Seismic data interpolation using nonlocal self-similarity prior
作者:
Niu, Xiao;Fu, Lihua;Fang, Wenqian;Wang, Qin;Zhang, Meng
期刊:
GEOPHYSICS ,2023年88(1):WA65-WA80 ISSN:0016-8033
通讯作者:
Fu, Lihua(lihuafu@cug.edu.cn)
作者机构:
[Fang, Wenqian; Fu, Lihua; Niu, Xiao] China Univ Geosci Wuhan, Sch Math & Phys, Wuhan, Peoples R China.;[Wang, Qin] Hainan Med Univ, Coll Biomed Informat & Engn, Haikou, Peoples R China.;[Zhang, Meng] Cent China Normal Univ, Dept Comp Sci, Wuhan, Peoples R China.
关键词:
interpolation;reduced-rank filtering;signal processing
摘要:
The use of a nonlocal self-similarity (NSS) prior, which refers to each reference patch always having many nonlocal similar patches, has demonstrated its effectiveness in seismic data random noise attenuation because of the repetitiveness of textures and structures in their global position. However, NSS-based approaches face challenges when dealing with seismic interpolation. In the presence of missing traces, similar patch matching may be highly unreliable, resulting in a limited performance of interpolation. To solve this problem, a two-stage iterative seismic-interpolation framework based on a rank-reduction (RR) algorithm is developed. In the first stage, preinterpolation seismic data are used to guide the similar patch matching, and the problem of missing trace recovery for the stacked matched patches is converted to the problem of low-rank matrix completion. In the second stage, the similar patches are directly searched on the interpolation result after stage 1 without external help; that is, exploiting its own NSS, which can achieve enhanced interpolation performance. For each iteration, we obtain accurate similarly matched groups and apply a simple and efficient truncated singular value decomposition for RR. Owing to the unique construction method of a low-rank matrix formed by similar patches, our approach can handle irregularly or regularly sampled seismic data. Numerical experiments verify the effectiveness of our method, compared with the curvelet, low-rank matrix fitting, and f-x prediction filtering methods. © 2023 Society of Exploration Geophysicists.
语种:
英文
展开
A training sample selection method for predicting software defects
作者:
Jin, Cong
期刊:
Applied Intelligence ,2023年53(10):12015-12031 ISSN:0924-669X
通讯作者:
Jin, Cong(jincong@ccnu.edu.cn)
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构:
[Cong Jin] S;School of Computer, Central China Normal University, Wuhan, People’s Republic of China
关键词:
Software defect prediction;Sample contribution;Sample selection;Predictive performance
摘要:
Software Defect Prediction (SDP) is an important method to analyze software quality and reduce development cost. Data from software life cycle has been widely used to predict the defect prone of software modules, and although many machine learning-based SDP models have been proposed, their predictive performance is not always satisfactory. Traditional machine learning-based classifiers usually assume that all samples have the same contribution to the training of SDP, which is not true. In fact, different training samples have different effects on the performance of the SDP model, the performance of machine learning-based SDP models is heavily dependent on the quality of training samples. For the above shortcoming of traditional machine learning-based classifiers, the contributions of this paper are as follows: (1) Inspired by the clustering algorithm, a method to calculate the contribution of each training sample to the SDP model is proposed, which not only considers the relationship between the contributions of the training samples to the SDP model, and also analyzes the influence of the distance between the sample and the category boundary on the performance of the SDP model, so it is different from the existing calculation method of sample contribution. (2) A Sample Selection (SS) method is proposed to improve the performance of the SDP model. It first calculates the contribution of each training sample based on several nearest neighbors of the sample and the label information of these neighbors, and then implements SS according to Hoeffding probability inequality and the contribution of each sample. To confirm the validity of the proposed SDP model, some experimental results are given. Both direct observations and statistical tests of the experimental results show that the SS method is very effective for improving the predictive performance of the SDP model. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
语种:
英文
展开
基于角色信息引导的多轮事件论元抽取
作者:
于媛芳;张勇;左皓阳;张连发;王婷婷
期刊:
北京大学学报(自然科学版) ,2023年59(1):83-91 ISSN:0479-8023
通讯作者:
Zhang, Yong(ychang@ccnu.edu.cn)
作者机构:
[于媛芳; 张勇; 左皓阳; 张连发; 王婷婷] School of Computer, Central China Normal University, Wuhan;430079, China;[于媛芳; 张勇; 左皓阳; 张连发; 王婷婷] 430079, China
通讯机构:
[Zhang, Y.] S;School of Computer, China
关键词:
事件论元抽取;角色知识;信息融合;多轮抽取
摘要:
针对通用领域的事件论元抽取研究中角色信息利用不足和论元间缺少交互两个问题, 提出角色信息引导的多轮事件论元抽取模型, 以增强文本的语义信息和论元之间的交互能力, 从而提升事件论元抽取的性能。首先, 为了更好地利用角色知识来引导论元的抽取, 该模型根据角色定义构造角色知识, 对角色信息和文本独立编码, 并采用基于注意力机制的方法获取标签知识增强的文本表示, 进而采用增强嵌入来预测各角色论元的起始和结束位置。同时, 为了在抽取过程中充分利用事件论元之间的交互作用, 受多轮对话模型的启发, 设计一种多轮事件论元抽取算法, 该算法参照“先易后难”的自然逻辑, 每次选择预测概率最大也即最容易确定的角色进行抽取。在论元抽取过程中, 为了对论元之间的交互进行建模, 模型引入历史嵌入, 并在每一次预测结束后更新历史嵌入, 帮助下一轮事件论元的抽取。实验结果表明, 角色信息的引导和多轮抽取算法均有效地提升了论元抽取的性能, 使得该模型的表现优于其他基线模型。
语种:
中文
展开
MDNN: Predicting Student Engagement via Gaze Direction and Facial Expression in Collaborative Learning
作者:
Chen, Yi;Zhou, Jin;Gao, Qianting;Gao, Jing;Zhang, Wei
期刊:
工程与科学中的计算机建模(英文) ,2023年136(1):381-401 ISSN:1526-1492
通讯作者:
Chen, Yi(chenyi30@ccnu.edu.cn)
作者机构:
[Chen, Yi; Zhou, Jin; Gao, Jing] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Gao, Qianting] Rensselaer Polytech Inst, Sch Sci, Comp Sci, Troy, NY 12180 USA.;[Zhang, Wei] Cent China Normal Univ, Natl Engn Lab Educ Big Data Applicat Technol, Wuhan 430079, Peoples R China.
通讯机构:
[Chen, Y.] S;School of Computer Science, China
关键词:
deep network;Engagement;facial expression;gaze
摘要:
Prediction of students’ engagement in a Collaborative Learning setting is essential to improve the quality of learning. Collaborative learning is a strategy of learning through groups or teams. When cooperative learning behavior occurs, each student in the group should participate in teaching activities. Researchers showed that students who are actively involved in a class gain more. Gaze behavior and facial expression are important nonverbal indicators to reveal engagement in collaborative learning environments. Previous studies require the wearing of sensor devices or eye tracker devices, which have cost barriers and technical interference for daily teaching practice. In this paper, student engagement is automatically analyzed based on computer vision. We tackle the problem of engagement in collaborative learning using a multi-modal deep neural network (MDNN). We combined facial expression and gaze direction as two individual components of MDNN to predict engagement levels in collaborative learning environments. Our multi-modal solution was evaluated in a real collaborative environment. The results show that the model can accurately predict students’ performance in the collaborative learning environment. © 2023 Tech Science Press. All rights reserved.
语种:
英文
展开
Fog-enabled private blockchain-based identity authentication scheme for smart home
作者:
Xu, Xianbin;Guo, Yajun;Guo, Yimin
期刊:
Computer Communications ,2023年205:58-68 ISSN:0140-3664
通讯作者:
Guo, YJ
作者机构:
[Guo, Yajun; Xu, Xianbin] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Guo, Yimin] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan, Peoples R China.
通讯机构:
[Guo, YJ ] C;Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
关键词:
Authentication;Fog node;Privacy protection;Private blockchain;Smart home
摘要:
As the Internet of Things (IoT) technology continues to advance, it has found widespread application in various fields, including smart health, smart cities, and smart transportation. Among these applications, smart homes are particularly noteworthy due to their intimate connection to our daily lives. However, the use of smart devices in a home environment exposes users to various security threats, such as impersonation attacks and insider privilege attacks, as users must communicate with multiple devices through a public channel. Additionally, traditional authentication schemes that rely on trusted third-party present a single point of failure, as users and smart devices must be registered and authenticated by a central authority. Blockchain technology offers a decentralized, tamper-proof, and flexible solution for authentication and access control of data. By using blockchain, the single point of failure problem in traditional authentication schemes can be resolved. In the context of smart homes, the real-time nature of the environment necessitates the use of fog nodes to provide localized computing services. Fog nodes are closer to IoT devices than cloud nodes, making fog computing more efficient and faster than cloud computing. This paper proposes an authentication scheme for blockchain-enabled fog nodes in smart homes. The scheme involves registering all fog nodes and intelligent devices on a local private blockchain, and authentication is performed jointly by smart contracts on the blockchain and off-chain operations. The scheme provides comprehensive security and better performance, as demonstrated by security analysis and performance evaluation. Moreover, the proposed scheme offers a certain level of user privacy protection. © 2023 Elsevier B.V.
语种:
英文
展开
Heterogeneous Network Embedding: A Survey
作者:
Zhao, Sufen;Peng, Rong;Hu, Po;Tan, Liansheng
期刊:
工程与科学中的计算机建模(英文) ,2023年137(1):83-130 ISSN:1526-1492
通讯作者:
Peng, Rong(rongpeng@whu.edu.cn)
作者机构:
[Peng, Rong; Zhao, Sufen] Wuhan Univ, Sch Comp Sci, Wuhan 430072, Peoples R China.;[Hu, Po; Tan, Liansheng; Zhao, Sufen] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Peng, R.] S;School of Computer Science, China
关键词:
graph neural networks;Heterogeneous information networks;heterogeneous network embedding;machine learning;representation learning
摘要:
Real-world complex networks are inherently heterogeneous; they have different types of nodes, attributes, and relationships. In recent years, various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks (HINs) into low-dimensional embeddings; this task is called heterogeneous network embedding (HNE). Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification, recommender systems, and information retrieval. Here, we provide a comprehensive survey of key advancements in the area of HNE. First, we define an encoder-decoder-based HNE model taxonomy. Then, we systematically overview, compare, and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks. We also summarize the application fields, benchmark datasets, open source tools, and performance evaluation in the HNE area. Finally, we discuss open issues and suggest promising future directions. We anticipate that this survey will provide deep insights into research in the field of HNE. © 2023 Tech Science Press. All rights reserved.
语种:
英文
展开
Optical flow for video super-resolution: a survey
作者:
Tu, Zhigang;Li, Hongyan;Xie, Wei;Liu, Yuanzhong;Zhang, Shifu;...
期刊:
Artificial Intelligence Review ,2022年55(8):6505-6546 ISSN:0269-2821
通讯作者:
Tu, Zhigang(tuzhigang@whu.edu.cn)
作者机构:
[Zhang, Shifu; Liu, Yuanzhong; Tu, Zhigang] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Peoples R China.;[Li, Hongyan] Hubei Univ Econ, Sch Informat Engn, Wuhan, Peoples R China.;[Xie, Wei] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Zhang, Shifu; Li, Baoxin] Arizona State Univ, Sch Comp Informat Decis Syst Engn, Tempe, AZ USA.;[Zhang, Shifu; Yuan, Junsong] SUNY Buffalo, Comp Sci & Engn Dept, Buffalo, NY USA.
通讯机构:
[Zhigang Tu] S;State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China
关键词:
Video super-resolution;Optical flow;Optical Flow-based video super-resolution;Temporal dependency
摘要:
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion compensation, which is used to estimate the displacement between successive video frames for temporal alignment. Optical flow, which can supply dense and sub-pixel motion between consecutive frames, is among the most common ways for this task. To obtain a good understanding of the effect that optical flow acts in video super-resolution, in this work, we conduct a comprehensive review on this subject for the first time. This investigation covers the following major topics: the function of super-resolution (i.e., why we require super-resolution); the concept of video super-resolution (i.e., what is video super-resolution); the description of evaluation metrics (i.e., how (video) super-resolution performs); the introduction of optical flow based video super-resolution; the investigation of using optical flow to capture temporal dependency for video super-resolution. Prominently, we give an in-depth study of the deep learning based video super-resolution method, where some representative algorithms are analyzed and compared. Additionally, we highlight some promising research directions and open issues that should be further addressed. © 2022, The Author(s), under exclusive licence to Springer Nature B.V.
语种:
英文
展开
A multi-dimension traceable privacy-preserving prevention and control scheme of the COVID-19 epidemic based on blockchain
作者:
Yao, Shixiong;Jing, Pujie;Li, Pei;Chen, Jiageng
期刊:
Connection Science ,2022年34(1):1654-1677 ISSN:0954-0091
通讯作者:
Chen, Jiageng(jiageng.chen@mail.ccnu.edu.cn)
作者机构:
[Li, Pei; Jing, Pujie; Yao, Shixiong; Chen, Jiageng] Cent China Normal Univ, Comp Sch, Wuhan, Hubei, Peoples R China.
通讯机构:
[Jiageng Chen] C;Computer School, Central China Normal University, Wuhan, Hubei, People's Republic of China
关键词:
Health QR code;HyperLedger Fabric;CP-ABE;searchable encryption
摘要:
The outbreak of COVID-19 has brought great pain to people around the world. As an epidemic prevention and control measure, the health QR code (HC)has been designed to trace the confirmed cases and close contacts quickly. Although some existing health code schemes preserve the privacy, but most of them are either unsupported for fine-grained auditability or centralised health code storage. Therefore, we propose a multi-dimension traceable privacy-preserving HC scheme based on blockchain. It prevents health code information being tampered with and supports the traceability of virus transmission chain. We utilise attribute-based encryption to protect residents' privacy information and achieve fine-grained access control. Furthermore, to support the multi-dimension traceability by the epidemic prevention and control departments, the searchable encryption has been introduced. Finally, we give the security analysis and performance evaluation to verify the feasibility and practical significance of our scheme. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
语种:
英文
展开
Generating Factoid Questions with Question Type Enhanced Representation and Attention-based Copy Mechanism
作者:
Hu, Yue;Yang, Haitong;Zhou, Guangyou;Huang, Jimmy Xiangji
期刊:
ACM Transactions on Asian and Low-Resource Language Information Processing ,2022年21(2) ISSN:2375-4699
通讯作者:
Zhou, GY
作者机构:
[Yang, Haitong; Zhou, Guangyou; Zhou, GY; Hu, Yue] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Huang, Jimmy Xiangji] York Univ, Sch Informat Technol, 4700 Keele St, Toronto, ON, Canada.
通讯机构:
[Zhou, GY ] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
关键词:
knowledge base;question answering;Question generation;text generation
摘要:
Question generation over knowledge bases is an important research topic. How to deal with rare and low-frequency words in traditional generation models is a key challenge for question generation. Although the copy mechanism provides significant performance improvements, the original copy mechanism weakens the focus on aspect generation in the overall representations. In this article, we present a novel method to improve question generation with a question type enhanced representation and attention-based copy mechanism. The proposed method exploits the advantages of the generate mode in the copy mechanism and replaces objects in the factual triples with question types, which attempts to improve the output quality in the generate mode and effectively generate questions with proper interrogative words. We evaluate the proposed method on two standard benchmark datasets. The experimental results demonstrate that our proposed method can produce higher-quality questions than these of the Encoder-Decoder-based and CopyNet-based methods. © 2022 Association for Computing Machinery.
语种:
英文
展开
Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment
作者:
Xie, Zhiwen;Zhu, Runjie;Zhao, Kunsong;Liu, Jin;Zhou, Guangyou;...
期刊:
ACM Transactions on Information Systems ,2022年40(3):1–30 ISSN:1046-8188
通讯作者:
Liu, Jin(jinliu@whu.edu.cn)
作者机构:
[Liu, Jin; Xie, Zhiwen; Zhao, Kunsong] Wuhan Univ, Sch Comp Sci, Wuhan, Peoples R China.;[Zhu, Runjie] York Univ, Lassonde Sch Engn, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON, Canada.;[Zhu, Runjie] AI Singapore, Singapore, Singapore.;[Zhou, Guangyou] Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.;[Huang, Jimmy Xiangji] York Univ, Sch Informat Technol, Informat Retrieval & Knowledge Management Res Lab, Toronto, ON, Canada.
通讯机构:
[Liu, J.] S;School of Computer Science, Wuhan University, Wuhan, China
关键词:
Knowledge graph;cross graph attention;entity alignment;iterative
摘要:
Cross-lingual entity alignment has attracted considerable attention in recent years. Past studies using conventional approaches to match entities share the common problem of missing important structural information beyond entities in the modeling process. This allows graph neural network models to step in. Most existing graph neural network approaches model individual knowledge graphs (KGs) separately with a small amount of pre-Aligned entities served as anchors to connect different KG embedding spaces. However, this characteristic can cause several major problems, including performance restraint due to the insufficiency of available seed alignments and ignorance of pre-Aligned links that are useful in contextual information in-between nodes. In this article, we propose DuGa-DIT, a dual gated graph attention network with dynamic iterative training, to address these problems in a unified model. The DuGa-DIT model captures neighborhood and cross-KG alignment features by using intra-KG attention and cross-KG attention layers. With the dynamic iterative process, we can dynamically update the cross-KG attention score matrices, which enables our model to capture more cross-KG information. We conduct extensive experiments on two benchmark datasets and a case study in cross-lingual personalized search. Our experimental results demonstrate that DuGa-DIT outperforms state-of-The-Art methods. © 2021 Association for Computing Machinery.
语种:
英文
展开
Improving generality and accuracy of existing public development project selection methods: a study on GitHub ecosystem
作者:
Cheng, Can;Li, Bing* ;Li, Zengyang;Liang, Peng;Han, Xiaofeng;...
期刊:
Automated Software Engineering ,2022年29(1):1-43 ISSN:0928-8910
通讯作者:
Li, Bing;Liang, P
作者机构:
[Han, Xiaofeng; Zhang, Jiahua; Cheng, Can; Liang, Peng; Li, Bing; Li, B] Wuhan Univ, Sch Comp Sci, Wuhan, Peoples R China.;[Li, Zengyang] Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.
通讯机构:
[Liang, P ; Li, B] W;Wuhan Univ, Sch Comp Sci, Wuhan, Peoples R China.
关键词:
Open source software project;GitHub;Public development project
摘要:
With available tools and datasets existing on GitHub ecosystem, researchers have the opportunities to study diverse software engineering problems on a large-scale dataset. However, there are many potential threats when researchers try to directly use large-scale datasets, and one important threat is that GitHub contains many private projects (e.g., homework) and non-development projects (e.g., blog). For researchers who want to study cooperative behavior of developers or development process of projects, their research samples should not contain private projects and non-development projects. To solve this problem, we first analyzed the weaknesses of the base line methods (i.e., selecting top projects) and extended ML-based methods (i.e., training models on a labeled training dataset using ML algorithms, Extended_MLMs for short), and proposed two methods called Enhanced_RFM and Fusion_DL_RFM to address the weaknesses of Extended_RFM (the Extended_MLM that is based on Random Forest and has the best performance among all the Extended_MLMs). The results show that: (1) existing project sample selection methods have a low F-measure and poor generality (i.e., have a bad performance on the testing dataset); (2) Enhanced_RFM outperforms Fusion_DL_RFM on accuracy and stability; and (3) by adopting Enhanced_RFM, the F-measure of Extended_RFM is improved from 0.690 to 0.810 and the precision of Extended_RFM is improved from 0.559 to 0.785 under cross validation, which indicates that the generality of Extended_RFM is significantly improved.
语种:
英文
展开
Adversarial Separation Network for Text Style Transfer
作者:
Yang, Haitong;Zhou, Guangyou;He, Tingting
期刊:
ACM Transactions on Asian and Low-Resource Language Information Processing ,2022年21(2):1–14 ISSN:2375-4699
通讯作者:
Yang, HT
作者机构:
[Yang, Haitong; Zhou, Guangyou; Yang, HT; He, Tingting] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Peoples R China.;[Yang, Haitong; Zhou, Guangyou; Yang, HT; He, Tingting] Cent China Normal Univ, Natl Language Resources Monitoring, Wuhan, Peoples R China.;[Yang, Haitong; Zhou, Guangyou; Yang, HT; He, Tingting] Cent China Normal Univ, Res Ctr Network Media, Wuhan, Peoples R China.;[Yang, Haitong; Zhou, Guangyou; Yang, HT; He, Tingting] Cent China Normal Univ, Sch Comp, Luo Yu Rd, Wuhan, Hubei, Peoples R China.
通讯机构:
[Yang, HT ] C;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Peoples R China.;Cent China Normal Univ, Natl Language Resources Monitoring, Wuhan, Peoples R China.;Cent China Normal Univ, Res Ctr Network Media, Wuhan, Peoples R China.;Cent China Normal Univ, Sch Comp, Luo Yu Rd, Wuhan, Hubei, Peoples R China.
关键词:
Adversarial learning;adversarial separation network;latent factor;mapping;neural generative model;text style transfer;variational autoencoder
摘要:
This article considers the task of text style transfer: transforming a specific style of sentence into another while preserving its style-independent content. A dominate approach to text style transfer is to learn a good content factor of text, define a fixed vector for every style and recombine them to generate text in the required style. In fact, there are a large number of different words to convey the same style from different aspects. Thus, using a fixed vector to represent one style is very inefficient, which causes the weak representation power of the style vector and limits text diversity of the same style. To address this problem, we propose a novel neural generative model called Adversarial Separation Network (ASN), which can learn the content and style vector jointly and the learnt vectors have strong representation power and good interpretabilities. In our method, adversarial learning is implemented to enhance our model's capability of disentangling the two factors. To evaluate our method, we conduct experiments on two benchmark datasets. Experimental results show our method can perform style transfer better than strong comparison systems. We also demonstrate the strong interpretability of the learnt latent vectors. © 2021 Association for Computing Machinery.
语种:
英文
展开
A novel threshold changeable secret sharing scheme
作者:
Harn, Lein;Hsu, Chingfang* ;Xia, Zhe
期刊:
计算机科学前沿(英文) ,2022年16(1):1-7 ISSN:2095-2228
通讯作者:
Hsu, Chingfang
作者机构:
[Harn, Lein] Univ Missouri, Dept Comp Sci Elect Engn, Kansas City, MO 64110 USA.;[Hsu, Chingfang] Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.;[Xia, Zhe] Wuhan Univ Technol, Dept Comp Sci, Wuhan 430071, Peoples R China.
通讯机构:
[Hsu, Chingfang] C;Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.
关键词:
cryptography 94A60;authentication and secret sharing 94A62
摘要:
A (t, n) threshold secret sharing scheme is a fundamental tool in many security applications such as cloud computing and multiparty computing. In conventional threshold secret sharing schemes, like Shamir’s scheme based on a univariate polynomial, additional communication key share scheme is needed for shareholders to protect the secrecy of their shares if secret reconstruction is performed over a network. In the secret reconstruction, the threshold changeable secret sharing (TCSS) allows the threshold to be a dynamic value so that if some shares have been compromised in a given time, it needs more shares to reconstruct the secret. Recently, a new secret sharing scheme based on a bivariate polynomial is proposed in which shares generated initially by a dealer can be used not only to reconstruct the secret but also to protect the secrecy of shares when the secret reconstruction is performed over a network. In this paper, we further extend this scheme to enable it to be a TCSS without any modification. Our proposed TCSS is dealer-free and non-interactive. Shares generated by a dealer in our scheme can serve for three purposes, (a) to reconstruct a secret; (b) to protect the secrecy of shares if secret reconstruction is performed over a network; and (c) to enable the threshold changeable property. © 2022, Higher Education Press.
语种:
英文
展开
Deep-seismic-prior-based reconstruction of seismic data using convolutional neural networksDSP reconstruction using CNN
作者:
Liu, Qun;Fu, Lihua;Zhang, Meng
期刊:
GEOPHYSICS ,2021年86(2):V131-V142 ISSN:0016-8033
通讯作者:
Liu, Qun(q.liu@cug.edu.cn);Fu, Lihua(lihuafu@cug.edu.cn)
作者机构:
[Liu, Qun; Fu, Lihua] China Univ Geosci Wuhan, Sch Math & Phys, Wuhan 430074, Peoples R China.;[Zhang, Meng] Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Liu, Q.; Fu, L.] C;China University of Geosciences (Wuhan), China
关键词:
convolutional neural networks;deep seismic prior;encoder-decoder;seismic data reconstruction
摘要:
The reconstruction of seismic data with missing traces has been a long-standing issue in seismic data processing. Deep learning (DL) has emerged as a popular tool for seismic interpolation; it learns priors from training data sets of incomplete/complete data pairs. However, these DL methods are restricted to training data because they are supervised. When the features of the testing and training data are different, the recovery performance decreases, which prevents practical application. We have introduced a 'deep-seismic-prior-based'approach via a convolution neural network (CNN), which captures priors based on the particular structure of the CNN, but it does not need any training data set. The ill-posed inverse problem in seismic interpolation is thus solved using the CNN structure as a prior, and the learned network weights are the parameters that represent the seismic data. Because the convolutional filter weights are shared to achieve spatial invariance, the CNN structure can function as a regularizer to guide network learning. In our method, corrupted seismic data are reconstructed during the iterative process by minimizing the mean square error between the network output and the original data. We applied our method for interpolating irregularly and regularly missing traces in prestack and poststack seismic data. The experimental results indicate that our approach outperforms the traditional singular spectrum analysis and the dealiased Cadzow methods commonly used in the reconstruction of such data. © 2021 Society of Exploration Geophysicists.
语种:
英文
展开
A Semi-supervised Learning Approach Based on Adaptive Weighted Fusion for Automatic Image Annotation
作者:
Li, Zhixin;Lin, Lan;Zhang, Canlong;Ma, Huifang;Zhao, Weizhong;...
期刊:
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS ,2021年17(1):37:1-37:23 ISSN:1551-6857
通讯作者:
Li, Zhixin(lizx@gxnu.edu.cn)
作者机构:
[Zhang, Canlong; Li, Zhixin; Lin, Lan] Guangxi Normal Univ, Guangxi Key Lab Multisource Informat Min & Secur, 15 Yucai Rd Qixing Dist, Guilin 541004, Guangxi, Peoples R China.;[Ma, Huifang] Northwest Normal Univ, Coll Comp Sci & Engn, 967 Anning East Rd Anning Dist, Lanzhou 730070, Gansu, Peoples R China.;[Zhao, Weizhong] Cent China Normal Univ, Sch Comp, 152 Luoyu Rd Hongshan Dist, Wuhan 430079, Hubei, Peoples R China.;[Shi, Zhiping] Capital Normal Univ, Coll Informat Engn, 105 West Third Ring North Rd & Laidian Dist, Beijing 100048, Peoples R China.
通讯机构:
[Li, Z.] G;Guangxi Key Lab of Multi-source Information Mining and Security, No.15 Yucai Rd of Qixing District, China
关键词:
adaptive weighted fusion;Automatic image annotation;co-training;covolutional neural network;semi-supervised learning;support vector machine
摘要:
To learn a well-performed image annotation model, a large number of labeled samples are usually required. Although the unlabeled samples are readily available and abundant, it is a difficult task for humans to annotate large numbers of images manually. In this article, we propose a novel semi-supervised approach based on adaptive weighted fusion for automatic image annotation that can simultaneously utilize the labeled data and unlabeled data to improve the annotation performance. At first, two different classifiers, constructed based on support vector machine and covolutional neural network, respectively, are trained by different features extracted from the labeled data. Therefore, these two classifiers are independently represented as different feature views. Then, the corresponding features of unlabeled images are extracted and input into these two classifiers, and the semantic annotation of images can be obtained respectively. At the same time, the confidence of corresponding image annotation can be measured by an adaptive weighted fusion strategy. After that, the images and its semantic annotations with high confidence are submitted to the classifiers for retraining until a certain stop condition is reached. As a result, we can obtain a strong classifier that can make full use of unlabeled data. Finally, we conduct experiments on four datasets, namely, Corel 5K, IAPR TC12, ESP Game, and NUS-WIDE. In addition, we measure the performance of our approach with standard criteria, including precision, recall, F-measure, N+, and mAP. The experimental results show that our approach has superior performance and outperforms many state-of-the-art approaches. © 2021 Association for Computing Machinery.
语种:
英文
展开
Superword: A honeyword system for achieving higher security goals
作者:
Guo, Yimin* ;Zhang, Zhenfeng;Guo, Yajun
期刊:
Computers & Security ,2021年103:101689 ISSN:0167-4048
通讯作者:
Guo, Yimin
作者机构:
[Guo, Yimin; Zhang, Zhenfeng] Chinese Acad Sci, Inst Software, Trusted Comp & Informat Assurance Lab, Beijing, Peoples R China.;[Guo, Yimin; Zhang, Zhenfeng] Univ Chinese Acad Sci, Beijing, Peoples R China.;[Guo, Yajun] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
通讯机构:
[Guo, Yimin] C;Chinese Acad Sci, Inst Software, Trusted Comp & Informat Assurance Lab, Beijing, Peoples R China.
关键词:
Authentication;Honeypot;Honeywords;Matching attack;Passwords
摘要:
Generating honeywords for each user's account is an effective way to detect whether password databases are compromised. However, there are several underlying security issues associated with honeyword techniques that need to be addressed, for example, (1) How to make it more difficult for an attacker to find an accurate match of "username-real password"? (2) How to prevent the intersection attack in multiple systems caused by password reuse without reducing usability? (3) How to reduce the success rate of targeted password guessing? In this study, we first propose a "matching attack" model and find that although Erguler's honeyword system can achieve perfect flatness, the success rate of the attacker is 100% under matching attack. Secondly, we propose a new honeyword approach named Superword that isolates the direct relationship between username and the corresponding hashed password in password files. Additional honeypots are mixed with real accounts to detect online guessing attacks. The analysis reveals that our approach makes a matching attacker difficult to find a real password from N password hashes. Since there is no connection between the username and password in password files, our honeyword system also alleviates the multiple systems intersection attack and targeted password guessing. (c) 2019 Elsevier Ltd. All rights reserved.
语种:
英文
展开
MDepressionKG: A knowledge graph for metabolism-depression associations
作者:
Fu, Chengcheng;Jiang, Xiaobin;He, Tingting;Jiang, Xingpeng
作者机构:
[Fu, Chengcheng] National Engineering Research Center for E-Learning Central, China Normal University, Wuhan, China;[Jiang, Xiaobin; He, Tingting; Jiang, Xingpeng] School of Computer, Central China Normal University, Wuhan, China
会议名称:
2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021
会议时间:
October 29, 2021 - October 31, 2021
会议地点:
Virtual, Online, China
摘要:
Depression, as a global psychological disorder, is one of the important factors that cause human health, economic or social burden. Researches have shown that metabolism disorders caused by immune system diseases (i.e. diabetes, crohn disease, irritable bowel syndrome) are closely related to depression. There are large numbers of microbes in human micro-ecological environment. The metabolites of these microbes can also affect as the neurochemical and inflammatory factors in the human brain through the human brain-gut axis, which further affect the emergence of depression. In recent years, researches on the association between microbial metabolism and depression have been published in scientific literature, Wikipedia pages and other biological databases. But few efforts have been made to curate them as structured knowledge, which will make more convenient for the biological and medical community. In this research, we propose and construct a model of knowledge graph linking all metabolism entities of human and their microbes to depression disorder (called MDepressionKG). MDepressionKG has the following advantages: (1) It integrates the human microbial metabolism network, human diseases, microbes and other fields ontologies. (2) The knowledge graph provides a semantic-based logical reasoning for generating potential associations automatically. (3) Various applications such as the discovery of depression comorbidities can be applied as case studies to provide explorations for further depression intervention. The friendly interactive platform for knowledge retrieval and visualization, which is freely available at the URL at http://microbekg.msbio.pro/explore/MDepressionKG. © 2021 ACM.
语种:
英文
展开
Parameter Identification of Memristor-Based Chaotic Systems via the Drive-Response Synchronization Method
作者:
Liu, Hui;Chi, Jun;Li, Zengyang;Zeng, Zhigang;Lu, Jinhu
期刊:
IEEE Transactions on Circuits and Systems II: Express Briefs ,2021年68(6):2082-2086 ISSN:1549-7747
通讯作者:
Lu, Jinhu(jhlu@iss.ac.cn)
作者机构:
[Chi, Jun; Zeng, Zhigang; Liu, Hui] Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automat, Wuhan 430074, Peoples R China.;[Chi, Jun; Zeng, Zhigang; Liu, Hui] Huazhong Univ Sci & Technol, Educ Minist China, Key Lab Image Proc & Intelligent Control, Wuhan 430074, Peoples R China.;[Li, Zengyang] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Lu, Jinhu] Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China.;[Lu, Jinhu] Beihang Univ, State Key Lab Software Dev Environm, Beijing 100191, Peoples R China.
通讯机构:
[Lu, J.] S;School of Automation Science and Electrical Engineering, China
关键词:
Synchronization;Memristors;Inductors;Circuits and systems;Numerical simulation;Mathematical model;Lyapunov methods;Memristor;chaotic system;synchronization;parameter identification
摘要:
Memristor-based chaotic systems have been received great attention from researchers in the last decade. This brief investigates parameter identification of a memristor-based chaotic system (proposed by Muthuswamy in 2010). Uncertain parameter identification has not been studied yet for memristor-based chaotic systems. Using the Lyapunov stability theory and Barbǎlat lemma, two theorems are established to identify uncertain parameters of the system under the following two cases: i) the memductance is unknown; ii) capacitances and inductances are unknown. Finally, numerical simulations are carried out and the results show that the proposed parameter identification methods are effective. © 2004-2012 IEEE.
语种:
英文
展开
Spatial-Temporal Multi-Head Attention Networks for Traffic Flow Forecasting
作者:
Zhang, Zhao;Liu, Ming;Xu, Wenquan
作者机构:
[Zhang, Zhao; Liu, Ming; Xu, Wenquan] School of Computer, Central China Normal University, Hubei, Wuhan, China
会议名称:
5th International Conference on Computer Science and Application Engineering, CSAE 2021
会议时间:
October 19, 2021 - October 21, 2021
会议地点:
Virtual, Online, China
摘要:
Traffic flow forecasting plays an important role in the intelligent traffic system, which is the basis for traffic control and traffic management. However, due to the complex spatial-temporal dependence, traffic flow forecasting has always been a difficulty in the field of intelligent traffic. In order to select a suitable spatialtemporal forecasting method and solve the problem that recurrent neural architecture is not conducive to parallel computing, we construct a spatial-temporal forecasting model by using multi-head attention models. Use graph attention networks with multi-head attention mechanism to capture spatial features, and use the scaled dot product attention with positional encoding like Transformer to capture temporal features. Experimental results on two real-world datasets demonstrate that the forecasting error of our method is lower than baseline methods.. © 2021 Association for Computing Machinery. All rights reserved.
语种:
英文
展开
Spatial attention model-modulated bi-directional long short-term memory for unsupervised video summarisation
作者:
Zhong, Rui* ;Xiao, Diyang;Dong, Shi;Hu, Min
期刊:
Electronics Letters ,2021年57(6):252-254 ISSN:0013-5194
通讯作者:
Zhong, Rui
作者机构:
[Dong, Shi; Zhong, Rui; Xiao, Diyang] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Hu, Min] Wuhan Univ, NERCMS, Wuhan, Peoples R China.
通讯机构:
[Zhong, Rui] C;Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
关键词:
Image recognition;Optimisation techniques;Computer vision and image processing techniques;Video signal processing;Other topics in statistics;Optimisation techniques;Other topics in statistics;Unsupervised learning;Reinforcement learning;Neural nets
摘要:
Compared with surveillance video, user-created videos contain more frequent shot changes, which lead to diversified backgrounds and a wide variety of content. The high redundancy among keyframes is a critical issue for the existing summarising methods in dealing with user-created videos. To address the critical issue, we designed a salient- area-size-based spatial attention model (SAM) on the observation that humans tend to focus on sizable and moving objects in videos. Moreover, the SAM is taken as guidance to refine frame-wise soft selected probability for the bi-directional long short-term memory model. The reinforcement learning framework, trained by the deep deterministic policy gradient algorithm, is adopted to do unsupervised training. Extensive experiments on the SumMe and TVSum datasets demonstrate that our method outperforms the state-of-the-art in terms of F-score.
语种:
英文
展开