18 June 2020 in IEEE Transactions on Industrial Informatics
Recently, traffic flow prediction has drawn significant attention because it is a prerequisite in intelligent transportation management in urban informatics. The massively-available traffic data collected from various sensors in Transportation Cyber-Physical Systems brings the opportunities in accurately forecasting traffic trend. Recent advances in deep learning shows the effectiveness on traffic flow prediction though most of them only demonstrate the superior performance on traffic data from a single type of vehicular carriers (e.g., cars) and does not perform well in other types of vehicles. To fill this gap, we propose a wide-attention and deep-composite (WADC) model consisting of a wide-attention module and a deep-composite module in this paper. In particular, the wide-attention module can extract global key features from traffic flows via a linear model with self-attention mechanism. The deep-composite module can generalize local key features via Convolutional Neural Network component and Long Short-Term Memory Network component. We also perform extensive experiments on different types of traffic flow datasets to investigate the performance of WADC model. Our experimental results exhibit that WADC model outperforms other existing approaches.
25 December 2019 in IEEE Access
It is non-trivial to predict the prices of precious metals since a number of factors can affect the fluctuations of precious metal prices. Either parametric models or machine learning models cannot accurately forecast the precious metal prices. Though deep learning approaches show their strengths in extracting key features from complicated data, they have the limitations of learning localization and losing some temporal and spatial features. The recent advances in attention mechanisms bring the opportunities to overcome the limitation of deep learning models. In this paper, we originally propose a Regularization Self-Attention Regression Model for precious metal price prediction. In particular, the proposed RSAR model consists of convolutional neural network (CNN) component and Long Short-Term Memory Neural Networks (LSTM) component. Integrating with self-attention mechanism, this model can extract both spatial and temporal features from precious metal price data. Meanwhile, the proper configuration of regularization functions can also lead to the further performance improvement. Extensive experiments on realistic precious metal price dataset show that our proposed approach outperforms other conventional machine learning and deep learning methods.
2 April 2020 in IEEE Access
The optimal control of denitrification system in coal-fired power plants in China has recently received widespread attention. The accurate prediction of denitrification efficiency and formulate control strategy of denitrification efficiency can guide the control and operation of the denitrification system better. Meanwhile, it can achieve the effect of energy conservation and Nitrogen oxides (NOx) reduction. In this paper, we take a domestic 1000 MW unit as an example, consider each of the major factors that affect the denitrification efficiency of selective catalytic reduction (SCR). We put forward a deep reinforcement learning (DRL) model by combining the Long short-term memory (LSTM) model and the Asynchronous Advantage Actor - Critic algorithm (A3C). We first use the LSTM to build a prediction model for denitrification efficiency. We then use the DRL model to obtain a control strategy for SCR denitrification efficiency in coal-fired power plants. The experimental results demonstrate that the accuracy of denitrification efficiency prediction model we established is better than other machine learning models, reaching 91.7%. Our control strategy model is industrially feasible and universally applicable.