检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chan, Nimeesha Parker, Felix Bennett, William Wu, Tianyi Jia, Mung Yao Fackler, James Ghobadi, Kimia Department of Civil and Systems Engineering Johns Hopkins University United States Department of Anesthesiology and Critical Care Medicine Johns Hopkins University United States Department of Applied Mathematics and Statistics Johns Hopkins University United States Department of Computer Science Johns Hopkins University United States

The complexity and heterogeneity of data in many real-world applications pose significant challenges for traditional machine learning and signal processing techniques. For instance, in medicine, effective analysis of diverse physiological signals is crucial for patient monitoring and clinical decision-making and yet highly challenging. We introduce MedTsLLM, a general multimodal large language model (LLM) framework that effectively integrates time series data and rich contextual information in the form of text to analyze physiological signals, performing three tasks with clinical relevance: semantic segmentation, boundary detection, and anomaly detection in time series. These critical tasks enable deeper analysis of physiological signals and can provide actionable insights for clinicians. We utilize a reprogramming layer to align embeddings of time series patches with a pretrained LLM's embedding space and make effective use of raw time series, in conjunction with textual context. Given the multivariate nature of medical datasets, we develop methods to handle multiple covariates. We additionally tailor the text prompt to include patient-specific information. Our model outperforms state-of-the-art baselines, including deep learning models, other LLMs, and clinical methods across multiple medical domains, specifically electrocardiograms and respiratory waveforms. MedTsLLM presents a promising step towards harnessing the power of LLMs for medical time series analysis that can elevate data-driven tools for clinicians and improve patient outcomes. © 2024, CC BY-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep Reference Priors: What is the best way to pretrain a model?

arXiv

引用

arXiv 2022年

作者： Gao, Yansong Ramesh, Rahul Chaudhari, Pratik Applied Mathematics and Computational Sciences University of Pennsylvania United States Computer and Information Science University of Pennsylvania United States Electrical and Systems Engineering University of Pennsylvania United States

What is the best way to exploit extra data-be it unlabeled data from the same task, or labeled data from a related task-to learn a given task? This paper formalizes the question using the theory of reference priors. Reference priors are objective, uninformative Bayesian priors that maximize the mutual information between the task and the weights of the model. Such priors enable the task to maximally affect the Bayesian posterior, e.g., reference priors depend upon the number of samples available for learning the task and for very small sample sizes, the prior puts more probability mass on low-complexity models in the hypothesis space. This paper presents the first demonstration of reference priors for medium-scale deep networks and image-based data. We develop generalizations of reference priors and demonstrate applications to two problems. First, by using unlabeled data to compute the reference prior, we develop new Bayesian semi-supervised learning methods that remain effective even with very few samples per class. Second, by using labeled data from the source task to compute the reference prior, we develop a new pretraining method for transfer learning that allows data from the target task to maximally affect the Bayesian posterior. Empirical validation of these methods is conducted on image classification datasets. Code is available at https://***/grasp-lyrl/deep_reference_priors. © 2022, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

MetaUE: Model-based Meta-learning for Underwater Image Enhancement

arXiv

引用

arXiv 2023年

作者： Zhang, Zhenwei Yan, Haorui Tang, Ke Duan, Yuping Center for Applied Mathematics Tianjin University Tianjin300072 China The Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing data, it may result in over-fitting and enhancement degradation. This paper proposes a model-based deep learning method for restoring clean images under various underwater scenarios, which exhibits good interpretability and generalization ability. More specifically, we build up a multi-variable convolutional neural network model to estimate the clean image, background light and transmission map, respectively. An efficient loss function is also designed to closely integrate the variables based on the underwater image model. The meta-learning strategy is used to obtain a pre-trained model on the synthetic underwater dataset, which contains different types of degradation to cover the various underwater environments. The pre-trained model is then fine-tuned on real underwater datasets to obtain a reliable underwater image enhancement model, called MetaUE. Numerical experiments demonstrate that the pre-trained model has good generalization ability, allowing it to remove the color degradation for various underwater attenuation images such as blue, green and yellow, etc. The fine-tuning makes the model able to adapt to different underwater datasets, the enhancement results of which outperform the state-of-the-art underwater image restoration methods. All our codes and data are available at https://***/Duanlab123/MetaUE. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI

引用

computers in Biology and Medicine 2024年 182卷 109183-109183页

作者： Ullah, Muhammad Sami Khan, Muhammad Attique Albarakati, Hussain Mubarak Damaševičius, Robertas Alsenan, Shrooq Department of Computer Science HITEC University Taxila47080 Pakistan Department of Artificial Intelligence College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al Khobar Saudi Arabia Computer and Network Engineering Department College of Computing Umm Al-Qura University Makkah24382 Saudi Arabia Faculty of Applied Mathematics Silesian University of Technology Gliwice44-100 Poland Information Systems Department College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Explainable artificial intelligence (XAI) aims to offer machine learning (ML) methods that enable people to comprehend, properly trust, and create more explainable models. In medical imaging, XAI has been adopted to interpret deep learning black box models to demonstrate the trustworthiness of machine decisions and predictions. In this work, we proposed a deep learning and explainable AI-based framework for segmenting and classifying brain tumors. The proposed framework consists of two parts. The first part, encoder-decoder-based DeepLabv3+ architecture, is implemented with Bayesian Optimization (BO) based hyperparameter initialization. The different scales are performed, and features are extracted through the Atrous Spatial Pyramid Pooling (ASPP) technique. The extracted features are passed to the output layer for tumor segmentation. In the second part of the proposed framework, two customized models have been proposed named Inverted Residual Bottleneck 96 layers (IRB-96) and Inverted Residual Bottleneck Self-Attention (IRB-Self). Both models are trained on the selected brain tumor datasets and extracted features from the global average pooling and self-attention layers. Features are fused using a serial approach, and classification is performed. The BO-based hyperparameters optimization of the neural network classifiers is performed and the classification results have been optimized. An XAI method named LIME is implemented to check the interpretability of the proposed models. The experimental process of the proposed framework was performed on the Figshare dataset, and an average segmentation accuracy of 92.68 % and classification accuracy of 95.42 % were obtained, respectively. Compared with state-of-the-art techniques, the proposed framework shows improved accuracy. © 2024 Elsevier Ltd

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Quantum Hamiltonian Descent for Non-smooth Optimization

arXiv

引用

arXiv 2025年

作者： Leng, Jiaqi Zheng, Yufan Jia, Zhiyuan Fan, Lei Zhao, Chaoyue Peng, Yuxiang Wu, Xiaodi Simons Institute for the Theory of Computing University of California Berkeley United States Department of Mathematics University of California Berkeley United States Department of Computer Science University of Maryland College Park United States Joint Center for Quantum Information and Computer Science University of Maryland United States Department of Applied Mathematics University of Washington United States Department of Engineering Technology University of Houston United States Department of Electrical and Computer Engineering University of Houston United States Department of Industrial and Systems Engineering University of Washington United States Artephi Computing Inc United States

Non-smooth optimization models play a fundamental role in various disciplines, including engineering, science, management, and finance. However, classical algorithms for solving such models often struggle with convergence speed, scalability, and parameter tuning, particularly in high-dimensional and non-convex settings. In this paper, we explore how quantum mechanics can be leveraged to overcome these limitations. Specifically, we investigate the theoretical properties of the Quantum Hamiltonian Descent (QHD) algorithm for non-smooth optimization in both continuous and discrete time. First, we propose continuous-time variants of the general QHD algorithm and establish their global convergence and convergence rate for non-smooth convex and strongly convex problems through a novel Lyapunov function design. Furthermore, we prove the finite-time global convergence of continuous-time QHD for non-smooth non-convex problems under mild conditions (i.e., locally Lipschitz). In addition, we propose discrete-time QHD, a fully digitized implementation of QHD via operator splitting (i.e., product formula). We find that discrete-time QHD exhibits similar convergence properties even with large time steps. Finally, numerical experiments validate our theoretical findings and demonstrate the computational advantages of QHD over classical non-smooth non-convex optimization algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

A New Approach to Eliminate Rank Reversal in the MCDA Problems 21st

A New Approach to Eliminate Rank Reversal in the MCDA Proble...

引用

21st International Conference on Computational science, ICCS 2021

作者： Kizielewicz, Bartlomiej Shekhovtsov, Andrii Salabun, Wojciech Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Żolnierska 49 Szczecin71-210 Poland

ISBN: (纸本)9783030779603

In the multi-criteria decision analysis (MCDA) domain, one of the most important challenges of today is Rank Reversal. In short, it is a paradox that the order of alternatives belonging to a certain set is changed when a new alternative is added to that set or one of the current ones is removed. It may undermine the credibility of ratings and rankings, which are returned by methods exposed to the Rank Reversal phenomenon. In this paper, we propose to use the Characteristic Objects method (COMET), which is resistant to the Rank Reversal phenomenon and combining it with the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Preference Ranking Organization Method for Enrichment Evaluations II (PROMETHEE II) methods. The COMET method requires a very large number of pair comparisons, which depends exponentially on the number of criteria used. Therefore, the task of pair comparisons will be performed using the PROMETHEE II and TOPSIS methods. In order to compare the quality of both proposed approaches, simple comparative experiments will be presented. Both proposed methods have high accuracy and are resistant to the Rank Reveral phenomenon. © 2021, Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Researching the Problem of Providing Quality of Service in Software-Defined Networks 8

Researching the Problem of Providing Quality of Service in S...

引用

8th IEEE International Conference on Problems of Infocommunications, science and Technology, PIC S and T 2021

作者： Ushakov, Yuri Ushakova, Margarita Irina, Bolodurina Veniamin, Tarasov Orenburg State University Geometry And Computer Science Department Orenburg Russia Orenburg State University Applied Mathematics Department Orenburg Russia Povolzhskiy State University of Telecommunications And Informatics Department of Software And Management In Technical Systems Samara Russia

ISBN: (纸本)9781665406826

Modern trends in the development of information technology require new approaches to network traffic management. SDNs allow you to shift control layer outside the equipment and perform routing centrally, avoid overloads, and monitor network performance in real time. In recent papers on software-defined networks, the problem of providing quality of service was not studied in detail. Working with queues, limiting the rate of flows, marking the exceeding of thresholds is available in most modern devices working with the OpenFlow protocol. This paper will consider approaches to ensuring the quality of service in various software-defined environments and different versions of OpenFlow, proposed a structural mathematical model for describing queues and working with them within the OpenFlow protocol, and consider a mechanism for fair limiting the flow rate during overloads. © 2021 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Bifurcation Analysis of Incompressible Fluid Flow by a High Order Mesh-Free Indicator with Padé Approximants 15th

Bifurcation Analysis of Incompressible Fluid Flow by a Hi...

引用

15th International Moroccan Congress of Mechanics, CMM 2022

作者： Rammane, M. Mesmoudi, S. Askour, O. Tri, A. Braikat, B. Damil, N. Laboratory of Materials Signals Systems and Physical Modeling Department of Physics Faculty of Sciences Agadir University Ibn Zohr BP 8106 Agadir80000 Morocco Hassan First University of Settat National School of applied Sciences LISA Laboratory Berrechid26100 Morocco Mathematics Computer Science and Communication Systems Laboratory National School of Applied Sciences of Safi Cadi Ayyad University BP 63 Safi Sidi Bouzid46000 Morocco Laboratory of Mechanics Faculty of Sciences Ain Chock Hassan II University of Casablanca Casablanca Morocco Km 7 Route d’El Jadida Casablanca Morocco Laboratory of Engineering and Materials Faculty of Sciences Ben M’sik Hassan II University of Casablanca B.P 7955 Sidi Othman Casablanca Morocco Central Casablanca Complex Systems and Interactions Research Center Green City Bouskoura27182 Morocco

ISBN: (纸本)9783031469725

In this work, a mesh-free indicator is proposed to detect the bifurcation points of incompressible viscous fluid flow in a 2D sudden expansion. This indicator is mainly based on the high order mesh-free algorithm (HO-MFA) to solve the nonlinear problems obtained from the linear stability analysis. The Padé approximants are then used to improve the validity range of the HO-MFA and to determinate the roots of the indicator. The combination of these mathematical tools allows us to determine the zero of the indicator corresponding to the critical point. The Lyapunov-Schmidt reduction is used to search all the bifurcated branches from the critical point. To show the accuracy of our model, comparisons of the obtained results with those of the literature are made. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Linear stability analysis

来源：评论

学校读者我要写书评

暂无评论

A New Consistency Coefficient in the Multi-criteria Decision Analysis Domain 21st

A New Consistency Coefficient in the Multi-criteria Decision...

引用

21st International Conference on Computational science, ICCS 2021

作者： Salabun, Wojciech Shekhovtsov, Andrii Kizielewicz, Bartlomiej Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Żolnierska 49 Szczecin71-210 Poland

ISBN: (纸本)9783030779603

The logical consistency of decision making matrices is an important topic in developing each multi-criteria decision analysis (MCDA) method. For instance, many published papers are addressed to the decisional matrix’s consistency in the Analytic Hierarchy Process method (AHP), which uses Saaty’s seventeen-values scale. This work proposes a new approach to measuring consistency for using a simple three-value scale (binary with a tie). The paper’s main contribution is a proposal of a new consistency coefficient for a decision matrix containing judgments from an expert. We show this consistency coefficient based on an effective MCDA method called the Characteristic Objects METhod (COMET). The new coefficient is explained based on the Matrix of Expert Judgment (MEJ), which is the critical step of the COMET method. The proposed coefficient is based on analysing the relationship between judgments from the MEJ matrix and transitive principles (triads analysis). Four triads classes have been identified and discussed. The proposed coefficient makes it easy to determine the logical consistency and, thus, the expert responses’ quality is essential in the reliable decision-making process. Results are presented in some short study cases. © 2021, Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Automatic Traffic Control of Autonomous Vessels in Coastal Waters

Automatic Traffic Control of Autonomous Vessels in Coastal W...

引用

IEEE Conference on Quality Management, Transport and Information Security, Information Technologies (IT&MQ&IS)

作者： Nelly A. Sedova Viktor A. Sedov Ruslan I. Bazhenov Elena F. Alutina Tatiana N. Gorbunova Irina A. Ledovskikh Automatic and Information Systems Maritime State University named after G.I. Nevelskoy Vladivostok Russia Electrician Theoretical Bases Maritime State University named after G.I. Nevelskoy Vladivostok Russia Information Systems and Mathematics Sholom-Aleichem Priamursky State University Birobidzhan Russia Computer Science and Methods of Teaching Computer Science Blagoveschensk State Pedagogical University Blagoveschensk Russia Applied Mathematics Moscow State University of Civil Engineering Moscow Russia Mathematics and Information Technology Pacific National University Khabarovsk Russia

The paper examines an approach to arrange marine autonomous surface ships (both with and without crew) traffic surveillance illustrated with the Amur Bay and the Golden Horn Bay water area of the city of Vladivostok. The approach involves real-time application of a computer alliance based on General Packet Radio Service (GPRS) and Global Positioning System (GPS) satellite navigation technologies. The research presents the diagram of the system to observe autonomous surface ships located in the coastal area, as well as the assessment algorithm of the current navigation. Machine learning methods applied for analyzing the obtained information contribute to the fast and quite accurate review of the surface navigation, as well as hazard evaluation of vehicles caught in the area of heading in a sea autonomous surface vessel assessment.

关键词：

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：