检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Zepeng Ma, Chao Zhou, Linjiang Wu, Libing Yang, Lei Shi, Xiaochuan Peng, Guojun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China School of Software Engineering South China University of Technology China

Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose E2CFD, an effective and efficient cost function design framework. E2CFD leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the fast performance evaluation (FPE) method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, E2CFD aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques in Mobile Edge computing for Internet of Medical Things 3

Deep Learning Techniques in Mobile Edge Computing for Intern...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Alawadhi, Abdulwadood Ahmad, R. Badlishah Almogahed, Abdullah Abrar, Ahmad Department of Computers and Information Technology Yemen Universiti Malaysia Perlis Faculty of Electronic Engineering and Technology Perlis Malaysia Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Parit Raja Malaysia School of Computing Universiti Utara Malaysia InterNetWorks Research Laboratory Sintok-Kedah Malaysia

ISBN: (纸本)9798350305333

The fast expansion of the Internet of Medical Things (IoMT) has resulted in a ubiquitous home health diagnostic network. High patient demand results in high costs, short latency, and communication overload. As a result, 6G is the next generation of IoT, IoMT, and cellular networks, intending to considerably improve the quality of smart healthcare services through high throughput and decreased latency. So far, adopting cloud computing for time-critical applications and decreasing access delays to resources is difficult. Deep learning has been extensively employed to extract characteristics from complicated networks as artificial intelligence technology has advanced. On the other hand, deep learning models are often run in cloud computing data centres with tremendous processing resources. Conventional cloud computing systems primarily rely on the network, which has significant latency and security and privacy issues. One of the successful solutions is the Mobile Edge computing (MEC) paradigm, which brings cloud computing services closer to the edge network and uses available resources. Mobile edge computing places computer and storage nodes near mobile devices at the Internet's edge, leading to considerable savings in system operating time, memory cost, and power usage. Deep learning is used in mobile edge computing to forecast changes in demand based on daily patient behaviours. It also prepares the network by scaling up network resources as required. This study aims to discuss IoMT and identfy the problems in deep learning for mobile edge computing technology and its applications. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

UMixer: A Novel U-shaped Convolutional Mixer for Multi-scale Feature Fusion in Medical Image Segmentation 16th

UMixer: A Novel U-shaped Convolutional Mixer for Multi-scal...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Su, Yongxin Huang, Hongbo Song, Zun Lin, Lei Liu, Jinhan Mechanical Electrical Engineering School Beijing Information Science and Technology University Beijing China Computer School Beijing Information Science and Technology University Beijing China School of Economics and Management Beijing Information Science and Technology University Beijing China Institute of Computing Intelligence Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9783031202322

Medical image segmentation plays a critical role in assisting diagnosis and prognosis. Since the transformer was first introduced to the field, the neural network structure has experienced a transition from ConvNet into Transformer. However, some redesigned ConvNets in recent works show astonishing effects, which outperforms classic elaborate ConvNets, and even complicated transformers. Inspired by these works, we introduced large-kernel convolutions to improve the ConvNets in capturing the long-range dependency. Cooperated with a novel multi-scale feature fusion method, we proposed a U-shaped convolutional structure, dubbed UMixer, which effectively integrates shallow spatial information with deep semantic information and high-resolution detailed information with low-resolution global information. Without any attention mechanism and pre-training on large datasets, UMixer achieves more accurate segmentation results than traditional ConvNets and Transformers on the Synapse dataset. Experiments demonstrate the effectiveness of this multi-scale feature fusion structure and its capability in modeling long-range dependency. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Reliability-Aware DQN-based Optimization Method of Initial Mapping Solutions in Optical Network-on- Chip (ONoC) 21

Reliability-Aware DQN-based Optimization Method of Initial M...

引用

21st International Conference on Optical Communications and Networks, ICOCN 2023

作者： Niu, Yuxiang Li, Hui Liu, Feiyang Xidian University State Key Laboratory of Integrated Services Network School of Telecommunications Engineering Xi'an China Hangzhou Institute of Technology Xidian University Hangzhou China Xi'an Aeronautics Computing Technique Research Institute Avic Xi'an China

ISBN: (纸本)9798350343502

Optical Network-on-Chip (ONoC) provides a promising solution for on-chip communication with higher bandwidth and lower latency, compared to traditional Electrical Network-on-Chip (ENoC). However, the reliability challenges (such as insertion loss and crosstalk) exist in ONoC. As for this issue, reliability-aware mapping can be considered. This work proposes a reliability-aware DQN-based optimization method of initial mapping solutions in ONoC, to generate better initial mapping solutions. This optimization method of initial mapping solutions can be combined with existing mapping algorithms, further improving the mapping performance. The evaluation results show that for a given core graph and network topology, our proposed method generates better solutions compared to the traditional random method. Also, the proposed method is helpful for finding the optimal mapping solution more efficiently when combined with the existing mapping algorithms. © 2023 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

CSFIR: Leveraging Code-Specific Features to Augment Information Retrieval in Low-Resource Code Datasets

CSFIR: Leveraging Code-Specific Features to Augment Informat...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhenyu Tong Chenxi Luo Tiejian Luo School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computing Engineering and Mathematics La Trobe University Melbourne VIC Australia

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

From search engines like Google to advanced applications such as Retrieval Augmented Generation integrating Large Language Model (LLM), Information Retrieval (IR) serves a crucial role. To facilitate the development of increasingly large and complex code program projects, researchers introduce IR systems into the code domain. Unfortunately, although IR systems achieve significant success in retrieving natural language corpus and query, they face challenges when tasked with retrieving corpus consisting of code sequences. Primarily, in practical applications, most code sequences lack corresponding natural language annotations, which are known as low-resource scenarios, hindering the training of neural network-based retriever in IR systems. Furthermore, modern IR systems often overlook the structural features of code sequences, which may be beneficial for understanding these sequences. Additionally, the length of most code sequences exceeds that of equivalent natural language expressions, complicating the processing of relationships between code and natural language sequences. To address these challenges, we propose a novel IR system CSFIR, which leverages Code-Speclflc Features to augment IR. For the prevalent issue of unlabeled code sequences in low-resource scenarios, we employ a supervised fine-tuned LLM as a generator to generate natural language queries for unlabeled code sequence. Subsequently, we extract structural features from the abstract syntax tree of code sequence using graph convolution networks and integrate these features to enhance the original retriever. Finally, given the adverse effects of lengthy code sequences on generators, we propose a subtree segmentation algorithm, which reduces the length of code sequences without compromising their original meaning, thereby enhancing the quality of queries generated by the generator. We conduct comparative experiments to ascertain the efficacy of our method. Regarding Recall@100, our CSFIR system improves f

关键词： Training Codes Convolution Large language models Natural languages Retrieval augmented generation Syntactics Search engines Feature extraction Generators

来源：评论

学校读者我要写书评

暂无评论

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional Network

引用

Computers, Materials & Continua 2022年第3期70卷 5503-5518页

作者： Kanika Bhalla Deepika Koundal Surbhi Bhatia Mohammad Khalid Imam Rahmani Muhammad Tahir Department of Electrical Engineering National Taipei University of TechnologyTaipei10608Taiwan Department Virtualization School of Computer ScienceUniversity of Petroleum&Energy StudiesDehradunIndia College of Computer Science and Information technology King Faisal University36362Saudi Arabia College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared(IR)/visible(VS)*** in various kind of features in these images are vital to preserve in the single fused ***,simultaneous preservation of both the aspects at the same time is a challenging ***,most of the existing methods utilize the manual extraction of features;and manual complicated designing of fusion rules resulted in a blurry artifact in the fused ***,this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous ***,fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the ***,images have been learned by two parallel branches of the siamese convolutional neural network(CNN)to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image ***,the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixelwise strategy to result in fused *** parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information(MI),0.841 for entropy(EG),0.655 for edge information(EI),0.652 for human perception(HP),and 0.980 for image structural similarity(ISS).Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform(DCT),anisotropic diffusion&karhunen-loeve(ADKL),guided filter(GF),random walk(RW),principal component analysis(PCA),and convolutional neural network(CNN)methods.

关键词： Convolutional neural network fuzzy sets infrared and visible image fusion deep learning

来源：评论

学校读者我要写书评

暂无评论

Ethical Concerns of Generative AI and Mitigation Strategies: A Systematic Mapping Study

arXiv

引用

arXiv 2025年

作者： Huang, Yutan Arora, Chetan Houng, Wen Cheng Kanij, Tanjila Madulgalla, Anuradha Grundy, John Faculty of Information Technology Monash University ClaytonVIC Australia School of Science Computing and Engineering Technologies Swinburne University HawthornVIC Australia School of Information Technology Deakin University GeelongVIC Australia

[Context] Generative AI technologies, particularly Large Language Models (LLMs), have transformed numerous domains by enhancing convenience and efficiency in information retrieval, content generation, and decision-making processes. However, deploying LLMs also presents diverse ethical challenges, and their mitigation strategies remain complex and domain-dependent. [Objective] This paper aims to identify and categorize the key ethical concerns associated with using LLMs, examine existing mitigation strategies, and assess the outstanding challenges in implementing these strategies across various domains. [Method] We conducted a systematic mapping study, reviewing 39 studies that discuss ethical concerns and mitigation strategies related to LLMs. We analyzed these ethical concerns using five ethical dimensions that we extracted based on various existing guidelines, frameworks, and an analysis of the mitigation strategies and implementation challenges. [Results] Our findings reveal that ethical concerns in LLMs are multi-dimensional and context-dependent. While proposed mitigation strategies address some of these concerns, significant challenges still remain. [Conclusion] Our results highlight that ethical issues often hinder the practical implementation of the mitigation strategies, particularly in high-stake areas like healthcare and public governance;existing frameworks often lack adaptability, failing to accommodate evolving societal expectations and diverse contexts. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

What’s My Line? Exploring the Expressive Capacity of Lines in Scientific Visualization

What’s My Line? Exploring the Expressive Capacity of Lines ...

引用

IEEE VIS Arts Program (VISAP)

作者： Francesca Samsel Lyn Bartram Anne Bowen Ben Carlton Gregory Abram Texas Advanced Computing Center University of Texas at Austin School of Interactive Art and Technology Simon Fraser University Cockrell School of Engineering University of Texas at Austin

ISBN: (数字)9798331517298

ISBN: (纸本)9798331517304

Data is moving beyond the scientific community, flooding communication channels and addressing issues of importance to all aspects of daily life. This highlights the need for rich and expressive data representations to communicate the science on which society rests and must act. However, current visualization techniques often lack the broad visual vocabulary needed to accommodate the explosion in data scale, diversity, and audience perspectives. While previous work has mined artistic and design knowledge for color maps and shape affordances (glyphs) in visualization, line encoding has received little attention. In this paper, we report on an exploration of visual properties that extend the vocabulary of the line, particularly for categorical encoding. We describe the creation of a corpus of lines motivated by artistic practice, Gestalt theory, and design principles, and present initial results from a study of how different visual properties influence how people associate these into sets of similar lines. While very preliminary, the findings suggest that a rich set of line attributes will support both association and categorical hierarchies, as well as provoke further inquiry into how and why line encoding can be more expressive in encoding multivariate, multidimensional data.

关键词： Visualization Vocabulary Art Shape Image color analysis Data visualization Communication channels Encoding Explosions Cultural differences

来源：评论

学校读者我要写书评

暂无评论

A Study on Quantum Machine Learning for Accurate and Efficient Weather Prediction 6

A Study on Quantum Machine Learning for Accurate and Efficie...

引用

6th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2022

作者： Surendiran, B. Dhanasekaran, K. Tamizhselvi, A. Department of Computer Science and Engineering Karaikal Puducherry India Srm Institute of Science and Technology Kattankulathur School of Computing Chennai603203 India St. Joseph's College of Engineering Omr Department of Information Technology Chennai600119 India

ISBN: (数字)9781665469418

ISBN: (纸本)9781665469418

Recently Quantum computing has gained much attention in the field of data science and computational problem solving. It is expected that the quantum machine learning will help researchers to find solutions for many complex problems in areas such as weather forecasting, data science, computational biology, energy management, secure communication, and many others. This paper presents a study on quantum machine learning techniques, challenges and applications of these techniques in climate change prediction, and weather forecasting towards future research in Quantum Machine Learning and Quantum computing. It also discusses the latest developments and trends in Quantum machine Learning and presents practical examples to understand how Quantum Machine Learning considerably improves the performances of existing machine learning approaches. © 2022 IEEE.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

TGNet: Learning 3D Shape from Sparse and Incomplete Point Cloud 9

TGNet: Learning 3D Shape from Sparse and Incomplete Point Cl...

引用

9th International Conference on Virtual Reality, ICVR 2023

作者： Li, Yushi Wang, Jia Wang, Yunzhe Xiang, Rong Wang, Yihong Pan, Yushan Xi'an Jiaotong-Liverpool University Department of Intelligent Science Suzhou China Suzhou University of Science and Technology School of Electronic & Information Engineering Suzhou China The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

ISBN: (纸本)9798350345810

Learning accurate 3D shapes from sparse and incomplete point clouds is challenging and meaningful, on account that the point clouds with low resolution always lack representative and informative details. This paper presents a novel deep auto-encoder called TGNet, which is formulated based on a tree-based generative adversarial network (GAN), to address self-supervised learning tasks on the point cloud with low sparsity. On the encoder side, we employ a PointNet-based framework to intensively capture the global representations. To better infer the spatial information in latent space, we propose a spectral graph learning module in with due consideration to graph topology. Further, we present a new loss that combines Wasserstein metric and multi-resolution Chamfer distance to better estimate global 3D geometry and structural details. The proposed TGNet achieves state-of-the-art performance for various point cloud learning tasks. Qualitative and quantitative evaluations demonstrate the novelty of the proposed model. © 2023 IEEE.

关键词： Generative adversarial networks

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：