Urban2Vec combines street view imagery and POIs for better urban neighborhood embeddings.
problem Lack of comprehensive representation of urban neighborhoods using heterogeneous data.
method Unsupervised multi-modal framework using CNN for visual features and bag-of-words for POI data.
result Urban2Vec achieves better performance than baseline models and comparable to fully-supervised methods.
Master thesis uses CNNs to estimate bike attractivity from street view images.
problem Estimating bike routes attractiveness from image data.
method Abstraction of locations into nodes and edges, enhancement with street view photos and neighborhood info, transfer learning.
result Improved road scoring using enhanced dataset and various model architectures.
Gursky-Streets introduced a formal Riemannian metric on the space of conformal metrics in a fixed conformal class of a compact Riemannian four-manifold in the context of the σ2-Yamabe problem. The geodesic equation of Gursky-Streets' metric is a fully nonlinear degenerate elliptic equation and Gursky-Streets have pr…
End-to-end method learns geometry and appearance for multi-view object detection.
problem Challenges in multi-view object detection, including viewpoint, lighting, and scale variability.
method Jointly learns multi-view geometry and warping for robust cross-view object detection.
result Superior performance compared to baselines on a new street-level panorama data set.
The paper proposes a model to learn street network representations directly from graphs.
problem Loss of detailed topological data in raster representations of street networks.
method Variational autoencoder with graph convolutional layers and a probabilistic fully-connected graph decoder.
result The model infers good representations directly from street networks, capturing both local structure and spatial distribution.
AI helps Vancouver identify where off-street parking saves time and space.
problem On-street parking inefficiencies and associated costs in Vancouver.
method Developed AI models for on-street and off-street parking, comparing time costs.
result Many areas off-street parking saves time and space, aligning with city goals.
VAE models generate urban street networks from data.
problem Quantitative description of urban patterns.
method Variational Autoencoders (VAEs) for urban street network data.
result VAEs can capture urban network metrics and generate new urban forms.
Generative adversarial networks transform streetscape images to improve health and wellbeing.
problem Improving health and wellbeing outcomes through better streetscape design.
method Generative adversarial networks were used to translate Google Street View images, preserving structure while changing the style from bad health to good health areas.
result Translated images show that good health areas have more green space and compact urban design, while good social capital areas have more footpaths and less fencing.
Deep learning generates addresses for under-addressed cities.
problem Lack of street addresses in developing countries.
method Deep learning applied to satellite images to generate addresses.
result Algorithm generates addresses for neighborhoods and regions.
Research confirms Streets-Tian conjecture for 2-step solvmanifolds.
problem Streets-Tian conjecture for compact complex manifolds.
method Used special non-unitary frames to reveal hidden symmetries.
result Confirms conjecture for all 2-step solvmanifolds.
Solves Gursky-Streets equations for σk Yamabe problem in dimensions n≥2k.
problem Solving the σk Yamabe problem in dimensions n≥2k. method Introduced and solved the Gursky-Streets equations with uniform C1,1 estimates using concavity of the operator and Garding's theory of hyperbolic polynomials. result Established the uniqueness of the solution to the degenerate equations for the first time.
Model infers street-level air quality using mobile station data.
problem Inferring air quality from limited mobile station data.
method Variational Graph Autoencoder for matrix completion on graph-based data.
result Model outperforms state-of-the-art approaches in air quality inference.
Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented. The images from Cityscap…
Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing…
In recent years, Streets and Tian introduced a series of curvature flows to study non-Kähler geometry. In this paper, we study how to construct second order curvature flows in a uniform way, under some natural assumptions which holds in Streets and Tian's works. As a result, by classifying the lower order tensors, we c…
New dataset for automated pavement distress classification and density estimation.
problem Challenges in automated pavement distress detection using road images.
method Pavement Image Dataset (PID) method, combining wide-view and top-down view images.
result Accuracy scores of 0.84 for YOLOv2 and 0.65 for Faster R-CNN, suitable for practical applications.
The Streets-Tian conjecture is confirmed for specific types of Hermitian manifolds.
problem The Streets-Tian conjecture on compact Hermitian manifolds.
method Elementary approach, explicit descriptions, and pathways of deformation.
result The conjecture is confirmed for special types of compact Hermitian manifolds.
Method estimates travel times on urban roads using Uber data.
problem Estimating travel times on urban roads where data is scarce.
method Graph representation, trip sampling, least-squares optimization.
result Estimates travel times on arterial roads using aggregated Uber data.
New model predicts informal settlements using street intersections data.
problem Identifying and predicting informal settlements in cities.
method Spatial statistics and machine learning (MNL and ANN).
result High validity and accuracy in identifying and predicting informality.
Study extends Kähler-Ricci flow to symplectic manifolds.
problem Extend Kähler-Ricci flow to symplectic manifolds.
method Establish new formulas for canonical quantities and characterize fixed points.
result Extended characterization of fixed points.
Method generates uncertainty measures for street scene segmentation.
problem Reliability and uncertainty measures in semantic segmentation of street scenes.
method Nested crops, neural network segmentation, post-processing, uncertainty heat maps.
result Significant improvements in classification and regression performance.
Study uses Viber and street polls to estimate Belarus election ratings and turnout.
problem Obtaining accurate ratings of candidates in Belarus's banned polls.
method Bayesian multilevel regression with poststratification.
result Estimated ratings and turnout contradict official election results.
MAVENs combine GAN and VAE for better image generation and classification.
problem Improve image generation and classification using unsupervised learning.
method Introduce MAVENs, an ensemble of discriminators in a VAE-GAN network.
result Demonstrated competitive performance in image generation and classification tasks.
This essay suggests that a proper assessment of the presently unfolding financial crisis, and its cure, requires going back at least to the late 1990s, accounting for the cumulative effect of the ITC, real-estate and financial derivative bubbles. We focus on the deep loss of trust, not only in Wall Street, but more imp…
The Streets-Tian conjecture is confirmed for Lie algebras with specific abelian ideals.
problem The Streets-Tian conjecture on compact complex manifolds admitting Hermitian-symplectic metrics.
method Detailed case analysis of Lie algebras with abelian ideals of codimension 2, explicit construction of Hermitian-symplectic metrics and pathways to Kähler metrics.
result The Streets-Tian conjecture is confirmed for Lie algebras containing abelian ideals of codimension 2.
Study shows high-rise buildings in Dhaka affect mental health, especially lower-income residents.
problem Mental health risks due to high-rise buildings in Dhaka.
method Computer vision pipeline to analyze sky visibility, greenery, and colors in streets.
result Lower-income residents suffer more from lack of sky visibility and greenery in their environment.
We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1. Parseval networks are empirically and theoretically motivated by an analysis of the robustness of the predictions made by deep neural networ…
VCAE uses vine copulas to improve AE generative models for high-dimensional data.
problem Creating flexible generative models for high-dimensional data.
method Three-step procedure: autoencoder compression, vine copula estimation, and generative model combination.
result VCAEs achieve competitive results compared to standard baselines.
Recently, J. Streets and G. Tian introduced a natural way to evolve an almost-Kähler manifold called the symplectic curvature flow, in which the metric, the symplectic structure and the almost-complex structure are all evolving. We study in this paper different aspects of the flow on locally homogeneous manifolds, incl…
This reports on the fundamental objects revealed by Ross Street, which he called `orientals'. Street's work was in part inspired by Robert's attempts to use N-category ideas to construct nets of C*-algebras in Minkowski space for applications to relativistic quantum field theory: Roberts' additional challenge was that …
Automated tool reduces FPGA inference latency to 5 μs for deep neural networks.
problem Deploying ultra low-latency, low-power deep neural networks on FPGAs.
method Extending hls4ml library, using model compression techniques like pruning and quantization-aware training.
result Achieved inference latency of 5 μs with 97% resource reduction.
Prove long-time existence of pluriclosed flow on certain fibrations
problem Long-time existence of pluriclosed flow on fibrations
method General theorem on holomorphic submersions
result Long-time existence of pluriclosed flow on nilmanifolds, almost-abelian solvmanifolds, and certain complex surfaces
Streets and Tian introduced pluriclosed flow and symplectic curvature flow in recent years. Here we construct a curvature flow to unify these two flows. We show the short time existence of our flow and exhibit an obstruction to long time existence.
Mobile app uses CNN to help visually impaired cross streets.
problem Helping visually impaired cross streets safely.
method LytNetV2 deep learning model for pedestrian traffic light detection.
result 96% classification accuracy and 6.15 degree angle error.
This paper presents a comparison of six machine learning (ML) algorithms: GRU-SVM (Agarap, 2017), Linear Regression, Multilayer Perceptron (MLP), Nearest Neighbor (NN) search, Softmax Regression, and Support Vector Machine (SVM) on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (Wolberg, Street, & Mangasarian, 1…
Let C be a spherical fusion category. We prove that the Turaev-Viro-Barrett-Westbury state sum invariant of 3-manifolds derived from C is equal to the Reshetikhin-Turaev surgery invariant of 3-manifolds derived from Z(C), where Z(C) is the Drinfeld-Joyal-Street center of C.
A method solves weakly supervised multiclass MIL problems.
problem Weakly supervised multiclass MIL problems in image recognition.
method Maximizing exact likelihood fitting given observations.
result Our method can learn all convolutional neural networks.
SVHN dataset's split affects generative models but not digit classification.
problem Distribution mismatch between SVHN training and test sets impacts generative models.
method Empirically showed distribution mismatch affects generative models; proposed mixing and re-splitting.
result Distribution mismatch in SVHN dataset significantly impacts probabilistic generative models.
Streets and Tian introduced a parabolic flow of pluriclosed metrics. We classify the long time behavior of homogeneous solutions of this flow on closed complex surfaces including minimal Hopf, Inoue, Kodaira, and non-Kahler, properly elliptic surfaces. We also construct expanding soliton solutions to the flow on the un…
We prove a priori interior C2,α estimates for solutions of fully nonlinear elliptic equations of twisted type. For example, our estimates apply to equations of the type convex + concave. These results are particularly well suited to equations arising from elliptic regularization. As application, we obtain a new pr…
ChatGPT struggles in predicting stock movements, underperforming traditional methods.
problem Predicting stock market movements using ChatGPT.
method Zero-shot analysis of ChatGPT's multimodal stock prediction capabilities.
result ChatGPT underperforms traditional methods and state-of-the-art models in predicting stock movements.
Optimizes data labeling for causal effect estimation with missing outcomes.
problem Estimating causal effects with missing outcome data and budget constraints.
method Optimizes batch sampling probability to minimize variance of causal inference estimator.
result Achieves lower mean-squared error with fewer labeled data points.
This article contains the lecture notes for the short course ``Introduction to Econophysics,'' delivered at the II Brazilian School on Statistical Mechanics, held in Sao Carlos, Brazil, in February 2004. The main goal of the present notes is twofold: i) to provide a brief introduction to the problem of pricing financia…
We derive a closed-form formula for computing bond prices between coupon payments. Our results cover both the `Treasury' and the `Street' pricing methods used by sovereign and corporate issuers. We apply our formulas to two UK gilts, the 8% Treasury Gilt 2015, and the 0.5% Treasury Gilt 2022, and show that we can obtai…
We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall …
GenAI offers financial benefits but requires risk management.
problem Managing risks in financial applications of AI.
method Balancing AI's potential with risk control strategies.
result Proper risk management is essential for AI growth in finance.
We consider the problem of developing a method to reconstruct a potential q from the partial data Dirichlet-to-Neumann map for the Schrödinger equation (−Δg+q)u=0 on a fixed admissible manifold (M,g). If the part of the boundary that is inaccessible for measurements satisfies a flatness condition in one directio…
J. Streets and G. Tian recently introduced symplectic curvature flow, a geometric flow on almost Kähler manifolds generalising Kähler-Ricci flow. The present article gives examples of explicit solutions to this flow of non-Kähler structures on several nilmanifolds and on twistor fibrations over hyperbolic space studied…