检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Pu, Hua Mi, Jiacong Lu, Shan He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Jiangsu Nanjing210018 China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd Jiangsu Nanjing211161 China

Traditional Chinese medicine (TCM) prescription is the most critical form of TCM treatment, and uncovering the complex nonlinear relationship between symptoms and TCM is of great significance for clinical practice and assisting physicians in diagnosis and treatment. Although there have been some studies on TCM prescription generation, these studies consider a single factor and directly model the symptom-prescription generation problem mainly based on symptom descriptions, lacking guidance from TCM knowledge. To this end, we propose a RoBERTa and Knowledge Enhancement model for Prescription Generation of Traditional Chinese Medicine (RoKEPG). RoKEPG is firstly pre-trained by our constructed TCM corpus, followed by fine-tuning the pre-trained model, and the model is guided to generate TCM prescriptions by introducing four classes of knowledge of TCM through the attention mask matrix. Experimental results on the publicly availab.e TCM prescription dataset show that RoKEPG improves the F1 metric by about 2% over the baseline model with the best results. © 2023, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Learning Expectation of lab.l Distribution for Facial Age and Attractiveness Estimation

arXiv

引用

arXiv 2020年

作者： Gao, Bin-Bin Liu, Xin-Xin Zhou, Hong-Yu Wu, Jianxin Geng, Xin YouTu Lab Tencent Shenzhen518075 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China MOE Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China

Facial attributes (e.g., age and attractiveness) estimation performance has been greatly improved by using convolutional neural networks. However, existing methods have an inconsistency between the training objectives and the evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which carry expensive computation cost and storage overhead. In this paper, we firstly analyze the essential relationship between two state-of-the-art methods (Ranking-CNN and DLDL) and show that the Ranking method is in fact learning lab.l distribution implicitly. This result thus firstly unifies two existing popular state-of-the-art methods into the DLDL framework. Second, in order to alleviate the inconsistency and reduce resource consumption, we design a lightweight network architecture and propose a unified framework which can jointly learn facial attribute distribution and regress attribute value. The effectiveness of our approach has been demonstrated on both facial age and attractiveness estimation tasks. Our method achieves new state-of-the-art results using the single model with 36× fewer parameters and 3× faster inference speed on facial age/attractiveness estimation. Moreover, our method can achieve comparable results as the state-of-the-art even though the number of parameters is further reduced to 0.9M (3.8MB disk storage). Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An algorithm of anisotropy and self-adaptive point cloud denoising

引用

Journal of information and Computational Science 2014年第8期11卷 2827-2834页

作者： Cao, Feifei Liu, Yongshan Gu, Xiaoying College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Lab. for Computer Virtual Tech. and Syst. Integration of Hebei Province Yanshan University Qinhuangdao 066004 China Data Industry Research Lab Qinhuangdao 066004 China

Since the method of isotropic filtering will result in blurring sharp features, a new approach of anisotropic filtering algorithm is proposed, direction and scale of such filter vary according to changes of sharp features' direction and scale. According to the local neighborhood of the point to be processed, the direction and scale of the filter were adaptively computed by covariance analysis. And because the results of covariance analysis are determined by the selection of neighborhood points, order to adaptively select neighborhood points, a method about the selection of optimal neighborhood radius was also proposed which is based on projection direction. This method adopts projection direction to restrict the selection of neighboring points, thus adaptively get best neighborhood radius related with surface features. Experimental results show that: the algorithm combined with bilateral filtering not only can make point cloud smooth while retaining sharp features but also can adaptively select parameters. Copyright © 2014 Binary information Press.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Multi-user private keyword search for cloud computing

Multi-user private keyword search for cloud computing

引用

2011 3rd IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2011

作者： Yang, Yanjiang Lu, Haibing Weng, Jian Institute for Infocomm Research Singapore Singapore Dept. of Operations Management and Information Systems Leavey School of Business Santa Clara University United States Department of Computer Science Emergency Technology Research Center of Risk Evaluation and Prewarning on Public Network Security Jinan University Guangzhou China State Key Laboratory of Information Security Institute of Software Chinese Academy of Sciences China State Key Lab. of Networking and Switching Technology Beijing University of Posts and Telecommunications China

ISBN: (纸本)9780769546223

Enterprises outsourcing their databases to the cloud and authorizing multiple users for access represents a typical use scenario of cloud storage services. In such a case of database outsourcing, data encryption is a good approach enabling the data owner to retain its control over the outsourced data. Searchable encryption is a cryptographic primitive allowing for private keyword based search over the encrypted database. The above setting of enterprise outsourcing database to the cloud requires multi-user searchable encryption, whereas virtually all of the existing schemes consider the single-user setting. To bridge this gap, we are motivated to propose a practical multi-user searchable encryption scheme, which has a number of advantages over the known approaches. The associated model and security requirements are also formulated. We further discuss to extend our scheme in several ways so as to achieve different search capabilities. © 2011 IEEE.

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

MultiModal-Learning for Predicting Molecular Properties: A Framework Based on Image and Graph Structures

arXiv

引用

arXiv 2023年

作者： Wang, Zhuoyuan Mi, Jiacong Lu, Shan He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Jiangsu Nanjing210018 China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd. Jiangsu Nanjing211161 China

The quest for accurate prediction of drug molecule properties poses a fundamental challenge in the realm of Artificial Intelligence Drug Discovery (AIDD). An effective representation of drug molecules emerges as a pivotal component in this pursuit. Contemporary leading-edge research predominantly resorts to self-supervised learning (SSL) techniques to extract meaningful structural representations from large-scale, unlab.led molecular data, subsequently fine-tuning these representations for an array of downstream tasks. However, an inherent shortcoming of these studies lies in their singular reliance on one modality of molecular information, such as molecule image or SMILES representations, thus neglecting the potential complementarity of various molecular modalities. In response to this limitation, we propose MolIG, a novel MultiModaL molecular pre-training framework for predicting molecular properties based on Image and Graph structures. MolIG model innovatively leverages the coherence and correlation between molecule graph and molecule image to execute self-supervised tasks, effectively amalgamating the strengths of both molecular representation forms. This holistic approach allows for the capture of pivotal molecular structural characteristics and high-level semantic information. Upon completion of pre-training, Graph Neural network (GNN) Encoder is used for the prediction of downstream tasks. In comparison to advanced baseline models, MolIG exhibits enhanced performance in downstream tasks pertaining to molecular property prediction within benchmark groups such as MoleculeNet Benchmark Group and ADMET Benchmark Group. © 2023, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

A load balancing algorithm for multi-root ONS

引用

Journal of Computational information Systems 2014年第7期10卷 2735-2742页

作者： Hao, Fengzhai Liu, Yongshan Chen, Wei College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao 066004 China Data Industry Research Lab. Qinhuangdao 066004 China

In order to solve the overload problem of root ONS in the EPC network, a load balancing algorithm based on multi-root ONS is proposed. Based on the proposed load balancing ONS (LB ONS) architecture, the ONS Root is defined to have two states, idle or busy. According to CPU utilization and memory utilization of the ONS Root and in combination with threshold controlling to periodically update the ONS Root states, which makes the requests coming from client applications be transferred to an ONS Root which is idle. Experiment results show that the algorithm can reduce query hops and query delays effectively and offer lookup service efficiently. © 2014 Binary information Press.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Edge collapse mesh simplification algorithm based on detail features preserving

引用

Journal of Computational information Systems 2014年第7期10卷 2883-2890页

作者： Jia, Qi Liu, Yongshan Gu, Xiaoying College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao 066004 China Data Industry Research Lab. Qinhuangdao 066004 China

The existing model simplification algorithm in simplified speed and quality can't reach a better compromise, so we present an improved quadric error metrics edge collapse mesh simplification algorithm. This algorithm makes the local region unevenness of vertex, the local region average area of vertex and edge length as constraint factors add to the edge collapse cost, by changing the order of the edge collapse to retain the important detail features of the original model. New vertex position is calculated on the different types of edge, keeping the boundary characteristics of the mesh model. Experimental results show that the improved algorithm not only runs faster, but also maintains a higher degree on the model feature region. © 2014 Binary information Press.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Research on load balancing strategy based on middleware

引用

ICIC Express Letters 2014年第9期8卷 2655-2661页

作者： Gu, Xiaoying Liu, Yongshan Man, Yubao Department of Information Science and Engineering Qinhuangdao 066004 China The Key Lab. for Computer Virtual Tech. and System Integration of Hebei Province Yanshan University No. 438 Hebei Ave Qinhuangdao 066004 China Data Industry Research Lab Qinhuangdao 066004 China

According to the former research achievements about load balancing strategy, considering the load distribution, the load condition of service node and the number of user connections, we propose a load balancing strategy based on middleware. According to the cluster service load and the number of user connections, the requests from user will be reasonably allocated to each service node by using middleware technology, then service node and requested user establish a temporary connection, after all the requests of this user are processed by this node. Experiments show that, this strategy reduces the number of requests for allocation, improves the resource utilization rate of cluster system and load balancing degree, and effectively suppresses the load jitter of system. © 2014 ISSN 1881-803X.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

SAM-Event-Adapter: Adapting Segment Anything Model for Event-RGB Semantic Segmentation

SAM-Event-Adapter: Adapting Segment Anything Model for Event...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Bowen Yao Yongjian Deng Yuhan Liu Hao Chen Youfu Li Zhen Yang College of Computer Science Beijing University of Technology Beijing China Key Lab of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China Department of Mechanical Engineering City University of Hong Kong Kowloon Hong Kong SAR

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Semantic segmentation, a fundamental visual task ubiquitously employed in sectors ranging from transportation and robotics to healthcare, has always captivated the research community. In the wake of rapid advancements in large model research, the foundation model for semantic segmentation tasks, termed the Segment Anything Model (SAM), has been introduced. This model substantially addresses the dilemma of poor generalizability of previous segmentation models and the disadvantage in requiring to retrain the whole model on variant datasets. Nonetheless, segmentation models developed on SAM remain constrained by the inherent limitations of RGB sensors, particularly in scenarios characterized by complex lighting conditions and high-speed motion. Motivated by these observations, a natural recourse is to adapt SAM to additional visual modalities without compromising its robust generalizability. To achieve this, we introduce a lightweight SAM-Event-Adapter (SE-Adapter) module, which incorporates event camera data into a cross-modal learning architecture based on SAM, with only limited tunable parameters incremental. Capitalizing on the high dynamic range and temporal resolution afforded by event cameras, our proposed multi-modal Event-RGB learning architecture effectively augments the performance of semantic segmentation tasks. In addition, we propose a novel paradigm for representing event data in a patch format compatible with transformer-based models, employing multi-spatiotemporal scale encoding to efficiently extract motion and semantic correlations from event representations. Exhaustive empirical evaluations conducted on the DSEC-Semantic and DDD17 datasets provide validation of the effectiveness and rationality of our proposed approach.

关键词： Adaptation models Visualization Semantic segmentation Motion segmentation Transportation Cameras Transformers

来源：评论

学校读者我要写书评

暂无评论

Comments on a threshold authenticated encryption scheme

引用

International Journal of computers and Applications 2011年第2期33卷 132-136页

作者： Tan, Zuowen Department of Computer Science and Technology School of Information Technology Jiangxi University of Finance and Economics Nanchang 330032 Jiangxi Province China Key Lab. of Network Security and Cryptology School of Mathematics and Computer Science Fujian Normal University Fuzhou 350007 China

An authenticated encryption scheme (AE scheme) allows the signer to generate a valid authenticated ciphertext on a message such that the designated recipient can recover the message. AE schemes can achieve confidentiality and authenticity when message is transmitted over an insecure channel. The previous AE scheme only can allow one signer to generate the authenticated ciphertext. Recently, Chung et al. proposed a (t, n) threshold authenticated encryption scheme (TAE scheme) in which any t or more signers cooperate to produce a signature for a message and no one except the designated verifier can obtain the message from the ciphertext and verify the authenticity and integrity of the message. The scheme is based on elliptic curve cryptosystem. Moreover, the scheme applies a division-of-lab.ur signature technique to reduce the load of every signer. In other words, every signer only needs to sign a message block assigned to it. Therefore, the (t, n) TAE scheme is more efficient than other AE schemes. However, some flaws of the scheme are found in this paper. Several security defects of the scheme are elab.rated: (i) It suffers from conspiracy attack. (ii) It does not hold robustness. (iii) It is insecure against insider attacks. In addition, there exist some design defects in the TAE scheme. Some measures to remove these weaknesses are given in this paper.

关键词： Authentication

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：