检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhu, Yabin Li, Chenglong Luo, Bin Tang, Jin Wang, Xiao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Institute of Physical Science and Information Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei Anhui China

How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network. To deploy the complementarity of features of all layers, we propose a recursive strategy to densely aggregate these features that yield robust representations of target objects in each modality. In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way. In a specific, we employ the operations of global average pooling and weighted random selection to perform channel scoring and selection, which could remove redundant and noisy features to achieve more robust feature representation. Experimental results on two RGBT tracking benchmark datasets suggest that our tracker achieves clear state-of-the-art against other RGB and RGBT tracking methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning With Localized Generalization Error Model

Multi-Task Learning With Localized Generalization Error Mode...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Wendi Li Yi Zhu Ting Wang Wing W. Y. Ng Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781728128177

In cases, the same or similar network architecture is used to deal with related but different tasks, where tasks come from different statistical distributions in the sample input space and share some common features. Multi-Task Learning (MTL) combines multiple related tasks for training at the same time, so as to learn some shared feature representation among multiple tasks. However, it is difficult to improve each task when statistical distributions of these related tasks are greatly different. This is caused by the difficulty of extracting an effective generalization of feature representation from multiple tasks. Moreover, it also slows down the convergence rate of MTL. Therefore, we propose a MTL method based on the Localized Generalization Error Model (L-GEM). The L-GEM improves the generalization capability of the trained model by minimizing the upper bound of generalization error of it with respect to unseen samples similar to training samples. It also helps to narrow the gap between different tasks due to different statistical distributions in MTL. Experimental results show that the L-GEM speeds up the training process while significantly improves the final convergence results.

关键词： Multi-Task learning Multi-layer perceptron neural network Convolutional neural network Localized generalization error model statistical distribution Religious Missions generalization error Multilayer neural networks Learning Training NETWORK STRUCTURE

来源：评论

学校读者我要写书评

暂无评论

A dynamic level interaction method based on trusted value

引用

Journal of computers (Taiwan) 2019年第1期30卷 142-152页

作者： Zhang, Yong-sheng Fan, Yue-qin Cui, Ran-ran Wei, Yu Department of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China

With the rapid development of the cloud computing, there is a large amount of service providers with low quality in the marketplace. The mendacious service providers cause a serious loss for the users. In order to select an efficient cloud service, it can be trust and meet the user’s privacy protection requirements. In this paper, a dynamic level interaction method based on credible value is indicated. The cloud service providers and cloud users are divided into different dynamic levels according to their historical records. The security level of privacy data is decided according to the users’ trust level. This model introduces the center degree factor to filter the mendacious service and it can get a more accurate service evaluation by limiting the malicious users to make false evaluation for the service and it can control the providers’ access rights to protect the users’ information. The results of simulation experiment show that this model can improve the interaction successful rate and strengthen the safety of user privacy data. It demonstrates the efficiency and effectiveness of our approach in trusted interaction with other counterparts. 2019 © computer Society of the Republic of China. All Rights Reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

A network security entity recognition method based on feature template and CNN-BiLSTM-CRF

引用

Frontiers of information technology & Electronic Engineering 2019年第6期20卷 872-884页

作者： Ya QIN Guo-wei SHEN Wen-bo ZHAO Yan-ping CHEN Miao YU Xin JIN College of Computer Science and Technology Guizhou University Guiyang 550025 China Guizhou Provincial Key Laboratory of Public Big Data Guiyang 550025 China Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing 100029 China

By network security threat intelligence analysis based on a security knowledge graph(SKG), multi-source threat intelligence data can be analyzed in a fine-grained manner. This has received extensive attention. It is difficult for traditional named entity recognition methods to identify mixed security entities in Chinese and English in the field of network security, and there are difficulties in accurately identifying network security entities because of insufficient features extracted. In this paper, we propose a novel FT-CNN-BiLSTM-CRF security entity recognition method based on a neural network CNN-BiLSTM-CRF model combined with a feature template(FT). The feature template is used to extract local context features, and a neural network model is used to automatically extract character features and text global features. Experimental results showed that our method can achieve an F-score of 86% on a large-scale network security dataset and outperforms other methods.

关键词： Network security entity Security knowledge graph (SKG) Entity recognition Feature template Neural network

来源：评论

学校读者我要写书评

暂无评论

Mixed Word Embedding Method Based on Knowledge Graph Augment for Text Classification

Mixed Word Embedding Method Based on Knowledge Graph Augment...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Hongzhong Wang Kun Guo Zhanghui Liu Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou China College of Mathematics and Computer Science Fuzhou University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

This paper presents a self-training word embedding text classification model based on knowledge graph expansion for text classification. Current mixed word embedding methods are overly dependent on the Fasttext pre-training model and here is still a problem of missing words with rich semantic information are not mapped. First, we propose a method for extracting missing nouns based on shape near word filtering. Second, we design a self-training word embedding method based on knowledge graph that mixes with pre-training word embedding to obtain a high-quality mixed word vector with rich semantics and rich semantics. Third, we designed a GRU model based on improved mixed word embedding to improve the quality of text classification. Experiments conducted on multiple text classification datasets demonstrate that our methods can effectively improve the text classification accuracy.

关键词： Text categorization Context modeling Feature extraction Training Task analysis Predictive models

来源：评论

学校读者我要写书评

暂无评论

Estimating crop primary productivity with sentinel-2 and landsat 8 using machine learning methods trained with radiative transfer simulations

arXiv

引用

arXiv 2020年

作者： Wolanin, Aleksandra Camps-Valls, Gustau Gómez-Chova, Luis Mateo-García, Gonzalo van der Tol, Christiaan Zhang, Yongguang Guanter, Luis Section 1.4 Remote Sensing GFZ German Research Centre for Geosciences Helmholtz-Centre Potsdam Germany Image Processing Laboratory Universitat de València València Spain Faculty of ITC University of Twente Enschede Netherlands Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology International Institute for Earth System Sciences Nanjing University Nanjing210023 China

Satellite remote sensing has been widely used in the last decades for agricultural applications, both for assessing vegetation condition and for subsequent yield prediction. Existing remote sensing-based methods to estimate gross primary productivity (GPP), which is an important variable to indicate crop photosynthetic function and stress, typically rely on empirical or semi-empirical approaches, which tend to over-simplify photosynthetic mechanisms. In this work, we take advantage of all parallel developments in mechanistic photosynthesis modeling and satellite data availability for an advanced monitoring of crop productivity. In particular, we combine process-based modeling with the soil-canopy energy balance radiative transfer model (SCOPE) with Sentinel-2 and Landsat 8 optical remote sensing data and machine learning methods in order to estimate crop GPP. With this approach, we by-pass the need for an intermediate step to retrieve the set of vegetation biophysical parameters needed to accurately model photosynthesis, while still accounting for the complex processes of the original physically-based model. Several implementations of the machine learning models are tested and validated using simulated and flux tower-based GPP data. Our final neural network model is able to estimate GPP at the tested flux tower sites with r2 of 0.92 and RMSE of 1.38 gC d−1 m−2, which outperforms empirical models based on vegetation indices. The first test of applicability of this model to Landsat 8 data showed good results (r2 of 0.82 and RMSE of 1.97 gC d−1 m−2), which suggests that our approach can be further applied to other sensors. Modeling and testing is restricted to C3 crops in this study, but can be extended to C4 crops by producing a new training dataset with SCOPE that accounts for the different photosynthetic pathways. Our model successfully estimates GPP across a variety of C3 crop types and environmental conditions even though it does not use any local information from

关键词： Photosynthesis

来源：评论

学校读者我要写书评

暂无评论

A skeleton pattern representation method for anomaly detection in wireless sensor networks 21

A skeleton pattern representation method for anomaly detecti...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Chen, Yanping Yang, Ping Gao, Cong Wang, Zhongmin Yu, Zhong School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an China School of Communications and Information Engineering Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781728120584

Anomaly detection of time series in wireless sensor networks has gained significant attention. Researchers employ representation techniques to reduce the dimensionality of time series. The Piecewise Aggregate Pattern Representation (PAPR) method vertically divides the time series and represents as patterns. However, the computational cost of the PAPR method for anomaly detection is high. To overcome this issue, we propose a time series representation method for anomaly detection called Skeleton Pattern Representation for anomaly detection (SPR-AD). An improved Perceptually Important Point (iPIP) identification algorithm is devised to transform the subsequence into a skeleton with PIPs. Then the skeleton is divided into several equal-sized subspaces in the amplitude domain. Statistical information of the PIPs located in subspaces is constructed to represent the skeleton as a pattern. Based on the two-phase representation scheme, anomaly is determined by anomaly scores which are based on the of similarity among pattern. The experimental results demonstrate the performance of the SPR-AD method is better in terms of computational cost and detection accuracy than the PAPR method. © 2019 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A new parallel simulation method for massive crowd

引用

Procedia computer Science 2019年 147卷 283-287页

作者： Xiukai Zhao Lei Lyu Chen Lyu Cun Ji School of Information Science and Engineering Shandong Normal University Jinan 250014 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan 250014 China

With the advent of multi-core and even many-core processors, massively parallel computing processing has presented a trend of low cost and popularity. It provides new technical means and feasible solutions for the rapid simulation calculation of large-scale group movements and the simulable problem of super-large group movements. In the process of parallel computing, the design of parallel architecture and parallel algorithm is closely related to the group motion simulation algorithm itself due to the original task needs to be decomposed. A parallel simulation algorithm for the continuum crowds has been proposed in this paper. We use the transition block-based scene segmentation algorithm on the management node to divide the simulated scene after initializing the virtual scene, and assign each block to a different computing node for processing. Then, the compute node gets information about the individual it is responsible for. Based on the method, a parallel simulation prototype system was developed on the Sugon high-performance computing platform. Experimental results show that our parallel simulation algorithm can increase the efficiency of scene-rendering and solve the bottleneck in group scale.

关键词： parallel computing massive crowd compute node scene segmentation

来源：评论

学校读者我要写书评

暂无评论

Financial Big Data Hot and Cold Separation Scheme Based on HBase and Redis

Financial Big Data Hot and Cold Separation Scheme Based on H...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Kunhui Li Kun Guo Hong Guo Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining Information Sharing Ministry of Education Fuzhou China College of Mathematics and Computer Science Fuzhou University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

In the era of big data, HBase has been widely used in scenarios of massive unstructured data. For the financial big data, due to the integrity and timing of it, unreasonable data storage and management usually lead to hot spots that decreases the query performance. In practice, the separation of hot and cold financial data will improve data query performance and utilization rate of cluster resources. In this paper, a hot and cold data separation scheme is designed, to store infrequently queried financial data to HBase, and frequently queried one to Redis. The cold data is reasonably planned and managed through pre-partitioning and row key design for HBase. A hot data cache based on Redis is realized to improve the query speed and reduces the pressure of HBase. In addition, due to the lack of Redis's inherent cache elimination strategy, we propose a caching strategy based on the frequencies of updating and querying operations. The experimental results show that the scheme can effectively avoid the hot storage problem, and improve the query performance, and improve the cache hit ratio of Redis. Therefore, the number of cold data access requests can be effectively reduced.

关键词： Big Data Distributed databases Memory Time series analysis Stock markets

来源：评论

学校读者我要写书评

暂无评论

MultiAdapt: A Neural Network Adaptation For Pruning Filters Base on Multi-layers Group

引用

Journal of Physics: Conference Series 2021年第1期1873卷

作者： Jie Yang Zhihong Xie Ping Li School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Hunan Changsha 410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha Hunan Changsha 410114 China

Deep convolutional neural networks have been widely used in various AI applications. The most advanced neural networks are becoming deeper and wider, which has caused some large convolutional neural networks to exceed the size limit of the server or application. The pruning algorithm provides a way to reduce the size of the neural network while keeping the accuracy as high as possible. The automatic progressive pruning algorithm is one of the widely used pruning algorithms. The progressive pruning algorithm prunes a certain layer of the network in each iteration to reduce the sparsity while preserving the accuracy as much as possible. In this article, we design a new automatic progressive pruning algorithm named MultiAdapt. MultiAdapt combines the combination method and the greedy algorithm. This multi-layers progressive pruning method greatly increases the search space of the greedy algorithm, making it possible to obtain a better pruning network. We use MultiAdapt to prune large neural networks VGG-16 and ResNet. The experimental results show that the MultiAdapt algorithm is better than other mainstream methods in the balance of neural network model size and accuracy. For image classification tasks on the ImageNet dataset, our method achieved 88.72% and 90.55% TOP-5 accuracy on the 50% sparsity VGG-16 and ResNet, while obtaining nearly 2×reduction in parameters and floating point numbers. The operation is reduced, and the reduction is higher than the recent popular method.

关键词：

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：