Search

Mathematical modeling plays a critical role toward the mitigation of nitrous oxide (N 2 O) emissions from wastewater treatment plants (WWTPs). In this work, we proposed a novel hybrid modeling approach by integrating the first principal model with deep learning techniques to predict N 2 O emissions. The hybrid model was successfully implemented and validated with the N 2 O emission data from a full-scale WWTP. This hybrid model is demonstrated to have higher accuracy for N 2 O emission modeling in the WWTP than the mechanistic model or pure deep learning model. Equally important, the hybrid model is more applicable than the pure deep learning model due to the lower requirement of data and the pure mechanistic model due to the less calibration requirement. This superior performance was due to the hybrid nature of the proposed model. It integrated the essential wastewater treatment knowledge as the first principal component and the less understood N 2 O production processes by the data-driven deep learning approach. The developed hybrid model was also successfully implemented under different circumstances for the prediction of N 2 O flux, which showed the generalizability of the model. The hybrid model also showed great potential to be applied for the N 2 O mitigation work. Nevertheless, the capability of the hybrid model in evaluating N 2 O mitigation strategies still requires validation with experiments. Going beyond N 2 O modeling in WWTP, the novel hybridization modeling concept can potentially be applied to other environmental systems.

Multi-focus image fusion (MFIF) attempts to achieve an “all-focused” image from multiple source images with the same scene but different focused objects. Given the lack of multi-focus image sets for network training, we propose a self-supervised residual feature learning model in this paper. The model consists of a feature extraction network and a fusion module. We select image super-resolution as a pretext task in the MFIF field, which is supported by a new residual gradient prior discovered by our theoretical study for low- and high-resolution (LR-HR) image pairs, as well as for multi-focus images. In the pretext task, our network’s training set is LR-HR image pairs generated from natural images, and HR images can be regarded as pseudo-labels of LR images. In the fusion task, the trained network extracts residual features of multi-focus images firstly. Secondly, the fusion module, consisting of an activity level measurement and a new boundary refinement method, is leveraged for the features to generated decision maps. Experimental results, both subjective evaluations and objective evaluations, demonstrate that our approach outperforms other state-of-the-art fusion algorithms. [ABSTRACT FROM AUTHOR]

Crowd counting is still a practical and challenging problem owing to scale variations and information loss. Most existing methods based on the straightforward fusion of different features from a deep neural network seem to eliminate this limitation. However, these features are difficult to be fused since they often differ significantly in modality and dimensionality. Unlike previous works, a multi‐level features extraction network with gating mechanism for crowd counting is proposed. Specifically, a multi‐channel gated unit to adaptively extract features in different levels of the network is proposed, which can avoid interference from confusing information. To fully aggregate features via multi‐level fusion, multi‐level features extraction scheme is presented. The multi‐level features extraction network learns to fuse features from multiple levels and reduce false predictions. Extensive experiments and evaluations clearly illustrate that the proposed approach achieves state‐of‐the‐art counting performance against other methods on four mainstream crowd counting benchmarks. [ABSTRACT FROM AUTHOR]

In the case of poor lighting conditions, it is easy to capture the underexposed images with low contrast and low quality. Traditional single-image enhancement methods often fail in revealing image details because of the limited information in a single-source image. A single underexposed image enhancement method based on adaptive decomposition and convolutional neural network (CNN) is proposed. The CNN training models only need images with different brightness rather than a strict ground-truth image. First, a simple effective synchronous decomposition method is proposed to solve the synergy problem in multisource image decomposition. Then, two CNN models are designed for the high-frequency part and low-frequency part, respectively. They process the high-frequency and low-frequency sub-bands, instead of the entire source images. The weight map obtained from the CNN model represents the contrast distribution. The exposure map generated by gradient-based visibility assessment indicates the exposure distribution. Finally, the weight map and the exposure map are multiplied to generate the final decision map. Experimental results demonstrate that the proposed method outperforms competing methods. [ABSTRACT FROM AUTHOR]