检索结果-内蒙古大学图书馆

TechRxiv 2023年

作者： Wang, Junkai Quan, Lijun Jin, Zhi Wu, Hongjie Ma, Xuhao Wang, Xuejiao Xie, Jingxin Pan, Deng Chen, Taoning Wu, Tingfang Lyu, Qiang School of Computer Science and Technology of Soochow University Jiangsu215006 China Province Key Lab for Information Processing Technologies Soochow University Jiangsu215006 China Collaborative Innovation Center of Novel Software Technology and Industrialization Jiangsu210000 China School of Electronic and Information Engineering Suzhou University of Science and Technology Jiangsu215009 China

This study aims to address the complexity of predicting RNA-small molecule binding sites to explore the potential value in the field of RNA drug targets. To address this challenge, we propose the MultiModRLBP method, which integrates multi-modal features using deep learning algorithms. These features include 3D structural properties at the nucleotide base level, relational graphs based on overall RNA structure, and semantically rich RNA sequence information. Different deep modules are employed to learn high-dimensional different modility of semantic features. RNAbert is fine-tuned to learn sequence information, relational graph convolutional network focuses on capturing various relationships between different nodes in the RNA graph, and CNN directly and indirectly captures local and global 3D structural features. Consequently, MultiModRLBP can better reflect the inherent complex relationships within RNA. Furthermore, we expanded the dataset to include RNA complexes with the same RNA sequences but varying structures, enabling the model to better grasp subtle changes at the structural level. The research results demonstrate that the performance of MultiModRLBP outperforms state of the art methods across multiple classic test sets, especially in predicting binding sites located in pockets or those that are distantly distributed along the sequences. This advancement holds promise in reducing the costs of RNA-targeted drugs development. © 2023, CC BY.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder

arXiv

引用

arXiv 2024年

作者： Han, Tingxu Huang, Shenghan Ding, Ziqi Sun, Weisong Feng, Yebo Fang, Chunrong Li, Jun Qian, Hanwei Wu, Cong Zhang, Quanjun Liu, Yang Chen, Zhenyu The State Key Laboratory for Novel Software Technology Nanjing University Jiangsu210093 China The School of Computer Science University of New South Wales NSW2052 Australia The School of Computer Science and Engineering Nanyang Technological University Nanyang639798 Singapore The Department of Computer Science The Director of the Network & Security Research Laboratory The University of Oregon United States

With the development of deep learning, self-supervised learning (SSL) has become particularly popular. SSL pre-trains an encoder (e.g., an image encoder) to learn generic features from a large amount of unlabeled data, releases it on a third-party platform, and allows any downstream task (e.g., an image classification task) to further fine-tune the encoder with task-specific data to derive the model for the task. However, despite the tremendous performance improvements it brings, SSL faces serious security risks. An adversary can poison pre-training datasets used to pre-train an encoder or publish a poisoned encoder directly to third-party platforms, which will also poison the model for any downstream task that uses these encoders. In this paper, we study a defense against poisoned encoders in SSL called distillation, which is a defense used in supervised learning originally. Distillation aims to distill knowledge from a given model (a.k.a the teacher net) and transfer it to another (a.k.a the student net). Now, we use it to distill benign knowledge from poisoned pre-trained encoders and transfer it to a new encoder, resulting in a clean pre-trained encoder. In particular, we conduct an empirical study on the effectiveness and performance of distillation against poisoned encoders. Using two state-of-the-art backdoor attacks against pre-trained image encoders and four commonly used image classification datasets, our experimental results show that distillation can reduce attack success rate from 80.87% to 27.51% while suffering a 6.35% loss in accuracy. Moreover, we investigate the impact of three core components of distillation on performance: Teacher net, student net, and distillation loss. By comparing 4 different teacher nets, 3 student nets, and 6 distillation losses, we find that fine-tuned teacher nets, warm-up-training-based student nets, and attention-based distillation loss perform best, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Time Series Data Classification on Grassmann Manifold 4

Time Series Data Classification on Grassmann Manifold

引用

2021 4th International Conference on Advanced Algorithms and Control engineering, ICAACE 2021

作者： Al-Samhi, Waheeb Al-Soswa, Mohammed Al-Dhabi, Yunes School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing Jiangsu210094 China School of Information Engineering Chang'An University Xi'an710064 China Software College Northeastern University Shenyang Liaoning110819 China

Time Series Classification has become one of the most challenging problems in many signal processing and machine learning applications, e.g., audio/video signal processing and EEG signal processing. We propose a novel method of extracting features from data for classification and representing data on a Grassmann manifold by parameterizing it using the autoregressive moving model (ARMA). Then we perform classification on these extracted features by training support vector machines (SVM), with appropriate kernels on the Grassmann manifold. We performed tests on several publicly available datasets. We found that an SVM with a proper kernel on the Grassmann manifold consistently performs better than an SVM using a typical Gaussian kernel that acts on the data in Euclidean space. Furthermore, we found that the Grassmann SVM technique overperforms the literature in some high-dimensional datasets, without the need for any other preprocessing techniques. This work demonstrates the power of data-based manifold techniques in improving the performance of existing algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Multi-Feature Learning Model with Enhanced Local Attention for Vehicle Re-Identification

引用

computers, Materials & Continua 2021年第12期69卷 3549-3561页

作者： Wei Sun Xuan Chen Xiaorui Zhang Guangzhao Dai Pengshuai Chang Xiaozheng He Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Rensselaer Polytechnic Institute TroyNY12180USA

Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera *** has gradually become a core technology of intelligent transportation *** existing vehicle re-identification models adopt the joint learning of global and local ***,they directly use the extracted global features,resulting in insufficient feature ***,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional *** solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this *** model consists of global and local *** global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation *** addition,multi-scale pooling operations are used to obtain multiscale *** the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local *** features from both branches are combined to provide a more comprehensive and distinctive feature *** experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.

关键词： Vehicle re-identification region batch dropblock multi-feature learning local attention

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of Large Language Models for Method Name Prediction

SSRN

引用

SSRN 2024年

作者： Qian, Hanwei Xu, Tingting Ding, Ziqi Liu, Wei Zhu, Shaomin Yin, Jie Feng, Xia Fang, Chunrong Zhao, Jianhua Sun, Weisong State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210093 China Jiangsu Police Institute China City University of Macau 999078 China Tongji University Shanghai200092 China School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

High-quality method names are essential for understanding and maintaining programs. However, naming methods can be challenging, especially for new developers. To address this, deep-learning techniques have been developed to predict suitable names for method code bodies. Large Language Models (LLMs) have recently shown exceptional performance in Natural Language Processing (NLP), significantly impacting the software engineering (SE) field. LLMs have been applied to tasks like code summarization, indicating their considerable potential. Yet, there hasn't been a systematic study on adapting LLMs for method name prediction (MNP). This paper fills this gap with the first empirical study exploring LLMs' capabilities in MNP tasks. We evaluate LLMs’ comprehension and interaction patterns in MNP, finding they perform best with a 0 temperature and a few-shot prompt template. Comparing prompt-guided LLMs and fine-tuned PLMs, GPT-3.5 excels among LLMs while CodeT5 leads among PLMs, with minimal performance differences. SentenceBert with Cosine Similarity (SBCS) quantifies semantic differences between predicted and ground-truth names. Human evaluation surpasses the F1 metric for LLMs, identifying challenges like insufficient global information and dataset quality. Finally, we discuss applying LLMs to MNP tasks and suggest future research directions. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

CARE-EMRs: Efficient and Privacy-Preserving Data Sharing Framework for Electronic Medical Records

CARE-EMRs: Efficient and Privacy-Preserving Data Sharing Fra...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yu Tao Lu Zhou Yi Zhu Yuhang Li Chunpeng Ge College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & Software School Shandong University Jinan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Cross-institutional Electronic Medical Records (EMRs) sharing significantly improves healthcare quality and reduces costs. Current EMRs are often stored on cloud servers and protected by Attribute-based Encryption (ABE) for access control. Cross-institutional sharing allows doctors to request EMRs access from target Healthcare Institutions (HIs) through attribute-based collaboration, enabling flexible and secure access. However, existing collaboration in practical EMRs sharing scenarios suffers from inefficiency, hindering timely access and treatment. This paper proposes an efficient and privacy-preserving data sharing framework for EMRs, called CARE-EMRs. CARE-EMRs enables efficient EMRs data access for doctors across different HIs through an outsourcing mechanism. Furthermore, we designed an improved cryptographic primitive PPD-CP-ABE to serve as the security foundation for CARE-EMRs framework, ensuring privacy of the outsourced process. We prove the security of CARE-EMRs. Performance analysis indicates that it significantly reduces the computation and communication overhead.

关键词： Performance evaluation Privacy Data privacy Collaboration Medical services Outsourcing Performance analysis Encryption Servers Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

arXiv

引用

arXiv 2024年

作者： Xue, Yu Zhu, Chenchen Zhou, MengChu Wahib, Mohamed Gabbouj, Moncef School of Software Nanjing University of Information Science and Technology Jiangsu China Department of Electrical and Computer Engineering NewJersey Institute of Technology NewarkNJ07102 United States Japan Department of Computing Sciences Tampere University Tampere Finland

Neural architecture search (NAS) enables researchers to automatically explore vast search spaces and find efficient neural networks. But NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process, which requires a lot of computing resources and time. In order to improve the efficiency of NAS, a series of methods have been proposed to reduce the evaluation time of neural architectures. However, they are not efficient enough and still only focus on the accuracy of architectures. In addition to the classification accuracy, more efficient and smaller network architectures are required in real-world applications. To address the above problems, we propose the SMEM-NAS, a pairwise comparison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism. In the SMEM-NAS, a surrogate model is constructed based on pairwise comparison relations to predict the accuracy ranking of architectures, rather than the absolute accuracy. Moreover, two populations cooperate with each other in the search process, i.e., a main population guides the evolution, while a vice population expands the diversity. Our method aims to provide high-performance models that take into account multiple optimization objectives. We conduct a series of experiments on the CIFAR-10, CIFAR- 100 and ImageNet datasets to verify its effectiveness. With only a single GPU searching for 0.17 days, competitive architectures can be found by SMEM-NAS which achieves 78.91% accuracy with the MAdds of 570M on the ImageNet. This work makes a significant advance in the important field of NAS. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Quantum Privacy-Preserving Price E-Negotiation

arXiv

引用

arXiv 2023年

作者： Liu, Wen-Jie Li, Chun-Tang Zheng, Yu Xu, Yong Xu, Yin-Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China

Privacy-preserving price e-negotiation (3PEN) is an important topic of secure multi-party computation (SMC) in the electronic commerce field, and the key point of its security is to guarantee the privacy of seller’s and buyer’s prices. In this study, a novel and efficient quantum solution to the 3PEN problem is proposed, where the oracle operation and the qubit comparator are utilized to obtain the comparative results of buyer’s and seller’s prices, and then quantum counting is executed to summarize the total number of products which meets the trading conditions. Analysis shows that our solution not only guarantees the correctness and the privacy of 3PEN, but also has lower communication complexity than those classical ones. © 2023, CC BY.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Neural Network with Representation Self-challenge for Fingerprint Liveness Detection

引用

computers, Materials & Continua 2022年第10期73卷 719-733页

作者： Jie Chen Chengsheng Yuan Chen Cui Zhihua Xia Xingming Sun Thangarajah Akilan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310053China Jiangsu Yuchi Blockchain Research Institute Nanjing210044China Department of Software Engineering Lakehead UniversityThunder BayON P7B 5E1Canada

Fingerprint identification systems have been widely deployed in many occasions of our daily ***,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit *** address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s *** vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model *** at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint ***,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection ***,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and *** size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.

关键词： FLD lightweight multi-scale RSC blind materials

来源：评论

学校读者我要写书评

暂无评论

Quantum Algorithms and Experiment Implementations Based on IBM Q

引用

computers, Materials & Continua 2020年第11期65卷 1671-1689页

作者： Wenjie Liu Junxiu Chen Yinsong Xu Jiahao Tang Lian Tong Xiaoyu Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China School of Information Engineering Jiangsu Maritime InstituteNanjing211100China Department of Electrical and Computer Engineering Portland State UniversityOregon97207USA

With the rapid development of quantum theory and technology in recent years,especially the emergence of some quantum cloud computing platforms,more and more researchers are not satisfied with the theoretical derivation and simulation verification of quantum computation(especially quantum algorithms),experimental verification on real quantum devices has become a new *** this paper,three representative quantum algorithms,namely Deutsch-Jozsa,Grover,and Shor algorithms,are briefly depicted,and then their implementation circuits are presented,*** program these circuits on python with QISKit to connect the remote real quantum devices(i.e.,ibmqx4,ibmqx5)on IBM Q to verify these *** experimental results not only show the feasibility of these algorithms,but also serve to evaluate the functionality of these devices.

关键词： Quantum algorithms implementation circuit IBM Q QISKit program

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：