Combination of Artificial Intelligence Techniques for prediction the Behavior of Urban Vehicular traffic in the city of São Paulo

Ferreira, Ricardo

doi:10.21528/cbic2011-12.1

Cited by 6 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brazilian traffic data. We used the Sao Paulo traffic benchmark (Ferreira, 2016) to perform independence testing. The dataset consists of 16 different integer-valued statistics about the hourly traffic in Sao Paulo such as blockages, fires and other reasons that might hold up traffic.…”

Section: Real-world Datamentioning

confidence: 99%

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Bonnier¹,

Oberhauser²,

Szabó³

2023

Preprint

View full text Add to dashboard Cite

In R d , it is well-known that cumulants provide an alternative to moments that can achieve the same goals with numerous benefits such as lower variance estimators. In this paper we extend cumulants to reproducing kernel Hilbert spaces (RKHS) using tools from tensor algebras and show that they are computationally tractable by a kernel trick. These kernelized cumulants provide a new set of all-purpose statistics; the classical maximum mean discrepancy and Hilbert-Schmidt independence criterion arise as the degree one objects in our general construction. We argue both theoretically and empirically (on synthetic, environmental, and traffic data analysis) that going beyond degree one has several advantages and can be achieved with the same computational complexity and minimal overhead in our experiments.

show abstract

Section: Real-world Datamentioning

confidence: 99%

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Bonnier¹,

Oberhauser²,

Szabó³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The fusion center is initialized within a BS where the vehicles are placed randomly within 500 meter coverage of or switch between different BSs or RSUs. The dataset used in the evaluation are collected from vehicular environment in urban area [31]. In the dataset, there are 16 individual features to define the traffic pattern such as hour, immobilized bus, broken truck, vehicle excess, accident victim, running over, fire vehicles, occurrence involving freight, incident involving dangerous freight, lack of electricity, fire, point of flooding, manifestations, defect in the network of trolleybuses, tree on the road, semaphore off and intermittent semaphore.…”

Section: Performance Evaluationmentioning

confidence: 99%

Lagrange Coded Federated Learning (L-CoFL) Model for Internet of Vehicles

Zhu

Karim

et al. 2022

2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

show abstract

“…Real-World Datasets: Five real-world datasets were used to evaluate the proposed methods and the comparison methods, including: 1) School Dataset [10], 2) Computer Dataset [15], 3) Facebook Metrics Dataset [23], 4) Traffic SP Dataset [9], and 5) Cars Dataset [21]. Their detailed descriptions and download links are elaborated in Section C.1 of our supplementary material.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Traffic SP related to measurements of the behavior of the urban traffic of the city of Sao Paulo in Brazil [9] 5 . There are 135 records from Monday to Friday during the week of December 14, 2009.…”

Section: Experiments C1 Real-world Datasetsmentioning

confidence: 99%

Sign-regularized Multi-task Learning

Torres¹,

Guangji²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that strives to handle several core issues; particularly, which tasks are correlated and similar, and how to share the knowledge among correlated tasks. Existing works usually do not distinguish the polarity and magnitude of feature weights and commonly rely on linear correlation, due to three major technical challenges in: 1) optimizing the models that regularize feature weight polarity, 2) deciding whether to regularize sign or magnitude, 3) identifying which tasks should share their sign and/or magnitude patterns. To address them, this paper proposes a new multi-task learning framework that can regularize feature weight signs across tasks. We innovatively formulate it as a biconvex inequality constrained optimization with slacks and propose a new efficient algorithm for the optimization with theoretical guarantees on generalization performance and convergence. Extensive experiments on multiple datasets demonstrate the proposed methods' effectiveness, efficiency, and reasonableness of the regularized feature weighted patterns.

show abstract

Combination of Artificial Intelligence Techniques for prediction the Behavior of Urban Vehicular traffic in the city of São Paulo

Cited by 6 publications

References 5 publications

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Lagrange Coded Federated Learning (L-CoFL) Model for Internet of Vehicles

Sign-regularized Multi-task Learning

Contact Info

Product

Resources

About