检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Mou, Xudong Wang, Rui Wang, Tiejun Sun, Jie Li, Bo Wo, Tianyu Liu, Xudong Beihang University School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Beihang University Sklsde School of Software Beijing China

ISBN: (纸本)9781728163277

Time-series Anomaly Detection(AD) is widely used in monitoring and security applications in various industries and has become a hot spot in the field of deep learning. Normality-representation-based methods perform well in certain scenarios but may ignore some aspects of the overall normality. Feature-extraction-based methods always take a process of pre-training, whose target differs from AD, leading to a decline in AD performance. In this paper, we propose a new AD method called deep Autoencoding One-Class (AOC), which learns features with AutoEncoder(AE). Meanwhile, the normal context vectors from AE are constrained into a hypersphere small enough, similar to one-class methods. With an objective function that optimizes the two assumptions simultaneously, AOC learns various aspects of normality, which is more effective for AD. Experiments on public datasets show that our method outperforms existing baseline approaches. © 2023 IEEE.

关键词： Autoen-coder One-class classification Time Series Anomaly Detection

来源：评论

学校读者我要写书评

暂无评论

Crack Detection Method for Asphalt Pavement Combining Multi-scale Features and Attention Mechanism 4

Crack Detection Method for Asphalt Pavement Combining Multi-...

引用

4th International Conference on Advances in Electrical engineering and computer Applications, AEECA 2023

作者： Xu, Zijian Wang, Lili Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing China Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing China

ISBN: (纸本)9798350308082

Crack, as one of the common diseases of asphalt pavements, seriously affects the health of asphalt pavements. To cope with the demand of crack detection in the context of complex pavements, an improved network model with an encoder-decoder structure is proposed. First, dense long and short connections are combined with full-scale jump connections, and the jump connection structure yields fullscale feature information to each node of the decoding layer. Second, spatial and channel attention modules are incorporated into the proposed network. The former is used at the low level of the network to improve the ability to capture crack detail information, and the latter is applied at the high level of the proposed network to obtain the semantic information. Finally, improve network performance by building deep supervision network. The proposed network is compared with on three datasets, DeepCrack, CFD, and Crack500, and the F-score reaches 86.79%. In this paper, the network is effective in crack detection and plays a certain role in maintaining road safety. © 2023 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

CIFD: A Distance for Complex Intuitionistic Fuzzy Set 4th

CIFD: A Distance for Complex Intuitionistic Fuzzy Set

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhao, Yangyang Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9783031200953

Intuitionistic fuzzy set (IFS) has attracted much attention because it can deal with fuzziness and uncertainty more flexibly than traditional fuzzy set. Complex intuitionistic fuzzy set (CIFS) extends intuitionistic fuzzy to the complex plane, which can better express and process uncertain information. In this paper, a novel distance measure complex intuitionistic fuzzy distance (CIFD) is proposed for CIFSs. Firstly, inspired by Tanimoto coefficient, a new similarity measure between CIFSs is proposed. Then, based on the similarity measure, the CIFD is proposed and its non-negativity, non-degeneracy, and symmetry are analyzed. Moreover, when CIFS degenerates into classical IFS, CIFD is also applicable to measure the differences between IFSs. Finally, to illustrate the effectiveness of CIFD, an example is given at the end. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Reseed Skipping of Linear Congruential Generator for Multi-level Image Steganography Security of Financial Data

引用

SN computer science 2023年第2期4卷 124页

作者： Danso, Juliana Mantebea Missah, Yaw Marfo Gyamfi, Enoch Opanin Dankwa, Stephen Kwabena, Sarpong Department of Computer Science Kwame Nkrumah University of Science and Technology (KNUST) Kumasi Ghana School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Cyber Security and Computer Engineering Technology School of Computing and Information Sciences C.K. Tedam University of Technology and Applied Sciences Upper East Region Navrongo Ghana School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

This paper proposed a multi-level image steganography model that integrates with image and plaintext encryption schemes. The model starts by partitioning the cover-image pixel positions into two regions of respective purposes, one is reserved to hold the data, and through the implementation of the dynamic difference expansion principle, the other sloughs some parts to the reserved region in responsive to the size of the data to embed. Continuously reseeding and initializing the parameter values of a Linear Congruential Generator (LCG), generate a set of random pixel positions as members of the reserved region. Before data embedding, the region reserved to hold the data as well as the data bits to embed, are then encrypted using AES with respective keys. Encryption keys are randomly generated using a Cryptographically Secure Pseudo-Random Number Generator (CSPRNG), the Fortuna algorithm. Multiplex security nature of using a randomization generator to reserve image region for encryption and encrypting plaintext data before performing steganography still ensures stability in computational complexities better than a logarithmic O(n log n). A visual inspection by evaluators who made 3000 choices to correctly differentiate stego images from its cover-images shows that only 47 choices were correct, 1884 choices were wrong, while 1069 choices were uncertain. An experiment shows an average Embedding Rates (ERs) of 0.00109 bpp and an average PSNR of 72. This concludes, as our integrated steganography and image encryption which implements the dynamic difference expansion principle, outputs encrypted stego mages that can deceive the naked human eyes into identifying them as rather cover-images, its embedding rate is faster (i.e. ER < 0.1), suitably good, and ensures better imperceptibility of cover-image alterations. When comparing these experimental results with existing methods, our proposed model shows significant competitiveness. We even show real-life scenarios on how this

关键词： AES encryption scheme Dynamic difference expansion principle Linear congruential generator Pseudo-random number generator Reserving room before encryption Steganography

来源：评论

学校读者我要写书评

暂无评论

Tri-PANet: Triplanar Ensemble Network with Parallelly Aggregating Global and Local Information for Brain Tumor Segmentation

Tri-PANet: Triplanar Ensemble Network with Parallelly Aggreg...

引用

2023 International Conference on Machine Vision, Image Processing and Imaging Technology, MVIPIT 2023

作者： Zhou, Li Fang Li, Jun Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing China Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing China

ISBN: (纸本)9798350306545

Accurate segmentation of brain tumor images holds great importance in the clinical diagnosis and effective treatment of brain tumors diseases. Nonetheless, tumors exhibit extensive variations in their characteristics, both in terms of their visual appearance and their location within brain MR images. This poses a significant challenge in achieving robust tumor segmentation. Furthermore, sample labeling bias problem also limits the segmentation accuracy of current methods. In this work, we propose a innovation approach named Tri-PANet for brain tumor segmentation. On the one hand, Tri-PANet learns both local features and global dependencies of images to better obtain shape and location information from a global perspective. On the other hand, Tri-PANet constrains tumor regions that are prone to mislabeling by a triplanar ensemble framework, with an independent tumour core prediction module. We evaluate our method using publicly accessible brain tumor segmentation datasets BraTS2019 and BraTS2020. The experimental results demonstrate that our propose model effective segmentation the tumor region and consistently outperform state-of-the-art methods. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Tencent pretrain: A scalable and flexible toolkit for pre-Training models of different modalities 61

Tencent pretrain: A scalable and flexible toolkit for pre-Tr...

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL-DEMO 2023

作者： Zhao, Zhe Li, Yudong Hou, Cheng Zhao, Jing Tian, Rong Liu, Weijie Chen, Yiren Sun, Ningyuan Liu, Haoyan Mao, Weiquan Guo, Han Guo, Weigang Wu, Taiqiang Zhu, Tao Shi, Wenhang Chen, Chen Huang, Shan Chen, Sihong Liu, Liqun Li, Feifei Chen, Xiaoshuai Sun, Xingwu Kang, Zhanhui Du, Xiaoyong Shen, Linlin Yan, Kimmo Tencent AI Lab School of Computer Science and Software Engineering Shenzhen University China School of Information and DEKE MOE Renmin University of China China

ISBN: (纸本)9781959429708

Recently, the success of pre-Training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-Training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-Training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-Training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pretraining models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-Training model. The modular design enables users to efficiently reproduce existing pre-Training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations. © ACL-DEMO 2023. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Research on key technologies of edge cache in virtual data space across WAN

引用

Frontiers of computer science 2023年第1期17卷 15-34页

作者： Jiantong HUO Yaowen XU Zhisheng HUO Limin XIAO Zhenxue HE State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China High Performance Computing Center Beihang UniversityBeijing 100191China College of Software Beihang UniversityBeijing 100191China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China College of Computer Science and Technology Zhejiang UniversityHangZhou 310013China

The authors of this paper have previously proposed the global virtual data space system (GVDS) to aggregate the scattered and autonomous storage resources in China’s national supercomputer grid (National Supercomputing Center in Guangzhou, National Supercomputing Center in Jinan, National Supercomputing Center in Changsha, Shanghai Supercomputing Center, and computer Network Information Center in Chinese Academy of sciences) into a storage system that spans the wide area network (WAN), which realizes the unified management of global storage resources in China. At present, the GVDS has been successfully deployed in the China National Grid environment. However, when accessing and sharing remote data in the WAN, the GVDS will cause redundant transmission of data and waste a lot of network bandwidth resources. In this paper, we propose an edge cache system as a supplementary system of the GVDS to improve the performance of upper-level applications accessing and sharing remote data. Specifically, we first designs the architecture of the edge cache system, and then study the key technologies of this architecture: the edge cache index mechanism based on double-layer hashing, the edge cache replacement strategy based on the GDSF algorithm, the request routing based on consistent hashing method, and the cluster member maintenance method based on the SWIM protocol. The experimental results show that the edge cache system has successfully implemented the relevant operation functions (read, write, deletion, modification, etc.) and is compatible with the POSIX interface in terms of function. Further, it can greatly reduce the amount of data transmission and increase the data access bandwidth when the accessed file is located at the edge cache system in terms of performance, i.e., its performance is close to the performance of the network file system in the local area network (LAN).

关键词： virtual data space system wide area network edge cache redundant data transmission

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain

FreqSense: Universal and Low-Latency Adversarial Example Det...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Yihuan Li, Yuanzhe Ren, Yanzhen Tu, Weiping Yang, Yuhong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education China School of Cyber Science and Engineering Wuhan University China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China

ISBN: (纸本)9798350368741

Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes, this paper proposes FreqSense, an AE detection scheme based on frequency distribution features. FreqSense detects a variety of unknown AE attacks with low latency, and provides interpretability in its detection process. The basic idea of FreqSense is that AE typically introduce carefully designed noise in specific frequency bands that are associated with highly distinctive speaker identities. Therefore, leveraging the distributional variations in these frequency bands can effectively distinguish between AE and benign audio. FreqSense models frequency distribution features by integrating time-frequency transformation technology with a self-attention mechanism and employs a neural network-based classifier to distinguish between AE and benign audio. Experimental results show that FreqSense achieves an overall detection accuracy of 99.2%, surpassing state-of-the-art (SOTA) schemes by 27.2%. When confronting unknown AE attacks, FreqSense achieves a detection accuracy of 98.3% with a latency of just 0.0014 seconds. © 2025 IEEE.

关键词： Adversarial Attack Adversarial Example Detection Speaker Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

MSKI-Net: Towards modality-specific knowledge interaction for glioma survival prediction

MSKI-Net: Towards modality-specific knowledge interaction fo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Su, Ran Xiao, Jin Cui, Hui Xuan, Ping Feng, Xikang Wei, Leyi Jin, Qiangguo Tianjin University School of Computer Software College of Intelligence and Computing Tianjin China La Trobe University Department of Computer Science and Information Technology Melbourne Australia Shantou University School of Engineering Department of Computer Science China Northwestern Polytechnical University School of Software China Macao Polytechnic University AIDD Faculty of Applied Science China Xiamen University School of Information Xiamen China Yangtze River Delta Research Institute Northwestern Polytechnical University Taicang China

ISBN: (纸本)9798350386226

Gliomas hold a prominent position in neurooncology due to their high malignancy and poor survival rates. Accurately predicting the prognosis and survival risk of glioma patients is crucial for clinical treatment. Recent advances in survival prediction methods emphasize the importance of integrating complementary information from diverse modalities while neglecting the significant modality gap between pathological images and genomic data. To address this issue, we propose a modality-specific knowledge interaction network (MSKI-Net), which integrates whole slide images (WSI), RNA-Seq gene expression data, and copy number variation (CNV) data for glioma survival analysis. The MSKI-Net consists of a modality-specific feature enhancement (MSFE) module, a modality-interactive cross-attention (MICA) module, and a modality-specific knowledge-guided representation learning (MSKR) module. The three modules collaborate by complementing modality-specific features with modality-agnostic knowledge to improve the learning capability of MSKI-Net. Furthermore, we construct a dataset named TCGAmm, which combines WSI, RNA-Seq, and CNV data from The Cancer Genome Atlas (TCGA) to address the issue of data scarcity. Extensive experiments demonstrate that MSKI-Net achieves superior performance in predicting the survival risk of glioma cancer. © 2024 IEEE.

关键词： Gene expression

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：