Thirty-three bituminous coal samples were utilized to test the application of laser-induced breakdown spectroscopy technique for coal elemental concentration measurement in the air. The heterogeneity of the samples and the pyrolysis or combustion of coal during the laser-sample interaction processes were analyzed to be the main reason for large fluctuation of detected spectra and low calibration quality. Compared with the generally applied normalization with the whole spectral area, normalization with segmental spectral area was found to largely improve the measurement precision and accuracy. The concentrations of major element C in coal were determined by a novel partial least squares (PLS) model based on dominant factor. Dominant C concentration information was taken from the carbon characteristic line intensity since it contains the most-related information, even if not accurately. This dominant factor model was further improved by inducting non-linear relation by partially modeling the inter-element interference effect. The residuals were further corrected by PLS with the full spectrum information. With the physical-principle-based dominant factor to calculate the main quantitative information and to partially explicitly include the non-linear relation, the proposed PLS model avoids the overuse of unrelated noise to some extent and becomes more robust over a wider C concentration range. Results show that RMSEP in the proposed PLS model decreased to 4.47% from 5.52% for the conventional PLS with full spectrum input, while R(2) remained as high as 0.999, and RMSEC&P was reduced from 3.60% to 2.92%, showing the overall improvement of the proposed PLS model.

Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving the urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal control. Different from traditional transportation approaches which rely heavily on prior knowledge, RL can learn directly from the feedback. On the other side, without a careful model design, existing RL methods typically take a long time to converge and the learned models may not be able to adapt to new scenarios. For example, a model that is trained well for morning traffic may not work for the afternoon traffic because the traffic flow could be reversed, resulting in a very different state representation.In this paper, we propose a novel design called FRAP, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Through the phase competition modeling, our model achieves invariance to symmetrical cases such as flipping and rotation in traffic flow. By conducting comprehensive experiments, we demonstrate that our model finds better solutions than existing RL methods in the complicated all-phase selection problem, converges much faster during training, and achieves superior generalizability for different road structures and traffic conditions.

Crowd flow prediction is of great importance in a wide range of applications from urban planning, traffic control to public safety. It aims to predict the inflow (the traffic of crowds entering a region in a given time interval) and outflow (the traffic of crowds leaving a region for other places) of each region in the city with knowing the historical flow data. In this paper, we propose DeepSTN+, a deep learning-based convolutional model, to predict crowd flows in the metropolis. First, DeepSTN+ employs the ConvPlus structure to model the longrange spatial dependence among crowd flows in different regions. Further, PoI distributions and time factor are combined to express the effect of location attributes to introduce prior knowledge of the crowd movements. Finally, we propose an effective fusion mechanism to stabilize the training process, which further improves the performance. Extensive experimental results based on two real-life datasets demonstrate the superiority of our model, i.e., DeepSTN+ reduces the error of the crowd flow prediction by approximately 8%∼13% compared with the state-of-the-art baselines.

No abstract

No abstract