检索结果-内蒙古大学图书馆

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

Minimizing Deployment Cost of Hybrid Applications 4

Minimizing Deployment Cost of Hybrid Applications

引用

4th IEEE International Conference on Quantum computing and engineering, QCE 2023

作者： Aparicio-Morales, Alvaro M. Herrera, Juan Luis Moguel, Enrique Berrocal, Javier Garcia-Alonso, Jose Murillo, Juan M. Universidad de Extremadura Quercus Software Engineering Group Cáceres Spain Computing and Advanced Technologies Foundation of Extremadura Cáceres Spain

ISBN: (纸本)9798350343236

Within Quantum software engineering, the development of hybrid classical-quantum applications is an active research topic. Concretely, there is a focus on the usage of microservices architectures to offer quantum functionalities through classical service gateways. However, while there are methodologies and tools to automatically determine the best deployment for classical applications, this is not the case for hybrid applications, which are especially complicated to deploy due to their specific quantum-requirements. In this paper, we propose Cost Minimizer, a tool to determine the most cost-effective classical and quantum machines to deploy hybrid microservice-based applications. We believe Cost Minimizer will be a step towards achieving a better interaction between classical and quantum computing systems. © 2023 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Empirical Study on Mispronunciation Detection for Tajweed Rules during Quran Recitation 6

Empirical Study on Mispronunciation Detection for Tajweed Ru...

引用

6th International Conference on computing and Informatics, ICCI 2024

作者： Alsahafí, Yousef S. Asad, Muhammad Department of Information technology Computing and Information technology Khulis College University of Jeddah Jeddah Saudi Arabia Department of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Science and Technology Islamabad Pakistan

ISBN: (纸本)9798350373875

This paper presents an extensive empirical study aiming to identify the optimal combination of feature extraction techniques and machine learning algorithms, including deep learning, for automated mispronunciation detection during Quran recitation. Three feature extraction methods-Mel-Frequency Cepstral Coefficients (MFCC), Spectrogram, and Kaldi pitch - are systematically evaluated in conjunction with a diverse set of classifiers, including Gradient Boosting (GB), Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Artificial Neural Network (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. The study leverages the QDAT dataset, comprising 1500 audio samples from 150 readers, with metadata specifying age, gender, and three distinct rules for mispronunciation detection. Experimental results demonstrate that the integration of MFCC with deep learning classifiers consistently achieves the highest performance across multiple evaluation metrics. Model robustness is validated using receiver operator characteristic curves (ROC) and accuracy metrics. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

CA-Res2UNet++: a Deep Residual UNet Based Method for Brain Tumor Segmentation in Multimodal MRI 2

CA-Res2UNet++: a Deep Residual UNet Based Method for Brain T...

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Hu, Yujiao Chen, Weiting Wu, Wenjing Long, Jianghao MOE Research Center of Software / Hardware Co-Design Engineering Shanghai Key Laboratory of Trustworthy Computing East China Normal University China

ISBN: (纸本)9781510666733

In recent years, segmentation of the multimodal brain tumor image puts forward high requirements for performance. To meet the accuracy requirements, we propose a multimodal brain tumor image segmentation method based on UNet and deep residual learning, which can make full use of multimodal information in order to obtain details. The model achieves the information extraction and integration of multimodal images at different scales by introducing a multiscale feature extraction module, a coordinate attention module, and a dense atrous spatial pyramid pooling module. The results show that the proposed method can fully exploit the multi-scale context information of multimodal images, alleviate the problem of blurred edges in segmentation regions, and achieve good performance on popular evaluation metrics. © 2023 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Transformation Based Image Representation and Analysis of Amplitude-integrated EEG 2

Multi-scale Transformation Based Image Representation and An...

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Wu, Wenjing Chen, Weiting Hu, Yujiao MOE Research Center of Software / Hardware Co-Design Engineering Shanghai Key Laboratory of Trustworthy Computing East China Normal University China

ISBN: (纸本)9781510666733

Amplitude-integrated electroencephalography (aEEG) is widely adopted for recognizing neonatal neurological disorders in clinics. Previous work has mainly analyzed aEEGs from a time series perspective, while clinicians are more concerned about images. This paper studies the efficacy of image representations in aEEG interpretation. To this end, we employ Amplitude-frequency contour map (AFCM) to express information on local amplitude distributions and overall temporal trend. During its generation, Multi-scale Box-Cox transformation is introduced to flexibly control the degree of amplitude compression and capture details in different amplitude regions. Moreover, one- and two-dimensional features are extracted and combined to enhance model predictions. The experimental results show the potential of image representation for aEEG recognition. This method can provide new ideas to analyze time series signals like aEEGs from the perspective of combining time series and image. © 2023 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

The Current and Future Role of Visual Question Answering in eXplainable Artificial Intelligence 31

The Current and Future Role of Visual Question Answering in ...

引用

Workshops at the 31st International Conference on Case-Based Reasoning, ICCBR-WS 2023

作者： Caro-Martínez, Marta Wijekoon, Anjana Díaz-Agudo, Belén Recio-García, Juan A. Department of Software Engineering and Artificial Intelligence Universidad Complutense de Madrid Spain School of Computing Robert Gordon University Aberdeen United Kingdom

Over the last few years, we have seen how the interest of the computer science research community on eXplainable Artificial Intelligence has grown in leaps and bounds. The reason behind this rise is the use of Artificial Intelligence in many daily life tasks, and the consequent necessity of people to understand the intelligent systems’ behaviour. Computer vision-related tasks are not an exception, for example, Visual Question Answering tasks. The Artificial Intelligence models that carry out this specific task make an effort to answer questions about what we can watch in a particular image. In this work, we review the existing work about eXplainable Artificial Intelligence on Visual Question Answering which is a problem on which there is still much work to be done. Moreover, we open the discussion about the challenges to overcome regarding this topic, like the future role of Visual Question Answering to address eXplainable Artificial Intelligence issues or difficulties. © 2023 CEUR-WS. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

PESTA: An Elastic Motion Capture Data Retrieval Method

引用

Journal of Computer Science & Technology 2023年第4期38卷 867-884页

作者：蒋子飞李伟黄艳尹义龙郭宗杰彭京亮 School of Software Shandong UniversityJinan 250101China Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles 90089U.S.A Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan 250022China School of Information Science and Engineering University of JinanJinan 250022China

Prevalent use of motion capture(MoCap)produces large volumes of data and MoCap data retrieval becomes crucial for efficient data *** clips may not be neatly segmented and labeled,increasing the difficulty of *** order to effectively retrieve such data,we propose an elastic content-based retrieval scheme via unsupervised posture encoding and strided temporal alignment(PESTA)in this *** retrieves similarities at the sub-sequence level,achieves robustness against singular frames and enables control of tradeoff between precision and *** firstly learns a dictionary of encoded postures utilizing unsupervised adversarial autoencoder techniques and,based on which,compactly symbolizes any MoCap ***,it conducts strided temporal alignment to align a query sequence to repository sequences to retrieve the best-matching sub-sequences from the ***,it extends to find matches for multiple sub-queries in a long query at sharply promoted efficiency and minutely sacrificed *** performance of the proposed scheme is well demonstrated by experiments on two public MoCap datasets and one MoCap dataset captured by ourselves.

关键词： motion capture(MoCap) content-based retrieval adversarial autoencoder temporal alignment

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning-based inter-dependent task dispatching and co-location in an integrated edge computing system

引用

Digital Communications and Networks 2024年第6期10卷 1837-1850页

作者： Uchechukwu Awada Jiankang Zhang Sheng Chen Shuangzhi Li Shouyi Yang School of Software Henan Institute of Science and TechnologyXinxiang 453003China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computing and Informatics Bournemouth UniversityPoole BH125BBUK School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China

Recently,several edge deployment types,such as on-premise edge clusters,Unmanned Aerial Vehicles(UAV)-attached edge devices,telecommunication base stations installed with edge clusters,etc.,are being deployed to enable faster response time for latency-sensitive *** fundamental problem is where and how to offload and schedule multi-dependent tasks so as to minimize their collective execution time and to achieve high resource *** approaches randomly dispatch tasks naively to available edge nodes without considering the resource demands of tasks,inter-dependencies of tasks and edge resource *** approaches can result in the longer waiting time for tasks due to insufficient resource availability or dependency support,as well as provider ***,we present Edge Colla,which is based on the integration of edge resources running across multi-edge *** Colla leverages learning techniques to intelligently dispatch multidependent tasks,and a variant bin-packing optimization method to co-locate these tasks firmly on available nodes to optimally utilize *** experiments on real-world datasets from Alibaba on task dependencies show that our approach can achieve optimal performance than the baseline schemes.

关键词： Edge computing Collaborative learning Resource utilization Execution time Edge federation Gang scheduling

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Person Re-Identification Based on Dual Network Architecture

引用

Computers, Materials & Continua 2025年第5期83卷 2889-2905页

作者： Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen College of Information Engineering Harbin UniversityHarbin150086China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin UniversityHarbin150086China College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China Heilongjiang Forestry Intelligent Equipment Engineering Research Center Northeast Forestry UniversityHarbin150040China Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning *** this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal *** proposed approach can be classified into two main ***,the spatial attention feature map is formed by aggregating features in the spatial ***,the same operation is carried out on the channel dimension to formchannel attention ***,the receptive field size is adjusted adaptively tomitigate the changing person posture ***,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution *** experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading *** proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MSMT17,and DukeMTMC-reID ***,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 ***,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关键词： Person reidentification ReID computer vision self-attention spatial-temporal information

来源：评论

学校读者我要写书评

暂无评论

Mobile Devices Interface Adaptivity Using Ontologies

引用

Computers, Materials & Continua 2022年第6期71卷 4767-4784页

作者： Muhammad Waseem Iqbal Muhammad Raza Naqvi Muhammad Adnan Khan Faheem Khan T.Whangbo Department of Software Engineering The Superior UniversityLahore53700Pakistan INP-ENIT University of ToulouseTarbes65000France Riphah School of Computing&Innovation Faculty of ComputingRiphah International University Lahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnam13557Korea Department of Computer Engineering Gachon UniversitySeongnam13557Korea

Currently,many mobile devices provide various interaction styles and modes which create complexity in the usage of *** context offers the information base for the development of Adaptive user interface(AUI)frameworks to overcome the *** this purpose,the ontological modeling has been made for specific context and *** type of philosophy states to the relationship among elements(e.g.,classes,relations,or capacities etc.)with understandable satisfied *** contextmechanisms can be examined and understood by anymachine or computational framework with these formal definitions expressed in Web ontology language(WOL)/Resource description frame work(RDF).The Protégéis used to create taxonomy in which system is framed based on four contexts such as user,device,task and *** competency questions and use-cases are utilized for knowledge obtaining while the information is refined through the instances of concerned parts of context *** consistency of the model has been verified through the reasoning software while SPARQL querying ensured the data availability in the models for defined *** semantic context model is focused to bring in the usage of adaptive *** exploration has finished up with a versatile,scalable and semantically verified context learning *** model can be mapped to individual User interface(UI)display through smart calculations for versatile UIs.

关键词： User context adaptive interfaces human computer interaction

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：