A comparative study between artificial neural networks and support vector regression for modeling of the dissipated energy through tire-obstacle collision dynamics

Taghavifar, Hamid; Mardani, Aref; Maslak, Haleh Karim

doi:10.1016/j.energy.2015.05.122

Cited by 15 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, equation 3represents the free space propagation of the beam results in divergence of the beam width, ω(z), where z is the propagation distance. This is true for distances that are less than the Rayleigh length (Svelto and Hanna 1998)…”

Section: Laser Beam Modelmentioning

confidence: 91%

“…where ω0 = λ / (π Θ) is the beam width (radius) of the pulse at z = 0 also known as the beam waist (Svelto and Hanna 1998). The radial distance (in metres) at which the profile value is decreased to 1/e 2 from its peak value is zr = π ω0 / λ, where λ is the laser wavelength.…”

Section: Laser Beam Modelmentioning

confidence: 99%

“…Nowadays, many classifiers rely on machine-learning approaches to exploit data redundancy and abundance to finding out patterns, trends and relations amongst the input attributes and the class labels (Kala 2016). Within obstacle recognition techniques, vector support machines have been widely applied for classification and regression problems (Taghavifar et al 2015;Apatean et al 2013). An interesting application using machine learning for the pedestrian detection in autonomous vehicles based on HD 3D LiDAR is reported in (Navarro et al 2016), providing more accurate data to be successfully used in any kind of lighting conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computational Intelligence for Simulating a LiDAR Sensor

Castaño

Beruvides

Villalonga

et al. 2019

Sensor Systems Simulations

View full text Add to dashboard Cite

In this chapter, an overview of some of the most commonly Computational Intelligence techniques used to provide new capabilities to sensor networks in Cyber-Physical and Internet-of-Things environments, and for verifying and evaluating the reliability issues of sensor networks is presented. Nowadays, on-chip Light Detection and Ranging (LiDAR) concept has driven a great technological challenge into sensor networks application for Cyber-Physical and Internet-of-Things systems. Therefore, the modelling and simulation of a LiDAR sensor networks is also included in this chapter that is structured as follows. First, a brief description of the theoretical modelling of the mathematical principle of operation is outlined. Subsequently, a review of the state-of-art of Computational Intelligence techniques in sensor system simulations is explained. Likewise, a use case of applying computational intelligence techniques to LiDAR sensor networks in a Cyber-Physical System environment is presented. In this use case, a model library with four specific Artificial Intelligence-based methods is also designed based on sensory information database provided by the LiDAR simulation. Some of them are multi-layer perceptron neural network, a self-organization map, a support vector machine and a k-nearest neighbours. The results demonstrate the suitability of using Computational Intelligence methods to increase the reliability of sensor networks when addressing the key challenges of safety and security in automotive applications.

show abstract

Section: Laser Beam Modelmentioning

confidence: 91%

Section: Laser Beam Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational Intelligence for Simulating a LiDAR Sensor

Castaño

Beruvides

Villalonga

et al. 2019

Sensor Systems Simulations

View full text Add to dashboard Cite

show abstract

“…Nowadays, many classifiers rely on machine-learning approaches to exploit data redundancy and abundance to find out patterns, trends and relations amongst input attributes and class labels [ 8 , 9 , 10 ]. Within obstacle-recognition techniques, vector support machines have been widely applied for classification and regression problems [ 11 ]. An interesting application using machine learning for pedestrian detection in autonomous vehicles based on High Definition (HD) 3DLiDAR is reported in [ 12 ], providing more accurate data to be successfully used in any kind of lighting conditions.…”

Section: Introductionmentioning

confidence: 99%

Obstacle Recognition Based on Machine Learning for On-Chip LiDAR Sensors in a Cyber-Physical System

Castaño

Beruvides

Haber

et al. 2017

Sensors

View full text Add to dashboard Cite

Collision avoidance is an important feature in advanced driver-assistance systems, aimed at providing correct, timely and reliable warnings before an imminent collision (with objects, vehicles, pedestrians, etc.). The obstacle recognition library is designed and implemented to address the design and evaluation of obstacle detection in a transportation cyber-physical system. The library is integrated into a co-simulation framework that is supported on the interaction between SCANeR software and Matlab/Simulink. From the best of the authors’ knowledge, two main contributions are reported in this paper. Firstly, the modelling and simulation of virtual on-chip light detection and ranging sensors in a cyber-physical system, for traffic scenarios, is presented. The cyber-physical system is designed and implemented in SCANeR. Secondly, three specific artificial intelligence-based methods for obstacle recognition libraries are also designed and applied using a sensory information database provided by SCANeR. The computational library has three methods for obstacle detection: a multi-layer perceptron neural network, a self-organization map and a support vector machine. Finally, a comparison among these methods under different weather conditions is presented, with very promising results in terms of accuracy. The best results are achieved using the multi-layer perceptron in sunny and foggy conditions, the support vector machine in rainy conditions and the self-organized map in snowy conditions.

show abstract

Integration and Demonstrations

Artuñedo

2020

Decision-Making Strategies for Automated Driving in Urban Environments

View full text Add to dashboard Cite

A comparative study between artificial neural networks and support vector regression for modeling of the dissipated energy through tire-obstacle collision dynamics

Cited by 15 publications

References 22 publications

Computational Intelligence for Simulating a LiDAR Sensor

Computational Intelligence for Simulating a LiDAR Sensor

Obstacle Recognition Based on Machine Learning for On-Chip LiDAR Sensors in a Cyber-Physical System

Integration and Demonstrations

Contact Info

Product

Resources

About