Images captured under low-light environments typically have poor visibility, affecting many advanced computer vision tasks. In recent years, there have been some low-light image enhancement models based on deep learning, but they have not been able to effectively mine the deep multiscale features in the image, resulting in poor generalization performance and instability of the model. The disadvantages are mainly reflected in the color distortion, color unsaturation and artifacts. Current methods unable to adjust the exposure effectively, resulting in uneven exposure or partial overexposure. To address these issues, we propose an end-to-end low-light image enhancement model, which is called multiscale low-light image enhancement network with illumination constraint(MLLEN-IC), to achieve preferable generalization ability and stable performance. On the one hand, we use the squeeze-and-excitation-Res2Net block(SE-Res2block) as a base unit to enhance the model’s ability by extracting deep multiscale features. On the other hand, to make the model more adaptable in low-light image enhancement tasks, we calculate the illumination constraint by the low-light itself to prevent overexposure, uneven exposure, and unsaturated colors. Extensive experiments are conducted to demonstrate MLLEN-IC not only adjusts light levels, but also has a more natural visual effect, and avoids problems such as color distortion, artifacts, and uneven exposure. In particular, MLLEN-IC has pretty generalization and stability performance. The source code and supplementary are available at https://github.com/CCECfgd/MLLEN-IC.

Global principal component analysis (PCA) has been successfully introduced for modeling distributed parameter systems (DPSs). In spite of the merits, this method is not feasible due to parameter variations and multiple operating domains. A novel multimode spatiotemporal modeling method based on the locally weighted PCA (LW-PCA) method is developed for large-scale highly nonlinear DPSs with parameter variations, by separating the original dataset into tractable subsets. This method implements the decomposition by making full use of the dependence among subset densities. First, the spatiotemporal snapshots are divided into multiple different Gaussian components by using a finite Gaussian mixture model (FGMM). Once the components are derived, a Bayesian inference strategy is then applied to calculate the posterior probabilities of each spatiotemporal snapshot belonging to each component, which will be regarded as the local weights of the LW-PCA method. Second, LW-PCA is adopted to calculate each locally weighted snapshot matrix, and the corresponding local spatial basis functions (SBFs) can be generated by the PCA method. Third, all the local temporal models are estimated using the extreme learning machine (ELM). Thus, the local spatiotemporal models can be produced with local SBFs and corresponding temporal model. Finally, the original system can be approximated using the sum form of each local spatiotemporal model. Unlike global PCA, which uses global SBFs to construct a global spatiotemporal model, LW-PCA approximates the original system by multiple local reduced SBFs. Numerical simulations verify the effectiveness of the developed multimode spatiotemporal model.

In this paper, deep extreme learning machines (DELM) based two-phase spatiotemporal modeling framework is proposed for DPSs. The modeling process consists of two phases. In phase I, DELM based model is constructed to approximate the spatiotemporal dynamics of DPSs. First, an unsupervised stacked ELM autoencoder (ELM-AE) is designed to create a multilayer ELM (ML-ELM), by which the high-dimensional spatiotemporal data can be transformed into low-dimensional time data. The corresponding parameters are optimized by a fast leave-one-out cross-validation (FLOO-CV) algorithm. Second, an ELM model is employed to disclose the temporal dynamic of the low-dimensional time data. Finally, the spatiotemporal model can be reconstructed by kernel ELM (K-ELM). In phase II, a Karhunen-Loeve (KL) based ELM model is constructed to compensate for modeling errors caused by reconstructed error or unknown nonlinear dynamics. The two-phase model can be obtained by integrating these two models. Experiments demonstrate the superior model performance.

In this article, we propose a multiscale cross-connected dehazing network with scene depth fusion. We focus on the correlation between a hazy image and the corresponding depth image. The model encodes and decodes the hazy image and the depth image separately and includes cross connections at the decoding end to directly generate a clean image in an end-to-end manner. Specifically, we first construct an input pyramid to obtain the receptive fields of the depth image and the hazy image at multiple levels. Then, we add the features of the corresponding dimensions in the input pyramid to the encoder. Finally, the two paths of the decoder are cross-connected. In addition, the proposed model uses wavelet pooling and residual channel attention modules (RCAMs) as components. A series of ablation experiments shows that the wavelet pooling and RCAMs effectively improve the performance of the model. We conducted extensive experiments on multiple dehazing datasets, and the results show that the model is superior to other advanced methods in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual effects. The source code and supplementary are available at https://github.com/CCECfgd/MSCDN-master.

Background: Emergency department (ED) overcrowding is a concerning global health care issue, which is mainly caused by the uncertainty of patient arrivals, especially during the pandemic. Accurate forecasting of patient arrivals can allow health resource allocation in advance to reduce overcrowding. Currently, traditional data, such as historical patient visits, weather, holiday, and calendar, are primarily used to create forecasting models. However, data from an internet search engine (eg, Google) is less studied, although they can provide pivotal real-time surveillance information. The internet data can be employed to improve forecasting performance and provide early warning, especially during the epidemic. Moreover, possible nonlinearities between patient arrivals and these variables are often ignored. Objective: This study aims to develop an intelligent forecasting system with machine learning models and internet search index to provide an accurate prediction of ED patient arrivals, to verify the effectiveness of the internet search index, and to explore whether nonlinear models can improve the forecasting accuracy. Methods: Data on ED patient arrivals were collected from July 12, 2009, to June 27, 2010, the period of the 2009 H1N1 pandemic. These included 139,910 ED visits in our collaborative hospital, which is one of the biggest public hospitals in Hong Kong. Traditional data were also collected during the same period. The internet search index was generated from 268 search queries on Google to comprehensively capture the information about potential patients. The relationship between the index and patient arrivals was verified by Pearson correlation coefficient, Johansen cointegration, and Granger causality. Linear and nonlinear models were then developed with the internet search index to predict patient arrivals. The accuracy and robustness were also examined. Results: All models could accurately predict patient arrivals. The causality test indicated internet search index as a strong predictor of ED patient arrivals. With the internet search index, the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the linear model reduced from 5.3% to 5.0% and from 24.44 to 23.18, respectively, whereas the MAPE and RMSE of the nonlinear model decreased even more, from 3.5% to 3% and from 16.72 to 14.55, respectively. Compared with each other, the experimental results revealed that the forecasting system with extreme learning machine, as well as the internet search index, had the best performance in both forecasting accuracy and robustness analysis. Conclusions: The proposed forecasting system can make accurate, real-time prediction of ED patient arrivals. Compared with the static traditional variables, the internet search index significantly improves forecasting as a reliable predictor monitoring continuous behavior trend and sudden changes during the epidemic (P=.002). The nonlinear model performs better than the linear counterparts by capturing the dynamic relationship between the index and patient arrivals. Thus, the system can facilitate staff planning and workflow monitoring.