检索结果-内蒙古大学图书馆

Sustainable Expert Systems (ICSES), International Conference on

作者： Ar Arunarani V. Vijayagopal L. Kartheesan Vijay Kumar Dwivedi Rajesh Kumar A Neerav Nishant Department of Computational Intelligence School of Computing College of Engineering SRM Institute of Science and Technology Chennai Tamilnadu India Faculty of Computer Applications Dr. M.G.R. Educational and Research Institute Chennai Tamilnadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Mathematics Vishwavidyalaya Engineering College Surguja Chhattisgarh India Department of Computer Science and Engineering N.S.N. College of Engineering and Technology Karur Tamilnadu India Department of Computer Science and Engineering School of Engineering Babu Banarasi Das University Lucknow India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Many services have made the transition to the cloud because of the increased reliability and efficiency of cloud computing. Due to their capacity to ease service access while also securing communications in the public network, the three-factor Mutual Authentication and Key Agreement (MAKA) protocols are seeing increased use in multi-server designs. A lack of formal security proof or high communication and computation costs makes the limited three-factor MAKA protocols that are currently available susceptible to a wide range of attacks. The proposed approach consists of three phases, which are preprocessing, feature selection, and model training. Text scheduling and normalization make up preprocessing. In feature selection, the PSO is an optimization method that uses a population-based approach to find optimal solutions. An ANN-SVM was employed throughout the model's training phase. With an average accuracy of 93.30%, the proposed technique surpasses ANN and SVM.

关键词： Training Support vector machines Protocols Accuracy Systematics Cloud computing security Neural networks Feature extraction Vectors Reliability

来源：评论

学校读者我要写书评

暂无评论

Prediction of Interstitial Glucose Levels Through Wearable Sensors Using Machine Learning

Prediction of Interstitial Glucose Levels Through Wearable S...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Ali, Haider Madanian, Samaneh Malik, Naveed White, David Russel, Brian K Niazi, Imran Khan Engineering Computer and Mathematical Sciences Auckland University of Technology Chiropractic Research Center New Zealand College of Chiropractic Auckland New Zealand Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland New Zealand Health & Rehabilitation Research Institute Aut University Chiropractic Research Center New Zealand College of Chiropractic Faculty of Health & Environmental Sciences Auckland New Zealand Engineering Computer and Mathematical Sciences Auckland University of Technology Biodesign Lab Auckland New Zealand Centre for Chiropractic Research New Zealand College of Chiropractic New Zealand Health & Rehabilitation Research Institute Aut University Faculty of Health & Environmental Sciences New Zealand Aalborg University Auckland Department of Health Science and Technology New Zealand

ISBN: (纸本)9798350341072

The incidence of diabetes has been increasing, resulting in an increasing cost of managing and tracking the correlates for blood glucose levels. Just for New Zealand alone, 2.1 billion dollars are spent annually on diabetes management. This is 4 times the current tertiary education budget in the same country. Compared to the traditional cumulative HbA1c marker of glucose used to monitor the health of diabetics, continuous glucose monitoring allows for tracking the trends in glucose value in real time. It also helps in gauging important statistics such as time in range of glucose values. For healthy individuals, glucose tracking can inform the user of the effect various activities and foods have on an individual's level. This paper aims to present a method of predicting the level of glucose through wearable continuous glucose monitors (Empatica E4 and Dexcom) and machine learning. The data from these wearable sensors comprises of inter beat interval (IBI), electrodermal activity (EDA), tri-axial accelerometry (ACC), heart rate (HR), skin temperature, food log, and blood volume pulse (BVP). It was collected over 8-10 days for 19 individuals and used to calculate 73 statistical features. 69 features were used from previous literature and 4 novel features proposed in this research were used. These features were in turn used to train support vector machine (SVM) and decision tree model (DTM) with stratified K-fold validation which yield accuracies of 69.10 ± 14.2 % and 72.38 ± 2.4 %. The combined feature importance of the 4 novel features was calculated to be 5%, highlighting their significance in the model. © 2023 IEEE.

关键词： Glucose

来源：评论

学校读者我要写书评

暂无评论

Examination System Automation Using Natural Language Processing

Examination System Automation Using Natural Language Process...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： R Praveen Kumar N. Muthukumaran Cheruku Hanisha Pohar Rithvik M.Saipavan Goud Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

Numerous examination portals have been created and distributed over several servers for a number of objectives, including the administration of tests in connection withadmission exams, Olympic competitions at national and worldwide levels, and the administration of placement tests. It turns out that practically all portals are set up for multiple-choice examinations, as we found. Our goal here is not to work on current technology, but rather to work on technology that is very uncommon. The descriptive online examination method is discussed here. Simple to use, multiple choice questions are composed of a question, many possible answers to the same question as well as a field to record the correct response in the database. Descriptive queries, on the other hand, do not fall within this category. To award marks to replies, it incorporates or employs Natural Language Processing (NLP) ideas. The model's responsibility is to lead procedure on the response string so it can give the right stamps to the examinee's responses. The data is generally assembled utilizing an enlightening web-based appraisal procedure. It is likewise inspected, and the made model honors right stamps to the inquiry's answers. With respect to the front-end, HTML 5, CS S 3, Bootstrap, and JavaS cript are utilized. The back-end was created in Python using Django, NLTK for Natural Language Processing, and SQLite version 3 as the database.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linear Regression on Manifold Structured Data: the Impact of Extrinsic Geometry on Solutions

arXiv

引用

arXiv 2023年

作者： Liu, Liangchen He, Juncai Tsai, Richard Department of Mathematics University of Texas at Austin AustinTX United States Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Oden Institute for Computational Engineering and Sciences University of Texas at Austin AustinTX United States

In this paper, we study linear regression applied to data structured on a manifold. We assume that the data manifold is smooth and is embedded in a Euclidean space, and our objective is to reveal the impact of the data manifold’s extrinsic geometry on the regression. Specifically, we analyze the impact of the manifold’s curvatures (or higher order nonlinearity in the parameterization when the curvatures are locally zero) on the uniqueness of the regression solution. Our findings suggest that the corresponding linear regression does not have a unique solution when the embedded submanifold is flat in some dimensions. Otherwise, the manifold’s curvature (or higher order nonlinearity in the embedding) may contribute significantly, particularly in the solution associated with the normal directions of the manifold. Our findings thus reveal the role of data manifold geometry in ensuring the stability of regression models for out-of-distribution *** Codes 53Z50 62J05 (Primary) 65D18 68T07 (Secondary) © 2023, CC BY-NC-ND.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Secure De-Duplication Over Wireless Sensing Data Using Convergent Encryption 3

Secure De-Duplication Over Wireless Sensing Data Using Conve...

引用

3rd IEEE Global Conference for Advancement in Technology, GCAT 2022

作者： Yuvaraj, D. Kumar, V. Pradeep Anandaram, Harishchander Samatha, Badugu Krishnamoorthy, R. Thiyagarajan, R. Cihan University Department of Computer Science Duhok Iraq B v Raju Institute of Technology Dept of Cse Narsapur India Centre for Excellence in Computational Engineering and Networking Amrita Vishwa India Vignan's Foundation for Science Technology and Research Department of Cse Guntur India Prathyusha Engineering College Department of Ece Chennai India Prathyusha Engineering College Department of It Chennai India

ISBN: (数字)9781665468558

ISBN: (纸本)9781665468534

The fast development of cloud computing technology has greatly accelerated the gathering and sharing of numerous types of data. Utilizing data deduplication technologies is crucial to decrease storage overhead and transmission costs. A significant quantity of processing and storage resources are made available for a variety of high-quality service applications using cloud computing, which is an online data center. In any case, cloud clients never again approach their information in a nearby information stockpiling foundation, making it challenging to really look at the respectability of information that has been re-appropriated. It has become crucial to assist the user in fully verifying the accuracy of the data that has been outsourced. This issue is settled utilizing safe encryption and de-duplication systems, and clients might use an outsider examiner to confirm the precision of information that has been re-appropriated and the encryption technique. Existing data deduplication systems still have efficiency and security issues. Information deduplication is achieved by the proposed procedures preceding the information being shipped off the distributed storage server, which brings down the expense of calculation and transmission. in particular, block-level deduplication with variable size. De-duplication strategies have been utilized to forestall information duplication by contrasting records in the client data set utilizing PHP;this further develops stock piling's memory proficiency and rates up handling. Clients encode information utilizing concurrent encryption techniques prior to re-appropriating it to the cloud to keep unapproved clients from getting to the information. © 2022 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Sparse-view CBCT reconstruction using meta-learned neural attenuation field and hash-encoding regularization

引用

computers in Biology and Medicine 2025年 189卷 109900-109900页

作者： Shin, Heejun Kim, Taehee Lee, Jongho Chun, Se Young Cho, Seungryong Shin, Dongmyung Artificial Intelligence Engineering Division Radisen Co. Ltd. Seoul Korea Republic of Laboratory for Imaging Science and Technology Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Intelligent Computational Imaging Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Medical Imaging and Radiotherapy Laboratory Department of Nuclear and Quantum Engineering Korea Advanced Institute of Science and Technology Daejean Korea Republic of

Cone beam computed tomography (CBCT) is an emerging medical imaging technique to visualize the internal anatomical structures of patients. During a CBCT scan, several projection images of different angles or views are collectively utilized to reconstruct a tomographic image. However, reducing the number of projections in a CBCT scan while preserving the quality of a reconstructed image is challenging due to the nature of an ill-posed inverse problem. Recently, a neural attenuation field (NAF) method was proposed by adopting a neural radiance field algorithm as a new way for CBCT reconstruction, demonstrating fast and promising results using only 50 views. However, decreasing the number of projections is still preferable to reduce potential radiation exposure, and a faster reconstruction time is required considering a typical scan time. In this work, we propose a fast and accurate sparse-view CBCT reconstruction (FACT) method to provide better reconstruction quality and faster optimization speed in the minimal number of view acquisitions ( © 2025 Elsevier Ltd

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multilevel Particle Filters for a Class of Partially Observed Piecewise Deterministic Markov Processes

arXiv

引用

arXiv 2023年

作者： Jasra, Ajay Kamatani, Kengo Maama, Mohamed Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Institute of Statistical Mathematics Tokyo190-0014 Japan

In this paper we consider the filtering of a class of partially observed piecewise deterministic Markov processes (PDMPs). In particular, we assume that an ordinary differential equation (ODE) drives the deterministic element and can only be solved numerically via a time discretization. We develop, based upon the approach in [20], a new particle and multilevel particle filter (MLPF) in order to approximate the filter associated to the discretized ODE. We provide a bound on the mean square error associated to the MLPF which provides guidance on setting the simulation parameter of that algorithm and implies that significant computational gains can be obtained versus using a particle filter. Our theoretical claims are confirmed in several numerical examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Probabilistic decomposed linear dynamical systems for robust discovery of latent neural dynamics 24

Probabilistic decomposed linear dynamical systems for robust...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yenho Chen Noga Mudrik Kyle A. Johnsen Sankaraleengam Alagapan Adam S. Charles Christopher J. Rozell Machine Learning Center Georgia Institute of Technology and Coulter Dept. of Biomedical Engineering Emory University and Georgia Institute of Technology Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University Coulter Dept. of Biomedical Engineering Emory University and Georgia Institute of Technology School of Electrical and Computer Engineering Georgia Institute of Technology Machine Learning Center Georgia Institute of Technology and School of Electrical and Computer Engineering Georgia Institute of Technology

ISBN: (纸本)9798331314385

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model's ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. Code is available at: https://***/siplab-gt/probabilistic-decomposed-linear-dynamical-systems

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conceptual structure of federated learning research field

引用

Procedia computer science 2022年 214卷 1374-1381页

作者： A. Velez-Estevez P. Ducange I.J. Perez M.J. Cobo Department of Computer Science and Engineering University of Cadiz Cádiz Spain Department of Information Engineering University of Pisa Italy Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain

Nowadays there are a great amount of data that can be used to train artificial intelligent systems for classification, or prediction purposes. Although there are tons of publicly available data, there are also very valuable data that is private, and therefore, it can not be shared without breaking the data protections laws. For example, hospital data has great value, but it involves persons, so we must try to preserve their privacy rights. Furthermore, although it could be interesting to train a model with the data of only one entity (i.e. a hospital), it could have more value to train the model with the data of several entities. But, since the data of each entity might not be shared, it is not possible to train a global model. In that sense, Federated Learning has emerged as a research field that deals with the training of complex models, without the necessity to share data, and therefore, keeping the data private. In this contribution, we present a global conceptual analysis based on co-words networks of the Federated Learning research field. To do that, the field was delimited using an advance query in Web of science. The corpus contain a total of 2444 documents. As the main result, it should be highlighted that the Federated Learning research field is focused on six main global areas: telecommunications, privacy and security, computer architecture and data modeling, machine learning, and applications.

关键词： Federated Learning bibliometric analysis science mapping analysis co-words SciMAT

来源：评论

学校读者我要写书评

暂无评论

Improved approximation algorithms for 2-dimensional knapsack: Packing into multiple L-shapes, spirals, and more 37

Improved approximation algorithms for 2-dimensional knapsack...

引用

37th International Symposium on computational Geometry, SoCG 2021

作者： Gálvez, Waldo Grandoni, Fabrizio Khan, Arindam Ramírez-Romero, Diego Wiese, Andreas Department of Computer Science TU München Germany IDSIA USI-SUPSI Lugano Switzerland Department of Computer Science and Automation Indian Institute of Science Bangalore India Department of Mathematical Engineering Universidad de Chile Santiago Chile Department of Industrial Engineering Center for Mathematical Modeling Universidad de Chile Santiago Chile

ISBN: (纸本)9783959771849

In the 2-Dimensional Knapsack problem (2DK) we are given a square knapsack and a collection of n rectangular items with integer sizes and profits. Our goal is to find the most profitable subset of items that can be packed non-overlappingly into the knapsack. The currently best known polynomial-time approximation factor for 2DK is 17/9 + Ε © Waldo Gálvez, Fabrizio Grandoni, Arindam Khan, Diego Ramírez-Romero, and Andreas Wiese;licensed under Creative Commons License CC-BY 4.0 37th International Symposium on computational Geometry (SoCG 2021).

关键词： Approximation algorithms

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：