Search

Accurately predicting runoff is crucial for managing water resources, preventing and mitigating floods, scheduling hydropower plant operations, and protecting the environment. The hydrological dynamic composite system that forms runoff is complex and random, and seemingly random behavior may be caused by nonlinear variables in a simple deterministic system, which poses a challenge to runoff prediction. In this paper, we construct parallel and multi-timescale reservoirs from a chaotic theory perspective to simulate the stochasticity of chaotic systems. We propose a multi-task-based "Decomposition-Integration-Prediction" (Multi-SDIPC) model for runoff prediction. To validate our research results, we use the Catchment Attributes and Meteorology for Large-Sample Studies (CAMELS) dataset and compare our proposed model with 10 baseline models. The results show that our model has an average NSE metric of 0.83 and exhibits higher accuracy, better generalization, and greater stability than the other models in multi-step forecasting. Based on our findings, we recommend wider application of the Multi-SDIPC model in different regions of the world for medium or long-term runoff prediction. [ABSTRACT FROM AUTHOR]

Catastrophic forgetting is a non-trivial challenge for class incremental learning, which is caused by new knowledge learning and data imbalance between old and new classes. To alleviate this challenge, we propose a class incremental learning method with dual-branch classifier. First, inspired by ensemble learning, the proposed method constructs a dual network consisting of two complementary branches to alleviate the impact of data imbalance. Second, activation transfer loss is employed to reduce the catastrophic forgetting from the view of feature representation, preserving the feature separability of old classes. Third, we use the nearest class mean classifier with natural advantages for classification. Moreover, we formulate an end-to-end training algorithm for the feature extraction and classifier, to boost module matching degree. Extensive evaluation results show our proposed method achieves nice incremental recognition ability with less training time. Moreover, the ablation study shows the importance and necessity of dual-branch structure, end-to-end training, and activation transfer loss. [ABSTRACT FROM AUTHOR]

Rice XA21 is an immune receptor kinase that confers broad-spectrum resistance against Xanthomonas oryzae pv. oryzae (Xoo). Pathogenesis-related (PR) proteins are located downstream of the plant immune system and OsPR1A can be induced by Xoo. In this study, it was found that the OsPR1A protein was concentrated in the lesion region in rice leaves and barely detectable in the Xoo-free regions. The OsPR1A protein was detectable at 2 days post-inoculation (dpi) in 4021. In contrast, the expression of OsPR1A protein was detectable at 8 dpi in TP309. It indicated that the rapid induction of OsPR1A expression in 4021 is crucial for disease resistance. To investigate the function of OsPR1A protein in Xa21-mediated resistance, an RNA interference construct was transformed into 4021. The lesion lengths of OsPR1a-RNAi lines were shorter than that of TP309 and longer than that of 4021. OsPR1a-RNAi lines showed reduced OsPR1A abundance, in correlation with the compromised resistance to Xoo, supporting that OsPR1A play a positive role for Xa21-mediated resistance. These results enhance our understanding regarding the mechanism of Xa21-mediated resistance and the function of the OsPR1a gene. [ABSTRACT FROM AUTHOR]

With the success of the deep residual network for image recognition tasks, the residual connection or skip connection has been widely used in deep learning models for various vision tasks, including single image super-resolution (SISR). Most existing SISR approaches pay particular attention to residual learning, while few studies investigate highway connection for SISR. Although skip connection can help to alleviate the vanishing gradient problem and enable fast training of the deep network, it still provides the coarse level of approximation in both forward and backward propagation paths and thus challenging to recover high-frequency details. To address this issue, we propose a novel model for SISR by using highway connection (HNSR), which composes of a nonlinear gating mechanism to further regulate the information. By using the global residual learning and replacing all local residual learning with designed gate unit in highway connection, HNSR has the capability of efficiently learning different hierarchical features and recovering much more details in image reconstruction. The experimental results have validated that HNSR can provide not only improved quality but also less prone to a few common problems during training. Besides, the more robust and efficient model is suitable for implementation in real-time and mobile systems. [ABSTRACT FROM AUTHOR]

In this paper, a local cloud model similarity measurement (CMSM) is proposed as a novel method to measure the similarity of time series. Time series similarity measurement is an indispensable part for improving the efficiency and accuracy of prediction. The randomness and uncertainty of series data are critical problems in the processing of similarity measurement. CMSM obtains the internal information of time series from the general perspective and local trend using the cloud model, which reduces the uncertainty of measurement. The neighbor set is selected from time series by CMSM and used to construct a prediction model based on least squares support vector machine. The proposed technique reduces the potential for overfitting and uncertainty and improves model prediction quality and generalization. Experiments were performed with four datasets selected from Time Series Data Library. The experimental results show the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Multimodal data have recently become nearly ubiquitous in the real world. Exploring the multimodal fusion is beneficial to improve the performance of the system. However, it is difficult to ensure that data collected from different sources are full pairing. In this paper, we will focus on the weakly paired case of multimodal data, i.e., each modality is partitioned into multiple groups, only paired information on groups is known instead of full pairing between data samples. A new framework of weakly paired multimodal fusion based on multilayer extreme learning machine (ML-ELM) is proposed in this paper, which will find complex nonlinear transformations of each modality of data such that the resulting representations are highly correlated. In this framework, unsupervised hierarchical ELM performs feature extraction for all modalities separately. Then, the higher-level representations from all modalities perform joint dimension reduction by weakly paired maximum covariance analysis. We evaluate our framework on three challenging cross-modal datasets, and the results have proved the effectiveness of proposed method. [ABSTRACT FROM AUTHOR]

Infrared and visible light image fusion technology is a hot spot in the research of multi-sensor fusion technology in recent years. Existing infrared and visible light fusion technologies need to register before fusion because of using two cameras. However, the application effect of the registration technology has yet to be improved. Hence, a novel integrative multi-spectral sensor device is proposed for infrared and visible light fusion, and by using the beam splitter prism, the coaxial light incident from the same lens is projected to the infrared charge coupled device (CCD) and visible light CCD, respectively. In this paper, the imaging mechanism of the proposed sensor device is studied with the process of the signals acquisition and fusion. The simulation experiment, which involves the entire process of the optic system, signal acquisition, and signal fusion, is constructed based on imaging effect model. Additionally, the quality evaluation index is adopted to analyze the simulation result. The experimental results demonstrate that the proposed sensor device is effective and feasible. [ABSTRACT FROM AUTHOR]

Recognizing which part of an object is graspable or not is important for intelligent robot to perform some complicated tasks. In order to obtain good grasping performance, learning rich representations efficiently from multi-modal RGB-D images is crucial. To address this problem, in this paper, we propose an effective multi-modal deep extreme learning machine structure. In this structure, unsupervised hierarchical extreme learning machine (ELM) is conducted for feature extraction for RGB and depth modalities separately. Then, the shared layer is developed by combining both RGB and depth features. Finally, the ELM is used as supervised feature classifier for final decision. Experimental validation on Cornell grasping dataset illustrates that the proposed multiple modality fusion method achieves better grasp recognition performance. [ABSTRACT FROM AUTHOR]