We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

System Identification I

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

/pdf/analysis-of-observed-chaotic-data-3spe9uweeb.pdf

Analysis of observed chaotic data

Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling

Adaptive Street Lighting Predictive Control

Data-driven models for short-term thermal behaviour prediction in real buildings

The role of data sample size and dimensionality in neural network based forecasting of building heating related variables

In this work, we propose a new street lighting energy management system in order to reduce energy consumption. The key idea we want to accomplish is that of “energy on demand” meaning that energy, in this case light, is provided only when needed. In order to achieve this goal, it is critical to have a reliable demand model, which in the case of street lighting turns out to be a traffic flow rate forecasting model. In order to achieve this goal, several methods on the 1-h prediction have been compared and the one providing the best results is based on artificial neural networks. Moreover, several control strategies have been tested and the one which gave the best energy savings is the adaptive one we carried out. Experimentation has been carried out on real data and the study shows that with the proposed approach, it is possible to save up to 50 % of energy compared to no regulation systems.

Stefano Pizzuti

Papers

Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling

Adaptive Street Lighting Predictive Control

Data-driven models for short-term thermal behaviour prediction in real buildings

The role of data sample size and dimensionality in neural network based forecasting of building heating related variables

Smart street lighting management