检索结果-内蒙古大学图书馆

Proceedings of the 2020 9th International Conference on computing and Pattern Recognition

作者： Wei Li Junqing Yuan Haonan Luo Zhou Lei Qingzheng Xu School of Computer Science and Engineering Xi'an University of Technology and Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China School of Computer Science and Engineering Xi'an University of Technology Xi'an China College of Information and Communication National University of Defense Technology Xi'an China

ISBN: (纸本)9781450387835

In the real world, many problems possess the high degree of similarity. Inspired by multifactorial inheritance model, evolutionary multi-task optimization paradigm is proposed to simultaneously solve multiple optimization problems. However, experimental results have revealed that the performance of multifactorial evolutionary algorithm deteriorates with negative knowledge transfer between uncorrelated tasks. To alleviate this issue, we proposed an enhanced competitive swarm optimizer to explore the generality of the multitasking paradigm. A new velocity update mechanism for losers is proposed to improve the search ability. Further, a mating approach is proposed to transfer implicit knowledge among tasks for generating offspring. Experimental and statistical analyses are performed on CEC2017 evolutionary multitask optimization competition. Results show that the proposed algorithm is competitive in comparison with other state-of-the-art multifactorial optimization algorithms.

关键词： Evolutionary multitasking competitive swarm optimizer evolutionary algorithms

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

On The Uncertainty Principle of Neural networks

arXiv

引用

arXiv 2022年

作者： Zhang, Jun-Jie Zhang, Dong-Xiao Chen, Jian-Nan Pang, Long-Gang Meng, Deyu Division of Computational physics and Intelligent modeling Institute of Nuclear Technology Shaanxi Xi’an710024 China Key Laboratory of Quark & Lepton Physics Ministry of Education Central China Normal University Hubei Wuhan30079 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China

In this study, we explore the inherent trade-off between accuracy and robustness in neural networks, drawing an analogy to the uncertainty principle in quantum mechanics. We propose that neural networks are subject to an uncertainty relation, which manifests as a fundamental limitation in their ability to simultaneously achieve high accuracy and robustness against adversarial attacks. Through mathematical proofs and empirical evidence, we demonstrate that this trade-off is a natural consequence of the sharp boundaries formed between different class concepts during training. Our findings reveal that the complementarity principle, a cornerstone of quantum physics, applies to neural networks, imposing fundamental limits on their capabilities in simultaneous learning of conjugate features. Meanwhile, our work suggests that achieving human-level intelligence through a single network architecture or massive datasets alone may be inherently limited. Our work provides new insights into the theoretical foundations of neural network vulnerability and opens up avenues for designing more robust neural network architectures. © 2022, CC0.

关键词： Adversarial machine learning

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

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Wei Ding Luyao Wang Wei Zhang Myung Jin Lee Ling Wang Kwang Woo Nam Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Industry-University Cooperstion Foundation Chungbuk National University Cheongju Korea School of Computer Science Northeast Electric Power University Jilin China School of Computer Science and Engineering Kunsan National University Gunsan Korea

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In this paper, we propose a new UAV video similarity measurement algorithm to cluster and analyze UAV videos by measuring the similarity between UAV videos and train them in sub-groups, which in turn improves the efficiency of UAV video data mining. Our preliminary work introduces the maximum common view subsequence (LCVS) to compute the similarity between UAV videos, but LCVS needs to frequently compute the common visible region of video frames generating extremely high time cost. In order to solve the problem of high computational cost of LCVS, we propose a similarity algorithm based on minimum tilted outer rectangle clustering (MTORC) for UAV videos. The MTORC algorithm adopts minimum tilted outer rectangle to cluster the field of view of the marked points in each frame, which reduces the time complexity of calculating the common visible region. By comparing experiments with LCSS and LCVS, the experimental results prove that MTORC is better than the present previous research in terms of algorithm accuracy and time cost.

关键词： Training Visualization Costs Accuracy Clustering algorithms Autonomous aerial vehicles Time measurement

来源：评论

学校读者我要写书评

暂无评论

A 3D Memristive Cubic Map with Dual Discrete Memristors: Design, Implementation, and Application in Image Encryption

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Gao, Suo Iu, Herbert Ho-Ching Erkan, Ugur Simsek, Cemaleddin Toktas, Abdurrahim Cao, Yinghong Wu, Rui Mou, Jun Li, Qi Wang, Chunpeng Dalian Polytechnic University School of Information Science and Engineering Dalian116034 China The University of Western Australia School of Electrical Electronic and Computer Engineering Perth6009 Australia Faculty of Engineering Electrical and Electronics Engineering Respectively Karamanoglu Mehmetbey University Karaman70200 Turkey Ankara University Engineering Faculty Department of Artificial Intelligence and Data Engineering Ankara06830 Turkey Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250000 China

Discrete chaotic systems based on memristors exhibit excellent dynamical properties and are more straightforward to implement in hardware, making them highly suitable for generating cryptographic keystreams. However, most existing memristor-based chaotic systems rely on a single memristor. This paper introduces a novel discrete chaotic system employing dual memristors, named the 3D memristive cubic map with dual discrete memristors (3D-MCM). The 3D-MCM system demonstrates richer and more intricate dynamical behaviors compared to its single-memristor counterparts, as verified through bifurcation diagrams, Lyapunov exponent spectra, and complexity analyses. Notably, the system exhibits coexisting attractors, substantially enhancing its dynamical complexity. Hardware implementation of the 3D-MCM attractors confirms its feasibility for industrial applications. To illustrate the system's potential in encryption tasks, this study integrates the quaternary-based permutation and dynamic emanating diffusion (QPDED-IE) scheme for image encryption with the *** results demonstrate that the QPDED-IE scheme based on the 3D-MCM exhibits strong diffusion and confusion properties, effectively resisting cryptanalytic attacks. © 1991-2012 IEEE.

关键词： Bifurcation (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Rapid Maize Seedling Detection Based on Receptive-Field and Cross-Dimensional Information Interaction

Rapid Maize Seedling Detection Based on Receptive-Field and ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Fengqi Hao Shulei Zhu Dexin Ma Xiangjun Dong Hoiio Kong Xia Liu Chunhua Mu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Data Science City University of Macau Macau China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Communication College Qingdao Agricultural University Qingdao China National Engineering Laboratory of Wheat and Maize/Key Laboratory of Biology and Genetic Improvement of Maize in Northern Yellow-huai River Plain Ministry of Agriculture Maize Research Institute Shandong Academy of Agricultural Sciences Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The seedling stage is important in the growth and development of maize, and it is also a critical period that affects maize yield and quality. Accurately recognizing this stage of maize is challenging, as current maize seedling detection methods struggle with small sizes and complex environments. This paper proposes a rapid maize seedling detection method that emphasizes spatial feature extraction in the receptive field and cross-dimensional interaction—receptive field triplet attention YOLO (RFT-YOLO). First, we design a convolutional module for cross-dimensional information interaction within the receptive field. Second, we introduce an advanced selective fusion network, which boosts the multi-scale fusion capability of small object features while reducing the GFLOPs of the model. Additionally, we employ Inner-IoU to diminish sensitivity to positional biases of small objects and expedite the convergence of the loss function. Finally, we create a dataset of maize seedlings to conduct our experiments. Experimental results demonstrate that the RFT-YOLO significantly enhances performance, reducing the number of parameters by 35.3% and GFLOPs by 14.24%, compared to the baseline model. Moreover, the mean average precision (mAP) improves from 89.6% to 91.5%. These improvements confirm the model's effectiveness in detecting maize seedlings.

关键词： YOLO Sensitivity Accuracy Semantics Feature extraction Complexity theory Data mining Cybernetics Convergence

来源：评论

学校读者我要写书评

暂无评论

network security Situational Awareness Model Based on Threat Intelligence 14th

Network Security Situational Awareness Model Based on Threat...

引用

14th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2021

作者： Zhang, Hongbin Yin, Yan Zhao, Dongmei Liu, Bin Gao, Hongbin School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050018 China Hebei Key Laboratory of Network and Information Security Hebei Normal University Hebei Shijiazhuang050024 China School of Economics and Management Hebei University of Science and Technology Shijiazhuang050000 China Research Center of Big Data and Social Computing Hebei University of Science Shijiazhuang05000 China

ISBN: (纸本)9783030898137

In order to deal with the problems that the increasing scale of the network in the real environment leads to the continuous high incidence of network attacks, the threat intelligence was applied to situational awareness, and the situational awareness model based on random game was constructed. Threat perception of the target system was performed by comparing the similarity between the exogenous threat intelligence and the internal security events of the system. At the same time, internal threat intelligence was generated based on the threat information inside the system. In this process, game theory was used to quantify the current network security situation of the system, evaluate the security status of the network. Finally, the prediction of the network security situation was realized. The experimental results show that the network security situation awareness method based on threat intelligence can reflect the changes in the network security situation and predict attack behaviors accurately. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Social-enhanced recommendation using graph-based contrastive learning

Social-enhanced recommendation using graph-based contrastive...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Peng Xue Qian Gao Jun Fan Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Shandong China China Telecom Digital Intelligence Techonology Co Ltd Jinan Shandong China

The social network-based recommendation model use social network information to mitigate data sparsity issues and improve the accuracy of recommendation models. However, In most social network-based recommendation algorithms, the social neighbors' contributions are difficult to distinguish from the central user's, neglecting hidden correlations in social infor-mation. In order to solve this problem, this paper presents a graph-based contrastive learning framework for social-enhanced recommendation (SoGCLR) that utilizes implicit social information captured by a new social relation attention mechanism, en-rich user representations, and improve model robustness through graph-based contrastive learning. Specifically, the paper captures the degree of contribution of each neighbor in the social graph to the central user through a social relation attention layer, thus obtaining hidden correlations in social information, and further integrates this with user information in the user-item interaction graph to enrich user representations. In addition, the paper incorporates graph-based contrastive learning into the recommendation task using cross-layer contrastive learning, calculating contrastive loss and mapping nodes with similar but different exposure rates to nearby regions to mitigate exposure bias issues. Results from Ciao and Epinions demonstrate that SoGCLR reduces RMSE and MAE by 1.33% to 1.84% compared with baseline models.

关键词：

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：