检索结果-内蒙古大学图书馆

作者： Zihao Fu Yang Gao Wanli Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui University

Reversible data hiding in encrypted domain(RDH-ED) fortifies data security and privacy safeguards while upholding the original data's integrity and *** research on RDH-ED focuses on 2D images,while research on 3D mesh models is still *** paper introduces an RDH-ED method using block modulus encryption and multi-MSB ***,the original mesh model is partitioned into non-overlapping subblocks of equal size,and then the vertices in each subblock are encrypted with the same key for additive modulus encryption,ensuring that the spatial correlation present in the original mesh subblocks remains preserved within the encrypted ***,the subblocks are disrupted one by one using the 3D Arnold Transform to enhance *** vertices in each embeddable subblock are divided into a reference vertex and several embeddable vertices,where the multi-MSB prediction strategy is employed to allocate embedding room for each embeddable ***,the secret information is embedded into the allocated *** the proposed method almost completely preserves the spatial correlation within each subblock,the achieved embedding rate surpasses that of all previous outstanding methods that rely on vacating room after encryption(VRAE).The experimental findings demonstrate that the proposed approach achieves an average embedding rate of 45.55 bits per vertex(bpv),surpassing the state-of-the-art method that achieves 25.63 bpv.

关键词： 3D mesh model Additive modulus encryption Reversible data hiding 3D Arnold Transform

来源：评论

学校读者我要写书评

暂无评论

A novel approach to deriving adaboost classifier weights using squared loss function for overlapping speech detection

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Asbai, Nassim Bounazou, Hadjer Zitouni, Sihem Department of Electronics Faculty of Sciences and Technology Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj City34030 Algeria Speech Com. & Signal Proc. Lab. Faculty of Electrical Engineering USTHB Bab Ezzouar City16111 Algeria Department of Computer Science Faculty of Mathematics and Computer Science Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj City34030 Algeria

In this paper, we address the complex problem of detecting overlapping speech segments, a key challenge in speech processing with applications in speaker diarization, automatic transcription, and multi-speaker recognition systems. Traditional approaches, often relying on exponential loss functions within the AdaBoost framework, struggle to maintain robustness in noisy or imbalanced data environments. To enhance detection accuracy, we propose a novel AdaBoost variant—SLFAdaBoost—utilizing a squared loss function specifically tailored for overlapping speech detection. This model demonstrates superior stability and convergence, significantly outperforming conventional methods. Experimental evaluation on the NIST 2005 corpus revealed that SLFAdaBoost achieves an accuracy range of 92.5% to 98.6%, with F1 scores between 95.4% and 99.2%, notably surpassing standard AdaBoost and Random Forest classifiers. Additionally, our model shows resilience in noisy conditions, maintaining precision and recall metrics at higher noise levels than other classifiers. These results underscore SLFAdaBoost's capacity to handle intricate data patterns, offering a more robust solution for real-world speech processing applications where overlapping segments are prevalent. This contribution provides an efficient, high-performing model, advancing the capabilities of ensemble methods in complex audio environments. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

Disentangling Hierarchical Features for Anomalous Sound Dete...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jian Guan Jiantong Tian Qiaoxi Zhu Feiyang Xiao Hejing Zhang Xubo Liu Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin China Acoustics Lab University of Technology Sydney Ultimo NSW Australia Centre for Vision Speech and Signal Processing University of Surrey Guildford UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model’s ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging availab.e metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift.

关键词： Metadata signal processing Feature extraction Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Indoor Accidents Detection for Elderly Based on Features Fusion and LSTM

Indoor Accidents Detection for Elderly Based on Features Fus...

引用

computer Applications (ICCA), IEEE Conference on

作者： Win Pa Pa San Sai Maung Maung Zaw Image and Signal Processing Lab University of Computer Studies Mandalay Mandalay Myanmar Faculty of Computer Systems and Technology University of Computer Studies Mandalay Mandalay Myanmar

ISBN: (数字)9798350353624

ISBN: (纸本)9798350353631

Nowadays, with aging of the human society, the “ratio of family care givers and elderly” is not equivalent and cannot give enough caring to the elderly in some countries. Therefore, automatic health monitoring system for elderly draws the interests of many researchers and become as special issue. In the implementation of elderly people monitoring system, the detection of fall events plays as an important role because the fall is the common cause which is very risky and threaten the health of elderly. The aim of this research is to implement the vision-based fall detection system which is important for health monitoring of elderly by applying the computer vision and deep learning technology. Most of the traditional vision-based fall detection systems which based on the height, width of human posture, fail to detect the fall events from different camera viewpoints. In this research, to accurately detect the fall from different camera viewpoint, the features fusion approach is applied over the deep learning model. In the implementation of the system, firstly, the human silhouette image is created by using the background subtraction. After that, the human silhouette image which have been extracted from two consecutive frames are fused as a single image called Silhouette History Image (SHI). Then, the SHI results are used as shape feature. On the other hand, the motion features called Dense Optical Flow (DOF) is extracted over the two consecutive video frames and fuse SHI and DOF as a single input image. Then, the results of features fusion are feed as input for pretrained Convolution Neural Network (CNN) for extracting the deep CNN features. Finally, the Recurrent Neural Network (RNN) called Long-Short-Term-Memory (LSTM) is trained over those CNN features for recognizing the sequence of fall event. The experiments are performed using the publicly availab.e dataset of UP-fall detection dataset for evaluating and confirming the effectiveness of the proposed method.

关键词： Deep learning Recurrent neural networks Shape Feature extraction Cameras Older adults Fall detection

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

arXiv

引用

arXiv 2025年

作者： Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin150001 China Acoustics Lab. University of Technology Sydney UltimoNSW2007 Australia Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Combining Enhancement and Fusion for Low-Light Visible and Infrared Image

Combining Enhancement and Fusion for Low-Light Visible and I...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Shaoji Zhang, Kunpeng Liang, Yudong Zhang, Chao Shangguan, Xuekui School of Computer and Information Technology Shanxi University Taiyuan China Key Lab. of Computational Intelligence and Chinese Information Processing of Ministry of Education China Shanxi Information Industry Technology Research Institute Co. Ltd China

ISBN: (纸本)9798350303759

Visible and infrared fusion aims to create a fused image that encompasses not only complex texture details and target-specific information but also facilitates advanced visual analyses. However, existing fusion algorithms rarely focus on the fusion of visible and infrared images in low-light environments. Therefore, in this article we propose a enhancement and fusion network for low-light visible and infrared that processes images in two stages. In the first stage, we correct the color shift of the visible light image caused by abnormal-light source and enhance the brightness of the image. In the second stage, we use the fusion network to fuse the enhancement results of the first stage with infrared, and use the loss function to constrain the network. Finally, we explore the performance of our fusion results for object detection tasks. Experimental results show that our fusion results have obvious brightness enhancement effect, high color contrast, obvious texture details and target information, and also achieve good performance in target detection tasks. © 2023 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A Robust Interference Suppression Method Based on FDA-MIMO Radar 5

A Robust Interference Suppression Method Based on FDA-MIMO R...

引用

5th International Conference on Information Communication and signal processing, ICICSP 2022

作者： Wu, Zhixia Zhu, Shengqi Xu, Jingwei Lan, Lan Zhang, Mengdi Li, Ximin Xidian University National Lab. of Radar Signal Processing Xi'an710071 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China

ISBN: (纸本)9781665485890

In the issue of interference suppression, the performance of traditional adaptive methods will decrease when mainlobe interference and sidelobe interference have angle error. To this end, a robust adaptive beamforming technique based on frequency diversity array (FDA) multiple-input multiple-output (MIMO) is proposed in this work. Firstly, preprocessing in data domain is adopted for mainlobe interference cancellation. Then, the sidelobe interference is suppressed in the receiving dimension. Finally, robust adaptive beamforming method is applied to suppress sidelobe interference. Simulation results show the effectiveness of the proposed algorithm. © 2022 IEEE.

关键词： MIMO radar

来源：评论

学校读者我要写书评

暂无评论

The transformative potential of vector symbolic architecture for cognitive processing at the network edge 2

The transformative potential of vector symbolic architecture...

引用

Artificial Intelligence for Security and Defence Applications II 2024

作者： Bent, Graham Davies, Cai Vilamala, Marc Roig Li, Yuhua Preece, Alun Sola, Alex Vicente Di Caterina, Gaetano Kirkland, Paul Tutcher, Benomy Pearson, Gavin Neurosynapse Ltd. United Kingdom Security Crime and Intelligence Institute Cardiff University United Kingdom Neuromorphic Sensor Signal Processing Lab. EEE Department University of Strathclyde United Kingdom Frazer-Nash Consultancy United Kingdom Defence Science and Technology Laboratory United Kingdom

ISBN: (纸本)9781510681200

Vector Symbolic Architecture (VSA), a.k.a. Hyperdimensional Computing (HDC) has transformative potential for advancing cognitive processing capabilities at the network edge. This paper examines how this paradigm offers r obust s olutions f or A I a nd A utonomy w ithin a f uture c ommand, c ontrol, c ommunications, computers, cyber, intelligence, surveillance and reconnaissance (C5ISR) enterprise by effectively m odelling t he cognitive processes required to perform Observe, Orient, Decide and Act (OODA) loop processing. The paper summarises the theoretical underpinnings, operational efficiencies, and synergy between VSA and current AI methodologies, such as neural-symbolic integration and learning. It also addresses major research challenges and opportunities for future exploration, underscoring the potential for VSA to facilitate intelligent decision-making processes and maintain information superiority in complex environments. The paper intends to serve as a cornerstone for researchers and practitioners to harness the power of VSA in creating next-generation AI applications, especially in scenarios that demand rapid, adaptive, and autonomous responses. © 2024 SPIE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Concrete Structural Crack Damage Classification Using Nonlinear Dimension Reduction and Broad Learning System

Concrete Structural Crack Damage Classification Using Nonlin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Bingshu Lin, Jia Zhuang, Xiaodong Zhang, Guanghui Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi'an China Shenzhen University Guangdong Key Lab. of Intelligent Info. Processing and Shenzhen Key Laboratory of Media Security Shenzhen China School of Computer Science and Technology Shandong University Qingdao China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781665410205

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Positionally restricted masked knowledge graph completion via multi-head mutual attention

引用

Journal of Information and Intelligence 2025年第3期3卷 210-222页

作者： Qiang Yu Liang Bao Peng Nie Lei Zuo Hangzhou Institute of Technology Xidian University Hangzhou 311231 China School of Computer Science and Technology Xidian University Xi'an 710071 China National Lab of Radar Signal Processing Xidian University Xi'an 710071 China

Knowledge graph completion aims to enhance the completeness of knowledge graphs by predicting missing links. Link prediction is a common approach for this task, but existing methods, particularly those based on similarity computation, are often computationally expensive, especially for large models. To address this, we propose a novel method, positionally restricted masked knowledge graph completion (PR-MKGC), which reduces inference time by leveraging masked prediction and relying solely on structural information from the knowledge graph, without using textual data. We introduce a multi-head mutual attention mechanism that aggregates neighbor information more effectively, improving the model's ability to predict missing links. Experimental results demonstrate that PR-MKGC outperforms existing models in terms of both predictive performance and inference time on the FB15K-237 dataset.

关键词： Knowledge graph Link prediction Attention mechanism Information aggregation

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：