Search

Accurately predicting air pollutants, especially in urban areas with well-defined spatial structures, is crucial. Over the past decade, machine learning techniques have been widely used to forecast urban air quality. However, traditional machine learning approaches have limitations in accuracy and interpretability for predicting pollutants. In this study, we propose a convolutional neural network (CNN) model to predict the spatial distribution of CO concentration in Nanjing urban area at 10 m resolution. Our model incorporates various factors as input, such as building height, topography, emissions, and is trained against the outputs simulated by the parallelized large-eddy simulation model (PALM). The PALM model has 48 different scenarios that varied in emissions, wind speeds, and wind directions. The results display a strong consistency between the two models. Furthermore, we evaluate the performance of our model using a 10-fold cross-validation and out-of-sample cross-validation approach. This yields a robust correlation (with both R2 > 0.8) and a low RMSE between the CO predicted by the PALM and CNN models, which demonstrates the generalization capability of our CNN model. The CNN can extract crucial features from the resulted weight contribution map. This map indicates that the CO concentration at a location is more influenced by nearby buildings and emissions than distant ones. The interpretable patterns uncovered by our model are related to neighborhood effects, wind speeds, directions, and the impact of orientation on urban CO distribution. The model also shows high prediction accuracy (R > 0.8) when applied to another city. Overall, the integration of our CNN framework with the PALM model enhances the accuracy of air quality predictions, while enabling a fluid dynamic laws interpretation, providing effective tools for air quality management. [Display omitted] • Deep learning mimics physical air quality models and reduces computational costs. • Model results show robust accuracy and generalization capabilities. • Weight map improves the deep learning model interpretability. • Deep learning models can be generalized to different cities. [ABSTRACT FROM AUTHOR]

Learning-based image super-resolution method is a research hotspot in recent years which uses prior knowledge of sample to reconstruct the image and has obvious advantages over other reconstruction methods. In this paper, we first analyze the factors of reconstructed image quality. Then we use randomized rectified linear unit (RReLU) to solve the problem of over compression in the original network. Besides, Nesterov0s accelerated gradient (NAG) is invoked to accelerate convergence and avoid large oscillations. Finally, we conduct a quantitative experiments to prove the validity of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for visible and infrared image fusion by decomposing feature information, which is termed as CUFD. It adopts two pairs of encoder–decoder networks to implement feature map extraction and decomposition, respectively. On the one hand, the shallow features of the image contain abundant information while the deep features focus more on extracting the thermal targets. Thus, we use an encoder–decoder network to extract both shallow and deep features. Unlike existing methods, both of the shallow and deep features are used for fusion and reconstruction with different emphases. On the other hand, the infrared and visible features of the same layer have both similarities and differences. Therefore, we train the other encoder–decoder network to decompose the feature maps into common and unique information based on their similarities and differences. After that, we apply different fusion rules according to the flexible requirements. This operation is more beneficial to retain the significant feature information in the fusion results. Qualitative and quantitative experiments on publicly available TNO and RoadScene datasets demonstrate the superiority of our CUFD over the state-of-the-art. • Two encoder–decoders with different functions are designed for image fusion. • Feature maps of both shallow and deep levels are used for fusion and reconstruction. • The infrared and visible feature maps are decomposed into common and unique parts. • Diverse fusion rules are designed according to the data and flexible requirements. [ABSTRACT FROM AUTHOR]

The ability to automatically classify files based on their low-level, short-range structures is of particular importance in computer forensics. We report a study on the automatic learning of file classification using byte sub-stream kernels that capture these low-level structures. We automatically discover byte-level patterns in a file by extracting a byte sequence feature map and use a suffix trie data structure to efficiently store and manipulate the feature map. Using the feature map we compute the spectrum kernel and, together with a support vector machine classifier algorithm, we are able to efficiently categorize a variety of different system and application file types. Experiments have provided good file classification performance results. [Copyright &y& Elsevier]

The staging of sleep EEG is executed by the decision by human observations, and is utilized in the diagnosis of insomnia or psychiatric diseases. On the other hand, the sleep EEG includes a large amount of data, and the automation of the sleep staging is considered to be desirable. However, there has not been established a method for staging the biological state based on the awake EEG. This paper proposes an automatic method of staging the biological stage based on the hypothesis that the biological state is the same if the same kind of waveform occur with the same ratio. The proposed method is composed of two procedures: the first is to estimate the standard pattern for the waveform from the individual EEG and the cluster the waveforms; and the second is to examine the kind and ratio of the waveforms appearing in a specified interval of time so that the type of EEG can be identified. The results of staging the sleep EEG is compared to the result of the decision by a doctor, and an agreement of 79 percent is obtained. Generally, it is considered that there can be a difference of some 20 percent in the sleep staging by different doctors. Consequently, it is estimated that the proposed method has a performance comparable to that of the doctor. The staging of the awake EEG also is attempted, and the result is consistent with the skin potential response or the behavior of the subject. Thus it is concluded that the proposed method will be useful in the staging of the biological state. [ABSTRACT FROM AUTHOR]