检索结果-内蒙古大学图书馆

2024 International Conference on Biomedicine and Intelligent Technology, ICBIT 2024

作者： Huang, Shijia Diao, Su Wan, Yajie Song, Chaoda Fu Foundation School of Engineering and Applied Science Columbia University United States Department of Industrial & Systems Engineering Auburn University United States Department of Computer Science Brown University United States School of Engineering Department of Computer and Data Sciences United States

ISBN: (纸本)9798400710063

In the field of medical image analysis, with the growth of data volume and the increasing demand for privacy protection, traditional centralized learning methods are facing the problems of data silos and privacy leakage. Therefore, federated learning, as an emerging distributed machine learning framework, provides a solution to protect data privacy while effectively utilizing decentralized data. The purpose of this study is to develop a federated learning-based medical image analysis and classification system to solve the data isolation and privacy problems existing in traditional methods. This study uses a distributed federated learning framework that allows multiple healthcare organizations to share updates to their models instead of raw data. data privacy protection is further enhanced through the use of differential privacy and secure multi-party computation techniques. In addition, a deep convolutional neural network (CNN) is used to improve the accuracy of feature extraction and classification of medical images. Experimental analysis shows that the system can significantly improve the classification accuracy of medical images. Specifically, our system achieved a 15% improvement in classification accuracy compared to traditional centralized methods. Additionally, the implementation of differential privacy and secure multi-party computation resulted in a privacy leakage reduction of 25%. These results verify the application potential of federated learning in the field of medical image processing, demonstrating superior performance and enhanced privacy protection compared to traditional centralized learning methods. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Big data Implementation to Create Business Value and Architecture Proposed in the Banking Industry: A Systematic Review

Optimizing Big Data Implementation to Create Business Value ...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Kristiana, Idha Meyliana, Meyliana Hidayanto, Achmad Nizar Prabowo, Harjanto Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok Indonesia Bina Nusantara University BINUS Business School Undergraduate Program Management Departement Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

The exponential growth of data is compelling organizations to employ data in decision-making. As one of the businesses with an ecosystem that contributes to data growth, banks have challenges in generating insight. A high level of data security is frequently linked to a high level of data access difficulties. This poses a challenge to the implementation of data-driven business, where taking control of our data is one of the best ways to ensure that we not only own data but also have the ability to process and use data to extract business value. Through literature review, a number of challenges to optimizing the implementation of big data analytics in the banking industry were discovered. data governance refers to the methods and procedures that assist banks in managing and securing data. A big data architecture is presented to address the highlighted issues, particularly with a multi-tiered approach to big data structures. With the adoption of this architecture, it will be simpler to generate business-value-generating insights for the banking industry using big data with accessibility and protection of data. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A trust model for capability delegation in federated policy systems

A trust model for capability delegation in federated policy ...

引用

2010 International Conference on Network and Service Management, CNSM 2010

作者： Feeney, Kevin Brennan, Rob Foley, Simon N. FAME Knowledge and Data Engineering Group Trinity College Dublin Ireland FAME Department of Computer Science University College Cork Ireland

ISBN: (纸本)9781424489084

Federated policy systems are required to support the complexity and organizational heterogeneity of the modern marketplace. The Community-based Policy Management System (CBPMS) is such a distributed policy management approach. It utilizes a tree-based capability authority model to partition and delegate federated capabilities. However CBPMS delegation chains have limitations such as: performance overheads due to distributed rule evaluation, threats from malformed or malicious federated principals and a lack of flexibility with respect to delegation chain reduction or capability authority re-partitioning. In this paper we introduce a trust management model for CBPMS that addresses all of these issues. A brief security analysis is presented and a telecommunications service management use case described. © 2010 IEEE.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

RHC: A dataset for In-Room and Out-Room Human Counting

引用

Procedia computer science 2021年 179卷 33-39页

作者： Bens Pardamean Hery Harjono Muljo Faizal Abid Herman Albert Susanto Tjeng Wawan Cenggoro Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Accounting Information Systems Program Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

In recent years, research in human counting from CCTV (Closed Circuit Television) images have found an increasing demand to be deployed in real-world applications. The applications have been implemented in various settings, both indoor and outdoor. In the case of indoor setting, we found a type of room setting that conveys a problem to human counting model if we need to count only humans inside a room. With this respect, we present RHC (Room Human Counting) dataset, which images are captured in the aforementioned setting. The dataset can be used to develop a robust model that can differentiate between humans inside and outside a room. The dataset is publicly available at https://***/datasets/vt5c8h6kmh/1.

关键词： dataset human counting crowd counting in-room out-room

来源：评论

学校读者我要写书评

暂无评论

Selective Excitation of Superconducting Qubits with a Shared Control Line through Pulse Shaping

arXiv

引用

arXiv 2025年

作者： Matsuda, R. Ohira, R. Sumida, T. Shiomi, H. Machino, A. Morisaka, S. Koike, K. Miyoshi, T. Kurimoto, Y. Sugita, Y. Ito, Y. Suzuki, Y. Spring, P.A. Wang, S. Tamate, S. Tabuchi, Y. Nakamura, Y. Ogawa, K. Negoro, M. Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan QuEL Inc. Daiwaunyu Building 3F 2-9-2 Owadamachi Hachioji Tokyo192-0045 Japan Center for Quantum Information and Quantum Biology Osaka University 1-2 Machikaneyama Toyonaka Osaka560-0043 Japan e-trees.Japan Inc. Daiwaunyu Building 2F 2-9-2 Owadamachi Hachioji Tokyo192-0045 Japan NTT Computer and Data Science Laboratories NTT Corporation Musashino180-8585 Japan RIKEN Center for Quantum Computing Saitama Wako351-0198 Japan Department of Applied Physics Graduate School of Engineering University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan

In conventional architectures of superconducting quantum computers, each qubit is connected to its own control line, leading to a commensurate increase in the number of microwave lines as the system scales. Frequency-multiplexed qubit-control addresses this problem by enabling multiple qubits to share a single microwave line. However, it can cause unwanted excitation of non-target qubits, especially when the detuning between qubits is smaller than the pulse bandwidth. Here, we propose a selective-excitation-pulse (SEP) technique that suppresses unwanted excitations by shaping a drive pulse to create null points at non-target qubit frequencies. In a proof-of-concept experiment with three fixed-frequency transmon qubits, we demonstrate that the SEP technique achieves single-qubit gate fidelities comparable to those obtained with conventional Gaussian pulses while effectively suppressing unwanted excitations in non-target qubits. These results highlight the SEP technique as a promising tool for enhancing frequency-multiplexed qubit-control. © 2025, CC0.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

DBSCAN: Past, present and future

DBSCAN: Past, present and future

引用

5th International Conference on the Applications of Digital Information and Web Technologies, ICADIWT 2014

作者： Khan, Kamran Rehman, Saif Ur Aziz, Kamran Fong, Simon Sarasvady, S. Vishwa, Amrita Department of Computer Science SZABIST Islamabad Pakistan Center of Excellence in Data Engineering Mohammad Ali Jinnah University Islamabad Pakistan Department of Computer and Information Science University of Macau Taipa China Vidyapeetham University Ettimadai Coimbatore-641 112 India

ISBN: (纸本)9781479922581

data Mining is all about data analysis techniques. It is useful for extracting hidden and interesting patterns from large datasets. Clustering techniques are important when it comes to extracting knowledge from large amount of spatial data collected from various applications including GIS, satellite images, X-ray crystallography, remote sensing and environmental assessment and planning etc. To extract useful pattern from these complex data sources several popular spatial data clustering techniques have been proposed. DBSCAN (Density Based Spatial Clustering of Applications with Noise) is a pioneer density based algorithm. It can discover clusters of any arbitrary shape and size in databases containing even noise and outliers. DBSCAN however are known to have a number of problems such as: (a) it requires user's input to specify parameter values for executing the algorithm;(b) it is prone to dilemma in deciding meaningful clusters from datasets with varying densities;(c) and it incurs certain computational complexity. Many researchers attempted to enhance the basic DBSCAN algorithm, in order to overcome these drawbacks, such as VDBSCAN, FDBSCAN, DD-DBSCAN, and IDBSCAN. In this study, we survey over different variations of DBSCAN algorithms that were proposed so far. These variations are critically evaluated and their limitations are also listed. © 2014 IEEE.

关键词： X ray crystallography

来源：评论

学校读者我要写书评

暂无评论

Geometry-preserving topological landscapes

Geometry-preserving topological landscapes

引用

Workshop at SIGGRAPH Asia 2012, WASA 2012

作者： Beketayev, Kenes Weber, Gunther H. Morozov, Dmitriy Abzhanov, Aidos Hamann, Bernd Computational Research Division Lawrence Berkeley National Laboratory United States Institute for Data Analysis and Visualization Computer Science Department University of California Davis CA United States Computer Science Department Center for Energy Research Nazarbayev University Kazakhstan

ISBN: (纸本)9781450318358

We propose a novel technique for building geometry-preserving topological landscapes. Our technique creates a direct correlation between a scalar function and its topological landscape. This correlation is accomplished by introducing the notion of geometric proximity into the topological landscapes, reflecting the distance of topological features within the function domain. Furthermore, this technique enables direct comparative analysis between scalar functions, as long as they are defined on the same domain. We describe a construction technique that consists of three stages: contour tree computation, contour tree layout, and landscape construction. We provide a detailed description for the latter two steps. For the contour tree layout stage, we discuss dimension reduction and edge routing techniques that produce a drawing of the contour tree on the plane that preserves the geometric proximity. For the landscape construction stage, we develop a contour construction algorithm that takes the contour tree layout as an input, adds contours at heights that correspond to saddles of the contour tree, and produces a contour map. After an additional triangulation step, this construction method results in the landscape that has the same contour tree as the original function. © 2012 ACM.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Enhancing digital security using Signa-Deep for online signature verification and identity authentication

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第2期8卷 58-69页

作者： Ch, Ravikumar Sridevi, Mulagundla Ramchander, M. Ramesh, Vankudoth Kumar, Vadapally Praveen Department of Artificial Intelligence &Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Computer Science and Engineering CVR College of Engineering Hyderabad 501510 India Department of Computer Applications Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Emerging Technologies CVR College of Engineering Hyderabad 500039 India

In the contemporary digital realm, the utilization of online services has surged, facilitated by the seamless integration of deep learning technology, which is paramount in applications demanding precision and efficiency. A pivotal use case in this context is online handwritten signature verification, where the need for exceptional accuracy is indisputable. This paper introduces ‘Signa-Deep, ’ an innovative approach designed to address the challenge of online signature verification and the determination of an individual’s authorization status. The study explores a range of methodologies, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), GoogleNet, and MobileNet, to discern the authenticity of signatures and affirm the identity of the signatory. The results of our proposed method are promising, showcasing its potential to significantly enhance the security of digital transactions and identity verification processes. In summary, ‘Signa-Deep’ harnesses deep learning technology to bolster the accuracy and reliability of online signature verification, thereby contributing to the overall robustness of digital interactions and identity validation processes. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Authorization Status Deep Learning Digital Transactions Security Identity Authentication Online Signature Verification

来源：评论

学校读者我要写书评

暂无评论

Market Basket Analysis on Sales Transactions for Micro, Small and Medium Enterprises Using Apriori Algorithm to Support Business Promotion Strategy in RDA Hijab

Market Basket Analysis on Sales Transactions for Micro, Smal...

引用

2021 International Conference on Artificial Intelligence and Big data Analytics, ICAIBDA 2021

作者： Nabila, Aulia Ghassani Nurma Yulita, Intan Suryana, Ino Suryani, Mira Universitas Padjadjaran Department of Computer Science Bandung Indonesia Research Center for Artificial Intelligence and Big Data Universitas Padjadjaran Bandung Indonesia

ISBN: (纸本)9781665408905

The increasingly fierce business competition requires business owners to always innovate to create effective and efficient business promotion strategies to develop their business. One way to get recommendations for business promotion strategies is to process sales transaction data owned by the business. With data mining, the data can be processed so that new knowledge is obtained to support the creation of new business promotion strategies. The method used is the method of market basket analysis association rules with a priori algorithm. The results of the analysis in this study can be concluded for the rule with a combination of 2 items that have the highest confidence value of 41.61%, the lift ratio value of 12.10, and the frequency of the rule in the highest testing data is 66, that is, if consumers buy navy neck cuffs, then he will also buy white neck cuffs. And for the rule with a combination of 3 items that have the highest confidence value of 50.00%, the lift ratio value of 11.94, and the frequency of the rule in the highest testing data is 13, that is, if the consumer buys black neck cuffs and navy neck cuffs then he will also buy a light khaki neck cuff. © 2021 IEEE.

关键词： data mining

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

2024 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2024

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

ISBN: (纸本)9798350376135

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. © 2024 IEEE.

关键词： Contrastive Learning

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：