检索结果-内蒙古大学图书馆

PCLT-PPI: Predicting Multi-type Interactions between Proteins based on Point Cloud Structure and Local Topology Preservation

引用

IEEE Journal of Biomedical and Health Informatics 2025年

作者： Li, Minglei Hou, Yurui Wang, Shuqin Wei, Jinmao Liu, Jian Nankai University College of Computer Science Tianjin300071 China Nankai University Center for Bioinformatics and Intelligent Medicine Tianjin300071 China Tianjin Key Laboratory of Network and Data Security Technology Tianjin300071 China Tianjin Normal University College of Computer and Information Engineering Tianjin300387 China

Protein-protein interactions (PPIs) play a crucial role in cellular biochemical reactions. Computationally mining PPI can help us better understand cellular regulatory mechanisms. Most existing methods focus on the linear structure of proteins, ignoring the influence of native spatial structure on their properties. Furthermore, when neural networks are used to learn protein embeddings, the nonlinear transformations may change the topological relationships between proteins. To address the above issues, we propose a PPI prediction method based on protein point cloud structure and local topology preservation, naming it PCLT-PPI. It extracts structural features from protein point cloud structures and relational features through graph neural networks. Throughout the process, PCLT-PPI maintains the local topology of proteins in their origin and embedding spaces. Experimental results show that, under three test set partition modes (Random, BFS, DFS) and four evaluation metrics (F1, AUC, AUPR, Hamming Loss), PCLT-PPI performs better than several state-of-the-art PPI prediction methods, especially when predicting protein PPIs that are not visible during training, exhibiting stronger robustness and higher generalization ability. The results also demonstrate that point cloud structure and local topology preservation can improve PPI prediction performance, which may provide a reference for subsequent related research. © 2013 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Three-party Repeated Game Model for Data Privacy in Mobile Edge Crowdsensing of IoT 13

A Three-party Repeated Game Model for Data Privacy in Mobile...

引用

13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020

作者： Zhao, Mingfeng Chen, Lei Xiong, Jinbo Tian, Youliang Fujian Provincial Key Laboratory of Network Security and Cryptology College of Mathematics and Informatics Fujian Normal University Fuzhou350117 China College of Engineering and Computing Georgia Southern University GA30458 United States State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9781631902710

The low request response delay of mobile edge crowdsensing (MECS) paradigm allows quick interactions among entities in practical scenarios. However, there often exist dishonest behaviors in such interactions, and the personal information leakage involved seriously threatens the privacy and security of sensing users. To tackle this problem, previously we had proposed a non-repeated three-party game model, without the consideration of multiple interactions in the actual scenario. Based on game theory, this research therefore proposes a three-party repeated game model. Specifically, we propose the corresponding social norms for different phases of sensing data. It analyzes all possible behaviors deviating from rationality, calculates the change of corresponding payoff function, and explores the influencing factors and constraints of players' honest behaviors based on the premise of maximizing interests. Finally, a significant number of simulations and numerical analyse indicate that the proposed model is feasible and effective in maximizing the benefits of game participants. Copyright © 2020 EAI.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Enabling Deep Learning-based Physical-layer Secret Key Generation for FDD-OFDM Systems in Multi-Environments

arXiv

引用

arXiv 2022年

作者： Zhang, Xinwei Li, Guyue Zhang, Junqing Peng, Linning Hu, Aiqun Wang, Xianbin The School of Cyber Science and Engineering Southeast University Nanjing210096 China The Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 3GJ United Kingdom The School of Information Science and Engineering National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Purple Mountain Laboratories for Network and Communication Security Nanjing210096 China The Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada

Deep learning-based physical-layer secret key generation (PKG) has been used to overcome the imperfect uplink/downlink channel reciprocity in frequency division duplexing (FDD) orthogonal frequency division multiplexing (OFDM) systems. However, existing efforts have focused on key generation for users in a specific environment where the training samples and test samples follow the same distribution, which is unrealistic for real-world applications. This paper formulates the PKG problem in multiple environments as a learning-based problem by learning the knowledge such as data and models from known environments to generate keys quickly and efficiently in multiple new environments. Specifically, we propose deep transfer learning (DTL) and meta-learning-based channel feature mapping algorithms for key generation. The two algorithms use different training methods to pre-train the model in the known environments, and then quickly adapt and deploy the model to new environments. Simulation and experimental results show that compared with the methods without adaptation, the DTL and meta-learning algorithms both can improve the performance of generated keys. In addition, the complexity analysis shows that the meta-learning algorithm can achieve better performance than the DTL algorithm with less cost. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

WebIDE cloud server resource allocation with task pre-scheduling in IOT application development 2

WebIDE cloud server resource allocation with task pre-schedu...

引用

2nd IEEE International Conference on Industrial Internet Cloud, ICII 2019

作者： Wang, Huaijun Li, Junhuai Tian, Jubo Wang, Kan Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xian University of Technology Xian710048 China

ISBN: (纸本)9781728129778

WebIDE is leveraged for IOT applications development, which could adapt to the rapid growth of IOT applications and meanwhile facilitate the rapid development. Resource allocation is of vital significance in the WebIDE cloud service system. Existing resource allocation approaches may encounter issues such as unbalanced resource assignments, which could lead to the reduced system resource utilization or extended system response time. The fundamental reason behind it lies in the fact that existing ones are typically on the basis of predetermined resource demands for each task, and not applicable to the case with dynamic and unknown resource demands. Thus, in this paper, we propose a novel approach based on task pre-scheduling, which schedules beforehand each task into a virtual machine local task queue by means of demand prediction. Firstly, all tasks are classified, based on the execution state, execution operations and cloud server resource requirements. Secondly, the grouped tasks are mapped to different system states, with the Markov state transition probability matrix leveraged to model the transition probability between tasks, followed by the prediction model constructed. Finally, integrating both task pre-scheduling and ant colony algorithm, cloud server resource allocation is carried out. Simulation results show that the task prediction model could significantly not only reduce the task response time, but also improve the cloud server resource utilization. © 2019 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Threat-Based Declassification and Endorsement for Mobile Computing

引用

Chinese Journal of Electronics 2019年第5期28卷 1041-1052页

作者： YIN Lihua GUO Yunchuan ZHANG Huibing HUANG Wenting FANG Binxing Cyberspace Institute of Advanced Technology Guangzhou University The State Key Laboratory of Information Security Institute of Information Engineering CAS Guangxi Key Lab of Trusted Software Guilin University of Electronic Technology The National Computer Network Emergency Response Technical Team/Coordination Center of China

Declassification and endorsement can efficiently improve the usability of mobile ***, both declassify and endorse operations in practice are often ad-hoc and nondeterministic, thus, being insecure. From a new perspective of threat assessments,we propose the Threat-based typed security π-calculus(πTBTS) to model declassification and endorsement in mobile computing. Intuitively, when relaxing confidentiality policies and/or integrity policies, we respectively assess threats brought by performing these two relaxes. If these threats are acceptable, the declassification and/or endorsement operations are permitted; Otherwise, they are denied. The proposed assessments have explicit security conditions, results and less open parameters,so our approach solves the problem of the ad-hoc and nondeterministic semantics and builds a bridge between threat assessments and declassification/endorsement.

关键词： Declassification Endorsement Threat assessment Mobile computing π-Calculus

来源：评论

学校读者我要写书评

暂无评论

Q&A driven conversational recommendation integrating multiple interest modeling

引用

Neurocomputing 2025年 647卷

作者： Haiping Zhu Yuqi Sun Shuwei Che Yan Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an 710049 China

The conversational recommendation aims to provide users with recommendations in an interaction form of “System Ask-User Respond”. Existing studies rarely consider combining users’ multi-interest at the attribute level for preference modeling, and conduct inefficient conversational recommendation strategy learning, which affects the recommendation performance and conversation performance. To this end, we proposed a Q-A driven conversational recommendation method integrating multiple interest modeling. Specifically, we integrate the user’s positive and negative feedback to model a session dynamic graph, then use the signed graph convolutional network for graph representation learning, and we model multiple interest sequences based on the attention mechanism, then obtain the user interest state representation by fusing of sequence representations to solve the problem of insufficient user preference representation. Besides, we proposed a personalized decision space optimization method to narrow the range of action candidates and train the model with a multi-agent reinforcement learning method integrating hierarchical decision debiasing to solve the problem of poor conversational recommendation strategy learning effect. Experimental results on three public datasets, LastFM, Yelp, and Book, show that compared with existing conversational recommendation methods, our method demonstrates consistent performance improvement across all datasets. In addition, the results of ablation experiments verify the effectiveness of each component in our method.

关键词： Conversational recommendation Multi-interest modeling Recommendation system Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A 2-bit graphene encoder based on the plasmon-induced transparency effect and its sensing characteristics

引用

Results in Physics 2024年 59卷

作者： Zhu, Aijun Li, Zongteng Hou, Weigang Yang, Xinghua Cheng, Lei Hu, Cong Qiao, Fei Mahapatra, Rabi Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin 541004 China Shanxi Key Laboratory of Advanced Semiconductor Optoelectronic Devices and Integrated Systems Jincheng Shanxi 048000 China Institute of Intelligent Communication and Network Security Chongqing University of Posts and Telecommunications Chongqing 400000 China College of Science Beijing Forestry University Beijing 100083 China Jincheng Research Institute of Opto-mechatronics Industry Jincheng Shanxi 048000 China Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips Guangxi Normal University Guilin 541004 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Computer Science and Engineering Texas A&M University College Station 77843-3112 TX United States

A 2-bit encoder based on the plasmon-induced transparency (PIT) effect was proposed and investigated in the range from 2 to 7 THz. The Lorentz oscillation coupling model was utilized to confirm the simulation. By tuning the Fermi levels of cross1 and cross2, the 2-bit encoder was achieved. And the minimum MD was 94.73 %, the minimum ER was 12.77 dB, and the maximum IL was 0.32 dB. As a sensor, the structure had a sensitivity of up to 2.33 THz/RIU. In addition, due to the insensitivities to incidence angle and polarization angle, the encoder could be utilized to complex environments. Therefore, these results reveals that our work is significant in terahertz encoders, optical switches, sensors, slow light devices, and modulators. © 2024 The Author(s)

关键词： 2-bit encoder Metamaterial Plasmon-induced transparency (PIT) effect Plasmonic-graphene Terahertz (THz)

来源：评论

学校读者我要写书评

暂无评论

A lightweight privacy-preserving scheme using label-based pixel block mixing for image classification in deep learning

arXiv

引用

arXiv 2021年

作者： Xiang, Yuexin Li, Tiantian Ren, Wei Zhu, Tianqing Raymond Choo, Kim-Kwang School of Computer Science China University of Geosciences Wuhan China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249-0631 United States

To ensure the privacy of sensitive data used in the training of deep learning models, a number of privacy-preserving methods have been designed by the research community. However, existing schemes are generally designed to work with textual data, or are not efficient when a large number of images is used for training. Hence, in this paper we propose a lightweight and efficient approach to preserve image privacy while maintaining the availability of the training set. Specifically, we design the pixel block mixing algorithm for image classification privacy preservation in deep learning. To evaluate its utility, we use the mixed training set to train the ResNet50, VGG16, InceptionV3 and DenseNet121 models on the WIKI dataset and the CNBC face dataset. Experimental findings on the testing set show that our scheme preserves image privacy while maintaining the availability of the training set in the deep learning models. Additionally, the experimental results demonstrate that we achieve good performance for the VGG16 model on the WIKI dataset and both ResNet50 and DenseNet121 on the CNBC dataset. The pixel block algorithm achieves fairly high efficiency in the mixing of the images, and it is computationally challenging for the attackers to restore the mixed training set to the original training set. Moreover, data augmentation can be applied to the mixed training set to improve the training’s *** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised federated learning with non-IID data: Algorithm and system design

arXiv

引用

arXiv 2021年

作者： Zhang, Zhe Ma, Shiyao Nie, Jiangtian Wu, Yi Yan, Qiang Xu, Xiaoke Niyato, Dusit School of Data Science and Technology Heilongjiang University Harbin150080 China Cryptology and Network Security Laboratory of Heilongjiang University Harbin150080 China College of Information and Communication Engineering Dalian Minzu University School of Computer Science and Engineering Nanyang Technological University WeBank Co. Ltd. China

Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the training data of local clients have ground-truth. Furthermore, FL faces the challenge of statistical heterogeneity, i.e., the distribution of the client’s local training data is non-independent identically distributed (non-IID). In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL. In particular, this paper focuses on studying the labels-at-server scenario where there is only a limited amount of labeled data on the server and only unlabeled data on the clients. In our system design, we propose a novel method to tackle the problems, which we refer to as Federated Mixing (FedMix). FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models. To alleviate the non-IID problem, we propose a novel aggregation rule based on the frequency of the client’s participation in training, namely the FedFreq aggregation algorithm, which can adjust the weight of the corresponding local model according to this frequency. Extensive evaluations conducted on CIFAR-10 dataset show that the performance of our proposed method is significantly better than those of the current baseline. It is worth noting that our system is robust to different non-IID levels of client data. Index Terms—Federated Learning, Semi-supervised Learning, non-IID, Aggregation Algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Systems analysis

来源：评论

学校读者我要写书评

暂无评论

Domestic Violence Crisis Recognition Method based on Bi-LSTM+Attention

Domestic Violence Crisis Recognition Method based on Bi-LSTM...

引用

International Conference on network and Information Systems for computers (ICNISC)

作者： Zhixiao Wang Wenyao Yan Zhuochun Li Min Huang Qinyuan Fan Xin Wang Xi'an University of Technology Xi'an China Shaanxi Key Laboratory of Network Computing and Security Xi'an China College of Xi'an Innovation Yan'an University Xi'an China University of Pittsburgh Pittsburgh PA USA Art and Design Xi'an University of Technology Xi'an China Fakultät Verkehrs- und Maschinensysteme Technische Universität Berlin Berlin Germany Computer Science and Engineering Xi'an University of Technology Xi'an China

ISBN: (纸本)9781665453523

Domestic violence (DV) is getting more and more attention due to the critical trouble and danger that pose great challenge to human rights and health. The popularity of various social medias can help these victims to share their experiences and obtain more possible support from numerous open communities. However, it is not only inefficient but also laborious and time-consuming to manually access and browse through a great deal of available posts on the Internet and social media space. Therefore, considering the advantages of Deep Learning (DL) technology in Natural Language Processing, adopting DL as an efficient strategy for automatic recognition and evaluation of DV victims is in the urgent requirements. This paper takes social media Facebook posts about domestic violence as the research object and uses Word2Vec to build word vector model. The paper uses Bi-LSTM+self-Attention deep learning models to accomplish DV crisis recognition task and compares it with CNN, RNN and LSTM. The assessment of experimental results show that the accuracy of CNN and LSTM are both above 90% which is better than RNN; And the accuracy of Bi-LSTM is the highest after using the Attention mechanism. The research results of this article will provide reference and help for public DVCS to rescue DV victims.

关键词： Deep learning Social networking (online) Computational modeling Blogs Manuals Predictive models Data models

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：