检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cheng, Chun-Wun Zhao, Yining Cheng, Yanqi Montoya, Javier Schönlieb, Carola-Bibiane Aviles-Rivero, Angelica I. Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Siebel School of Computing and Data Science University of Illinois Urbana-Champaign United States Lucerne School of Computer Science and Information Technology Lucerne University of Applied Sciences and Arts United States Yau Mathematical Sciences Center Tsinghua University China

Image segmentation is a fundamental task in both image analysis and medical applications. State-of-the-art methods predominantly rely on encoder-decoder architectures with a U-shaped design, commonly referred to as U-Net. Recent advancements integrating transformers and MLPs improve performance but still face key limitations, such as poor interpretability, difficulty handling intrinsic noise, and constrained expressiveness due to discrete layer structures, often lacking a solid theoretical *** this work, we introduce Implicit U-KAN 2.0, a novel U-Net variant that adopts a two-phase encoder-decoder structure. In the SONO phase, we use a second-order neural ordinary differential equation (NODEs), called the SONO block, for a more efficient, expressive, and theoretically grounded modeling approach. In the SONO-MultiKAN phase, we integrate the second-order NODEs and MultiKAN layer as the core computational block to enhance interpretability and representation power. Our contributions are threefold. First, U-KAN 2.0 is an implicit deep neural network incorporating MultiKAN and second order NODEs, improving interpretability and performance while reducing computational costs. Second, we provide a theoretical analysis demonstrating that the approximation ability of the MultiKAN block is independent of the input dimension. Third, we conduct extensive experiments on a variety of 2D and a single 3D dataset, demonstrating that our model consistently outperforms existing segmentation networks. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Lower bound for simulation cost of open quantum systems: Lipschitz continuity approach

arXiv

引用

arXiv 2024年

作者： Ding, Zhiyan Junge, Marius Schleich, Philipp Wu, Peixue Department of Mathematics University of California Berkeley United States Department of Mathematics University of Illinois at Urbana and Champaign United States Department of Computer Science University of Toronto Canada Department of Applied Mathematics University of Waterloo Canada Institute for Quantum Computing University of Waterloo Canada

Simulating quantum dynamics is one of the most promising applications of quantum computers. While the upper bound of the simulation cost has been extensively studied through various quantum algorithms, much less work has focused on establishing the lower bound, particularly for the simulation of open quantum system dynamics. In this work, we present a general framework to calculate the lower bound for simulating a broad class of quantum Markov semigroups. Given a fixed accessible unitary set, we introduce the concept of convexified circuit depth to quantify the quantum simulation cost and analyze the necessary circuit depth to construct a quantum simulation scheme that achieves a specific order. Our framework can be applied to both unital and non-unital quantum dynamics, and the tightness of our lower bound technique is illustrated by showing that the upper and lower bounds coincide in several examples. © 2024, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Zeroth-order methods for constrained nonconvex nonsmooth stochastic optimization 24

Zeroth-order methods for constrained nonconvex nonsmooth sto...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zhuanghua Liu Cheng Chen Luo Luo Bryan Kian Hsiang Low Department of Computer Science National University of Singapore Singapore Singapore and CNRS@CREATE LTD Singapore Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China School of Data Science Fudan University Shanghai China and Shanghai Key Laboratory for Contemporary Applied Mathematics Department of Computer Science National University of Singapore Singapore Singapore

This paper studies the problem of solving nonconvex nonsmooth optimization over a closed convex set. Most previous works tackle such problems by transforming the constrained problem into an unconstrained problem. However, they only provide asymptotic convergence analysis for their methods. In this work, we provide the nonasymptotic convergence analysis for solving constrained nonconvex nonsmooth optimization. We first generalize classical gradient mapping and the Frank-Wolfe gap in the nonsmooth setting. Then we introduce novel notions of approximate stationarity concerning such generalized quantities. We also propose several stochastic zeroth-order algorithms for the problem, along with their nonasymptotic convergence guarantees of obtaining the proposed approximate stationarity. Finally, we conduct numerical experiments that demonstrate the effectiveness of our algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Cellular Potts Models

arXiv

引用

arXiv 2025年

作者： Minartz, Koen d’Hondt, Tim Hillmann, Leon Starruß, Jörn Brusch, Lutz Menkovski, Vlado Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands Department of Applied Physics and Science Education Eindhoven University of Technology Eindhoven Netherlands Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands Center for Information Services and High Performance Computing TUD Dresden University of Technology Dresden Germany

The cellular Potts model (CPM) is a powerful computational method for simulating collective spatiotemporal dynamics of biological cells. To drive the dynamics, CPMs rely on physics-inspired Hamiltonians. However, as first principles remain elusive in biology, these Hamiltonians only approximate the full complexity of real multicellular systems. To address this limitation, we propose NeuralCPM, a more expressive cellular Potts model that can be trained directly on observational data. At the core of NeuralCPM lies the Neural Hamiltonian, a neural network architecture that respects universal symmetries in collective cellular dynamics. Moreover, this approach enables seamless integration of domain knowledge by combining known biological mechanisms and the expressive Neural Hamiltonian into a hybrid model. Our evaluation with synthetic and real-world multicellular systems demonstrates that NeuralCPM is able to model cellular dynamics that cannot be accounted for by traditional analytical Hamiltonians. Copyright © 2025, The Authors. All rights reserved.

关键词： Potts model

来源：评论

学校读者我要写书评

暂无评论

Semi/Fully-Automated Segmentation of Gastric-Polyp Using Aquila-Optimization-Algorithm Enhanced Images

引用

computers, Materials & Continua 2022年第2期70卷 4087-4105页

作者： Venkatesan Rajinikanth Shabnam Mohamed Aslam Seifedine Kadry Orawit Thinnukool Department of Electronics and Instrumentation Engineering St.Joseph’s College of Engineering Chennai600119India Department of Information Technology College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Faculty of Applied Computing and Technology Noroff University CollegeKristiansand4608Norway Research Group of Embedded Systems and Mobile Application in Health Science College of ArtsMedia and TechnologyChiang Mai UniversityChiang Mai50200Thailand

The incident rate of the Gastrointestinal-Disease(GD)in humans is gradually rising due to a variety of reasons and the Endoscopic/Colonoscopic-Image(EI/CI)supported evaluation of the GD is an approved *** and evaluation of the suspicious section of the EI/CI is essential to diagnose the disease and its *** proposed research aims to implement a joint thresholding and segmentation framework to extract the Gastric-Polyp(GP)with better *** proposed GP detection system consist;(i)Enhancement of GP region using Aquila-Optimization-Algorithm supported tri-level thresholding with entropy(Fuzzy/Shannon/Kapur)and between-class-variance(Otsu)technique,(ii)Automated(Watershed/Markov-Random-Field)and semi-automated(Chan-Vese/Level-Set/Active-Contour)segmentation of GPfragment,and(iii)Performance evaluation and validation of the proposed *** experimental investigation was performed using four benchmark EI dataset(CVC-ClinicDB,ETIS-Larib,EndoCV2020 and Kvasir).The similarity measures,such as Jaccard,Dice,accuracy,precision,sensitivity and specificity are computed to confirm the clinical significance of the proposed *** outcome of this research confirms that the fuzzyentropy thresholding combined with Chan-Vese helps to achieve a better similarity measures compared to the alternative schemes considered in this research.

关键词： Endoscopic/colonoscopic-image gastric polyp aquila-optimizationalgorithm fuzzy entropy chan-vese segmentation

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Decentralized Authentication Model for IoT-Based E-Learning and Educational Environments

引用

computers, Materials & Continua 2023年第5期75卷 3133-3158页

作者： Osama A.Khashan Sultan Alamri Waleed Alomoush Mutasem K.Alsmadi Samer Atawneh Usama Mir Research and Innovation Centers Rabdan AcademyP.O.Box 114646Abu DhabiUnited Arab Emirates College of Computing and Informatics Saudi Electronic UniversityRiyadh13316Saudi Arabia School of Information Technology Skyline University CollegeP.O.Box 1797SharjahUnited Arab Emirates Department of MIS College of Applied Studies and Community ServicesImam Abdulrahman Bin Faisal UniversityP.O.Box 1982DammamSaudi Arabia Department of Computer Science University of WindsorWindsorN9J3Y1Canada

In recent times,technology has advanced significantly and is currently being integrated into educational environments to facilitate distance learning and interaction between *** the Internet of Things(IoT)into education can facilitate the teaching and learning process and expand the context in which students ***,learning data is very sensitive and must be protected when transmitted over the network or stored in data ***,the identity and the authenticity of interacting students,instructors,and staff need to be verified to mitigate the impact of ***,most of the current security and authentication schemes are centralized,relying on trusted third-party cloud servers,to facilitate continuous secure *** addition,most of these schemes are resourceintensive;thus,security and efficiency issues arise when heterogeneous and resource-limited IoT devices are being *** this paper,we propose a blockchain-based architecture that accurately identifies and authenticates learners and their IoT devices in a decentralized manner and prevents the unauthorized modification of stored learning records in a distributed university *** allows students and instructors to easily migrate to and join multiple universities within the network using their identity without the need for user *** proposed architecture was tested using a simulation tool,and measured to evaluate its *** simulation results demonstrate the ability of the proposed architecture to significantly increase the throughput of learning transactions(40%),reduce the communication overhead and response time(26%),improve authentication efficiency(27%),and reduce the IoT power consumption(35%)compared to the centralized authentication *** addition,the security analysis proves the effectiveness of the proposed architecture in resisting various attacks and ensuring the security requirements of learning data in the unive

关键词： Blockchain decentralized authentication Internet of Things(IoT) E-learning IoT security

来源：评论

学校读者我要写书评

暂无评论

Synergistic eigenanalysis of covariance and Hessian matrices for enhanced binary classification on health datasets

引用

computers in Biology and Medicine 2025年 190卷 109985-109985页

作者： Hartoyo, Agus Argasiński, Jan Trenk, Aleksandra Przybylska, Kinga Blasiak, Anna Crimi, Alessandro Sano – Centre for Computational Personalised Medicine International Research Foundation Krakow Poland Department of Neurophysiology and Chronobiology Institute of Zoology and Biomedical Research Faculty of Biology Jagiellonian University Krakow Poland AGH University of Krakow Krakow Poland School of Computing Telkom University Bandung Indonesia Department of Human-Centered Artificial Intelligence Institute of Applied Computer Science Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland Doctoral School of Exact and Natural Sciences Jagiellonian University Krakow Poland

Covariance and Hessian matrices have been analyzed separately in the literature for classification problems. However, integrating these matrices has the potential to enhance their combined power in improving classification performance. We present a novel approach that combines the eigenanalysis of a covariance matrix evaluated on a training set with a Hessian matrix evaluated on a deep learning model to achieve optimal class separability in binary classification tasks. Our approach is substantiated by formal proofs that establish its capability to maximize between-class mean distance (the concept of separation) and minimize within-class variances (the concept of compactness), which together define the two linear discriminant analysis (LDA) criteria, particularly under ideal data conditions such as isotropy around class means and dominant leading eigenvalues. By projecting data into the combined space of the most relevant eigendirections from both matrices, we achieve optimal class separability as per these LDA criteria. Empirical validation across neural and health datasets consistently supports our theoretical framework and demonstrates that our method outperforms established methods. Our method stands out by addressing both separation and compactness criteria, unlike PCA and the Hessian method, which predominantly emphasize one criterion each. This comprehensive approach captures intricate patterns and relationships, enhancing classification performance. Furthermore, through the utilization of both LDA criteria, our method outperforms LDA itself by leveraging higher-dimensional feature spaces, in accordance with Cover's theorem, which favors linear separability in higher dimensions. Additionally, our approach sheds light on complex DNN decision-making, rendering them comprehensible within a 2D space. © 2025

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Communicative Robot Signals: Presenting a New Typology for Human-Robot Interaction

arXiv

引用

arXiv 2023年

作者： Holthaus, Patrick Schulz, Trenton Lakatos, Gabriella Soma, Rebekka University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom Norwegian Computing Center Department of Applied Research in ICT Oslo Norway University of Oslo Department of Informatics Oslo Norway

We present a new typology for classifying signals from robots when they communicate with humans. For inspiration, we use ethology, the study of animal behaviour and previous efforts from literature as guides in defining the typology. The typology is based on communicative signals that consist of five properties: the origin where the signal comes from, the deliberateness of the signal, the signal’s reference, the genuineness of the signal, and its clarity (i.e., how implicit or explicit it is). Using the accompanying worksheet, the typology is straightforward to use to examine communicative signals from previous human-robot interactions and provides guidance for designers to use the typology when designing new robot behaviours. © 2023, CC BY.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Classifying Arabian Gulf Tweets to Detect People's Trends: A case study

Classifying Arabian Gulf Tweets to Detect People's Trends: A...

引用

International Conference on Social Networks Analysis, Management and Security (SNAMS)

作者： Khaled Balhaf Omar Darwish Emad Rawashdeh Mohammad Abu Awad Dirar Darweesh Yahya Tashtoush Saif Rawashdeh Department of Computer Science Jordan University of Science and Technology Irbid Jordan Information Security and Applied Computing Eastern Michigan University Ypsilanti USA

Recently, media and business companies are utilizing social media to reach a large set of users to maximize the amount of gained profit. Actually, these companies are looking for the best ways to satisfy their user's requirements. It is very difficult to understand these requirements because of the large set of users on social media like Twitter. For this reason, the goal of our research project is to build a classifier that can detect Arabian trends among Gulf area Twitter users. The new built classifier can assist these companies to deliver the convenient products and media contents like photos and videos according to users' trends. By using our own designed Java-based tool, we have collected a significant dataset of tweets. Also, two experiments of tweet classification have been implemented to compare the effects of balanced and imbalanced training data and to measure the effect of data size on the accuracy of classifiers. In both experiments, Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Naïve Bayes algorithms are used as classifiers. The first experiment uses small, imbalanced data sets and four classes of data, which are Sport, Politics, Islam and Culture. The Light and Root Stemmers were used with each classifier. The best outcome achieved in our research project by utilizing a Naïve Bayes algorithm with the Light Stemmer technique. It achieved an accuracy reaching 76.27%. In the second experiment, we used a balanced large data set with the same classifiers. In addition, we have added one more class to the new data set which is Economics. The experimental results showed that the best accuracy (81.17%) is obtained by using SVM with the Light Stemmer method. The Light Stemmer achieved the best outcomes for all classifiers since almost all of the tweets were written in dialects.

关键词： Support vector machines Social networking (online) Blogs Training data Companies Media Market research

来源：评论

学校读者我要写书评

暂无评论

Secure efficient signature for internet of things over near-ring 1

Secure efficient signature for internet of things over near-...

引用

1st International Conference on Advances in Computational science and Engineering, ICACSE 2020

作者： Muthukumaran, V. Arun, M. Satheesh Kumar, S. Kumta, Samyukta D. Angeline Kavitha, M. Vijayaraghavan, R. Department of Mathematics School of Applied Science REVA University Bengaluru-64 India School of Computing Kalasalingam Academy of Research and Education Tamilnadu 626128 India Department of Computer Science School of Applied Science REVA University Bengaluru-64 India Department of Computer Science School of Applied Scie REVA University Bengaluru-64 India Voorhees College Tamilnadu Vellore India Department of Mathematics Thiruvalluvar University Serkkadu Vellore632 115 India

Prediction of air quality is a topic of great interest in air quality research due to direct With rapid progression in remote innovation and inescapable computerized innovation have given in expanding prevalence and enthusiasm of Internet of Things (IoT) procedure, universally giving comfort and knowledge to our day by day exercises. In IoT based framework situation, shrewd parts are associated wherever as all inclusive things connected in an inescapable model. Guaranteeing security for intersection among brilliant items is fundamentally progressively significant, in this paper, we propose a novel signature scheme which is utilized for carrying communication amongst devices in IoT environment. Moreover we revealed different scheme that are vulnerable. The significance of the proposed scheme over other existing scheme are analyzed in terms of the summary which is illustrated using performance and security comparison. © Published under licence by IOP Publishing Ltd.

关键词： Internet of things

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：