检索结果-内蒙古大学图书馆

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Kanimozhi, N. Nayak, Swikruti Keshav Kumar, K. Manjramkar, Vinda Kumar, Ranjeet Suganthi, D. Srm Institute of Science and Technology School of Computing Department of Computational Intelligence Chennai Tamilnadu Kattankulathur India Jecrc University Department of Computer Science and Engineering Rajasthan Jaipur India Department of Humanities and Mathematics Shaikpet Telangana Hyderabad India Zoology Maharashtra Thane India University College of Engineering & Technology Vinoba Bhave University Department of Electronics & Communication Jharkhand Hazaribagh India Saveetha Institute of Medical and Technical Sciences Saveetha College of Liberal Arts and Sciences Department of Computer Science Thandalam Chennai India

ISBN: (纸本)9798350396638

Leukaemia is considered as the most common type of blood cancer. The length of time one requires to recover from this disease is determined by how quickly it is recognized and treated. Leukaemia develops when the bone marrow generates an abnormally large amount of white blood cells. Since images of human blood samples are studied under the microscope, haematologists employ techniques such as microscopic colour imaging, image segmentation, grouping, and classification to diagnose patients as fast as possible. Microscopy may identify blood cancer in visible and immature white blood cells in a variety of methods. Early and accurate diagnosis of leukaemia is critical for clinicians to properly treat patients. After the input image is provided, the gaussian filter is used to perform image enhancement, and the Wiener filter is used in image Deblurring, Adaptive K-Means clustering technique, Colour feature, Texture feature, GLCM and Hausdroff are also used, and lastly the Model is trained using AE and RELM. The proposed system outperforms conventional models such as RELM and ELM, which generates an accuracy of 98.45%. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Convergent Approaches to AI Explainability for HEP Muonic Particles Pattern Recognition

引用

Computing and Software for Big science 2023年第1期7卷 1-18页

作者： Maglianella, Leandro Nicoletti, Lorenzo Giagu, Stefano Napoli, Christian Scardapane, Simone Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy Department of Physics Sapienza University of Rome Rome Italy Institute for Systems Analysis and Computer Science Italian National Research Council Rome Italy Department of Computational Intelligence Electronics and Telecommunications Czestochowa University of Technology Czestochowa Poland Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy

Neural networks are commonly defined as ‘black-box’ models, meaning that the mechanism describing how they give predictions and perform decisions is not immediately clear or even understandable by humans. Therefore, Explainable Artificial Intelligence (xAI) aims at overcoming such limitation by providing explanations to Machine Learning (ML) algorithms and, consequently, making their outcomes reliable for users. However, different xAI methods may provide different explanations, both from a quantitative and a qualitative point of view, and the heterogeneity of approaches makes it difficult for a domain expert to select and interpret their result. In this work, we consider this issue in the context of a high-energy physics (HEP) use-case concerning muonic motion. In particular, we explored an array of xAI methods based on different approaches, and we tested their capabilities in our use-case. As a result, we obtained an array of potentially easy-to-understand and human-readable explanations of models’ predictions, and for each of them we describe strengths and drawbacks in this particular scenario, providing an interesting atlas on the convergent application of multiple xAI algorithms in a realistic context. © 2023, The Author(s).

关键词： Explainable Artificial Intelligence High-energy physics Intrinsically interpretable Decision Trees Saliency maps methods Tracing gradient descent

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Vulnerabilities on Confidentiality, Integrity, and Availability in Smart Systems 2

Assessing the Impact of Vulnerabilities on Confidentiality, ...

引用

2nd International Conference on Informatics, ICI 2023

作者： Minhass, Shubham Chauhan, Ritu Kaur, Harleen Amity University Amity Institute of Information Technology UP India Amity University IoT and Artificial Intelligence Lab Center for Computational Biology and Bioinformatics UP India Jamia Hamdard Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350343830

As Internet of Things (IoT) technologies proliferate and smart devices become more and more integrated into our daily lives and workplaces, it is becoming more and more important to address the complex issues of data security and privacy within smart homes and buildings. Even though the Internet of Things (IoT) has many benefits, such as remote control, real-time monitoring, and sophisticated security features, it also raises serious concerns about how sensitive data is protected. By examining the particular problems associated with protecting sensitive data in the IoT era and guaranteeing the continuous provision of dependable services within smart environments, this research paper seeks to close a significant knowledge gap. In order to do this, the research focuses on the complex data-centric features of smart ecosystems, including data processing, generation, and storage. This paper thoroughly examines the range of current IoT technologies, data management practices, and privacy challenges by using a qualitative research approach. It also offers a thorough examination of the privacy protections and security measures that are now in place in smart buildings and homes. This research focuses primarily on the interface between technology, security, and privacy of data. This work effectively fills in the significant research vacuum by clarifying the specific issues it seeks to solve. It provides useful advice and insights that can help individuals and organizations navigate the complex world of smart technologies, securely store their data, and realize the full potential of these game-changing advancements. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Electron charge qubit with 0.1 millisecond coherence time

引用

Nature Physics 2024年第1期20卷 116-122页

作者： Zhou, Xianjing Li, Xinhao Chen, Qianfan Koolstra, Gerwin Yang, Ge Dizdar, Brennan Huang, Yizhong Wang, Christopher S. Han, Xu Zhang, Xufeng Schuster, David I. Jin, Dafei Center for Nanoscale Materials Argonne National Laboratory LemontIL United States Pritzker School of Molecular Engineering University of Chicago ChicagoIL United States Computational Research Division Lawrence Berkeley National Laboratory BerkeleyCA United States The NSF AI Institute for Artificial Intelligence and Fundamental Interactions CambridgeMA United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA United States James Franck Institute and Department of Physics University of Chicago ChicagoIL United States Department of Electrical and Computer Engineering Northeastern University BostonMA United States Department of Applied Physics Stanford University StanfordCA United States Department of Physics and Astronomy University of Notre Dame Notre DameIN United States

Electron charge qubits are compelling candidates for solid-state quantum computing because of their inherent simplicity in qubit design, fabrication, control and readout. However, electron charge qubits built on conventional semiconductors and superconductors suffer from severe charge noise that limits their coherence time to the order of one microsecond. Here we report electron charge qubits that exceed this limit, based on isolated single electrons trapped on an ultraclean solid neon surface in a vacuum. Quantum information is encoded in the motional states of an electron that is strongly coupled with microwave photons in an on-chip superconducting resonator. The measured relaxation and coherence times are both on the order of 0.1 ms, surpassing all existing charge qubits and rivalling state-of-the-art superconducting transmon qubits. The simultaneous strong coupling of two qubits with a common resonator is also demonstrated, as the first step towards two-qubit entangling gates for universal quantum computing. © 2023, The Author(s), under exclusive licence to Springer Nature Limited.

关键词： Superconducting resonators

来源：评论

学校读者我要写书评

暂无评论

SecureChainAI: Integrating Blockchain and Artificial Intelligence for Enhanced Security in IoT Environments

SecureChainAI: Integrating Blockchain and Artificial Intelli...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： K. ThamaraiSelvi A. Pushpalatha K. Chidambarathanu Jaishri P. Wankhede S. Alagumuthukrishnan Velliangiri Sarveshwaran Department of Information Science and Engineering New Horizon College of Engineering Bangalore India Department of Computer Science and Design Karpagam College of Engineering Coimbatore India Department of Computer Science and Business Systems R.M.K. Engineering College Kavaraipettai India Department of Computer Science and Engineering CMR Institute of Technology Hyderabad India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Internet of Things (IoT) systems develop with paramount importance for security in view of the increased deployment of IoT devices over critical sectors like healthcare, industry automation, and smart cities. The risk exposure of such systems is extremely high to potent cyber threats, including those that may result in data integrity and privacy issues and operational unreliability. Security in IoT systems has thus emerged through heterogeneous integration with blockchain and artificial intelligence models. This blockchain technology provides a decentralized, immutable ledger for secure data transactions. AI models, especially those designed by anomaly detection and prediction algorithms, can identify and mitigate cyber threats. In this paper, the authors propose the SecureChainAI model that synergistically integrates artificial intelligence algorithms with blockchain to safeguard IoT environments. The two core building blocks that will make this proposed model real are CaSNet and the EchoChain algorithm. The CaSNet model integrates LSTM, RNN, and GRU techniques with novelty detection for proficient attack prediction and detection using their peculiar capabilities in sequential data handling and the identification of novel attack patterns. The EchoChain algorithm puts blockchain technology into the IoT infrastructure to provide security in communication and integrity of the values. This makes the architecture lightweight, shifting computational loads to the collector node, and hence suitable for IoT devices with low computational resources. Evaluations of the performance necessary to detect different classes of cyberattacks using SecureChainAI have improved on the detection accuracy, precision, recall, f1-score, and reduced error rates.

关键词： Accuracy Error analysis Predictive models Prediction algorithms Data models Blockchains Internet of Things Security Artificial intelligence Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Machine Learning With Data Assimilation and Uncertainty Quantification for Dynamical Systems:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2023年第6期10卷 1361-1387页

作者： Sibo Cheng César Quilodrán-Casas Said Ouala Alban Farchi Che Liu Pierre Tandeo Ronan Fablet Didier Lucor Bertrand Iooss Julien Brajard Dunhui Xiao Tijana Janjic Weiping Ding Yike Guo Alberto Carrassi Marc Bocquet Rossella Arcucci Data Science Institute Department of ComputingImperial College LondonSW72AZ London Department of Earth Science and Engineering Imperial College LondonSW72AZ London Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China the IMT Atlantique Lab-STICCUMR CNRS 6285France and OdysseyInria/IMTFrance.P.Tandeo is also with RIKEN Center for Computational ScienceKobeJapan the CEREA École des Ponts and EDF R&Dîle-de-FranceFrance the Laboratoire Interdisciplinaire des Sciences du Numérique CNRSParis-Saclay UniversityF-91403OrsayFrance the Electricitéde France(EDF) 78401 ChatouFranceInstitut de Mathématiques de Toulouse31062 ToulouseFrance and SINCLAIR AI LabSaclayFrance the Sorbonne University ParisFranceand also with Nansen Environmental and Remote Sensing Center(NERSC)BergenNorway the School of Mathematical Sciences Tongji UniversityShanghai 200092China the Mathematical Institute for Machine Learning and Data Science KU Eichstaett-IngolstadtBavariaGermany the School of Information Science and Technology Nantong UniversityNantong 226019China the Department of Physics and Astronomy“Augusto Righi” University of Bologna40124 BolognaItaly

Data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal *** applications span from computational fluid dynamics(CFD)to geoscience and climate ***,much effort has been given in combining DA,UQ and machine learning(ML)*** research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covariance specification and model error correction.A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains,resulting in the necessity for a comprehensive *** paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of *** review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their ***,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice *** exciting perspectives of this rapidly developing research field are also *** Terms-Data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncertainty quantification(UQ).

关键词： assimilation overcome apply

来源：评论

学校读者我要写书评

暂无评论

MRI Image Processing and Segmentation on Brain Tumor: A Survey

MRI Image Processing and Segmentation on Brain Tumor: A Surv...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Jayaraj Ramasamy Sreekumar Narayanan Gopirajan PV Ravikumar RN Department of Computer Science Botho University Botswana Africa Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur India Department of Computer Engineering Marwadi University Rajkot India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

Image segmentation is a critical step in many clinical applications and is crucial in computer-assisted diagnosis. Segmentation of brain is the technique of automatically recognizing malignant brain tissues and labeling them depending on tumor kind. Manual tumor segmentation using brain MRI was time consuming and prone to inaccuracy. In brain MRI research, image segmentation is commonly used to detect and interpret anatomical features, analyze changes to the brain, identify sick areas, organize therapy and image guided surgery. Over the last few decades, different segmentation methods were developed and published in the research, with varying degrees of detail and difficulty. This study will focus on the most common segmentation methods. To begin addressing the complex details and challenges of the MRI Brain issue, we have introduced fundamental image preprocessing stages and then we have performed Image segmentation.

关键词： Surveys Support vector machines Image segmentation Magnetic resonance imaging Brain tumors Surgery Watersheds Artificial intelligence Random forests Cancer

来源：评论

学校读者我要写书评

暂无评论

IMPROVING THE ADAPTIVE MOMENT ESTIMATION (ADAM) STOCHASTIC OPTIMIZER THROUGH AN IMPLICIT-EXPLICIT (IMEX) TIME-STEPPING APPROACH

arXiv

引用

arXiv 2024年

作者： Bhattacharjee, Abhinab Popov, Andrey A. Sarshar, Arash Sandu, Adrian Computational Science Lab Department of Computer Science Virginia Tech BlacksburgVA24060 United States The Oden Institute for Computational Engineering and Sciences The University of Texas AustinTX78712 United States Department of Computer Engineering and Computer Science California State University Long BeachCA90840 United States

The ADAM optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical ADAM algorithm is a first-order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the ADAM scheme obtained by using higher-order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical ADAM on several regression and classification problems. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Achieving Instance-dependent Sample Complexity for Constrained Markov Decision Process

arXiv

引用

arXiv 2024年

作者： Jiang, Jiashuo Ye, Yinyu Department of Industrial Engineering & Decision Analytics Hong Kong University of Science and Technology Hong Kong Institute for Computational and Mathematical Engineering Stanford University United States Department of Management Science & Engineering Stanford University United States

We consider the reinforcement learning problem for the constrained Markov decision process (CMDP), which plays a central role in satisfying safety or resource constraints in sequential learning and decision-making. In this problem, we are given finite resources and a MDP with unknown transition probabilities. At each stage, we take an action, collecting a reward and consuming some resources, all assumed to be unknown and need to be learned over time. In this work, we take the first step towards deriving optimal problem-dependent guarantees for the CMDP problems. We derive a logarithmic regret bound, which translates into a (formula presented) sample complexity bound, with ∆ being a problem-dependent parameter, yet independent of Ε. Our sample complexity bound is the first problem-dependent guarantee for CMDP problems. To achieve this advance, we develop a new framework for analyzing CMDP problems. To be specific, our algorithm operates in the primal space and we resolve the primal LP for the CMDP problem at each period in an online manner, with adaptive remaining resource capacities. The key elements of our algorithm are: i) a characterization of the instance hardness via LP basis, ii) an eliminating procedure that identifies one optimal basis of the primal LP, and;iii) a resolving procedure that is adaptive to the remaining resources and sticks to the characterized optimal basis. © 2024, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Threshold public key-sharing technique in block chain

Threshold public key-sharing technique in block chain

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Pande, Sagar Dhanraj Singh, Gurpreet Zekrifa, Djabeur Mohamed Seifeddine Kodgire, Shilpa Prashant Patel, Sunil A. Le, Viet-Thanh School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Faculty of Computational Science GNA University Phagwara India Centre for Quantum Computation and Communication Technology Sydney Australia Maharashtra Institute of Technology Maharashtra Aurangabad India Computer Engineering Department L.D. College of Engineering Ahmedabad India Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

ISBN: (纸本)9781032669663

A threshold key-sharing technology-based publicly verifiable key-sharing technology is presented to explore blockchain users’ private keys’ security. After receiving key fragments, participating nodes validate them. When splitting the key, the central splitting node does evil. In the critical recovery stage, the key fragments of the nodes participating in key splicing are publicly verified to prevent them from doing evil. In the critical distribution stage, add IDs to participating nodes to track malicious nodes and update node status in real-time, and a dynamic threshold mechanism is designed. To maintain private key fragment integrity, the owner of the key fragment and the controller node redistribute it to the new participating nodes once the vital fragment node goes offline. Experimental results reveal that this scheme’s private key recovery rate is 80% and has threshold properties, traceability, unforgeability, and recoverability. © 2024 The Author(s).

关键词： Blockchain

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：