检索结果-内蒙古大学图书馆

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Murugadoss, Bhuvanashree Amudha, J. Sugumaran, Vijayan Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science and Engineering Karnataka Bengaluru India Oakland University Center for Data Science and Big Data Analytics RochesterMI United States Oakland University Department of Decision and Information Sciences RochesterMI United States

ISBN: (纸本)9798350359527

Automated radiotherapy treatment planning aims to improve treatment accuracy and efficiency. However, the prevalent Knowledge-Based Planning (KBP) method faces issues like lengthy manual problem formulation and challenges in accurately modeling human anatomy and processing high-dimensional data. This work focuses on treatment plan optimization and considers deep learning as a potential solution. Deep learning algorithms, by virtue of their ability to learn from large quantities of data and model complex relationships, can automate the formulation of the optimization problem in KBP, saving significant time and effort. However, despite these compelling advantages, it should be noted that the current convolution-based encoder-decoder models used for radiotherapy treatment plan optimization have a limited capability in capturing long-range dependencies between distant voxels. This work aims to introduce 'DE-ConvGraph 3D UNet', a novel deep learning model, to address these limitations and optimize radiotherapy treatment plans for oropharyngeal cancer. The proposed 'DE-ConvGraph 3D UNet' model includes a Graph Convolutional Network (GCN) component to capture long-range dependencies between distant voxels. Furthermore, the dual-encoder structure of the model combines the strengths of GCN and 3D Convolutional U-Net, enabling global relationships and local pattern capturing in a 3D patient volume. Experiments were conducted using the benchmark dataset-OpenKBP-Opt. The proposed model shows improvements in performance in comparison to state-of-The-Art U-Net variants in terms of mean squared voxel-wise error, dose volume histogram points and clinical criteria satisfaction. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on Intelligent computing and Human-computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 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

UAV Deployment Optimization for Efficient data Forwarding in UAV-assisted Wireless Networks

UAV Deployment Optimization for Efficient Data Forwarding in...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Xueqi Wang, Aimin Sun, Geng Liu, Lingling Zhang, Jing Wang, Jiacheng Shi, Wenxiao Jilin University College of Computer Science and Technology Changchun130012 China Hainan University School of Information and Communication Engineering Haikou570000 China Jilin University College of Communication Engineering Changchun130012 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore

ISBN: (纸本)9798350351255

Given that the locations of base stations (BSs) remain fixed after installation, direct data forwarding to remote user equipment (UE) becomes challenging. Unmanned aerial vehicles (UAVs) offer a hopeful solution as mobile relays for next generation wireless communications to realize data forwarding with the flexible and cost-effective deployment. However, the limited onboard energy of UAVs and slow progress in energy storage technology pose significant challenges to achieving energy-efficient communication. Therefore, in this article, we investigate a wireless communication network utilizing a UAV as a high-altitude relay for data forwarding, and formulate a UAV relay deployment optimization problem (URDOP) to minimize the energy consumption of data forwarding and UAV hovering by optimizing UAV deployment, including the locations and number of UAV hover points. Given that the URDOP is a mixed-integer programming problem, conventional gradient-based approaches face limitations. To address this, we propose a self-adaptive differential evolution with a variable population size (SaDEVPS) algorithm to solve the URDOP. The performance of proposed SaDEVPS is verified through simulations, and the results show that it can successfully decrease the energy consumption of system when compared to other benchmark algorithms. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Searchable Encryption Scheme for Spatial Text data 13

Blockchain-based Searchable Encryption Scheme for Spatial Te...

引用

13th International Conference on Communication and Network Security, ICCNS 2023

作者： Lin, Zhirun Yang, Yang Zhan, Yonghua Li, Jiayin Dong, Chen College of Computer and Data Science Fuzhou University Fujian Fuzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou China

ISBN: (纸本)9798400707964

In today's society, an increasing number of users and enterprises encrypt substantial amounts of data, including spatial text data, and outsource it to cloud servers. However, efficiently and securely querying encrypted spatial text data remains a pressing issue. In this article, we propose a blockchain-based searchable encryption scheme for spatial text data. Users encrypt documents using methods such as order-preserving encryption and upload them to the blockchain for on-chain storage. The cloud server can only retrieve information stored within the blocks, facilitating keyword and coordinate comparisons. To enhance query speed, we introduce a sliding window that allows the server to quickly skip through non-matching blocks. Finally, through experiments and comparisons, this paper demonstrates that the proposed scheme excels in query efficiency and computational overhead, proving its superiority and feasibility compared to other solutions. © 2023 ACM.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 19-23页

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Faculty of Computing and Data Science FLAME University Maharashtra Pune India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023 The Authors

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

RAGRAPH: A General Retrieval-Augmented Graph Learning Framework 38

RAGRAPH: A General Retrieval-Augmented Graph Learning Framew...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Jiang, Xinke Qiu, Rihong Xu, Yongxin Zhang, Wentao Zhu, Yichen Zhang, Ruizhe Fang, Yuchen Chu, Xu Zhao, Junfeng Wang, Yasha School of Computer Science Peking University China University of Electronic Science and Technology of China China Center on Frontiers of Computing Studies Peking University Beijing China Big Data Technology Research Center Nanhu Laboratory Jiaxing China Peking University Information Technology Institute Binhai Tianjin China

Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGRAPH), which brings external graph data into the general graph foundation model to improve model generalization on unseen scenarios. On the top of our framework is a toy graph vector library that we established, which captures key attributes, such as features and task-specific label information. During inference, the RAGRAPH adeptly retrieves similar toy graphs based on key similarities in downstream tasks, integrating the retrieved data to enrich the learning context via the message-passing prompting mechanism. Our extensive experimental evaluations demonstrate that RAGRAPH significantly outperforms state-of-the-art graph learning methods in multiple tasks such as node classification, link prediction, and graph classification across both dynamic and static datasets. Furthermore, extensive testing confirms that RAGRAPH consistently maintains high performance without the need for task-specific fine-tuning, highlighting its adaptability, robustness, and broad applicability. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Local Regression-Based SLA-Aware Energy-Efficient Virtual Machine Consolidation Algorithm in data Centers 9

A Local Regression-Based SLA-Aware Energy-Efficient Virtual ...

引用

9th International Conference on Big data computing and Communications, BigCom 2023

作者： Wu, Xiaodong Wang, Ronghai Lin, Guoxin Quanzhou Normal University School of Mathmatics and Computer Science China Fujian Province University Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Fujian China Provincial Big Data Research Institute of Intelligent Manufacturing Quanzhou China

ISBN: (纸本)9798350331240

Virtual Machine Consolidation (VMC) is an effective means to improve the resource utilization and reduce energy consumption of data centers. However, the VMC optimization that only considers energy consumption may lead to SLA (Service-Level Agreements) violations and thus fail to guarantee the QoS (Quality of Service) provided. Therefore, it is necessary to consider both energy saving and SLA violations in the process of VMC. In this paper, we propose an energy and SLA-aware VMC algorithm that considers both energy saving and SLA violation optimization in data centers. The proposed algorithm uses the local regression method to predict the utilization of virtual machines, based on which it determines whether the host will be overloaded, so as to make the decision of virtual machine migrations. The proposed VMC algorithm is evaluated with CloudSim toolkit. Simulation results demonstrate that our algorithm has good energy saving performance and can effectively reduce SLA violation in cloud data center. Considering energy consumption and SLA violation, the ESV can be reduced by 7.57% on average and 16.36% at most compared with other algorithms. © 2023 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Fast Image matting based on matting pyramids and surrogate models 2

Fast Image matting based on matting pyramids and surrogate m...

引用

2nd International Conference on Robotics, Artificial Intelligence and Intelligent Control, RAIIC 2023

作者： Liang, Yihui Gou, Hongshan Liu, Guisong Huang, Sibo University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China University of Electronic Science and Technology of China Zhongshan Institute School of Computer Zhongshan China Guiyang Institute of Humanities and Technology College of Big Data and Information Engineering Guiyang China Southwestern University of Finance and Economics School of Computing and Artificial Intelligence Chengdu China Huizhou University Network and Information Centre Huizhou China

ISBN: (纸本)9798350328004

Image matting is a foundation task in the field of computer vision. Pixel-pair-optimization-based image matting methods have attracted lots of attention due to their distinct advantages on parallelization and handling spatially disconnected foregrounds. However, these methods struggle when the computing time is limited. To address this issue, this study presents the image matting method based on matting pyramid and surrogate model (IMMPSM). IMMPSM speeds up the process of pixel pair optimization by replaces the evolutionary algorithm in the pyramid matting framework, which consumes a lot of computing time, with the efficient surrogate-model-based method. The constructed surrogate model is reused by the presented surrogate model share strategy to save computing time. Specifically, the constructed surrogate model is shared with the pixel pair optimization subproblem adjacent to current subproblem avoiding repeated computation on the surrogate model construction. Extensive experimental results show that IMMPSM can provide acceptable alpha mattes even under limited computing time. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Sensor Fusion Against Inaudible Command Attacks in Advanced Driver-Assistance Systems

引用

IEEE Internet of Things Journal 2023年第19期10卷 17254-17264页

作者： Guan, Jiwei Pan, Lei Wang, Chen Yu, Shui Gao, Longxiang Zheng, Xi Macquarie University School of Computing SydneyNSW2109 Australia CSIRO Data61 SydneyNSW1710 Australia Deakin University School of Information Technology Waurn PondsVIC3125 Australia University of Technology Sydney Faculty of Engineering and Information Technology SydneyNSW2007 Australia Qilu University of Technology Shangdong Computer Science Center Jinan250316 China

There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become available in autonomous driving systems. How to empirically defend against these inaudible attacks remains an open question. Previous research investigates utilizing deep learning-based multimodal fusion for defense, without considering the model uncertainty in trustworthiness. As deep learning has been applied to increasingly sensitive tasks, uncertainty measurement is crucial in helping improve model robustness, especially in mission-critical scenarios. In this article, we propose the multimodal fusion framework (MFF) as an intelligent security system to defend against inaudible voice command attacks. MFF fuses heterogeneous audio-vision modalities using VGG family neural networks and achieves the detection accuracy of 92.25% in the comparative fusion method empirical study. Additionally, extensive experiments on audio-vision tasks reveal the model's uncertainty. Using expected calibration errors, we measure calibration errors and Monte Carlo Dropout to estimate the predictive distribution for the proposed models. Our findings show empirically to train robust multimodal models, improve standard accuracy and provide a further step toward interpretability. Finally, we discuss the pros and cons of our approach and its applicability for advanced driver assistance systems. © 2014 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

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：