检索结果-内蒙古大学图书馆

A Unified Deep Reinforcement Learning Approach for Constructing Rectilinear and Octilinear Steiner Minimum Tree

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2024年

作者： Lin, Zhenkun Liu, Genggeng Huang, Xing Lin, Yibo Zhang, Jixin Liu, Wen-Hao Wang, Ting-Chi Fuzhou University College of Computer and Data Science Fuzhou350100 China Northwestern Polytechnical University School of Computer Science Xi'an710072 China Peking University Beijing Advanced Innovation Center for Integrated Circuits School of Integrated Circuits Beijing China Peking University Institute of Electronic Design Automation Wuxi China Hubei University of Technology School of Computer Science Wuhan China Nvidia Taiwan National Tsing Hua University Department of Computer Science Hsinchu30013 Taiwan

The Steiner Minimum Tree (SMT) serves as an optimal connection model for multi-terminal nets in Very Large Scale Integration (VLSI). Constructing both Rectilinear Steiner Minimum Tree (RSMT) and Octilinear Steiner Minimum Tree (OSMT) are known to be NP-hard problems. Simultaneously, constructing multiple topologies of SMTs for a given net holds significant importance in alleviating routing constraints such as alleviating congestion and ensuring timing convergence. However, existing efforts predominantly focus on designing specialized methods to construct a specifically structured SMT for a given net, making it challenging to extend to different structures or topologies of SMTs, while also exhibiting insufficient optimization capabilities. In this work, we propose a unified approach based on Deep Reinforcement Learning (DRL) to address both RSMT and OSMT problems while generating diverse routing topologies. First, we design an Edge Point Sequence (EPS) that leverages the structural characteristics of SMT to connect the output of the deep learning model with the SMT structure. Second, we propose a deep learning model tailored for EPS, employing the negative wirelength of SMT as a reward to train the model using DRL. Third, we provide a corresponding rapid and accurate wirelength computation algorithm for evaluating the quality of the construction solution to expedite model training. Finally, we leverage the stochastic nature of machine learning to construct diverse SMT construction solutions. To the best of our knowledge, this is the first unified approach capable of simultaneously addressing both RSMT and OSMT problems while generating diverse solutions. The proposed unified approach demonstrates superior solution quality and higher efficiency compared to specifically designed algorithms. © 1982-2012 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Dr-Hydranet: Enhancing Diabetic Retinopathy Diagnosis by Integrating Hydra Attention and Removing Inefficient Heads

SSRN

引用

SSRN 2024年

作者： Ali, Muhammad Shafqat Azhar, Muhammad He, Yulin Wattoo, Waqas Ahmad Masood, Saba Ferzund, Javed Department of Computer Science Comsats University Islamabad Pakistan Department of Applied Data Science Hong Kong Shue Yan University Hong Kong Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China

Diabetic Retinopathy (DR) is a serious complication of diabetes that can lead to blindness if not diagnosed and treated promptly. While conventional machine learning (ML) techniques and deep learning models, especially Convolutional Neural Networks (CNNs), have been applied to automated DR diagnosis, CNNs encounter challenges such as high computational costs and difficulties in capturing long-range pixel relationships. The Vision Transformer (ViT) presents a promising architecture for image classification but is hindered by inefficiencies and accuracy issues due to the absence of specialized local attention mechanisms. To address these problems, we propose a novel solution, DR-HydraNet, which integrates hydra attention and optimizes the ViT model by removing inefficient attention heads. This approach effectively balances local and global feature extraction, reducing computation time while enhancing diagnostic accuracy. Extensive experiments demonstrate that our model achieves an accuracy of 97\%, an F1 score of 91\%, precision of 93\%, and recall of 90\%, significantly outperforming state-of-the-art models. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Heart Disease Classification: An Ensemble-Based Deep Learning Approach

Enhanced Heart Disease Classification: An Ensemble-Based Dee...

引用

IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)

作者： Nivaashini M Sathish Kumar G Uma Maheshwari G Soundariya R S Arun Kumar B Vijaya G Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Coimbatore Tamil Nadu India Department of Computer Technology Bannari Amman Institute of Technology Sathyamangalam Tamil Nadu India Department of Artificial Intelligence and Data Science Faculty of Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376142

The WHO's assessment indicates a rising prevalence of heart disease, exacerbated by challenges in detection and diagnosis in India due to population growth. Machine Learning (ML) is increasingly used for precise judgments in healthcare, aiming to accurately diagnose heart-related illnesses. This study proposes a Deep Learning (DL) ensemble method, combining ML classifiers to enhance accuracy. The ensemble model outperforms AdaBoost, XGBoost, Random Forest, Decision Tree, SVM, and Logistic Regression with 98.3% accuracy on a UCI dataset. Correlation-based Feature Selection (CFS) for relevant characteristic selection improves the model's accuracy, recall, precision, and f1-score. This research contributes to improved disease prediction and categorization in cardiovascular health, vital for effective healthcare interventions and outcomes.

关键词： Heart Deep learning Support vector machines Accuracy Medical services Signal processing SPICE Regression tree analysis Random forests Diseases

来源：评论

学校读者我要写书评

暂无评论

Demo: CaseFinder: Automated Visual and Quantitative Analysis Tool for Police Narrative

Demo: CaseFinder: Automated Visual and Quantitative Analysis...

引用

IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)

作者： Martin Brown Dominic Thomas Md Abdullah Al Hafiz Khan Abm Adnan Azmee Monica Nandan Yang Pei Department of Data Science and Analytics Kennesaw State University Marietta USA Information Systems Kennesaw State University Marietta USA Computer Science Kennesaw State University Marietta USA Computer Science Social Work and Human Services Kennesaw State University Marietta USA

ISBN: (数字)9798350345018

ISBN: (纸本)9798350345025

This demonstration introduces the CaseFinder tool, a GUI designed to automate visualizations and quantitatively analyze 911 police reports. The tool allows for efficient data exploration for non-technical users integrating behavioral health-related keywords. By amalgamating diverse keyword category inputs, CaseFinder provides a holistic approach to analyzing reports by uncovering indications of behavioral health problems while including perspectives from multiple professional domains. Ultimately, CaseFinder aims to improve the understanding of the magnitude of the problem of behavioral health issues involved in 911 crises to mitigate reoccurrence.

关键词： Visualization Law enforcement Statistical analysis data visualization Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

arXiv

引用

arXiv 2024年

作者： Guo, Jingcai Rao, Zhijie Chen, Zhi Guo, Song Zhou, Jingren Tao, Dacheng Department of Computing The Hong Kong Polytechnic University Hong Kong School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Alibaba Group Hangzhou311121 China College of Computing and Data Science Nanyang Technological University Singapore

Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain. The gist of ZSIR is constructing a well-aligned mapping between the input visual space and the target semantic space, which is a bottom-up paradigm inspired by the process by which humans observe the world. In recent years, ZSIR has witnessed significant progress on a broad spectrum, from theory to algorithm design, as well as widespread applications. However, to the best of our knowledge, there remains a lack of a systematic review of ZSIR from an element-wise perspective, i.e., learning fine-grained elements of data and their inferential associations. To fill the gap, this paper thoroughly investigates recent advances in element-wise ZSIR and provides a sound basis for its future development. Concretely, we first integrate three basic ZSIR tasks, i.e., object recognition, compositional recognition, and foundation model-based open-world recognition, into a unified element-wise paradigm and provide a detailed taxonomy and analysis of the main approaches. Next, we summarize the benchmarks, covering technical implementations, standardized datasets, and some more details as a library [link]. Last, we sketch out related applications, discuss vital challenges, and suggest potential future directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

arXiv

引用

arXiv 2024年

作者： Zhou, Yu Wu, Xingyu Wu, Jibin Feng, Liang Tan, Kay Chen Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University Chongqing China

Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the need for original training data and further training processes. However, most existing model merging approaches focus solely on exploring the parameter space, merging models with identical architectures. Merging within the architecture space, despite its potential, remains in its early stages due to the vast search space and the challenges of layer compatibility. This paper marks a significant advance toward more flexible and comprehensive model merging techniques by modeling the architecture-space merging process as a reinforcement learning task. We train policy and value networks using offline sampling of weight vectors, which are then employed for the online optimization of merging strategies. Moreover, a multi-objective optimization paradigm is introduced to accommodate users’ diverse task preferences, learning the Pareto front of optimal models to offer customized merging suggestions. Experimental results across multiple tasks, including text translation, mathematical reasoning, and code generation, validate the effectiveness and superiority of the proposed framework in model merging. The code will be made publicly available after the review process. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Image Encryption and Decoding Approach Based on DNA Coding and Arnold's Transformation for IoT Applications

A Novel Image Encryption and Decoding Approach Based on DNA ...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Nawal Shaltout Ahmed A. Abd El-Latif Waleed Al-Adrousy Mohamed Hammad Abdelhamied A. Ateya Samir Elmougy Department of Computer Science Faculty of Computers and Information Mansoura University Mansoura Egypt EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Department of Mathematics and Computer Science Faculty of Science Menoufia University Egypt Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom Egypt Department of Electronics and Communications Engineering Zagazig University Zagazig Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Nowadays, the Internet of Things (IoT) is significantly utilized by an extensive range of applications that lead to the enhancement of different aspects of defense and military capabilities. In IoT, a wide range of smart devices that can communicate with each other are connected through it. Therefore, it is essential to protect multimedia data, especially images with an encryption approach that offers a sufficient degree of security in military applications. Hence, this paper introduces an effective scheme for image encryption and decoding relying on Arnold's transformation DNA coding. It proposes a new pseudo-random number generation PRNG using the Sine-Logistic map and Duffing map called SLDM. The encryption method involves three phases: 1- Key generation and PRNG. 2- confusion phase using the Arnold transformation method. 3- diffusion using DNA rules and operations. The results based on the USC-SIPI dataset, show that the suggested scheme is sufficiently resistant to every kind of attack. Furthermore, the suggested method yields NPCR scores of around 99.62% and UACI scores of approximately 33.48%. Due to its low complexity, it has a great deal of potential for safe and real-time picture applications.

关键词： Resistance Image coding Chaotic communication DNA Encryption Decoding Telecommunications

来源：评论

学校读者我要写书评

暂无评论

VisTaxa: Developing a Taxonomy of Historical Visualizations

引用

IEEE Transactions on Visualization and computer Graphics 2025年第6期31卷 3850-3862页

作者： Yu Zhang Xinyue Chen Weili Zheng Yuhan Guo Guozheng Li Siming Chen Xiaoru Yuan Department of Computer Science University of Oxford Oxford U.K. National Key Laboratory of General Artificial Intelligence and School of Intelligence Science and Technology Peking University and PKU-WUHAN Institute for Artificial Intelligence Beijing China School of Data Science Fudan University Shanghai China Beijing Institute of Technology Beijing China

Historical visualizations are a rich resource for visualization research. While taxonomy is commonly used to structure and understand the design space of visualizations, existing taxonomies primarily focus on contemporary visualizations and largely overlook historical visualizations. To address this gap, we describe an empirical method for taxonomy development. We introduce a coding protocol and the VisTaxa system for taxonomy labeling and comparison. We demonstrate using our method to develop a historical visualization taxonomy by coding 400 images of historical visualizations. We analyze the coding result and reflect on the coding process. Our work is an initial step toward a systematic investigation of the design space of historical visualizations.

关键词： Taxonomy data visualization Visualization Encoding Protocols Image coding Labeling Artificial intelligence Image resolution Training

来源：评论

学校读者我要写书评

暂无评论

No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction data, and Benchmarks

arXiv

引用

arXiv 2024年

作者： Hu, Gang Qin, Ke Yuan, Chenhan Peng, Min Lopez-Lira, Alejandro Wang, Benyou Ananiadou, Sophia Yu, Wanlong Huang, Jimin Xie, Qianqian School of Information Science Yunnan University Kunming China Department of Computer Science The University of Manchester United Kingdom School of Computer Science Wuhan University Wuhan China Department of Finance Insurance and Real Estate University of Florida United States School of Data Science The Chinese University of Hong Kong Shenzhen China The Fin AI Singapore

While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. To bridge this chasm, we introduce ICE-PIXIU1, seamlessly amalgamating the ICE-INTENT model and ICE-FLARE benchmark for bilingual financial analysis. ICE-PIXIU uniquely integrates a spectrum of Chinese tasks, alongside translated and original English datasets, enriching the breadth and depth of bilingual financial modeling. It provides unrestricted access to diverse model variants, a substantial compilation of diverse cross-lingual and multi-modal instruction data, and an evaluation benchmark with expert annotations, comprising 10 NLP tasks, 20 bilingual specific tasks, totaling 95k datasets. Our thorough evaluation emphasizes the advantages of incorporating these bilingual datasets, especially in translation tasks and utilizing original English data, enhancing both linguistic flexibility and analytical acuity in financial contexts. Notably, ICE-INTENT distinguishes itself by showcasing significant enhancements over conventional LLMs and existing financial LLMs in bilingual milieus, underscoring the profound impact of robust bilingual data on the accuracy and efficacy of financial NLP. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Blockchain System for Decentralized Governance

Explainable AI in Blockchain System for Decentralized Govern...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Suman Chahar Kawaljit Kaur Kuldeep Singh Kaswan Jagjit Singh Dhatterwal University Institute of Computing Chandigarh University Mohali India Department of Computer Science and Engineering Galgotias University Greater Noida India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Decentralized governance is going through radical changes due to the innovative use of blockchain which allows decisions to be made in a transparent, secure and more im- portantly, immutable way, without the authority of a single individual or party. Thus, the introduction of artificial intelligence (AI) in blockchain governing systems complicates such thing as transparency and trust, especially in the case of deep AI systems. But more on this later – this is where Explainable AI or XAI comes into the picture. XAI methods enable understanding of the reasons behind the choices made by AI models and solves the "black box" problem that is predominant in machine learn- ing. When applied to decentralised governance, XAI provides clarifications of AI’s decision making in such areas as voting, resource distribution and the enactment of smart contracts. This way, the stakeholders are confident that the decision-making is fair and impartial and this is made possible by the use of XAI. This paper aims to find out more about the applicability of XAI concept in blockchain –based governance systems in terms of bias and fairness in automated decisions and explanation of the decisions made. The reasons why interpretability plays the crucial role in decentralized systems are explained with the help of the comparison between the classical artificial intelligence and the Xin Intelligent. The study also looks at various use cases such as, Decentralized Autonomous Organizations (DAOs), and voting systems implemented on blockchain platforms and how XAI can enhance the performance of the governance systems. As this study shows, XAI is vital in building trust, improving responsibility, and guaranteeing balanced majorities in decentralized blockchain governance structures.

关键词： Explainable AI Decentralized autonomous organization Computational modeling Smart contracts Decision making Blockchains Resource management Stakeholders Security Decision trees

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：