检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Kim, SangHyuk Gaibor, Edward Matejek, Brian Haehn, Daniel University of Massachusetts Boston Department of Computer Science BostonMA United States Sri International Computer Science Laboratory ArlingtonVA United States

ISBN: (纸本)9798331520526

Early detection of melanoma is crucial for improving survival rates. Current detection tools often utilize data-driven machine learning methods but often overlook the full integration of multiple datasets. We combine publicly available datasets to enhance data diversity, allowing numerous experiments to train and evaluate various classifiers. We then calibrate them to minimize misdiagnoses by incorporating uncertainty quantification. Our experiments on benchmark datasets show accuracies of up to 93.2% before and 97.8% after applying uncertainty-based rejection, leading to a reduction in misdiagnoses by over 40.5%. Our code and data are publicly available11Our GitHub repository, https: / /mpsych. org /melanoma, and a web-based interface220ur Web interface, https: / /mpsych. gi thub. io/melanoma/ for quick melanoma detection of user-supplied images is also provided. © 2025 IEEE.

关键词： calibration machine learning medical imaging melanoma detection uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Cascade Temporal Convolutional Network for Multitask Learning 6

Cascade Temporal Convolutional Network for Multitask Learnin...

引用

6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023

作者： Zhang, Huiyun Huang, Heming Han, Henry Baylor University School of Engineering and Computer Science Department of Computer Science United States Qinghai Normal University School of Computer Science Xining China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application School of Computer Science Xining China

ISBN: (纸本)9781665491259

Multi-task learning (MTL) is a powerful technique in machine learning that enables the simultaneous training of multiple tasks. In this paper, we propose a novel MTL approach for the recognition of emotions, speakers, and gender in speech signals. Our approach presents a novel deep learning model called the Cascade Temporal Convolutional Network (CTCN to handle MTL efficiently. CTCN is designed to effectively improve the parallel processing ability of the model in multitasking learning. It provides an effective solution for improving the performance of deep learning in multitasking scenarios. CTCN is particularly adept at processing sequences of data with varying lengths and extracting features that are relevant to multiple tasks. Our experimental results demonstrate that the proposed CTCN approach for MTL achieves significantly superior performance on all tasks on benchmark datasets compared to other deep learning models. This study will inspire more future work in the MTL field. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Analysis and Comparison Between Artificial Neural Network Models in Image Recognition 1

引用

12th International Conference on Integrated Design and Production, CPI 2022

作者： Belattar, Sara Abdoun, Otman Haimoudi, El khatir Computer Science Department Advanced Science and Technologies Laboratory Abdelmalek Essaâdi University Polydisciplinary Faculty Larache Morocco Computer Science Department Faculty of Science Abdelmalek Essaâdi University Tetouan Morocco

ISBN: (数字)9783031236150

ISBN: (纸本)9783031236143

Nowadays, face (or image) recognition represents a challenging problem and an important area in various applications due to issues that can be encountered in different domains such as monitoring operations, security, criminal identification, identifying a person, and so on. For that reason, many methods are proposed to develop the intelligent face recognition system, and each method provides a solution to a specific situation. Firstly, the Kohonen Neural Network (KNN) is proposed to create an intelligent system for face recognition to solve problems related to the identification of human faces. This type is a well-known neural network model and is based on an unsupervised learning mode;the goal of using it is to classify and cluster data, either numerical or image. Secondly, the convolutional neural network (CNN) is suggested in this study thanks to its capabilities in image classification and recognition tasks. The main objective of choosing these artificial neural network models is to analyze and compare their performances in learning, image classification, and recognition tasks. The experimental tests demonstrate that the KNN and CNN have some limitations and advantages in specific problems, and each of them gave good results in different cases. Therefore, this study provides an appropriate model for a particular issue. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Global video object segmentation with spatial constraint module

引用

Computational Visual Media 2023年第2期9卷 385-400页

作者： Yadang Chen Duolin Wang Zhiguo Chen Zhi-Xin Yang Enhua Wu Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of MacaoMacao 999078China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

We present a lightweight and efficient semisupervised video object segmentation network based on the space-time memory *** some extent,our method solves the two difficulties encountered in traditional video object segmentation:one is that the single frame calculation time is too long,and the other is that the current frame’s segmentation should use more information from past *** algorithm uses a global context(GC)module to achieve highperformance,real-time *** GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real ***,the prediction mask of the previous frame is helpful for the segmentation of the current frame,so we input it into a spatial constraint module(SCM),which constrains the areas of segments in the current *** SCM effectively alleviates mismatching of similar targets yet consumes few additional *** added a refinement module to the decoder to improve boundary *** model achieves state-of-the-art results on various datasets,scoring 80.1%on YouTube-VOS 2018 and a J&F score of 78.0%on DAVIS 2017,while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

关键词： video object segmentation semantic segmentation global context(GC)module spatial constraint

来源：评论

学校读者我要写书评

暂无评论

An MCDM-Based Methodology for Influential Nodes Detection in a Social Network. Facebook as a Case Study

An MCDM-Based Methodology for Influential Nodes Detection in...

引用

International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2022

作者： Qaffou, Issam Ait Rai, Khaoula LISI Laboratory Computer Science Department Faculty of Science Semlalia Cadi Ayyad University Marrakech Morocco Computer System and Vision Laboratory Faculty of Sciences Ibn Zohr University Agadir Morocco

ISBN: (纸本)9783031263835

The identification of influential nodes in a social network is very important for many uses like the control of information spreading. This paper studies how a multi- criteria decision method (MCDM) can find influential persons in a social network. The empirical study performed on a Facebook dataset shows how we can visualize links between profiles and who are the top-k influential ones. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

6G-SECUREIDS: Blockchain-Enhanced Secure Knowledge Transfer for Distributed Intrusion Detection Systems in Advanced Networks 6

6G-SECUREIDS: Blockchain-Enhanced Secure Knowledge Transfer ...

引用

6th International Conference on Networking and Advanced Systems, ICNAS 2023

作者： Sakraoui, Sabrina Derdour, Makhlouf Ahmim, Ahmed Badji Mokhtar Annaba University Networks and Systems Laboratory Department of Computer Science Annaba Algeria Oum El Bouaghi University Networks and Systems Laboratory Department of Computer Science Oum El Bouaghi Algeria Mohamed-Cherif Messaadia University Networks and Systems Laboratory Dpt. of Mathematics and Computer Science Souk Ahras Algeria

ISBN: (纸本)9798350319170

As the development of wireless networks advances towards the deployment of 6G technology, ensuring robust security measures becomes crucial. In this paper, we propose 6G-SECUREIDS, a novel intrusion detection system designed specifically for 6G wireless networks. The system leverages machine learning techniques and blockchain technology to detect and mitigate security threats, safeguard data privacy, and ensure efficient and optimized training. Our experimental results demonstrate the effectiveness and reliability of the system, with the clients achieving high accuracy scores across different model architectures. The promising results highlight the potential of 6G-SECUREIDS as a valuable security solution for future 6G networks, contributing to the overall protection and integrity of the wireless communication ecosystem. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of computer science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Learning: Taxonomy and Algorithms

引用

Informatica (Slovenia) 2022年第2期46卷 151-168页

作者： Chefrour, Aida Souici-Meslati, Labiba Computer Science Department Mohamed Cherif Messaadia University Souk Ahras Algeria LISCO Laboratory Computer Science Department Badji Mokhtar University B.P-12 Annaba23000 Algeria

Clustering is a fundamental challenge in many data-driven application fields and machine learning techniques. The data distribution determines the quality of the outcomes, which has a significant impact on clustering performance. As a result, deep neural networks can be used to learn more accurate data representations for clustering. Many recent studies have focused on employing deep neural networks to develop a clustering-friendly representation, which has resulted in a significant improvement in clustering performance. We present a systematic survey of clustering with deep learning in this study. Then, a taxonomy of deep clustering is proposed, as well as some sample algorithms for our overview. Finally, we discuss some exciting future possibilities for clustering using deep learning and offer some remarks. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Unlocking Music Archives: Openness and Accessibility 21

Unlocking Music Archives: Openness and Accessibility

引用

21st Conference on Information and Research science Connecting to Digital and Library science, IRCDL 2025

作者： Faschi, Vanessa Avanzini, Federico Ludovico, Luca Andrea Laboratory of Music Informatics Department of Computer Science University of Milan via G. Celoria 18 Milan20135 Italy

This paper focuses on the theme of unlocking the materials preserved by musical institutions such as opera houses, conservatories, and historical archives. In this context, "unlocking" means providing access to anyone, which can be interpreted in two different ways. The first meaning, related to openness, implies making preserved materials accessible to a wide audience. From this perspective, digitization campaigns and the subsequent enhancement of cultural assets through technology can open the way to new possibilities. For example, creating a dedicated Web portal can facilitate access by addressing issues such as physical distances, availability at any time of the day, the perishability of physical objects, insurance costs, etc. Moreover, technology can provide new services and foster advanced ways to exploit materials. Concerning the second meaning, related to accessibility, technologies can be used to assist people with physical and cognitive impairments and extend the use of these materials to people for whom it would be more difficult. For example, assistive technologies, such as screen readers or braille displays, allow blind and visually impaired (BVI) users to enjoy the transcription of music or literary texts. Similarly, computer-assisted approaches, such as large language models, can reduce the complexity of a text to meet the communicative abilities of people with special educational needs or cognitive impairments. To better illustrate the meanings of openness and accessibility, we will discuss two scenarios excerpted from the Ricordi Historical Archive. On the one hand, this work aims to highlight the fundamental role of technologies in supporting openness and accessibility, starting from digitization campaigns, through the online publishing of materials, to the release of ad hoc software tools. On the other hand, our research shows that there is still a long way to go before music archives can fully achieve the goals of openness and accessibility. © 20

关键词： Accessibility Archives Collections Inclusivity Music Usability

来源：评论

学校读者我要写书评

暂无评论

An Interpretable CNN for the Segmentation of the Left Ventricle in Cardiac MRI by Real-Time Visualization

引用

computer Modeling in Engineering & sciences 2023年第5期135卷 1571-1587页

作者： Jun Liu Geng Yuan Changdi Yang Houbing Song Liang Luo Robotics Institute School of Computer ScienceCarnegie Mellon UniversityPittsburghPA15217USA Department of Electrical&Computer Engineering College of EngineeringNortheastern UniversityBostonMA02115USA Security and Optimization for Networked Globe Laboratory(SONG Lab) Embry-Riddle Aeronautical UniversityDaytona BeachFL32114USA School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu610054China

The interpretability of deep learning models has emerged as a compelling area in artificial intelligence *** safety criteria for medical imaging are highly stringent,and models are required for an ***,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and ***,the interpretability of CNNs has come into the *** medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning ***,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these *** this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac *** enhanced GPU training system implemented interpretable global average pooling for graphics using deep *** deep learning tasks were *** included data management,neural network architecture,and *** system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment *** results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning *** model is lightweight and more convenient to deploy on mobile devices than transfer learning models.

关键词： Interpretable graphics training visualization image segmentation left ventricle CNNs global average pooling

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：