检索结果-内蒙古大学图书馆

arXiv 2023年

作者： You, Zi-Yi Pan, Yun-Rong Ma, Zhi Zhang, Li Xiao, Shuo Zhang, Dan-Dan Dang, Shi-Jun Zhao, Ru-Shuang Wang, Pei Dong, Ai-Jun Jiang, Jia-Tao Leng, Ji-Bing Li, Wei-An Li, Si-Yao School of Physics and Electronic Science Guizhou Normal University Guiyang550025 China College of Big Data and Information Engineering Guizhou University Guiyang550025 China CAS Key Laboratory of FAST National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University Guiyang550025 China School of Big data and Computer Science Guizhou Normal University Guiyang550025 China Guizhou Software Engineering Research Center Guiyang550000 China Key Laboratory of Information and Computing Guizhou Province Guizhou Normal University Guiyang550001 China

Pulsar search is always the basis of pulsar navigation, gravitational wave detection and other research topics. Currently, the volume of pulsar candidates collected by Five-hundred-meter Aperture Spherical radio Telescope (FAST) shows an explosive growth rate that has brought challenges for its pulsar candidate filtering System. Particularly, the multi-view heterogeneous data and class imbalance between true pulsars and non-pulsar candidates have negative effects on traditional single-modal supervised classification methods. In this study, a multi-modal and semi-supervised learning based pulsar candidate sifting algorithm is presented, which adopts a hybrid ensemble clustering scheme of density-based and partition-based methods combined with a feature-level fusion strategy for input data and a data partition strategy for parallelization. Experiments on both HTRU (The High Time Resolution Universe Survey) 2 and FAST actual observation data demonstrate that the proposed algorithm could excellently identify the pulsars: On HTRU2, the precision and recall rates of its parallel mode reach 0.981 and 0.988. On FAST data, those of its parallel mode reach 0.891 and 0.961, meanwhile, the running time also significantly decrease with the increment of parallel nodes within limits. So, we can get the conclusion that our algorithm could be a feasible idea for large scale pulsar candidate sifting of FAST drift scan observation. Copyright © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Scalable Inter-Domain Network Virtualization

SSRN

引用

SSRN 2022年

作者： Sun, Jie Wo, Tianyu Liu, Xudong Ma, Tianjiao Mou, Xudong Lan, Jinghong Zhang, Nan Niu, Jianwei SKLSDE School of Computer Science and Engineering Beihang University Beijing China SKLSDE School of Software Beihang University Beijing China Research Center of Big Data and Computational Intelligence Hangzhou Institute of Beihang University Hangzhou China

To realize inter-domain network virtualization for hybrid cloud, the following challenges must be resolved. (1) Scalability. The network virtualization system should allow tenant virtual networks to use on-demand addressing schema and span multiple domains. This requirement, combined with the expansion of the network scale, can lead to a rapid increase in flow rule consumption, posing a significant challenge for network scalability. (2) Inter-domain network flow scheduling. To allocate bandwidth for inter-domain network flows with low cost and guaranteed bandwidth is complex (NP-hard). Existing researches fail to address this problem in a flexible yet efficient manner. This paper proposes a network virtualization solution that jointly considers the two challenges. Towards the scalability challenge, we use MAC translation to encode location hierarchy and tenant information into MAC addresses, thereby enabling L2 forwarding rule aggregation on each switch. Besides, we offload the L3 virtual network rules onto the first hop software switches and tackle L3 routing through VMAC-based forwarding. We formally prove that our approach can bound the worst-case rule consumption by combining these two techniques. Towards the second challenge, we formulate the inter-domain network flow scheduling (INFOS) problem into an integer linear programming (ILP) problem and prove its NP-hardness. We also propose a heuristic algorithm that can guarantee bandwidth lower- bound while avoiding causing significant profit loss or introducing too many network updates. Evaluation shows that our approach can reduce the average flow rule consumption significantly, compared with state-of-the-art approaches. Besides, towards the same bandwidth guarantee target, we can avoid approximately 95% of the profit loss and 92% of the network update operations. © 2022, The Authors. All rights reserved.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

A novel weighted approach for time series forecasting based on visibility graph

arXiv

引用

arXiv 2021年

作者： Zhan, Tianxiang Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China

Time series has attracted a lot of attention in many fields today. Time series forecasting algorithm based on complex network analysis is a research hotspot. How to use time series information to achieve more accurate forecasting is a problem. To solve this problem, this paper proposes a weighted network forecasting method to improve the forecasting accuracy. Firstly, the time series will be transformed into a complex network, and the similarity between nodes will be found. Then, the similarity will be used as a weight to make weighted forecasting on the predicted values produced by different nodes. Compared with the previous method, the proposed method is more accurate. In order to verify the effect of the proposed method, the experimental part is tested on M1, M3 datasets and Construction Cost Index (CCI) dataset, which shows that the proposed method has more accurate forecasting performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

arXiv

引用

arXiv 2022年

作者： Xu, Jiazhi Huang, Sheng Zhou, Fengtao Huangfu, Luwen Zeng, Daniel Liu, Bo School of Big Data and Software Engineering Chongqing University China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University United States Institute of Automation Chinese Academy of Sciences China ***

Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to model overfitting, thus undermining the performance. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The explainable visual study also further validates that our method is able to learn both the category-specific and co-occurring features. The source code is released at https://***/Robbie-Xu/CPSD. © 2022, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Test-Time Model Adaptation without Forgetting

arXiv

引用

arXiv 2022年

作者： Niu, Shuaicheng Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zheng, Shijian Zhao, Peilin Tan, Mingkui School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Tencent AI Lab China National University of Singapore Singapore Pazhou Laboratory China

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two practical challenges: 1) existing methods have to perform backward computation for each test sample, resulting in unbearable prediction cost to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). In this paper, we point out that not all the test samples contribute equally to model adaptation, and high-entropy ones may lead to noisy gradients that could disrupt the model. Motivated by this, we propose an active sample selection criterion to identify reliable and non-redundant samples, on which the model is updated to minimize the entropy loss for test-time adaptation. Furthermore, to alleviate the forgetting issue, we introduce a Fisher regularizer to constrain important model parameters from drastic changes, where the Fisher importance is estimated from test samples with generated pseudo labels. Extensive experiments on CIFAR-10-C, ImageNet-C, and ImageNet-R verify the effectiveness of our proposed method. Code is available at https://***/mr-eggplant/EATA. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A Parameter Transfer Method for HMM-DNN Heterogeneous Model with the Scarce Mongolian data Set

引用

Procedia Computer Science 2021年 187卷 258-263页

作者： Zhiqiang Ma Junpeng Zhang Tuya Li Rui Yang Hongbin Wang Inner Mongolia University of Technology Hohhot 010080 China Inner Mongolia Autonomous Region Engineering & Technology Research Centre of Big Data Based Software Service Hohhot 010080 China

Hidden Markov Model-Deep Neural Network (HMM-DNN) is one of the most successful architecture in speech recognition. Although the HMM-DNN achieved state-of-the-art results on English and Mandarin, we find that there are lots of not updated parameters during the training of HMM-DNN acoustic model on a small scale Mongolian data set. This caused the model’s network training underfitting, which cannot learn the features of the data set. In the speech recognition scenario, the underfitting of speech features leads to a problem that the accuracy of the system decreases. In this regard, we define the concept of the homogeneous model heterogeneous model and propose a parameter learning method for HMM-DNN heterogeneous model in the scarce Mongolian data set. In our experiment, we choose KALDI as the experimental platform with the TIMIT English data set as the source data set and the scarce Mongolian data set as the target data set. Through the proposed parameter transfer method, we achieved much better performance on Mongolian recognition accuracy.

关键词： HMM-DNN Model Homogeneous Model Heterogeneous Model Parameter Transfer Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Interpretation Area-Guided Detection of Adversarial Samples 20

Interpretation Area-Guided Detection of Adversarial Samples

引用

20th IEEE International Conference on software Quality, Reliability, and Security, QRS 2020

作者： Wei, JiaLi Fan, Ming Xu, Xi Jia, Ang Xu, Zhou Xue, Lei School of Cyber Science and Engineering Xi'an Jiaotong University China School of Big Data and Software Engineering Chongqing University China The Hong Kong Polytechnic University Department of Computing China

ISBN: (纸本)9781728189154

Deep learning systems are known to be vulnerable to adversarial samples, which are implemented to change the prediction results by adding small perturbations to benign samples. It is significant to defend against an adversarial attack in critical fields such as automatic drive. In this paper, we propose an interpretation area-guided detection method of adversarial samples, which can improve the performance of the typical feature squeezing method by combining the generated interpretation results. Specifically, we divide the input image into two main parts, the interpretation part, and the non-interpretation part. Then we only squeeze the non-interpretation part, which can reduce the side-effect for benign samples. We evaluate our approach on two widely used datasets, and the results demonstrate that our approach outperforms the original feature squeezing method. © 2020 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

arXiv

引用

arXiv 2023年

作者： Wen, Xin-Cheng Chen, Yupan Gao, Cuiyun Zhang, Hongyu Zhang, Jie M. Liao, Qing School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Big Data and Software Engineering Chongqing University China Department of Informatics King’s College London United Kingdom Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies China Peng Cheng Laboratory China

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs;2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Empirical Research on Cluster Analysis of Spectral Information of Hyperspectral Remote Sensing data 13

Empirical Research on Cluster Analysis of Spectral Informati...

引用

2020 IEEE Congress on Cybermatics: 13th IEEE International Conferences on Internet of Things, iThings 2020, 16th IEEE International Conference on Green Computing and Communications, GreenCom 2020, 13th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2020 and 6th IEEE International Conference on Smart data, Smartdata 2020

作者： Dong, Yueyu Dai, Fei Xu, Xiaolong Qin, Mingming Qiang, Zhenping School of Big Data and Intellegent Engineering Southwest Forestry University Kunming China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9781728176475

The most notable features of hyperspectral remote sensing data are high spectral resolution and high dimensionality. Analyzing the spectral information of the data with clustering requires proper spectral measurements. And clustering results validating methods satisfy high-dimensional data are required. In this paper, three clustering algorithms of K-means, K-means++, and Chameleon were used in the empirical research, based on the famous data set of IndianPine. In the experiments, four spectral measures of SBD, SID, SSD and SPM were used as spectral similarity measures, and S-Dbw was chosen as clustering validating method. As S-Dbw is a relative validating index, the algorithms with different parameter combinations had been experimented many times, verified the effectiveness of the solution composed with selected clustering methods, spectral measures, and clustering validating method. Experimental results showed that hyperspectral information enhanced the ability to distinguish ground objects;Chameleon's performance was best, and S-Dbw could effectively analyze hyperspectral data;the performance of the spectral measurements showed a certain correlation with the clustering method. © 2020 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluating deep graph neural networks

arXiv

引用

arXiv 2021年

作者： Zhang, Wentao Sheng, Zeang Jiang, Yuezihan Xia, Yikuan Gao, Jun Yang, Zhi Cui, Bin School of EECS Key Laboratory of High Confidence Software Technologies Peking University Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications

Graph Neural Networks (GNNs) have already been widely applied in various graph mining tasks. However, they suffer from the shallow architecture issue, which is the key impediment that hinders the model performance improvement. Although several relevant approaches have been proposed, none of the existing studies provides an in-depth understanding of the root causes of performance degradation in deep GNNs. In this paper, we conduct the first systematic experimental evaluation to present the fundamental limitations of shallow architectures. Based on the experimental results, we answer the following two essential questions: (1) what actually leads to the compromised performance of deep GNNs;(2) when we need and how to build deep GNNs. The answers to the above questions provide empirical insights and guidelines for researchers to design deep and well-performed GNNs. To show the effectiveness of our proposed guidelines, we present Deep Graph Multi-Layer Perceptron (DGMLP), a powerful approach (a paradigm in its own right) that helps guide deep GNN designs. Experimental results demonstrate three advantages of DGMLP: 1) high accuracy - it achieves state-of-the-art node classification performance on various datasets;2) high flexibility - it can flexibly choose different propagation and transformation depths according to graph size and sparsity;3) high scalability and efficiency - it supports fast training on large-scale graphs. Our code is available in https://***/zwt233/DGMLP. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：