检索结果-内蒙古大学图书馆

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Chunlan He Yujian Bi Xingwei Liu Qi Wang Hong Sun School of Computer and Software Engineering Xihua University Chengdu China Chengdu Jiuzhou Electronic Information System Co. Ltd Chengdu China

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

Recently, deep learning has achieved significant success in various fields such as image classification, speech recognition, and natural language understanding. However, the security issues associated with deep learning are becoming increasingly apparent, particularly the challenges posed byad-versarial sample attacks. These attacks, which are both covert and potentially harmful, pose substantial security threats to deep learning models. In response to this, we propose a novel defense method against adversarial sample attacks tailored for speech recognition. This method involves constructing an audio reconstruction model that restores adversarial speech samples back to their normal state. The model incorporates an im-proved Wavenet residual network structure based on dilated convolutions, and utilizes Mel Frequency Cepstral Coefficients to enhance audio reconstruction. Experimental results indicate that the proposed audio reconstruction model exhibits superior reconstruction capabilities, effectively restoring and defending against various adversarial sample attacks.

关键词： Deep learning Training Speech recognition Speech enhancement Natural language processing Image restoration Security Mel frequency cepstral coefficient Image reconstruction Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Salient Object Detection With Oversize Bounding Box

引用

International Journal of computer Vision 2025年 1-20页

作者： Wu, Zhihao Xu, Yong Yang, Jian Zhang, David School of Artificial Intelligence Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Data Science The Chinese University of Hong Kong (Shenzhen) Shenzhen China

Compared to laborious pixel-level annotations, scribbles, bounding boxes, and points are much more efficient in salient object detection (SOD). However, the annotation cost of these forms linearly increases with the number of salient objects in the image, which is not ideal for real-world scenarios. To address this issue, we propose a novel annotation form called oversize bounding box (OBB), i.e., a box that encompasses all salient objects without the need for tight enclosure. It has two characteristics: (1) All pixels outside the box are from the background. (2) A subset of the pixels inside the box belongs to salient objects. Therefore, the core issue is how to highlight integral and accurate object regions as pseudo-labels. Inspired by the powerful visual understanding and vision-language correlations demonstrated by large multimodal models, we devise the first multimodal model-based pseudo-label generation method for SOD. It utilizes MiniGPT-4 to generate descriptions of salient objects as text prompts for CLIP, combined with the CAM-based technique and proposed refinement algorithm based on the multi-head self-attention and superpixel to activate the object regions. Then we use OBB to further correct the activation regions based on its two characteristics. Given the potential errors of pseudo-labels within the box, we propose a center-pixel-based cross entropy loss, as activated pixels closer to the center are generally more reliable. Moreover, we establish an OBB-supervised training dataset by relabeling the DUTS dataset. Extensive experiments on six benchmarks demonstrate that our method achieves the state-of-the-art performance.

关键词： Weak supervision Salient object detection Multimodal large model Activation map

来源：评论

学校读者我要写书评

暂无评论

Q-learning Based Meta-Heuristics for Scheduling Bi-Objective Surgery Problems with Setup Time

引用

Complex system Modeling and Simulation 2024年第4期4卷 321-338页

作者： Ruixue Zhang Hui Yu Adam Slowik Kaizhou Gao School of Computer Science Liaocheng UniversityLiaocheng 252000China Macao Institute of System Engineering Macao University of Science and TechnologyMacao 999078China the Department of Electronics and Computer Science Koszalin University of TechnologyKoszalin 75-453Poland

Since the increasing demand for surgeries in hospitals,the surgery scheduling problems have attracted extensive *** study focuses on solving a surgery scheduling problem with setup *** a mathematical model is created to minimize the maximum completion time(makespan)of all surgeres and patient waiting time,*** time by the fatigue effect is included in the surgery time,which is caused by doctors’long working ***,four mate-heuristics are optimized to address the relevant *** novel strategies are designed to improve the quality of the initial *** improve the convergence of the algorithms,seven local search operators are proposed based on the characteristics of the surgery scheduling ***,Q-learning is used to dynamically choose the optimal local search operator for the current state in each ***,by comparing the experimental results of 30 instances,the *** based local search strategy's effectiveness is *** all the compared algorithms,the improved artificial bee colony(ABC)with Q-leaming based local search has the best competiiveness.

关键词： surgery scheduling meta-heuristics Q-earning makespan

来源：评论

学校读者我要写书评

暂无评论

Comparison of Transformer Based and Traditional Models on Sentiment Analysis on Social Media Datasets

Comparison of Transformer Based and Traditional Models on Se...

引用

International Conference of computer and Informatics engineering (IC2IE)

作者： Arif Ridho Lubis Yulia Fatmi Deden Witarsyah Department of Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia School of Industrial and System Engineering Telkom University Bandung Indonesia

In the field of computers and natural language processing, there is an interesting sub-field, namely sentiment analysis. Currently, the use of social media Twitter to actively communicate between individuals contains various review data, opinion data, and emotional data from discussions of topics between users on social media. So that the data generated by Twitter social media can identify patterns in the data for the field of sentiment analysis. In the sentiment analysis sub-sector, there are approaches, namely transformer-based models and traditional models, the traditional model includes the naïve Bayes algorithm, support vector machine, and regression have weaknesses in overcoming data complexity in Indonesian language tweets on Twitter social media while the transformer model includes the BERT (Bidirectional Encoder Representations from Transformers) algorithm is often applied because it has advantages in overcoming the complexity of Indonesian sentences in tweets obtained from social media and in the process this model goes through a training stage with large amounts of data then is adjusted in the concept of sentiment analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Routing of Vehicular IoT Networks based on various routing Metrics, Characteristics, and Properties

Routing of Vehicular IoT Networks based on various routing M...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Rakesh Kumar Sunil K. Sinngh D.K. Lobiyal Computer Science & Engineering CCET Panjab University Chandigarh India School of Computer & System Sciences Jawaharlal Nehru University New Delhi India

The use of the Vehicular Internet of Things (VIoT) has been rapidly increasing in recent years, which has led to the development of various routing protocols to facilitate communication among vehicles. In this paper, we provide a comprehensive review of the state-of-the-art routing metrics, characteristics, and properties used in VIoT networks. We examine different types of routing protocols, including geographic, position-based, and topology-based. We also investigate various factors affecting the performance of these protocols, such as the mobility patterns of vehicles, network topology, and energy consumption. Furthermore, we compare and contrast the advantages and disadvantages of different routing protocols in terms of their suitability for different types of VIoT applications. Finally, we identify several open research issues and challenges that need to be addressed in future VIoT routing research. This review paper provides a valuable reference for researchers and practitioners working on VIoT networks and can help them select an appropriate routing protocol for their specific applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Deduction Heuristic Algorithm of Standard Contradiction Separation Rule Based on Reinforcement Learning

Active Deduction Heuristic Algorithm of Standard Contradicti...

引用

International Conference on Intelligent system and Knowledge engineering, ISKE

作者： Jian Zhong Peiyao Liu Shuwei Chen National-Local Joint Engineering Laboratory of System Credibility Automatic Verification School of Computer and Software Engineering Xihua University Chengdu China

Machine learning has been a prominent research focus in recent years, and integrating machine learning methods into automated theorem provers has become a current trend in theorem proving research. Standard contradiction separation rule is a newly proposed multi-clause, dynamic, and synergized deductive inference rule. The key aspect of standard contradiction separation rule is how to plan deduction paths. In order to better plan the deduction path, this paper explores the dynamic learning within the process of contradiction separation deduction and introduces a novel active deductive heuristic algorithm based on reinforcement learning. Experimental results demonstrate that this new algorithm enhances the reasoning capability of the theorem prover Prover9.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bat Algorithm: A Review on Theory, Modifications and Applications

Bat Algorithm: A Review on Theory, Modifications and Applica...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Hakam Singh Deden Witarsyah Alok Misra Raj Gaurang Tiwari Department of Computer Science and Engineering School of Engineering and Technology Chitkara University Baddi Himachal Paradesh India Information System Departement School of Industrial and System Engineering Telkom University Bandung Indonesia School of Computer Application Lovely Professional University Phagwara Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Due to its many applications in a variety of domains, including clustering, cloud computing, and power systems, metaheuristic algorithms have attracted a lot of interest from the scholarly community. By using their self-explorative and adaptive processes, these algorithms provide certain benefits over conventional methods. One well-known metaheuristic approach is effective in resolving optimization problems with constraints and without constraints. This technique was inspired by nature, notably the echolocation ability of bat species. The Bat Algorithm (BA) makes use of a powerful search mechanism to provide the best results when compared to other algorithms of the same class. The theoretical underpinnings of the BA are explored in depth in this research, along with several changes and advancements that have improved its functionality. These enhancements include adjustments to search tactics as well as other developments. The report also thoroughly examines how the BA may be used across a variety of fields, demonstrating its competence and adaptability. The BA has been effectively used in several real-world applications, from cloud computing to clustering, and each one is carefully investigated. The study also offers a thoughtful examination of the BA's possible advancements and future possibilities. It also entails investigating novel modifications and tactics that might improve its effectiveness in handling challenging optimization issues. This study seeks to direct practitioners and academics toward more effective and efficient metaheuristic algorithms, thereby stimulating improvements in optimization approaches. It does this by summarising the present state of the BA and imagining its future development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of SDN and Digital Twin for the Intelligent Detection of DoC Attacks in WRSNs

arXiv

引用

arXiv 2025年

作者： Qaisar, Muhammad Umar Farooq Yuan, Weijie Han, Guangjie Ahmed, Adeel Liu, Chang Piran, Md. Jalil School of Computer Science Northwestern Polytechnical University China School of System Design and Intelligent Manufacturing Southern University of Science and Technology China Department of Internet of Things Engineering Hohai University China School of Computer Science and Technology University of Science and Technology of China China School of Information Engineering Guangdong University of Technology Guangzhou China Department of Computer Science and Engineering Sejong University Seoul05006 Korea Republic of

Wireless rechargeable sensor networks (WRSNs), supported by recent advancements in wireless power transfer (WPT) technology, hold significant potential for extending network lifetime. However, traditional approaches often prioritize scheduling algorithms and network optimization, overlooking the security risks associated with the charging process, which exposes the network to potential attacks. This paper addresses this gap by integrating Software-Defined Networking (SDN) and Digital Twin technologies for the intelligent detection of Denial of Charging (DoC) attacks in WRSNs. First, it leverages the flexibility and intelligent control of SDN, in combination with Digital Twin, to enhance real-time detection and mitigation of DoC attacks. Second, it employs four key metrics to detect such attacks including charging request patterns, energy consumption, behavioral and reputation scores, and charging behavior and efficiency. The numerical results demonstrate the superior performance of the proposed protocol in terms of energy usage efficiency, survival rate, detection rate, and travel distance. © 2025, CC BY.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs 25

WebCode2M: A Real-World Dataset for Code Generation from Web...

引用

34th ACM Web Conference, WWW 2025

作者： Gui, Yi Li, Zhen Wan, Yao Shi, Yemin Zhang, Hongyu Su, Yi Chen, Bohua Chen, Dongping Wu, Siyuan Zhou, Xing Jiang, Wenbin Jin, Hai Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Peking University Beijing China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology China

ISBN: (纸本)9798400712746

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. © 2025 Copyright held by the owner/author(s).

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

A new symbol timing and carrier frequency offset estimation algorithm for OTFS for B5G 2

A new symbol timing and carrier frequency offset estimation ...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Thangavel, Gunasekaran Rajan, Sheeba Subbulekshmi, S. Anthonisamy, Arun Ganapathi, Rohini Velankanni, Gowri University of Technology and Applied Sciences Department of Electronics and Communication Engineering Muscat Oman SRM Institute of Science and Technology School of Computing Tiruchirapalli India Prathyusha Engineering College Department of Electronics and Communication Engineering Chennai India Panimalar Engineering College Department of Computer Science and Business System Chennai India St. Joseph's Institute of Technology Department of Electronics and Communication Engineering Chennai India K. Ramakrishnan College of Technology Department of Electronics and Communication Engineering Trichy India

ISBN: (纸本)9798331534950

In B5G networks, accurate symbol timing estimate and estimation of the carrier frequency offset are both absolutely necessary. Particularly in highly mobile and interference-ridden settings, these factors are of paramount importance for sustaining high-throughput, dependable wireless communication. Estimating symbol timing and carrier frequency offset in OTFS can be difficult due to factors including the time-varying nature of Doppler shifts and interference from surrounding cells as well as the non-stationary nature of wireless channels. In such changing settings, traditional algorithms often fail to produce reliable estimations. To account for frequency changes caused by things like Doppler effects and drift, this research uses Machine Learning-Based Carrier Frequency Prediction Analysis (ML-CFPA) to implement a dynamic carrier frequency offset estimation and correction system. To preserve signal coherence and lower interference in B5G settings, carrier frequency offset adjustment is essential. Communication solutions with high performance are required for these applications to ensure they can function normally despite the complexity and changeability of their contexts. The outcomes demonstrate the higher performance of the algorithm in contrast to conventional approaches, highlighting its applicability to B5G networks. Its potential as a crucial enabling technology for the B5G future has been solidified by these simulations, which verify its capacity to maintain reliable communication under a variety of real-world conditions. © 2024 IEEE.

关键词： Graphical user interfaces

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：