检索结果-内蒙古大学图书馆

2022 International Conference on Computer Application and Information Security, ICCAIS 2022

作者： He, Renjie Zheng, Xianghan Wang, Gong School of Computer and Big Data Fuzhou University Fujian Fuzhou China The Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fujian Fuzhou China

ISBN: (纸本)9781510663459

Data security has always been one of the public concerns, and homomorphic encryption technology, as one of the effective means to ensure data security, has always been a hot topic of academic research. Traditional machine learning is trained in a batch environment. In practice, data owners tend to outsource data and model training tasks to third-party clouds with huge computing resources, but data outsourcing carries the risk of privacy leakage. Therefore, in order to prevent this situation, an effective method is to encrypt the data before the outsourcing, and the third-party cloud trains the machine model of the ciphertext data. This method has special requirements for encryption algorithms which should support computation directly on the ciphertext data. This paper presents a novel data flow computing privacy protection framework based on the homomorphic encryption algorithm CKKS and the flow data processing engine Flink, called SDPPF (Streaming Data Privacy Protection on Flink). The proposed framework supports the functions of data stream encryption, decryption and ciphertext computing, and expands the functions of vector point multiplication and array sum operation on the basic simultaneous operation supported by the original CKKS algorithm. This paper also selects a classical machine learning algorithm: KNN algorithm, combined with the homomorphic encryption algorithm CKKS to realize the privacy protection machine learning algorithm. © 2023 SPIE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Efficient DOA Estimation Based on Cauchy Loss Variable Step Size Algorithm 6

Efficient DOA Estimation Based on Cauchy Loss Variable Step ...

引用

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Xu, Xingchao Li, Yingsong College of Information and Communications Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9798350399059

The Cauchy loss function is robust to large outliers and has successful applications in signal processing. In this paper, a DOA estimation algorithm based on adaptive zero technology is proposed, which updates the weight of the filter by applying the Cauchy loss function, and further improves the algorithm performance by using the variable step size method. The algorithm step size is adjusted by accumulating errors and establishing a nonlinear function with instantaneous errors. The DOA estimation ability, estimation error and accuracy of the improved Cauchy algorithm in the impulse noise environment are analyzed. The algorithm is verified by simulation experiments. © 2023 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRESSIVE MACHINE TRANSLATION 11

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Ma, Zhengrui Shao, Chenze Gui, Shangtong Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles the multi-modality problem by introducing dependency between vertices. However, training it with negative log-likelihood loss implicitly requires a strict alignment between reference tokens and vertices, weakening its ability to handle multiple translation modalities. In this paper, we hold the view that all paths in the graph are fuzzily aligned with the reference sentence. We do not require the exact alignment but train the model to maximize a fuzzy alignment score between the graph and reference, which takes captured translations in all modalities into account. Extensive experiments on major WMT benchmarks show that our method substantially improves translation performance and increases prediction confidence, setting a new state of the art for NAT on the raw training data. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Edge computing based multi-objective equilibrium task unloading of Internet of Vehicles 2

Edge computing based multi-objective equilibrium task unload...

引用

2nd International Conference on Electronic Information Technology, EIT 2023

作者： Wang, Lingjiao Tang, Chen Guo, Hua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiang Tan University 411105 China School of Automation and Electronic Information Xiang Tan University 411105 China

ISBN: (数字)9781510666627

ISBN: (纸本)9781510666610

The requirements of the Internet of Vehicles on the quality of service (QoS) of computing task offloading are constantly improving. The processing mode of edge computing, which deploys computing, bandwidth and storage resources near the user side, effectively improves the user experience. However, the computing capacity of edge servers is limited. Task offloading requests are overloaded and inefficient due to uneven server loads. Traditional cloud computing consumes a lot of energy and time. To solve the above problem, a KDQN based edge computing balanced task unloading mechanism is proposed: Q learning and convolutional neural network are used to obtain the optimal unloading strategy according to the returns of each step and continuous iterative updates, which reduces the convergence time of task unloading;K-means clustering is used to distribute part of the load of the overloaded server to the server with the closest European distance to achieve server load balancing. The experimental results show that compared to the existing offload mechanism, the new mechanism can reduce the average server energy consumption by 12.8%, the average service delay by 8.2%, and the average overload rate by 29.8%. © 2023 SPIE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Multi-Layer Cyclic Predictive Reversible Hiding Scheme for Data Blind Extraction of Compressed Domain

引用

Jisuanji Xuebao/Chinese Journal of Computers 2025年第4期48卷 910-926页

作者： Wen, Wen-Ying Yang, Yu-Heng Luo, Xin-Yu Zhang, Yu-Shu Fang, Yu-Ming School of Computing and Artificial Intelligence Jiangxi University of Finance and Economics Nanchang330013 China Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing Nanchang330013 China

Reversible data hiding in compressed sensing (CS) domains has been extensively studied in recent years. The proposal and development of reversible data hiding schemes in this domain have made it possible to hide large-capacity data in CS signals. However, existing reversible data hiding schemes in the CS domain face several challenges and limitations while realizing high-capacity data hiding. First, existing schemes usually lack directly usable measurements, which prevents the secret-carrying measurements from being directly used to reconstruct the original image, and thus can be easily detected during the transmission of the secret information. Second, some schemes generate auxiliary information when hiding the secret information, and these auxiliary information require an additional secure channel for transmission to ensure the correct extraction of the secret information, thus these schemes are unable to realize the blind extraction of the secret information. To address these problems, this paper proposes a new scheme, i. e., multi-layer cyclic predictive reversible hiding scheme for data blind-extraction of compressed domain. This new scheme utilizes the asymptotic recovery property of CS and the prediction error expansion technique to hide and extract data through multi-layer cyclic prediction. Specifically, this scheme performs cyclic prediction of CS measurements by CS multilayer cyclic prediction embedding technique and generates sharp histograms of prediction errors, which provide a large-capacity space for secret data embedding. Then, the additional information is embedded in the prediction error and then superimposed on the measurements by employing the histogram shifting method, and finally the auxiliary information is hidden in the lowest significant bit of the measurements in the specified region. In this way, blind extraction of information can also be realized when extracting information, and the lossless restoration of measurement values can be guar

关键词： Data encapsulation

来源：评论

学校读者我要写书评

暂无评论

Fourier ptychographic microscopy based on Gaussian apodization coherent transfer function constraints 3

Fourier ptychographic microscopy based on Gaussian apodizati...

引用

3rd International computing Imaging Conference, CITA 2023

作者： Cheng, Hong Li, Ju Liu, Hong Zhang, Hongyi Li, Yang School of Electronic and Information Engineering Anhui University Anhui Hefei230601 China Key Laboratory of Intelligent Computing & Signal Processing Anhui University Anhui Hefei230601 China

ISBN: (纸本)9781510671409

Fourier ptychographic microscopy technique combines the concept of phase retrieval algorithm and synthetic aperture, which can solve the problem that large field of view and high resolution cannot coexist. However, describing the linear transfer process of the imaging system by coherent transfer function in conventional calculations leads to ringing artifacts. Gaussian apodization coherent transfer function constraints is proposed and embedded into the software platform, and a high-resolution Fourier ptychographic microscopy imaging system is constructed together with the designed hardware. The proposed algorithm can reduce the ringing artifacts and ensure the accuracy and resolution of the reconstructed results by simulating experiments and acquiring real images. © 2023 SPIE.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Noise-tolerant fixed-time leader-follower consensus controller design for multi-agent systems via fuzzy-neural-network

引用

Neural computing and Applications 2025年 1-23页

作者： Dai, Jianhua Tan, Ping Xiao, Lin Wang, Zidong He, Yongjun Zuo, Qiuyue Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing MOE-LCSM Hunan Normal University Hunan Changsha410081 China Department of Computer Science Brunel University London UxbridgeUB8 3PH United Kingdom

The leader-follower consensus control problem in multi-agent systems (MASs) is critical and has received significant attention. However, the simultaneous achievement of fixed-time stability and robustness is often challenging in MASs due to their inherent complexity and uncertainty. This paper developed a controller based on the proposed noise-tolerant fixed-time fuzzy neural network (NF-FNN) model to realize the leader-follower consensus of MASs. Specifically, the introduction of an integral error term makes the NF-FNN model have powerful noise tolerance, and a fuzzy gain parameter generated by the Takagi-Sugeno fuzzy logic system makes the NF-FNN model have fuzzy adaptiveness. In addition, a new partition-sign-by-power activation function is developed to ensure fixed-time stability of the NF-FNN model. Theoretical analysis and comparative simulations confirm the superb swift stability and excellent noise tolerance of controllers based on the NF-FNN model for achieving the leader-follower consensus of MASs, as compared with existing methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Entity Alignment Through Joint Utilization of Multiple Pretrained Models for Attribution Relationship 11

Entity Alignment Through Joint Utilization of Multiple Pretr...

引用

11th IEEE International Conference on Cyber Security and Cloud computing, CSCloud 2024

作者： Yujia, Liu Tao, Xu Zhehan, Su Xinsong, Li Kaipeng, Xue Yuxin, Liu Northwest Minzu University Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing Gansu Lanzhou China Northwest Minzu University Key Laboratory of Linguistic and Cultural Computing Ministry of Education Gansu Lanzhou China College of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9798350376982

Most existing models for entity alignment tasks are based on a single pre-training mode. Through multiple experiments, it has been verified that a single pre-training model is no longer sufficient to meet the needs of current entity alignment tasks. Based on considerations of multiple pre-training models, this paper proposes an entity alignment method that utilizes multiple pre-training models. The purpose of this method is to address the limited accuracy in entity alignment tasks, with a particular focus on separately pre-training the embedding of entity attribute information and link relationship information for matching. To achieve the goal of improving entity alignment accuracy, this paper adopts joint alignment using pre-training with BERT and GloVe word embeddings. Experimental evaluations are conducted on the DBP15k dataset, and the results demonstrate that leveraging multiple pre-training models for attribute and relationship joint alignment can enhance model performance. The evaluation metrics of the model on three different language datasets, Hits@1 and MRR, are as follows: 0.899, 0.930, 0.964, and 0.932, 0.951, 0.975, respectively. These metrics indicate that the model performs well in aligning entities and outperforms current mainstream entity alignment methods. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Voice Acoustics for Speech Intelligence in Folk Songs 3rd

Research on the Application of Voice Acoustics for Speech In...

引用

3rd International Conference on Advanced intelligent Technologies, ICAIT 2022

作者： Lyu, Shiliang Chen, Shuang Qi, Hanyun Key Laboratory of Linguistic and Cultural Computing Ministry of Education Northwest Minzu University Gansu Lanzhou730000 China Gansu Provincial Key Laboratory of Intelligent Processing of National Languages Northwest Minzu University Gansu Lanzhou730000 China

ISBN: (纸本)9789819952021

Folk songs take language as the carrier, and the singing tune and cultural connotation of singing are the important research contents of many music scholars, ethnologists, and linguists. In the process of folk song singing, the vocalization of the singing voice has an important influence on the singing voice and artistic performance. The state of the singing pronunciation can be carefully observed through the acoustic analysis of the voice. This paper will introduce the specific application of voice acoustic analysis method in the research of folk song singing. Combined with the singing characteristics of folk songs, the vocal type of singing voice can be obtained through the parameters of voice acoustic analysis. The significance and the feasibility of the application of voice acoustic analysis in folk song research will be further explored. The research parameters and conclusions are helpful to speech recognition, speech synthesis, and artificial intelligence. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speech synthesis

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：