Multilayer Perceptron and Particle Swarm Optimization Applied to Traffic Flow Prediction on Smart Cities

Frank, Lucas R.; Ferreira, Yan Mendes; Julio, Eduardo Pagani; Ferreira, Francisco Henrique Cerdeira; Dembogurski, Bruno José; Silva, Edelberto Franco

doi:10.1007/978-3-030-24305-0_4

Cited by 10 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A beneficial feature in the MLP model used, compared to other ANN architectures such as the RNN and LSTM, is that there is no accumulated error derived from the estimation because MLP does not use the outcome predictions to feed the ANN. For a long time and until now, MLPs have been used effectively in several works to perform accurate predictions [ 31 , 32 , 33 ]. A multilayer perceptron contains three or more layers that use a nonlinear activation function (usually hyperbolic tangent or logistic function), which allow classifying data that is not linearly separable.…”

Section: Methodsmentioning

confidence: 99%

Simultaneous Estimation of Vehicle Roll and Sideslip Angles through a Deep Learning Approach

Prieto-González

Sánchez

García-Guzmán

et al. 2020

Sensors

View full text Add to dashboard Cite

Presently, autonomous vehicles are on the rise and are expected to be on the roads in the coming years. In this sense, it becomes necessary to have adequate knowledge about its states to design controllers capable of providing adequate performance in all driving scenarios. Sideslip and roll angles are critical parameters in vehicular lateral stability. The later has a high impact on vehicles with an elevated center of gravity, such as trucks, buses, and industrial vehicles, among others, as they are prone to rollover. Due to the high cost of the current sensors used to measure these angles directly, much of the research is focused on estimating them. One of the drawbacks is that vehicles are strong non-linear systems that require specific methods able to tackle this feature. The evolution in Artificial Intelligence models, such as the complex Artificial Neural Network architectures that compose the Deep Learning paradigm, has shown to provide excellent performance for complex and non-linear control problems. In this paper, the authors propose an inexpensive but powerful model based on Deep Learning to estimate the roll and sideslip angles simultaneously in mass production vehicles. The model uses input signals which can be obtained directly from onboard vehicle sensors such as the longitudinal and lateral accelerations, steering angle and roll and yaw rates. The model was trained using hundreds of thousands of data provided by Trucksim® and validated using data captured from real driving maneuvers using a calibrated ground truth device such as VBOX3i dual-antenna GPS from Racelogic®. The use of both Trucksim® software and the VBOX measuring equipment is recognized and widely used in the automotive sector, providing robust data for the research shown in this article.

show abstract

Section: Methodsmentioning

confidence: 99%

Simultaneous Estimation of Vehicle Roll and Sideslip Angles through a Deep Learning Approach

Prieto-González

Sánchez

García-Guzmán

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Attention-based method assists in identifying the nearby traffic information, since the speed is an important parameter to forecast the upcoming values of the flow. In literature [15], the authors presented ML and optimization methods to empower an intelligent ecosystem. For validation purpose, a computation was executed in this study with multilayer perceptron and Particle Swarm Optimization (PSO) approach.…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Slime Mould Optimization with Deep Learning Enabled Traffic Prediction in Smart Cities

Hamza¹,

Alsolai²,

Alamgeer³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Intelligent Transportation System (ITS) is one of the revolutionary technologies in smart cities that helps in reducing traffic congestion and enhancing traffic quality. With the help of big data and communication technologies, ITS offers real-time investigation and highly-effective traffic management. Traffic Flow Prediction (TFP) is a vital element in smart city management and is used to forecast the upcoming traffic conditions on transportation network based on past data. Neural Network (NN) and Machine Learning (ML) models are widely utilized in resolving real-time issues since these methods are capable of dealing with adaptive data over a period of time. Deep Learning (DL) is a kind of ML technique which yields effective performance on data classification and prediction tasks. With this motivation, the current study introduces a novel Slime Mould Optimization (SMO) model with Bidirectional Gated Recurrent Unit (BiGRU) model for Traffic Prediction (SMOBGRU-TP) in smart cities. Initially, data preprocessing is performed to normalize the input data in the range of [0, 1] using minmax normalization approach. Besides, BiGRU model is employed for effective forecasting of traffic in smart cities. Moreover, the novelty of the work lies in using SMO algorithm to effectively adjust the hyperparameters of BiGRU method. The proposed SMOBGRU-TP model was experimentally validated and the simulation results established the model's superior performance in terms of prediction compared to existing techniques.

show abstract

“…O MLP é uma Rede Neural Artificial (RNA) na qual todos os neurônios de uma camada estão conectados a todos os outros neurônios das camadas adjacentes. O MLP demonstrou sucesso na predic ¸ão de cenários cíclicos no passado ( [Frank et al 2019). Sua arquitetura contém uma camada de entrada, uma ou mais camadas oculta 3 , e uma camada de saída.…”

Section: Perceptron Multicamadasunclassified

Alocação de Recursos em Redes Sem Fio de Grande Porte por meio de Meta-Heurísticas e Predição da Carga de Usuários

Frank

Carnevale

Galletta

et al. 2022

Anais Do VI Workshop De Computação Urbana (CoUrb 2022)

View full text Add to dashboard Cite

Com o aumento significativo de usuários móveis, a busca pelo gerenciamento de recursos tornou-se essencial. Essa gerência deve visar atender à cobertura do sinal, mas, principalmente, manter o Acordo de Nível de Serviço desejado, independentemente do número de usuários conectados. Assim, propomos a utilização de quatro modelos de predição aplicado ao número de usuários conectados em uma rede sem fio. A partir dessas previsões, os recursos de rede podem ser alocados adequadamente. Investigamos o uso de Otimização de Enxame de Partículas e Algoritmo Genético para hiperparametrizar um Perceptron Multicamadas e uma Árvore de Decisão. Avaliamos nossa proposta utilizando dados reais de rede sem fio com mais de 20 mil usuários. Como resultado, obtivemos uma precisão média de 94,80%, melhorando consideravelmente a utilização de recursos da rede e atendendo um nível de acordo de serviço de 95%.

show abstract

Multilayer Perceptron and Particle Swarm Optimization Applied to Traffic Flow Prediction on Smart Cities

Cited by 10 publications

References 16 publications

Simultaneous Estimation of Vehicle Roll and Sideslip Angles through a Deep Learning Approach

Simultaneous Estimation of Vehicle Roll and Sideslip Angles through a Deep Learning Approach

Intelligent Slime Mould Optimization with Deep Learning Enabled Traffic Prediction in Smart Cities

Alocação de Recursos em Redes Sem Fio de Grande Porte por meio de Meta-Heurísticas e Predição da Carga de Usuários

Contact Info

Product

Resources

About