Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this paper, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (1D-CNNs) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and spatial correlation features, and the latter is to learn spatial-temporal dependencies. Then we design a jointly hybrid deep learning framework based on one-dimensional CNNs and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. We conduct extensive experimental evaluations using two real-world datasets, and the results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.

The performance of multilabel learning depends heavily on the quality of the input features. A mass of irrelevant and redundant features may seriously affect the performance of multilabel learning, and feature selection is an effective technique to solve this problem. However, most multilabel feature selection methods mainly emphasize removing these useless features, and the exploration of feature interaction is ignored. Moreover, the widespread existence of real-world data with uncertainty, ambiguity, and noise limits the performance of feature selection. To this end, our work is dedicated to designing an efficient and robust multilabel feature selection scheme. First, the distribution character of multilabel data is analyzed to generate robust fuzzy multi-neighborhood granules. By exploring the classification information implied in the data under the granularity structure, a robust multilabel $k$ -nearest neighbor fuzzy rough set model is constructed, and the concept of fuzzy dependency is studied. Second, a series of fuzzy multi-neighborhood uncertainty measures in $k$ -nearest neighbor fuzzy rough approximation spaces are studied to analyze the correlations of feature pairs, including interactivity. Third, by investigating the uncertainty measure between feature and label, between features, multilabel data is modeled as a complete weighted graph. Then, these vertices are assessed iteratively to guide the assignment of feature weights. Finally, a graph structure-based robust multilabel feature selection algorithm (GRMFS) is designed. The experiments are conducted on fifteen multilabel datasets. The results verify the superior performance of GRMFS as compared with nine representative feature selection methods.

Information fusion is capable of fusing and transforming multiple data derived from different sources to provide a unified representation for centralized knowledge mining that facilitates effective decision-making, classification and prediction, etc. Multi-source interval-valued data, characterizing the uncertainty phenomenons in the data in the form of intervals in different sources, are the most common symbolic data which widely exist in many real-world applications. This paper concentrates on efficient fusing of multi-source interval-valued data with the dynamic updating of data sources which involves the addition of new sources and the deletion of obsolete sources. We propose a novel data fusion method based on fuzzy information granulation, which translates multi-source interval-valued data into trapezoidal fuzzy granules. Given this effectively fusing capability, we develop incremental mechanisms and algorithms for fusing multi-source interval-valued data with dynamic variation of data sources. Finally, extensive experiments are carried out to verify the effectiveness of the proposed algorithms when comparing with other six different fusion algorithms. Experimental results show that the proposed fusion method outperforms the related approaches. Furthermore, the proposed incremental fusion algorithms can reduce the computing overhead in comparison with the static fusion algorithm when adding and deleting multiple data sources.

Ensuring data confidentiality in a vehicular ad hoc network (VANET) is an increasingly important issue. Message confidentiality, user privacy and access control are the most important problems that affect services provided by VANETs. However, access control that addresses data downloads while preserving users' privacy remains an open problem. Based on a set of attributes, the ciphertext-policy attribute-based encryption (CP-ABE) algorithm proposes a party data encryption/decryption mechanism for shared data; consequently, the algorithm has become a popular solution for data-sharing access control. However, the current CP-ABE schemes are still infeasible for VANETs because these schemes use a single authority and inefficient encryption/decryption and ignore revocation mechanisms. Here, over CP-ABE with revocation, we introduce an identity-based scheme that achieves secure data sharing in VANETs. To reduce the computation load for in-vehicle on-board units (OBUs), we outsource computationally intensive encryption and decryption operations to cloud compute nodes. Attributes are decentralized and managed by application service providers that provide services to vehicles based on subscriptions. Comprehensive experimental results and security analysis show that our scheme achieves fine-grained access control while preserving user privacy. Through implementation, performance analysis demonstrates that our scheme is suitable for VANETs.

Conventional haze-removal methods are designed to adjust the contrast and saturation, and in so doing enhance the quality of the reconstructed image. Unfortunately, the removal of haze in this manner can shift the luminance away from its ideal value. In other words, haze removal involves a tradeoff between luminance and contrast. We reformulated the problem of haze removal as a luminance reconstruction scheme, in which an energy term is used to achieve a favorable tradeoff between luminance and contrast. The proposed method bases the luminance values for the reconstructed image on statistical analysis of haze-free images, thereby achieving contrast values superior to those obtained using other methods for a given brightness level. We also developed a novel module for the estimation of atmospheric light using the color constancy method. This module was shown to outperform existing methods, particularly when noise is taken into account. The proposed framework requires only 0.55 seconds to process a 1-megapixel image. Experimental results demonstrate that the proposed haze-removal framework conforms to our theory of contrast.