Search

Neural network is one of the key technologies for deep learning. Experiments on some standard test datasets show that their recognition ability has reached the level of human beings. However, they are extremely vulnerable to adversarial examples, that is, adding some subtle perturbations to the input example can cause the model to give a wrong output with high confidence. In this paper, we propose a non-contact approach based on neural network and adversarial training to recognize the high-speed rail operating environment. We first built the environment dataset and trained neural network models to do the recognition. We found that our model had high prediction accuracy, but with poor security since it was easy to attack our model using Basic Iterative Methods (BIM). To improve its security, we performed adversarial training based on the adversarial training dataset we built. The evaluation experiments indicated that this approach could improve the security of our model at the same time ensuring the prediction accuracy on the original test dataset.

Air emissions from power plants can have a significant effect on air quality. However, models used to analyze and project trends in the energy system are not easily coupled with air quality simulation models. Most downscaling approaches use simplistic averaging and “growth in place” methods that do not account for future changes in the pattern of generation due to renewable penetration, nor for important variations in time and space in emissions that have important implications for air quality. For instance, emissions of NOx are strongly correlated with temperature, which is also correlated with conditions favorable for ozone (smog) episodes. This paper presents a new methodology for downscaling electric sector results from the USDOE National Energy Modeling System (NEMS) for input into air quality modeling systems. The downscaling methodology will be used to analyze air quality and resulting health impacts of energy sector transitions, including transportation electrification and increased use of natural gas and renewable sources.