检索结果-内蒙古大学图书馆

A Population Initialization Method Based on Similarity and Mutual Information in Evolutionary Algorithm for Bi-Objective Feature Selection

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-21页

作者： Cai, Xu Xue, Yu Artificial Intelligence Research Institute School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Software Nanjing University of Information Science and Technology Nanjing China

Feature selection (FS) is an important data pre-processing technique in classification. It aims to remove redundant and irrelevant features from the data, which reduces the dimensionality of data and improves the performance of the classifier. Thus, FS is a bi-objective optimization problem, and evolutionary algorithms (EAs) have been proven to be effective in solving bi-objective FS problems. EA is a population-based metaheuristic algorithm, and the quality of the initial population is an important factor affecting the performance of EA. An improper initial population may negatively affect the convergence speed of the EA and even make the algorithm fall into the local optimum. In this article, we propose a similarity and mutual information-based initialization method, named SMII, to improve the quality of the initial population. This method determines the distribution of initial solutions based on similarity and shields features with high correlation to the selected features according to mutual information. In the experiment, we embed SMII, the latest four initialization methods, and a traditional random initialization method into NSGA-II and compared their performance on 15 public datasets. The experimental results show that SMII performs best on most datasets and can effectively improve the performance of the algorithm. Moreover, we compare the performance of two other EAs before and after embedding SMII on 15 datasets, and the results further prove that the proposed method can effectively improve the search capability of the EA for FS. © 2024 Copyright held by the owner/author(s).

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Example Transferability via Regularized Constrained Feature Layer

引用

computers, Materials & Continua 2025年第4期83卷 157-175页

作者： Xiaoyin Yi Long Chen Jiacheng Huang Ning Yu Qian Huang School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of EducationChongqing400065China Artificial Intelligence and Big Data College Chongqing Polytechnic University of Electronic TechnologyChongqing401331China

Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior *** is achieved by leveraging the property of adversarial *** is,when generated from a surrogate model,they retain their features if applied to other models due to their good ***,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source ***,when attempting black-box transfer attacks on different target models,their effectiveness is *** solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency *** are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial ***,a regularized loss function is used to enhance the black-box transferability between different target *** proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.

关键词： Adversarial examples black-box transferability regularized constrained transfer-based adversarial attacks

来源：评论

学校读者我要写书评

暂无评论

Disentangling Prosody Representations With Unsupervised Speech Reconstruction

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 39-54页

作者： Qu, Leyuan Li, Taihao Weber, Cornelius Pekarek-Rosin, Theresa Ren, Fuji Wermter, Stefan Institute of Artificial Intelligence Zhejiang Lab Hangzhou311121 China Department of Informatics University of Hamburg Hamburg20148 Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in speech recognition and speaker verification tasks respectively. However, it is still an open challenging question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust speech recognition. The aim of this article is to address the disentanglement of emotional prosody based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain Prosody2Vec on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective and subjective evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Audio samples can be found on our demo website. © 2023 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Hate Speech in Hindi using Supervised Learning Models

Automated Detection of Hate Speech in Hindi using Supervised...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Rajak, Nikhil Phulre, Ajay Kumar Chandra Patel, Subhash Patel, Narottam Das Khekare, Ganesh Vit Bhopal University School of Computing Science Engineering and Artificial Intelligence Sehore India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350375442

This study addresses the pressing issue of hate speech on online platforms. Traditional text-based analysis is no longer adequate for identifying hate speech due to the growth of internet platform data. The project aims to create scalable automated methods for web platforms to detect hate speech in real-time. To find the best algorithms for recognizing hate speech, the study compares many machine learning models using a large dataset in Hindi from Twitter. Where the study matters is in the creation of advanced content filtering systems that offer a more secure and friendly online environment. Support Vector Machine (SVM) has the best performance, with outstanding precision (0.9468) and F1-score (0.944), showcasing the top-performing ones and talking about the difficulties and ways ahead in this field. The study recommends improving Hindi hate speech detection systems. With problems such as imbalanced data sets and the dynamic nature of online language, language research using hybrid models, constant model adjustments, and language trend monitoring are all necessary. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation on Point Clouds via High-Order Geometric Structure Modeling

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第12期5卷 6121-6133页

作者： Cheng, Jiang-Xing Lin, Huibin Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangdong Guangzhou510006 China

Point clouds can capture the precise geometric information of objects and scenes, which are an important source of 3-D data and one of the most popular 3-D geometric data structures for cognitions in many real-world applications like automatic driving and remote sensing. However, due to the influence of sensors and varieties of objects, the point clouds obtained by different devices may suffer obvious geometric changes, resulting in domain gaps that are prone to the neural networks trained in one domain failing to preserve the performance in other domains. To alleviate the above problem, this article proposes an unsupervised domain adaptation framework, named HO-GSM, as the first attempt to model high-order geometric structures of point clouds. First, we construct multiple self-supervised tasks to learn the invariant semantic and geometric features of the source and target domains, especially to capture the feature invariance of high-order geometric structures of point clouds. Second, the discriminative feature space of target domain is acquired by using contrastive learning to refine domain alignment to specific class level. Experiments on the PointDA-10 and GraspNetPC-10 collection of datasets show that the proposed HO-GSM can significantly outperform the state-of-the-art counterparts. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PromptCD: Coupled and Decoupled Prompt Learning for Vision-Language Models 27

PromptCD: Coupled and Decoupled Prompt Learning for Vision-L...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Wu, Junjie Sun, Mingjie Gong, Chen Yu, Nan Fu, Guohong School of Computer Science and Technology Soochow University Suzhou China Institute of Artificial Intelligence Soochow University China

ISBN: (纸本)9781643685489

Large-scale pre-trained vision-language models (VLMs), like CLIP, have presented striking generalizability for adapting to image classification in a few shot setting. Most existing methods explore a set of learnable tokens, such as prompt learning, on data-efficient utilization for task adaptation. However, they focus on either the coupled-modality property by prompt projection or decoupled-modality characteristic by prompt consistency, which ignores effective interaction between prompts. To model the deep yet sufficient cross-modal interaction and enhance the generalization between both seen and unseen tasks, in this paper, we propose a novel coupled and decoupled prompt learning framework, dubbed PromptCD, for vision-language models. Specifically, we introduce a bi-directional coupled-modality mechanism to intensify the interaction between both vision and language branches. Additionally, we propose mixture consistency to further improve the generalization and discrimination of the models on unseen tasks. The integration of such a mechanism and consistency facilitates the proposed framework adaptation for various downstream tasks. We conduct extensive experiments on 11 image classification datasets under a range of evaluation protocols, including base-to-novel and domain generalization, and cross-dataset recognition. Experimental results demonstrate that our proposed PromptCD overall outperforms state-of-the-art methods. © 2024 The Authors.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Reverse Distillation for Anomaly Detection 10

Two-Stream Reverse Distillation for Anomaly Detection

引用

10th International Conference on Systems and Informatics, ICSAI 2024

作者： Ding, Yunkang Tang, Hao Huang, Guoheng Cheng, Lianglun Pun, Chi-Man Li, Yan School of Computer Science and Technology Guangdong University of Technology Guangzhou China University of Macau Faculty of Science and Technology China School of Artificial Intelligence Shenzhen Polytechnic University Shenzhen China

ISBN: (纸本)9798331510138

Traditional industrial anomaly detection methods based on reverse distillation have been extensively studied due to their simplicity and efficiency. However, the intermediate embedding features generated by pre-trained teacher models often fail to provide precise reconstruction information to the student model, resulting in poor performance when detecting small defects or handling anomalies with significant errors. To address these limitations, we propose a Two-Stream Reverse Distillation (TSRD) framework that integrates self-similarity and edge information into the distillation process. In TSRD, the intermediate embedding features are divided into two streams: one employs a Regional Self-Similarity Encoder Module(RSSE) to capture intrinsic geometric features, while the other leverages an Shape Feature Enhancement Module (SFE) to enhance boundary perception. This design effectively harnesses local relational features and critical detail enhancements, significantly improving the accuracy and robustness of anomaly detection. Experimental results on the MVTec AD dataset demonstrate the effectiveness of the model and highlight its competitive performance. Source code will be available at https://***/neuraaal/TSRD. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Role-Specific Reward Design with Large Language Model for StarCraft II

Role-Specific Reward Design with Large Language Model for St...

引用

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

作者： Li, Sijia Luo, Haonan Zhang, Xu Zeng, Xin Shen, Zhixuan Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Nanjing University of Science and Technology School of Computer Science and Engineering China

ISBN: (纸本)9798350368741

Reward acts as a signal to guide the agent's learning process in Reinforcement Learning (RL), evaluating and assigning rewards to the agent's actions based on their alignment with goals. Designing reward is challenging in multi-agent environment such as StarCraft II benchmark since agents face credit allocation and role adaptation problems. Recent studies have successfully exploited the language understanding and reasoning capabilities of large language models (LLMs) to learn manipulation tasks. Impressed by the remarkable power of LLMs, this paper employs LLMs as role-specific reward designer for playing StarCraft II, making rewards more flexible and task-oriented. Firstly, we develop an interactive text and multi-agent RL environment to study real-time strategy generation in StarCraft II. Secondly, we use LLMs to interpret the game situation and understand agent roles from user instructions. Then, by assigning appropriate subtasks, LLMs quantify the completion of these subtasks to generate role-specific rewards. Further, credit assignment problem is addressed by introducing dynamic reward weights in value decomposition method. In StarCraft II maps, experiments show that role-aligned RL agents trained with our framework achieve superior policy performance, and win rate results demonstrates the effectiveness of our approach in decision-making for micromanagement and long-term planning. © 2025 IEEE.

关键词： Large Language Models Multi-agent Reinforcement Learning Reward design StarCraft II Value decomposition

来源：评论

学校读者我要写书评

暂无评论

Computing Challenges of UAV Networks: A Comprehensive Survey

引用

computers, Materials & Continua 2024年第11期81卷 1999-2051页

作者： Altaf Hussain Shuaiyong Li Tariq Hussain Xianxuan Lin Farman Ali Ahmad Ali AlZubi School of Computer Science&Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of EducationChongqing University of Posts and TelecommunicationsChongqing400065China School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China School of Artificial Intelligence Nanjing University of Information Science&TechnologyNanjing210044China Department of Computer Science and Engineering School of ConvergenceCollege of Computing and InformaticsSungkyunkwan UniversitySeoul03063Republic of Korea Department of Computer Science Community CollegeKing Saud UniversityRiyadh11495Saudi Arabia

Devices and networks constantly upgrade,leading to rapid technological ***-dimensional(3D)point cloud transmission plays a crucial role in aerial computing terminology,facilitating information *** network types,including sensor networks and 5G mobile networks,support this ***,Flying Ad hoc Networks(FANETs)utilize Unmanned Aerial Vehicles(UAVs)as nodes,operating in a 3D environment with Six Degrees of Freedom(6DoF).This study comprehensively surveys UAV networks,focusing on models for Light Detection and Ranging(LiDAR)3D point cloud compression/*** topics covered include autonomous navigation,challenges in video streaming infrastructure,motivations for Quality of Experience(QoE)enhancement,and avenues for future ***,the paper conducts an extensive review of UAVs,encompassing current wireless technologies,applications across various sectors,routing protocols,design considerations,security measures,blockchain applications in UAVs,contributions to healthcare systems,and integration with the Internet of Things(IoT),artificial intelligence(AI),Machine Learning(ML),and Deep Learning(DL).Furthermore,the paper thoroughly discusses the core contributions of LiDAR 3D point clouds in UAV systems and their future prediction along with mobility *** also explores the prospects of UAV systems and presents state-of-the-art solutions.

关键词： Autonomous vehicles UAV systems UAV transmission UAV in healthcare future of UAV system security measures

来源：评论

学校读者我要写书评

暂无评论

Secure multimedia communication: advanced asymmetric key authentication with grayscale visual cryptography

引用

Mathematical Biosciences and Engineering 2024年第3期21卷 4762-4778页

作者： Liu, Tao Vairagar, Shubhangi Adagale, Sushadevi Karthick, T. Karunya, Catherine Esther Blesswin, A. John Mary, G. Selva Tianjin Sino-German University of Applied Sciences Tianjin300350 China Department of Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune411018 India Department of Computer Engineering KJEI's Trinity Academy of Engineering Pune411048 India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Directorate of Learning and Development SRM Institute of Science and Technology Kattankulathur603203 India

The secure authentication of user data is crucial in various sectors, including digital banking, medical applications and e-governance, especially for images. Secure communication protects against data tampering and forgery, thereby bolstering the foundation for informed decision-making, whether managing traffic, enhancing public safety, or monitoring environmental conditions. Conventional visual cryptographic protocols offer solutions, particularly for color images, though they grapple with challenges such as high computational demands and reliance on multiple cover images. Additionally, they often require third-party authorization to verify the image integrity. On the other hand, visual cryptography offers a streamlined approach. It divides images into shares, where each pixel represented uniquely, thus allowing visual decryption without complex computations. The optimized multi-tiered authentication protocol (OMTAP), which is integrated with the visual sharing scheme (VSS), takes secure image sharing to the next level. It reduces share count, prioritizes image fidelity and transmission security, and introduces the self-verification of decrypted image integrity through asymmetric key matrix generators, thus eliminating external validation. Rigorous testing has confirmed OMTAP's robustness and broad applicability, thereby ensuring that decrypted images maintain their quality with a peak signal-to-noise ratio (PSNR) of 40 dB and full integrity at the receiver's end. © 2024 American Institute of Mathematical sciences. All rights reserved.

关键词： Medical applications

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：