Search

In recent years, high-frequency resonance (HFR) events occurred in several modular multilevel converter based high-voltage direct current (MMC-HVDC) projects. The time delay of an MMC-HVDC system is the critical factor that induces HFR. The frequency coupling affects the impedance characteristics of an MMC and further deteriorates system stability. Therefore, in this paper, a multi-input multi-output admittance model of an MMC-HVDC system is developed to analyze its frequency characteristics. The effects of current loop, power loop, phase-locked loop, and operating point on the MMC frequency coupling degree are analyzed in detail. Meanwhile, to further suppress HFR in the MMC-HVDC system, an enhanced impedance reshaping control strategy based on the equivalent single-input single-output impedance model is proposed. Finally, the accuracy of the enhanced impedance model and the effectiveness of the impedance reshaping control are verified by electromagnetic transient simulations in PSCAD.

Automatic classification of sea ice and open water plays a vital role in climate change research, polar shipping, and other applications. Many deep-learning-based methods are proposed to automatically classify sea ice and open water to address this issue. Even though these methods have achieved remarkable success, the noise phenomenon in synthetic aperture radar (SAR) images still causes considerable limitations in the model performance. Meanwhile, these existing methods ignore multiscale global information from large-scale SAR images, which tends to produce misclassification. In this article, we propose a novel multiscale dual attention network (MSDA-Net) for the task. To tackle the first drawback, we introduce the information of relative position and high-pass filtering as two extra channels to reduce the noisy effects. Moreover, we propose a patch dual attention mechanism and embed it into the ConvNeXt blocks to capture the multichannel and spatial features. To address the second problem, we propose a multiscale spatial attention module to capture multiscale global spatial information. The experiments show that the proposed method significantly outperforms state-of-the-art methods. In addition, comprehensive case studies are conducted, which verify the effectiveness of MSDA-Net in different SAR scenes.

Precipitation nowcasting is an important task, which can serve numerous applications such as urban alert and transportation. Previous studies leverage convolutional recurrent neural networks (RNNs) to address the problem. However, they all suffer from two inherent drawbacks of the convolutional RNN, namely, the lack of a memory cell to preserve the fine-grained spatial appearances and the position misalignment issue when combining current observations with previous hidden states. In this article, we aim to overcome the defects. Specifically, we propose a novel pseudo flow spatiotemporal LSTM unit (PFST-LSTM), where a spatial memory cell and a position alignment module are developed and embedded in the structure of LSTM. Upon the PFST-LSTM units, we develop a new sequence-to-sequence architecture for precipitation nowcasting, which can effectively combine the spatial appearances and motion information. Extensive empirical evaluations are conducted on synthetic MovingMNIST++ and CIKM AnalytiCup 2017 datasets. Our experimental results demonstrate the superiority of the proposed PFST-LSTM over the state-of-the-art competitors. To reproduce the results, we release the source code at: https://github.com/luochuyao/PFST-LSTM.

Deep learning tools have been a new way for privacy attacks on remote sensing images. However, since labeled data of privacy objects in remote sensing images are less, the samples for training are commonly small. Besides, traditional deep neural networks have a huge amount of parameters which leads to over complexity of models and have a great heavy of computation. They are not suitable for small sample image classification task. A sparse method for deep neural network is proposed to reduce the complexity of deep learning model with small samples. A singular value decomposition algorithm is employed to reduce the dimensions of the output feature map of the upper convolution layers, which can alleviate the input burden of the current convolution layer, and decrease a large number of parameters of the deep neural networks, and then restrain the number of redundant or similar feature maps generated by the over-complete schemes in deep learning. Experiments with two remote sensing image data sets UCMLU and WHURS show that the image classification accuracy with our sparse model is better than the plain model, which is improving the accuracy by 3%, besides, its convergence speed is faster.

Heterogeneity in gene expression and epigenetic states exists across individual cells. Here, the authors develop scCAT-seq, a technique for simultaneously performing ATAC-seq and RNA-seq within the same single cell.

Sentiment analysis is an important but challenging task. Remarkable success has been achieved on domains where sufficient labeled training data is available. Nevertheless, annotating sufficient data is labor-intensive and time-consuming, establishing significant barriers for adapting the sentiment classification systems to new domains. In this paper, we introduce a Capsule network for sentiment analysis in domain adaptation scenario with semantic rules (CapsuleDAR). CapsuleDAR exploits capsule network to encode the intrinsic spatial part-whole relationship constituting domain invariant knowledge that bridges the knowledge gap between the source and target domains. Furthermore, we also propose a rule network to incorporate the semantic rules into the capsule network to enhance the comprehensive sentence representation learning. Extensive experiments are conducted to evaluate the effectiveness of the proposed CapsuleDAR model on a real world data set of four domains. Experimental results demonstrate that CapsuleDAR achieves substantially better performance than the strong competitors for the cross-domain sentiment classification task.

The task of precipitation nowcasting is significant in the operational weather forecast. The radar echo map extrapolation plays a vital role in this task. Recently, deep learning techniques such as Convolutional Recurrent Neural Network (ConvRNN) models have been designed to solve the task. These models, albeit performing much better than conventional optical flow based approaches, suffer from a common problem of underestimating the high echo value parts. The drawback is fatal to precipitation nowcasting, as the parts often lead to heavy rains that may cause natural disasters. In this paper, we propose a novel interaction dual attention long short-term memory (IDA-LSTM) model to address the drawback. In the method, an interaction framework is developed for the ConvRNN unit to fully exploit the short-term context information by constructing a serial of coupled convolutions on the input and hidden states. Moreover, a dual attention mechanism on channels and positions is developed to recall the forgotten information in the long term. Comprehensive experiments have been conducted on CIKM AnalytiCup 2017 data sets, and the results show the effectiveness of the IDA-LSTM in addressing the underestimation drawback. The extrapolation performance of IDA-LSTM is superior to that of the state-of-the-art methods.

Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hyperspectral images. On the other hand, few approaches make use of both spectral and spatial information simultaneously, which is critical to accurate hyperspectral image classification. This paper presents a novel Synergistic Convolutional Neural Network (SyCNN) for accurate hyperspectral image classification. The SyCNN consists of a hybrid module that combines 2D and 3D CNNs in feature learning and a data interaction module that fuses spectral and spatial hyperspectral information. Additionally, it introduces a 3D attention mechanism before the fully-connected layer which helps filter out interfering features and information effectively. Extensive experiments over three public benchmarking datasets show that our proposed SyCNNs clearly outperform state-of-the-art techniques that use 2D/3D CNNs.

Presently, many users are involved in multiple social networks. Identifying the same user in different networks, also known as anchor link prediction, becomes an important problem, which can serve numerous applications, e.g., cross-network recommendation, user profiling, etc. Previous studies mainly use hand-crafted structure features, which, if not carefully designed, may fail to reflect the intrinsic structure regularities. Moreover, most of the methods neglect the attribute information of social networks. In this paper, we propose a novel semi-supervised network-embedding model to address the problem. In the model, each node of the multiple networks is represented by a vector for anchor link prediction, which is learnt with awareness of observed anchor links as semi-supervised information, and topology structure and attributes as input. Experimental results on the real-world data sets demonstrate the superiority of the proposed model compared to state-of-the-art techniques.

With continuous queries that are used widely in location based mobile social networking services, how to protect the location privacy effectively for continuous query has been a hot topic for researchers. In this paper, we analyze the existing location privacy protection systems and algorithms for location based services; considering their disadvantages of slow responding time and high anonymization costs, we propose a new enhanced greedy cloaking algorithm which predicts a cloaking area at the initial query to be the cloaking region in the whole query lifetime by the comprehensive computation of privacy monitor, quality monitor, and dynamic adjuster. Privacy monitor and quality monitor charge the privacy protection level and service quality degree respectively; dynamic adjuster can adjust the cycle center point dynamically. We employ cycle as cloaking region form which can effectively alleviate the computation overhead. And we compare it with the earlier algorithm on three aspects. The experimental result shows that the enhanced greedy cloaking algorithm is better than the original greedy algorithm on average responding time or anonymization cost.

Textual stream classification has become a realistic and challenging issue since large-scale, high-dimensional, and non-stationary streams with class imbalance have been widely used in various real-life applications. According to the characters of textual streams, it is technically difficult to deal with the classification of textual stream, especially in imbalanced environment. In this paper, we propose a new ensemble framework, clustering forest, for learning from the textual imbalanced stream with concept drift (CFIM). The CFIM is based on ensemble learning by integrating a set of clustering trees (CTs). An adaptive selection method, which flexibly chooses the useful CTs by the property of the stream, is presented in CFIM. In particular, to deal with the problem of class imbalance, we collect and reuse both rare-class instances and misclassified instances from the historical chunks. Compared to most existing approaches, it is worth pointing out that our approach assumes that both majority class and rareclass may suffer from concept drift. Thus the distribution of resampled instances is similar to the current concept. The effectiveness of CFIM is examined in five real-world textual streams under an imbalanced nonstationary environment. Experimental results demonstrate that CFIM achieves better performance than four state-of-the-art ensemble models.