Search

Recent studies have shown great performance of Transformer-based models in long-term time series forecasting due to their ability in capturing long-term dependencies. However, Transformers have their limitations when training on small datasets because of their lack in necessary inductive bias for time series forecasting, and do not show significant benefits in short-time step forecasting as well as that in long-time step as the continuity of sequence is not focused on. In this paper, efficient designs in Transformers are reviewed and a design of decomposing residual convolution neural networks or DRCNN is proposed. The DRCNN method allows to utilize the continuity between data by decomposing data into residual and trend terms which are processed by a designed convolution block or DR-Block. DR-Block has its strength in extracting features by following the structural design of Transformers. In addition, by imitating the multi-head in Transformers, a Multi-head Sequence method is proposed such that the network is enabled to receive longer inputs and more accurate forecasts are obtained. The state-of-the-art performance of the presented model are demonstrated on several datasets. [ABSTRACT FROM AUTHOR]

Ground-based cloud images contain a wealth of cloud information and are an important part of meteorological research. However, in practice, ground cloud images must be segmented and classified to obtain the cloud volume, cloud type and cloud coverage. Existing methods ignore the relationship between cloud segmentation and classification, and usually only one of these is studied. Accordingly, our paper proposes a novel method for the joint classification and segmentation of cloud images, called CloudY-Net. Compared to the basic Y-Net framework, which extracts feature maps from the central layer, we extract feature maps from four different layers to obtain more useful information to improve the classification accuracy. These feature maps are combined to produce a feature vector to train the classifier. Additionally, the multi-head self-attention mechanism is implemented during the fusion process to enhance the information interaction among features further. A new module called Cloud Mixture-of-Experts (C-MoE) is proposed to enable the weights of each feature layer to be automatically learned by the model, thus improving the quality of the fused feature representation. Correspondingly, experiments are conducted on the open multi-modal ground-based cloud dataset (MGCD). The results demonstrate that the proposed model significantly improves the classification accuracy compared to classical networks and state-of-the-art algorithms, with classification accuracy of 88.58%. In addition, we annotate 4000 images in the MGCD for cloud segmentation and produce a cloud segmentation dataset called MGCD-Seg. Then, we obtain a 96.55 mIoU on MGCD-Seg, validating the efficacy of our method in ground-based cloud imagery segmentation and classification. [ABSTRACT FROM AUTHOR]

The current visual simultaneous localization and mapping (SLAM) systems require the use of matched feature point pairs to estimate camera pose and construct environmental maps. Therefore, they suffer from poor performance of the visual feature matchers. To address this problem, a visual SLAM using deep feature matcher is proposed, which is mainly composed of three parallel threads: Visual Odometry, Backend Optimizer and LoopClosing. In the Visual Odometry, the deep feature extractor with convolutional neural networks is utilized for extracting feature points in each image frame. Then, the deep feature matcher is used for obtaining the corresponding feature landmark pairs. Afterwards, a fusion method based on the last and the reference frame is proposed for camera pose estimation. The Backend Optimizer is designed to execute local bundle adjustment for a part of camera poses and landmarks (map points). While LoopClosing, consisting of a lightweight deep loop closure detector and the same matcher as the one used in Visual Odometry is utilized for loop correction based on pose graph. The proposed system has been tested extensively on most of benchmark KITTI odometry dataset. The experimental results show that our system yields better performance than the existing visual SLAM systems. It can not only run in real-time at a speed of 0.08 s per frame, but also reduce estimation error by at least 0.1 m. [ABSTRACT FROM AUTHOR]

Changes in clouds can affect the outpower of photovoltaics (PVs). Ground-based cloud images classification is an important prerequisite for PV power prediction. Due to the intra-class difference and inter-class similarity of cloud images, the classical convolutional network is obviously insufficient in distinguishing ability. In this paper, a classification method of ground-based cloud images by improved combined convolutional network is proposed. To solve the problem of sub-network overfitting caused by redundancy of pixel information, overlap pooling kernel is used to enhance the elimination effect of information redundancy in the pooling layer. A new channel attention module, ECA-WS (Efficient Channel Attention–Weight Sharing), is introduced to improve the network's ability to express channel information. The decision fusion algorithm is employed to fuse the outputs of sub-networks with multi-scales. According to the number of cloud images in each category, different weights are applied to the fusion results, which solves the problem of network scale limitation and dataset imbalance. Experiments are carried out on the open MGCD dataset and the self-built NRELCD dataset. The results show that the proposed model has significantly improved the classification accuracy compared with the classical network and the latest algorithms. [ABSTRACT FROM AUTHOR]

Though the traditional convolutional neural network has a high recognition rate in cloud classification, it has poor robustness in cloud classification with occlusion. In this paper, we propose a novel scheme for cloud classification, in which the convolutional neural networks are used for feature extraction and a weighted sparse representation coding is adopted for classification. Three such algorithms are proposed. Experiments are carried out using the multimodal ground-based cloud dataset and the results show that in the case of occlusion, the accuracy of the proposed methods can be much improved over the traditional convolutional neural network-based algorithms. [ABSTRACT FROM AUTHOR]

Being an important part of aerial insulated cable, the semiconductive shielding layer is made of a typical polymer material and can improve the cable transmission effects; the structural parameters will affect the cable quality directly. Then, the image processing of the semiconductive layer plays an essential role in the structural parameter measurements. However, the semiconductive layer images are often disturbed by the cutting marks, which affect the measurements seriously. In this paper, a novel method based on the convolutional neural network is proposed for image segmentation. In our proposed strategy, a deep fully convolutional network with a skip connection algorithm is defined as the main framework. The inception structure and residual connection are employed to fuse features extracted from the receptive fields with different sizes. Finally, an improved weighted loss function and refined algorithm are utilized for pixel classification. Experimental results show that our proposed algorithm achieves better performance than the current algorithms. [ABSTRACT FROM AUTHOR]