Search

The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing. The solutions to these topics can provide extremely useful information to support air pollution control, and consequently generate great societal and technical impacts. Most of the existing work solves the three problems separately by different models. In this paper, we propose a general and effective approach to solve the three problems in one model called the Deep Air Learning (DAL). The main idea of DAL lies in embedding feature selection and semi-supervised learning in different layers of the deep learning network. The proposed approach utilizes the information pertaining to the unlabeled spatio-temporal data to improve the performance of the interpolation and the prediction, and performs feature selection and association analysis to reveal the main relevant features to the variation of the air quality. We evaluate our approach with extensive experiments based on real data sources obtained in Beijing, China. Experiments show that DAL is superior to the peer models from the recent literature when solving the topics of interpolation, prediction, and feature analysis of fine-gained air quality. [ABSTRACT FROM AUTHOR]

Obtaining crowd flow distribution with recognized human intention is extremely valuable for a series of applications for metropolitan cities. Previous solutions look at spatial correlation and temporal periodicity based on historical crowd flow information to calculate future crowd flow distribution. However, these mechanisms cannot recognize the intention behind crowd flow. We address this problem by leveraging a key insight – people's intention behind their movement is highly correlated with the point-of-interest (POI) distribution of the corresponding regions and adjacent regions. Therefore, we propose DeepFlowGen to model the complicated relationship between crowd flow, POI, check-ins, and time to generate intention-aware crowd flow. Specifically, we solve the conflict between dynamic crowd flow and static POI distribution by fusing the information in both time and POI domains. Besides, we employ a sequence of residual blocks in DeepFlowGen to address the challenges of modeling the diverse temporal rhythms and heterogeneous influence of POI. Furthermore, we examine the generated intention-aware crowd flow from two aspects to substantiate the reasonability of DeepFlowGen. Extensive experiments demonstrate that our model outperforms the state-of-the-art solutions by at most 30 percent in terms of NRMSE of total crowd flow. Moreover, the correlation between the generated intention-aware crowd flow and the check-in distribution across different categories of POIs is as high as 0.90 and 0.80 in Beijing and Shanghai. Combined with extensive case studies, we demonstrate the strong ability of our model in generating intention-aware crowd flow. [ABSTRACT FROM AUTHOR]

The state of charge (SOC) is a crucial parameter of a battery management system for Li-ion batteries. The SOC indicates the amount of charge left in the battery of electric vehicles—akin to the fuel gauge in combustion vehicles. An accurate SOC knowledge contributes largely to the longevity, performance, and reliability of the battery. However, the SOC of Li-ion batteries cannot be easily measured by any apparatus. Furthermore, the SOC can also be influenced by numerous incalculable factors such as battery chemistry, ambient environment, aging factor, etc. In this article, we propose an SOC estimation model for a Li-ion battery using an improved deep neural network (DNN) approach for electric vehicle applications. We found that a DNN with a sufficient number of hidden layers is capable of predicting the SOC of the unseen drive cycles during training. We developed a series of DNN models with a varying number of hidden layers, and its training algorithm was to investigate their respective performance when evaluated on different drive cycles. We observe that the increasing number of hidden layers in the DNN (up to four hidden layers) decreases the error rate and improves SOC estimation. An additional increase in the number of hidden layers beyond that increases the error rate. In this study, we show that a four-hidden-layer DNN trained on Dynamic Stress Test drive cycle is capable of predicting SOC values unexpectedly well of other unseen drive cycles such as Federal Urban Driving Schedule, Beijing Dynamic Stress Test, and Supplemental Federal Test Procedure, respectively. [ABSTRACT FROM AUTHOR]