检索结果-内蒙古大学图书馆

Fusion of Multimodal Audio Data for Enhanced Speaker Identification Using Kolmogorov-Arnold Networks

IEEE Access 2025年 13卷 87640-87653页

作者： Tamotia, Aryaman Karmokar, Dhruv Shantu Komal, Rethi Nawas, K. Khadar Shahina, A. Khan, A. Nayeemulla Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India Sri Sivasubramaniya Nadar College of Engineering Department of Information Technology Tamil Nadu Kalavakkam603110 India

Speaker identification using audio data is quite challenging because of inherent differences between people, ambient noise, and variable recording conditions. Although the classical deep learning methods are effective, they have rather high computational cost, which leads to usually cumbersome parameter tuning processes and hence reduce their applicability to real-world deployments. In this paper, we discuss an efficient version of Kolmogorov-Arnold Network for audio-based speaker identification using three different types of audio inputs: bone conduction, air conduction, and throat microphone recordings, alongside evaluation on the publicly available LibriSpeech dataset to enhance reproducibility. To optimize the performance of these modalities, we investigate data-level, feature-level, and decision-level fusion techniques. An exhaustive comparison is performed against some of the prominent deep learning architectures, namely VGG-19, ResNet-152, EfficientNetV2, and DenseNet-121, both as standalone architectures and within multimodal combinations for the purpose of evaluating the proposed framework. We demonstrate that our model achieves a significant increase in accuracy up to 99.375% through the use of MFCC and GFCC feature inputs with data-level fusion through MFCC features and achieves this level of accuracy using substantially fewer parameters than those of conventional deep learning models. This makes the KAN framework a highly efficient choice for audio-based speaker identification. One of the critical innovations within this design is a class of trainable activation functions that eliminate the need for traditional weight parameters, thereby providing scalable and computationally efficient solutions. This work contributes to the field of biometrics by providing a refined, resource-efficient approach to speaker identification based on multimodal audio data. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A survey of video violence detection

引用

Cyber-Physical Systems 2023年第1期9卷 1-24页

作者： Yao, Huiling Hu, Xing School of Optical-Electrical Information and Computer Engineering University of Shanghai for Science and Technology Shanghai China

As one of the important applications of intelligent video surveillance, violent behaviour detection (VioBD) plays a crucial role in public security and safety. As a particular type of behaviour recognition, VioBD aims to identify whether the behaviours that occurred in the scene is aggressive, such as fighting and assault. To comprehensively analyse the current state and predict the future trend of VioBD research, we survey the existing approaches of VioBD in this work. First, we briefly introduce the basic principle and the challenges of VioBD;Then, we category the existing approaches according to their framework, including the traditional framework, end-to-end deep learning framework, and hybrid deep learning framework. Finally, we introduce the public datasets for evaluating the performance of VioBD approaches and compare their performances on these datasets. Besides, we also summarise the open problems in VioBD and predict its future trends. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Resilient Distributed Kalman Filtering Against Malicious Cyber Attacks

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 7610-7625页

作者： Xia, Wei Zhou, Mengqing University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Xinjiang University School of Computer Science and Technology School of Cyberspace Security Ürümqi830046 China

In this work, we consider the resilient distributed Kalman filtering (RDKF) for adversarial networks in the presence of different malicious cyber attacks, and develop an RDKF algorithm to enhance the network estimation accuracy. Specifically, we develop an attack detection approach such that each node would distinguish its secure neighbor(s) from its compromised counterpart(s), and determine whether it is compromised or not. We further propose a resilient fusion strategy to restrain the propagation of malicious intermediate estimates of each compromised node. We also theoretically analyze the mean and mean-square stability of the proposed RDKF algorithm, and develop an optimal reliable reference neighbor selection scheme, such that the network estimation accuracy could be further enhanced. Illustrative simulations validate the efficacy of the proposed algorithm for adversarial networks under different cyber attacks, even under potentially time-varying attacks. © 1965-2011 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China Communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

From Perception to Action:Brain-to-Brain information Transmission of Pigeons

引用

Journal of Bionic engineering 2024年第6期21卷 2913-2923页

作者： Lifang Yang Long Yang Haofeng Wang Mengmeng Li Zhigang Shang School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou450001China

Along with the flourishing of brain-computer interface technology,the brain-to-brain information transmission between different organisms has received high attention in recent ***,specific information transmission mode and implementation technology need to be further *** this paper,we constructed a brain-to-brain information transmission system between pigeons based on the neural information decoding and electrical stimulation encoding *** system consists of three parts:(1)the“perception pigeon”learns to distinguish different visual stimuli with two discrepant frequencies,(2)the computer decodes the stimuli based on the neural signals recorded from the“perception pigeon”through a frequency identification algorithm(neural information decoding)and encodes them into different kinds of electrical pulses,(3)the“action pigeon”receives the Intracortical Microstimulation(ICMS)and executes corresponding key-pecking actions through discriminative learning(electrical stimulation encoding).The experimental results show that our brain-to-brain system achieves information transmission from perception to action between two pigeons with the average accuracy of about 72%.Our study verifies the feasibility of information transmission between inter-brain based on neural information decoding and ICMS encoding,providing important technical methods and experimental program references for the development of brain-to-brain communication technology.

关键词： Pigeon Neural information Decoding Electrical Stimulation Encoding Intracortical Microstimulation Brain-to-brain information Transmission

来源：评论

学校读者我要写书评

暂无评论

Which is more faithful,seeing or saying? Multimodal sarcasm detection exploiting contrasting sentiment knowledge

引用

CAAI Transactions on Intelligence technology 2025年第2期10卷 375-386页

作者： Yutao Chen Shumin Shi Heyan Huang School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications BeijingChina

Using sarcasm on social media platforms to express negative opinions towards a person or object has become increasingly ***,detecting sarcasm in various forms of communication can be difficult due to conflicting *** this paper,we introduce a contrasting sentiment-based model for multimodal sarcasm detection(CS4MSD),which identifies inconsistent emotions by leveraging the CLIP knowledge module to produce sentiment features in both text and ***,five external sentiments are introduced to prompt the model learning sentimental preferences among ***,we highlight the importance of verbal descriptions embedded in illustrations and incorporate additional knowledge-sharing modules to fuse such imagelike *** results demonstrate that our model achieves state-of-the-art performance on the public multimodal sarcasm dataset.

关键词： CLIP image-text classification knowledge fusion multi-modal sarcasm detection

来源：评论

学校读者我要写书评

暂无评论

Improving graph collaborative filtering with network motifs

引用

Neural Computing and Applications 2025年第16期37卷 9413-9432页

作者： Zhang, Yuqi Yu, Jian Liu, Zhizhong Wang, Guiling Nguyen, Minh Sheng, Quan Z. Wang, Nancy Department of Computer and Information Sciences Auckland University of Technology Auckland Central1010 New Zealand School of Computer and Control Engineering Yantai University Shandong Yantai264005 China School of Information Science and Technology North China University of Technology Beijing100144 China School of Computing Macquarie University SydneyNSW2109 Australia

Deep learning on graphs, specifically graph convolutional networks (GCNs), has exhibited exceptional efficacy in the domain of recommender systems. Most GCNs have a message-passing architecture that enables nodes to aggregate information from neighbours iteratively through multiple layers. This enables GCNs to learn from higher-order information, but the model does not allow for direct captions of the local structural patterns. Our rationale is to investigate the effectiveness of capturing such local patterns for graph-based collaborative filtering to enhance model’s learning ability per layer. This technique combines lower-order and higher-order interactions during layer-wise propagation. In this paper, we propose MotifGCN to aggregate both lower-order and higher-order information in each graph convolution layer. Specifically, we develop dedicated algorithms of generating motif adjacency matrices. The matrices are then used for motif-enhanced neighbourhood aggregation in each layer. As this paper focuses on recommender systems, MotifGCN is built on the basis of bipartite graphs. Our experiments on four real-world datasets show that MotifGCN has a superior performance compared to various state-of-the-art methods. © The Author(s) 2025.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Sparse and Dense: Learning Confusion Representation Network for 3-D Action Recognition

引用

IEEE Internet of Things Journal 2025年第12期12卷 21240-21254页

作者： Hou, Xinran Geng, Pei Li, Tianchen Li, Yalin Li, Yan Lyu, Lei Shandong Normal University School of Information Science and Engineering Jinan250358 China Shandong Management University School of Information Engineering Jinan250100 China Shandong Normal University School of Information Science and Engineering Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250358 China

In the field of the Internet of Medical Things (IoMT), the demand for Human action recognition (HAR) is growing. Due to the limitations of portability and privacy of traditional sensors, many endeavors have made significant progress in 3-D skeleton-based action recognition. However, existing methods ignore potential higher-order semantic information between joints and fail to perceive rapidly changing dynamic details, resulting in frequent confusion of actions with similar motion trajectories. To alleviate this issue, we propose a novel learning confusion representation network (LCR-Net). Specifically, a progressive feature enhancement module is first designed to utilize self-attention to gradually aggregate lower-order features to higher-order features, emphasizing the relative movement between body parts. Second, we design the enhanced spatio-temporal convolution to explore the potential spatio-temporal dependencies between joints by adding a mask matrix and an attention fusion mechanism. To further perceive the spatio-temporal relationships in subtle changes, we divide the interactive sparse-dense pathways at different spatio-temporal resolutions and enhance the complementary information between the two pathways through feature interaction. Finally, the frequency excitation learning module is proposed to efficiently learn the importance of different frequencies by cross-channel modeling, promoting the compactness of actions within classes and the separability of confusion actions. In addition, the lightweight LCR-Net+ is achieved through model compression optimization to meet the deployment requirements of IoT systems. Comprehensive experiments conducted on three public datasets (NTU-RGB+D60&120, NW-UCLA) demonstrate the superior performance of our model. © 2014 IEEE.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

An Improved Dehazing Algorithm Combining Dark Channel Prior and Artificial Bee Colony Algorithm

An Improved Dehazing Algorithm Combining Dark Channel Prior ...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Li, Zhenguo Ma, Lisheng Hou, Yibin Li, Jiaxin Tao, Tao Anhui University of Technology School of Computer Science and Technology China Chuzhou University School of Computer and Information Engineering China

ISBN: (纸本)9798350355581

Aiming to address significant issues like severe halo effects and excessive noise present in images processed by the traditional dark channel prior-based dehazing algorithm using fixed values, a proposed enhancement method leverages the characteristics of the artificial bee colony algorithm for parameter optimization. It seeks the optimal atmospheric light transmission factor values within different average image brightness ranges and integrates these values into the dark channel prior-based dehazing algorithm. Simultaneously, in estimating the atmospheric light, a median filtering algorithm replaces the original twostep minimum value filtering process. This improvement exhibits notable effectiveness in reducing halo effects and noise compared to the traditional dark channel prior-based dehazing algorithm. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

FLAG: frequency-based local and global network for face forgery detection

引用

Multimedia Tools and Applications 2025年第2期84卷 647-663页

作者： Zhou, Kai Sun, Guanglu Wang, Jun Wang, Jiahui Yu, Linsen School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Department of Information Engineering and Mathematics University of Siena Siena53100 Italy

Deepfake detection aims to mitigate the threat of manipulated content by identifying and exposing forgeries. However, previous methods primarily tend to perform poorly when confronted with cross-dataset scenarios. To address the above issue, we propose an innovative hybrid network called the Frequency-based Local and Global (FLAG) network to explore local and global information with the help of frequency-domain cues for better generalization capability. In consideration of the fact that forged faces often exhibit flaws in the frequency domain, we design a Frequency-based Attention Enhancement Module (FAEM) to enhance the aggregation of CNN and Vision Transformer (ViT). In this design, local features from CNN are attentively enhanced by selected frequency coefficients in FAEM, facilitating generalizable global features learning by the ViT module. The effectiveness of the proposed method is validated via numerous experiments and the generalization performance is improved under cross-dataset scenarios. Especially, the proposed method have obtained an AUC of 99.26% and an ACC of 96.56% using intra-dataset experimental results on FaceForensics++ (C23). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Face recognition

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：