检索结果-内蒙古大学图书馆

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

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

Cloud-Based Intelligent Patient Triage Systems with SVM Classifiers for Emergency departments

Cloud-Based Intelligent Patient Triage Systems with SVM Clas...

引用

Innovations in Communications, Electrical and computer Engineering (ICICEC), International Conference on

作者： N V Shibu Sujatha M M. Xavier Suresh K. Sindhuja T Saju Raj C. Srinivasan Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Easwari Engineering College Chennai Tamil Nadu India Department of Physics School of Advanced Sciences and Languages VIT Bhopal University Bhopal Madhya Pradesh India Department of Information Technology J.J College of Engineering and Technology Tiruchirappalli Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

Efficient patient triage in emergency departments is crucial for the timely and successful allocation of resources and treatment in the constantly changing healthcare environment. To improve patient triage systems, this research suggests a new strategy that makes use of cloud computing and support vector machine (SVM) classifiers. The proposed solution endeavors to enhance patient outcomes in emergency departments by optimizing resource allocation via the use of cloud infrastructure's scalability and accessibility in conjunction with SVM algorithms' strong classification capabilities. Quickly classifying patients according to severity, the system integrates and analyzes data in real-time, allowing healthcare providers to prioritize high-risk situations and distribute resources appropriately. Healthcare practitioners can work together more efficiently and share patient data with cloud-based architecture, which promotes a more comprehensive approach to treatment. Results from the experiments prove that the system works as advertised and can be easily scaled up, highlighting its revolutionary potential to change the way emergency healthcare facilities handle patient triage. The growing body of evidence demonstrates the value of intelligent systems for healthcare delivery optimization and emergency patient care improvement via the use of technology.

关键词： Support vector machines Cloud computing Technological innovation Accuracy Scalability Medical services Real-time systems Safety Resource management Research and development

来源：评论

学校读者我要写书评

暂无评论

Arena: A Learning-based Synchronization Scheme for Hierarchical Federated Learning-Technical Report

arXiv

引用

arXiv 2023年

作者： Qi, Tianyu Zhan, Yufeng Li, Peng Guo, Jingcai Xia, Yuanqing The School of Automation Beijing Institute of Technology Beijing China The School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan The Department of Computing The Hong Kong Polytechnic University Hong Kong

Federated learning (FL) enables collaborative model training among distributed devices without data sharing, but existing FL suffers from poor scalability because of global model synchronization. To address this issue, hierarchical federated learning (HFL) has been recently proposed to let edge servers aggregate models of devices in proximity, while synchronizing via the cloud periodically. However, a critical open challenge about how to make a good synchronization scheme (when devices and edges should be synchronized) is still unsolved. Devices are heterogeneous in computing and communication capability, and their data could be non-IID. No existing work can well synchronize various roles (e.g., devices and edges) in HFL to guarantee high learning efficiency and accuracy. In this paper, we propose a learning-based synchronization scheme for HFL systems. By collecting data such as edge models, CPU usage, communication time, etc., we design a deep reinforcement learning-based approach to decide the frequencies of cloud aggregation and edge aggregation, respectively. The proposed scheme well considers device heterogeneity, non-IID data and device mobility, to maximize the training model accuracy while minimizing the energy overhead. Meanwhile, the convergence bound of the proposed synchronization scheme has been analyzed. And we build an HFL testbed and conduct the experiments with real data obtained from Raspberry Pi and Alibaba Cloud. Extensive experiments under various settings are conducted to confirm the effectiveness of Arena. © 2023, CC BY-NC-ND.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Robust quantum Walk Search Without Knowing the Number of Marked Vertices

arXiv

引用

arXiv 2021年

作者： Xu, Yongzhen Zhang, Delong Li, Lvzhou Institute of Quantum Computing and Computer Theory School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

There has been a very large body of research on searching a marked vertex on a graph based on quantum walks, and Grover's algorithm can be regarded as a quantum walk-based search algorithm on a special graph. However, the existing quantum walk-based search algorithms suffer severely from the soufflé problem which mainly means that the success probability of finding a marked vertex could shrink dramatically even to zero when the number of search steps is greater than the right one, thus heavily reducing the robustness and practicability of the algorithm. Surprisingly, while the soufflé problem of Grover's algorithm has attracted enough attention, how to address this problem for general quantum walk-based search algorithms is missing in the literature. Here we initiate the study of overcoming the soufflé problem for quantum walk-based search algorithms by presenting a new quantum walk-based search framework that achieves robustness without sacrificing the quantum speedup. In this framework, for any adjustable parameter Ε, the quantum algorithm can find a marked vertex on an N-vertex complete bipartite graph with probability at least 1 − Ε, whenever the number of search steps h satisfies (Equation presented). Note that the algorithm need not know the exact number of marked vertices. Consequently, we obtain quantum search algorithms with stronger robustness and practicability. © 2021, CC BY.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

TOOLTANGO: Common sense Generalization in Predicting Sequential Tool Interactions for Robot Plan Synthesis

arXiv

引用

arXiv 2022年

作者： Tuli, Shreshth Bansal, Rajas Paul, Rohan Mausam Department of Computing Imperial College London United Kingdom Department of Computer Science Stanford University United States Department of Computer Science and Engineering Yardi School of Artificial Intelligence Indian Institute of Technology Delhi India

Robots assisting us in environments such as factories or homes must learn to make use of objects as tools to perform tasks, for instance using a tray to carry objects. We consider the problem of learning commonsense knowledge of when a tool may be useful and how its use may be composed with other tools to accomplish a high-level task instructed by a human. Specifically, we introduce a novel neural model, termed TOOLTANGO, that first predicts the next tool to be used, and then uses this information to predict the next action. We show that this joint model can inform learning of a fine-grained policy enabling the robot to use a particular tool in sequence and adds a significant value in making the model more accurate. TOOLTANGO encodes the world state, comprising objects and symbolic relationships between them, using a graph neural network and is trained using demonstrations from human teachers instructing a virtual robot in a physics simulator. The model learns to attend over the scene using knowledge of the goal and the action history, finally decoding the symbolic action to execute. Crucially, we address generalization to unseen environments where some known tools are missing, but alternative unseen tools are present. We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments. Experimental results show at least 48.8-58.1% absolute improvement over the baselines in predicting successful symbolic plans for a simulated mobile manipulator in novel environments with unseen objects. This work takes a step in the direction of enabling robots to rapidly synthesize robust plans for complex tasks, particularly in novel settings. © 2022, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

AI Based Security for Internet of Transportation Systems

AI Based Security for Internet of Transportation Systems

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Heena Kousar Shaista Fatima Syed Imran Ahmed S. Sajithra Sumit Kushwaha N.Alangudi Balaji Department of Computer Science and Engineering East Point College of Engineering and Technology Bengaluru Karnataka India Department of Electronics and Communication Engineering MJ College Hyderabad Telangana India Department of Computer Science Engineering R.M.K. Engineering College Kavaraipettai Tamilnadu India Department of Computer Applications University Institute of Computing Chandigarh University Punjab India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

The intelligent transportation systems (ITS) use a combination of sensors, cameras, and communication technologies to provide real-time data on traffic conditions. This data can be used to adjust traffic lights, but it can also be used to provide information to drivers, such as real-time traffic updates and recommended routes. Overall, control of traffic lights is an effective solution to address traffic congestion problems in urban areas. By optimizing traffic flow, cities can reduce travel times, improve safety, and reduce emissions from idling vehicles. However, the success of these systems depend on the effective planning, implementation, and ongoing maintenance to ensure that they continue to meet the changing needs of the city. In this work, the interest is to control of traffic lights in order to solve problems related to congestion; in this sense, it is proposed five mechanisms to make traffic lights intelligent and not automatic based on machine learning. The mechanisms implemented are based on four algorithms of machine learning: decision tree (DT), support vector machine (SVM), k nearest neighbor (KNN) and random forest (RF). The solutions obtained make it possible to predict the decision in order to act in traffic depending on several parameters such as the road, cars, passengers etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knapsack Encryption with Elliptic Curve Cryptography Based Secured Wireless Network

Knapsack Encryption with Elliptic Curve Cryptography Based S...

引用

International Conference on Edge computing and Applications (ICECAA)

作者： V. Arun P.G. Kuppusamy G. Naveen P. Santhuja Department of Computing Technologies Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Electronics and Communication Engineering Siddharth Institue of Engineering & Technology (SIETK) Puttur Andhra Pradesh India Department of Electronics and Communication Engineering Jagannath Institute of Technology Chengalpattu Tamil Nadu India Department of Computer Science and Engineering B V Raju Institute of Technology Hyderabad Telangana India

This research study discusses about the prospective future research areas while presenting the state-of-the-art in wireless network cryptography. Elliptic Curve Cryptography (ECC) offers a safe way for interacting nodes to exchange keys. In order to implement ECC, the message is first converted into an affine point on the Elliptic Curve (EC), and then the knapsack method is applied to the ECC-encrypted message across the finite field. This approach presents Knapsack Encryption with ECC Algorithm (KECC) for improving data security in wireless networks. The data is encrypted by using the knapsack algorithm and the ECC algorithm. The necessary encrypted data is forwarded to the receiver via in-between nodes. As a result, it avoids the man-in-the-middle attack. Experimental results prove that the KECC strategy increases the forward ratio. In addition, it reduces the key generation, encryption, as well as decryption computational time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

System size dependent topological zero modes in coupled topolectrical chains

引用

Physical Review B 2022年第7期106卷 075158-075158页

作者： S. M. Rafi-Ul-Islam Zhuo Bin Siu Haydar Sahin Ching Hua Lee Mansoor B. A. Jalil Department of Electrical and Computer Engineering National University of Singapore Singapore 117583 Institute of High Performance Computing Agency for Science Technology and Research Singapore 138632 Department of Physics National University of Singapore Singapore 117551

In this paper, we demonstrate the emergence and disappearance of topological zero modes (TZMs) in a coupled topolectrical (TE) circuit lattice. Specifically, we consider non-Hermitian TE chains in which TZMs do not occur in the individual uncoupled chains, but emerge when these chains are coupled by interchain capacitors. The coupled system hosts TZMs which show size-dependent behaviors and vanish beyond a certain critical size. In addition, the emergence or disappearance of the TZMs in the open boundary condition spectra for a given size of the coupled system can be controlled by modulating the signs of its inverse decay length. Analytically, trivial and nontrivial phases of the coupled system can be distinguished by the differing ranks of their corresponding Laplacian matrix. The TE circuit framework enables the physical detection of the TZMs via electrical impedance measurements. Our work establishes the conditions for inducing TZMs and modulating their behavior in coupled TE chains.

关键词： Skin effect Topological insulators 1-dimensional systems Non-Hermitean systems Bloch wave theory Green's function methods Tight-binding model

来源：评论

学校读者我要写书评

暂无评论

Disentangling quantum neural networks for unified estimation of quantum entropies and distance measures

引用

Physical Review A 2024年第6期110卷 062418-062418页

作者： Myeongjin Shin Seungwoo Lee Junseo Lee Mingyu Lee Donghwa Ji Hyeonjun Yeo Kabgyun Jeong School of Computing KAIST Daejeon 34141 South Korea Quantum AI Team Norma Inc. Seoul 04799 South Korea Department of Computer Science and Engineering Seoul National University Seoul 08826 South Korea College of Liberal Studies Seoul National University Seoul 08826 South Korea Department of Physics and Astronomy Seoul National University Seoul 08826 South Korea Research Institute of Mathematics Seoul National University Seoul 08826 South Korea School of Computational Sciences Korea Institute for Advanced Study Seoul 02455 South Korea

The estimation of quantum entropies and distance measures, such as von Neumann entropy, Rényi entropy, Tsallis entropy, trace distance, and fidelity-induced distances such as the Bures distance, has been a key area of research in quantum information science. In our study, we introduce the disentangling quantum neural network (DEQNN), designed to efficiently estimate various physical quantities in quantum information. Estimation algorithms for these quantities are generally tied to the size of the Hilbert space of the quantum state to be estimated. Our proposed DEQNN offers a unified dimensionality reduction methodology that can significantly reduce the size of the Hilbert space while preserving the values of diverse physical quantities. We provide an in-depth discussion of the physical scenarios and limitations in which our algorithm is applicable, as well as the learnability of the proposed quantum neural network.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Nonreciprocal Superradiant Phase Transitions and Multicriticality in a Cavity QED System

arXiv

引用

arXiv 2024年

作者： Zhu, Gui-Lei Hu, Chang-Sheng Wang, Hui Qin, Wei Lü, Xin-You Nori, Franco Department of Physics Zhejiang Sci-Tech University Hangzhou310018 China Theoretical Quantum Physics Laboratory Cluster for Pioneering Research RIKEN Saitama Wakoshi 351-0198 Japan Department of Physics Anhui Normal University Wuhu241000 China Center for Joint Quantum Studies Department of Physics School of Science Tianjin University Tianjin300350 China School of Physics Huazhong University of Science and Technology Wuhan Institute of Quantum Technology Wuhan430074 China Quantum Computing Center RIKEN Saitama Wakoshi 351-0198 Japan Department of Physics The University of Michigan Ann ArborMI48109-1040 United States

We demonstrate the emergence of nonreciprocal superradiant phase transitions and novel multicriticality in a cavity quantum electrodynamics (QED) system, where a two-level atom interacts with two counter-propagating modes of a whispering-gallery-mode (WGM) microcavity. The cavity rotates at a certain angular velocity, and is directionally squeezed by a unidirectional parametric pumping χ(2) nonlinearity. The combination of cavity rotation and directional squeezing leads to nonreciprocal first- and second-order superradiant phase transitions. These transitions do not require ultrastrong atom-field couplings and can be easily controlled by the external pump field. Through a full quantum description of the system Hamiltonian, we identify two types of multicritical points in the phase diagram, both of which exhibit controllable nonreciprocity. These results open a new door for all-optical manipulation of superradiant transitions and multicritical behaviors in light-matter systems, with potential applications in engineering various integrated nonreciprocal quantum devices. © 2024, CC BY.

关键词： Whispering gallery modes

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：