检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Niu, Yan State Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China

Digital cameras that use Color Filter Arrays (CFA) entail a demosaicking procedure to form full RGB images. As today's camera users generally require images to be viewed instantly, demosaicking algorithms for real applications must be fast. Moreover, the associated cost should be lower than the cost saved by using CFA. For this purpose, we revisit the classical Hamilton-Adams (HA) algorithm, which outperforms many sophisticated techniques in both speed and accuracy. Based on a close look at HA's strength and weakness, we design a very low cost edge sensing scheme. Briefly, it guides demosaicking by a logistic functional of the difference between directional variations. We extensively compare our algorithm with 28 demosaicking algorithms by running their open source codes on benchmark datasets. Compared to methods of similar computational cost, our method achieves substantially higher accuracy;Whereas compared to methods of similar accuracy, our method has significantly lower cost. Moreover, on test images of currently popular resolution, the quality of our algorithm is comparable to top performers, whereas its speed is tens of times faster. Copyright © 2018, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

A Method for Authenticity Identification of Fritillaria Cirrhosa D. Don Based on Deep Learning 4

A Method for Authenticity Identification of Fritillaria Cirr...

引用

4th IEEE International Conference on Image, Vision and Computing, ICIVC 2019

作者： Hu, Ke Hu, Pan Cao, Dong Yan, Xin Yu, Xi Liu, Chang Chengdu University College of Information Science and Engineering Chengdu China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu China Research Institute of Big Data Chengdu University China Chengdu Institute of Chinese Herbal Medicine China

ISBN: (纸本)9781728123257

Since the authentic Fritillaria Cirrhosa D. Don resources are scarce due to its high price and valuable medical uses, it is difficult to meet the clinical needs. Therefore, the problem of adulteration in the market is more and more serious. At present, the identification of Fritillaria mainly relies on traditional trait identification, microscopic identification, physical and chemical identification and other methods, which is subjective and requires high practical experience for operators, and the pretreatment work is cumbersome. In this paper, the concept of deep learning is introduced into the identification of Fritillaria for the first time. First, we have created the first multi-angle Fritillaria standard datasets, including Fritillaria Cirrhosa D. Don and Fritillary bulb. We then have proposed a novel deep learning framework SE-DPU to classify Fritillaria datasets, from which we can get the highest classification accuracy. The framework is a hybrid of Squeeze-and-Excitation block (SE unit), U-Net and Dual Path Network (DPN). It reuses the features and explores the new features adaptively recalibrates channel-wise feature responses obtains abundance features while training. Experimental results with Fritillaria Cirrhosa D. Don data have indicated that the proposed method have provided competitive performance. © 2019 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An improved FOO voting scheme using blockchain

An improved FOO voting scheme using blockchain

引用

作者： Zhou, Yuanjian Liu, Yining Jiang, Chengshun Wang, Shulan College of Computer Science and Technology Henyang Normal University Henyang421002 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing408100 China College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China

The traditional FOO e-voting protocols adopt centralized and non-transparent count center, which leads to distrust to the center and doubts the fairness and correctness of the vote. However, blockchain is the most innovative technology in the current era and promises to solve the trust problem in the system with one center. In this paper, an improved FOO e-voting protocol is proposed using blockchain, which tries to address the limitation or weakness in existing systems. The traditional trusted third party is replaced by smart contract;specifically, our scheme is deployed using hyperledger fabric. The implementation is enforced by the consensus mechanism, which ensures the security of the blockchain. Through the analysis, the proposed scheme is proved to satisfy the necessary requirements for an e-voting protocol;meantime the trust assumption is reduced significantly. Therefore, the proposed protocol is more versatile and practical. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Joint Event Extraction Model based on Multi-feature Fusion 8

Joint Event Extraction Model based on Multi-feature Fusion

引用

8th International Conference on Identification, Information and knowledge in the Internet of Things, IIKI 2019

作者： Wang, Shuo Rao, Yuan Fan, Xiaobing Qi, Jiangnan Research Institute of Xi’an Jiaotong University Shenzhen China Lab of Social Intelligence and Complex Data Precessiong School of Software Engineering Xi’an Jiao Tong University Xi’an China Shaanxi Joint Key Laboratory for Artifact Intelligence Xi’an Jiaotong University Xi’an China

Event extraction is a challenging problem in information extraction, designed to extract structured information from unstructured text. The existing event extraction methods are mostly based on the pipeline model and use the traditional language representation model for word embedding. It is impossible to model the polysemy and the features is very simple, besides, the pipeline model is also easy to generate cascading errors. Aiming at the above problems, we propose a joint event extraction model, which combines part-of-speech features, entity features and word representation of BERT model. Because of the BERT can't capture local features, we use multi-CNN to capture the local features of different scales. and further use BiLSTM to capture context features to assist joint event extraction. Experimental results show that the precision, recall and F1 of the method on the CEC dataset are 88.83%, 90.91% and 89.86%, respectively, which are 1.61%, 3.6% and 2.6% higher than the PLMEE model. © 2020 The Authors. Published by Elsevier B.V.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Review on Fault Diagnosis Techniques for Distributed Parameter Systems

Review on Fault Diagnosis Techniques for Distributed Paramet...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Qiang Wang Kaixiang Peng Xuerui Cao Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781665401166

Fault diagnosis for distributed parameter systems (DPSs) is reviewed in this paper. Firstly, the difficulty and significance of fault diagnosis in DPSs are introduced, and the fault detection methods are classified from the view of time-space separation. Their basic ideas, research progresses, application and limitation are discussed in detail. Furthermore, considering the spatial distribution characteristics of the systems, researches on fault isolation and fault location in DPSs are summarized briefly. Finally, combined with the problems existing in the fault diagnosis of DPSs, we conclude this paper by pointing out several promising research topics on it.

关键词： Industries Parameter estimation Graphical models Fault detection Fault location Reliability theory Safety

来源：评论

学校读者我要写书评

暂无评论

How to Make Information-Flow Analysis Based Defense Ineffective: An ART Behavior-Mask Attack 20th

How to Make Information-Flow Analysis Based Defense Ineffect...

引用

20th International Conference on Information Security, ISC 2017

作者： Yang, Xueyi Liu, Limin Zhang, Lingchen Jiang, Weiyu Pan, Shiran School of Cyber Security University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783319696584

Android permission mechanism cannot resist permission abuse, the key of malware detection is to expose its malicious behavior. Although plentiful transformation attacks are used to bypass malware detection, the latest information-flow analysis based defenses claim that they can identify malicious flows with high accuracy. Nevertheless, in this paper, we expose a new attack surface known as Behavior-Mask attack in Android Runtime (ART), which can bypass most known information-flow analysis based defenses in practice. Our attack techniques can be utilized to hide Android applications’ actual behavior by only executing some irrelevant Java code in the normal way. We corrupt few runtime data through a small piece of JNI code to hijack the control flow and data flow of Java code dynamically in ART environment. Further, we implement an automatic development framework to demonstrate the viability of Behavior-Mask attack. We analyze the existing defenses on Android and traditional desktop operating systems, and put forward some new ideas for the design and implementation of future defenses against the proposed attack. © 2017, Springer International Publishing AG.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

A diversity-guided heuristic-based genetic algorithm for triangulation of Bayesian networks

A diversity-guided heuristic-based genetic algorithm for tri...

引用

International Conference on Networked Computing and Advanced Information Management (NCM)

作者： Xuchu Dong Haihong Yu Dantong Ouyang Yuxin Ye Yonggang Zhang Department of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun Jilin China

ISBN: (纸本)9781424476718

For the optimization problem about triangulation of Bayesian networks, a novel genetic algorithm, DHGA, is proposed in this paper. DHGA employs a heuristic-based mutation operation. Moreover, it uses population diversity to identify stagnation and convergence as well as to guide the search procedure. Experiments on representative benchmarks show that DHGA posses better performance and robustness than other swarm intelligence methods.

关键词： Bayesian methods

来源：评论

学校读者我要写书评

暂无评论

Redactable Blockchain Using Lattice-based Chameleon Hash Function

Redactable Blockchain Using Lattice-based Chameleon Hash Fun...

引用

2022 International Conference on Blockchain Technology and Information Security, ICBCTIS 2022

作者： Peng, Chunying Xu, Haixia Li, Peili Sklois Institute of Information Engineering Cas Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Cas Beijing China Guangxi Key Laboratory of Cryptography and Information Security Guilin China

ISBN: (数字)9781665496919

ISBN: (纸本)9781665496919

Blockchain as a tamper-proof, non-modifiable and traceable distributed ledger technology has received extensive attention. Although blockchain's immutability provides security guarantee, it prevents the development of new blockchain technology. As we think, there are several arguments to prefer a controlled modifiable blockchain, from the possibility to cancel the transaction and necessity to remove the illicit or harmful documents, to the ability to support the scalability of blockchain. Meanwhile, the rapid development of quantum technology has made the establishment of post-quantum cryptosystems an urgent need. In this paper, we put forward the first lattice-based redactable consortium blockchain scheme that makes it possible to rewrite or repeal the content of any blocks. Our approach uses a consensus-based election and lattice-based chameleon hash function (Cash and Hofheinz etc. EUROCRYPT 2010). With knowledge of secret trapdoor, the participant could find the hash collisions efficiently. And each member of the consortium blockchain has the right to edit the history. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Fish freshness evaluation based on MobileNetV1 and attention mechanism 22

Fish freshness evaluation based on MobileNetV1 and attention...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer engineering

作者： Xin Guo Shenming Gu Dan Wei School of Information Engineering Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province China

ISBN: (纸本)9781450397148

Rapid acquisition of fish freshness is an important task. The traditional freshness detection of aquatic fish has the problems of damaging samples, complicated operation and long detection time. A convenient, rapid, nondestructive and accurate freshness detection method is urgently needed in production. In this study, the freshness of aquatic fish was evaluated nondestructively and rapidly by machine vision. Firstly, we select the appropriate data set, and add the attention mechanism module to the end of the MobileNetV1 with the default alpha value. Secondly, the alpha value of all models is reduced to compare the performance for subsequent deployment to the cloud and small embedded devices with limited resources. Finally, the network is trained by real data. The results show that the MobilenetV1 network with attention mechanism module can better evaluate the freshness of fish through the fisheye image. The convergence speed and accuracy of the network are improved compared with the original network, and it is more suitable for the task of determining the freshness of fish through fisheye.

关键词： image recognition attention mechanism freshness evaluation deep learning fisheye

来源：评论

学校读者我要写书评

暂无评论

Survey of active learning for networked data

Survey of active learning for networked data

引用

2015 4th National Conference on Electrical,Electronics and Computer engineering(NCEECE 2015)

作者： Xinlei Wang Bo Yang Jing Huang The College of Computer Science and Technology Jilin University The College of Computer Science and Technology Key laboratory of Symbolic Computation and knowledge EngineeringJilin University

ISBN: (纸本)9781510819085

Classification in networked data is a popular research of complex network. Because of the large scale of networked data and the shortage of training data, active learning, which is an effective classification method for sparse data in machine learning, is often applied to networked data classification problems. Introduced in this paper are classification methods based on active learning for networked data classification problems with basic concepts and algorithms. Finally, according to the existing research, some problems for the future developing and research of networked data classification issues is presented.

关键词： Active Learning Networked data Classification Machine Learning

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：