Search

Rear-end collision prediction has gained an increasing attention for safety improvement in smart cities. It is urgent to design efficient warning strategies for rear-end collisions which is one of the main causes of traffic accidents. The existing researches have been conducted to predict the collisions. Learning-based methods are proposed to solve this complicated issue, which the traditional methods are difficult to solve. However, due to some limitations in terms of the feature extraction and prediction performance, back-propagation learning methods are facing challenge. In this paper, we proposed a novel Rear-end Collision Prediction Mechanism with deep learning method (RCPM), in which a convolutional neural network model is established. In RCPM, the dataset is smoothed and expanded based on genetic theory to alleviate the class imbalance problem. The preprocessed dataset is divided into training and testing sets as the input to train our convolutional neural network model. The experimental results show that compared with the Honda, Berkeley and multi-layer perception neural-network-based algorithms, RCPM effectively improves performance to predict rear-end collisions. [ABSTRACT FROM AUTHOR]

This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high correct classification rate level and a high classification rate for each class. This last objective is not usually optimized in classification, but is considered here given the need to obtain high precision in each class in real problems. To solve this machine learning problem, we use a Pareto-based multiobjective optimization methodology based on a memetic evolutionary algorithm. We consider a memetic Pareto evolutionary approach based on the NSGA2 evolutionary algorithm (MPENSGA2). Once the Pareto front is built, two strategies or automatic individual selection are used: the best model in accuracy and the best model in sensitivity (extremes in the Pareto front). These methodologies are applied to solve 17 classification benchmark problems obtained from the University of California at Irvine (UCI) repository and one complex real classification problem. The models obtained show high accuracy and a high classification rate for each class. [ABSTRACT FROM AUTHOR]

The Heavy Ion Fusion (HIF) program is progressing through a series of physics and technology demonstrations leading to an inertial fusion power plant. The High Current Experiment (HCX) at Lawrence Berkeley National Laboratory is exploring the physics of intense beams with high line-charge density. Superconducting focusing quadrupoles were developed for magnetic transport studies at the HCX. A baseline design was selected following several pre-series models. Optimization of the baseline design led to the development of a first prototype that achieved a conductor-limited gradient of 132 T/m in a 70 mm bore, without training, with measured field errors at the 0.1% level. Based on these results, the magnet geometry and fabrication procedures were adjusted to improve the field quality. These modifications were implemented in a second prototype. In this paper, the optimized design is presented and comparisons between the design harmonics and magnetic measurements performed on the new prototype are discussed. [ABSTRACT FROM AUTHOR]