arXiv research

Predicts routing congestion in FPGA designs using machine learning.

New algorithm for traffic routing in congested conditions.

This study develops methods to coordinate travel routes to reduce congestion.

A new router uses attention-based reinforcement learning to solve detailed routing problems efficiently.

Because of the prominent position of urban rail in reducing urban transport-related problems, such as congestion and air pollution, insights into the costs of possible new urban rail projects is very relevant for those involved with cost estimations, policy makers, cost-benefit analysts, and other target groups. Knowle…

Intelligent AQM uses ECN to predict and control network congestion.

Survey of deep learning applications in traffic congestion detection, prediction, and alleviation.

Potential games, originally introduced in the early 1990's by Lloyd Shapley, the 2012 Nobel Laureate in Economics, and his colleague Dov Monderer, are a very important class of models in game theory. They have special properties such as the existence of Nash equilibria in pure strategies. This note introduces graphical…

Vehicular Ad-hoc NETworks (VANET) can efficiently detect traffic congestion, but detection is not enough because congestion can be further classified as recurrent and non-recurrent congestion (NRC). In particular, NRC in an urban network is mainly caused by incidents, workzones, special events and adverse weather. We p…

Model traffic congestion events using multi-modal data and attention-based neural networks.

The paper tackles Nash-regret minimization in congestion games with bandit feedback.

Study of congestion in negative curvature manifolds using fair-division algorithms.

New method estimates traffic congestion delays using statistical causality.

Wasserstein GANs with Gradient Penalty compute a different optimal transport problem called congested transport.

MVFST-RL tackles real-time network congestion control with RL.

NAC-FL optimizes model updates in FL systems by adapting compression to network congestion.

Study predicts traffic congestion based on population mobility data.

Paper uses DeePC to improve urban traffic lights, reducing congestion and emissions.

New framework analyzes LLM personalization trade-offs under congestion.

Predicts morning traffic congestion using social media data from the previous evening.

Advanced travel information and warning, if provided accurately, can help road users avoid traffic congestion through dynamic route planning and behavior change. It also enables traffic control centres mitigate the impact of congestion by activating Intelligent Transport System (ITS) proactively. Deep learning has beco…

Decentralized algorithm reduces regret and converges to Nash equilibrium in online congestion games.

Non-recurring traffic congestion is caused by temporary disruptions, such as accidents, sports games, adverse weather, etc. We use data related to real-time traffic speed, jam factors (a traffic congestion indicator), and events collected over a year from Nashville, TN to train a multi-layered deep neural network. The …

Dynamic linear models improve travel time prediction for congested freeways.

Framework predicts and prepares for rain-induced microwave link attenuation.

Online learning improves traffic congestion prediction over time.

This paper connects deep neural networks to game theory, revealing their congestion game properties.

Overprocuring reserves can improve network efficiency by using excess reserves for congestion management.

This paper proposes MM-DAGs for analyzing traffic congestion, learning multiple DAGs jointly.

A new framework reduces traffic congestion by 36%.

Capsule networks improve performance on image classification tasks with fewer parameters.

Service-induced congestion in memory-constrained LLM serving

RL techniques improve radar spectrum sharing in crowded conditions.

Deep RL solves global routing problems more efficiently.

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of ef…

Capsules learn from expert neurons using dynamic routing.

JAMPR learns to solve complex VRP with time windows.

A large GPS dataset reveals that a single route often covers 60% of travel observations.

Capsule networks can only represent symmetric functions due to routing limitations.

Study on-chain peak shaving to reduce Ethereum transaction costs.

Proposes three decentralized multi-agent reinforcement learning algorithms to reduce network congestion.

This paper improves nearest neighbor search by learning optimal routing functions.

We propose and systematically evaluate three strategies for training dynamically-routed artificial neural networks: graphs of learned transformations through which different input signals may take different paths. Though some approaches have advantages over others, the resulting networks are often qualitatively similar…

Backdoor attacks on DRL-based traffic controllers cause stop-and-go waves or crashes.

Graph neural networks improve topology control of power grids.

The DEBS Grand Challenge 2018 is set in the context of maritime route prediction. Vessel routes are modeled as streams of Automatic Identification System (AIS) data points selected from real-world tracking data. The challenge requires to correctly estimate the destination ports and arrival times of vessel trips, as ear…

Project learns to model Capsule Networks' routing procedures for better expressiveness.

Unified routing and arbitrage with concave continuation.