,13,14,15,16,17,18k \in {11, 13, 14, 15, 16, 17, 18}) by using the idea of Răsdeaconu and Şuvaina (2009) and the constructions in Park, Park, and Shin (arXiv:0906.5195v2) and…

2010-09-06abs ↗pdf ↗

Deep learning predicts real-time parking occupancy using multiple data sources.

problem Predicting real-time parking occupancy in spatio-temporal networks.
method Graph-Convolutional Neural Networks (GCNN) for spatial relations, Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) for temporal features, multiple data sources.
result The model outperforms other methods with an average testing MAPE of 10.6%.

In a recent paper, Park constructs certain exotic simply-connected four-manifolds with small Euler characteristics. Our aim here is to prove that the four-manifolds in his constructions are minimal.

2004-11-10abs ↗pdf ↗

Being one of the most important factors of economic growth of the country, innovations became one of the key vectors in Russian economic policy. In this field technology parks are one of the most effective instruments which can provide growth of innovative activity in sectors, regions and economies. In this paper, we m…

2014-02-21abs ↗pdf ↗

As a generalization of slant Riemannian maps (Sahin), semi-slant Riemannian maps (Park), almost h-slant submersions (Park 2012), and almost h-semi-slant submersions (Park 2011), we introduce the notion of almost h-semi-slant Riemannian maps from almost quaternionic Hermitian manifolds to Riemannian manifolds. We invest…

2012-09-24abs ↗pdf ↗

Researchers prove conjecture about contractible subcomplexes in noncrossing partition link.

problem Understanding contractibility of subcomplexes in the noncrossing partition link.
method Combining contractibility of flag complexes' stars with noncrossing hypertrees theory.
result Proved conjecture about contractible subcomplexes in the noncrossing partition link.

In an article from 2008, A. Akhmedov and B. D. Park constructed irreducible symplectic 4-manifolds homeomorphic but not diffeomorphic to the manifolds CP^2#3CP^2bar and 3CP^2#5CP^2bar. These manifolds are constructed by using generalized fibre sums. In this note we describe an explicit splitting of the second (co-)homo…

2011-02-07abs ↗pdf ↗

Detects illegal stock market trading behaviors using graph ranking methods.

problem Detecting irregular trade behaviors in the stock market.
method Three graph Laplacian based semi-supervised ranking methods.
result Un-normalized and symmetric normalized graph Laplacian based methods outperform the random walk Laplacian method.

ParK efficiently solves kernel ridge regression for large datasets.

problem Large-scale kernel ridge regression efficiency and accuracy.
method Partitioning feature space with random projections and iterative optimization.
result Provably maintains statistical accuracy with reduced space and time complexity.

Insider trading is one of the numerous white collar crimes that can contribute to the instability of the economy. Traditionally, the detection of illegal insider trades has been a human-driven process. In this paper, we collect the insider tradings made available by the US Securities and Exchange Commissions (SEC) thro…

2017-02-19abs ↗pdf ↗

We study the role that Hamiltonian and symplectic diffeomorphisms play in the deformation problem of coisotropic submanifolds. We prove that the action by Hamiltonian diffeomorphisms corresponds to the gauge-action of the LL_\infty-algebra of Oh and Park. Moreover we introduce the notion of extended gauge-equivalence …

2014-11-12abs ↗pdf ↗

Deep learning approximates TSP solutions for parking violations.

problem Solving the Travelling Salesman Problem for parking violation datasets.
method Converted TSP into a classification problem, designed a customised deep learning network.
result Empirically showed critical architectural components affecting network performance.

The curvature tensor of a pseudo-Riemannian metric, and its covariant derivatives, satisfy certain identities that hold on any manifold of dimension less or equal than nn. In this paper, we re-elaborate recent results by Gilkey-Park-Sekigawa regarding pp-covariant dimensional curvature identities, for p=0,2p=0,2. To thi…

2013-10-10abs ↗pdf ↗

We note a simple mechanism that may at least partially resolve several outstanding economic puzzles, including why the cyclically adjusted price to earnings ratio of the S&P 500 index has been oddly high for the past two decades, why gains to capital have outpaced gains to wages, and the persistence of the equity premi…

2016-10-25abs ↗pdf ↗

We show that for a special alternating link diagram, the following three polynomials are essentially the same: a) the part of the HOMFLY polynomial that corresponds to the leading term in the Alexander polynomial; b) the hh-vector for a triangulation of the root polytope of the Seifert graph and c) the enumerator of p…

2013-05-21abs ↗pdf ↗

An article based on a four-lecture introductory minicourse on minimal surface theory given at the 2013 summer program of the Institute for Advanced Study and the Park City Mathematics Institute.

2013-08-15abs ↗pdf ↗

HW2MP-GAN tackles ancient handwritten text recognition.

problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.

New method learns decisions from collective preferences without individual covariates.

problem Making decisions online without individual covariates.
method Collaborative filtering, matrix completion bandit, ε-greedy policy, online gradient descent, inverse propensity weighting.
result Method outperforms benchmarks and reveals new discoveries.

These notes are based on a lecture series given at the Park City Math Institute in the summer of 2013. The notes are intended as a leisurely introduction to the Kähler-Ricci flow on compact Kähler manifolds, aimed at graduate students with some background in differential geometry.

2015-02-24abs ↗pdf ↗

We study scalar and symmetric 2-form valued universal curvature identities. We use this to establish the Gauss-Bonnet theorem using heat equation methods, to give a new proof of a result of Kuz'mina and Labbi concerning the Euler-Lagrange equations of the Gauss-Bonnet integral, and to give a new derivation of the Euh-P…

2011-04-11abs ↗pdf ↗