检索结果-内蒙古大学图书馆

Distributed private preserving learning based chaotic encryption framework for cognitive healthcare IoT systems

Informatics in Medicine Unlocked 2024年 49卷

作者： Nabi, Shaik Abdul Kalpana, Ponugoti Chandra, N. Subhash Smitha, L. Naresh, K. Ezugwu, Absalom E. Abualigah, Laith Department of Computer Science and Engineering AVN Institute of Engineering and Technology Department of Computer Science and Engineering CVR College of Engineering Department of Information Technology G Narayanamma Institute of Technology and Science Department of Computer Science and Engineering TKR College of Engineering & Technology Unit for Data Science and Computing North-West University Computer Science Department Al Al-Bayt University MEU Research Unit Middle East University Applied Science Research Center Applied Science Private University Jadara Research Center Jadara University Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk School of Engineering and Technology Sunway University Malaysia

In the field of cognitive healthcare Internet of Things (CH-IoT), there is a strong demand for reliable and minimally intrusive smart gadgets that consistently acquire, analyse, and obtain the confidential health details of the individual. In fact, CH-IoT is empowered with artificial intelligence (AI) to transmute a fewer operational inputs into actionable, intelligent actions through the digitization of medical healthcare data. However, these systems consume more network complexity, interaction, and overhead costs, while inducing a blend of susceptibility and confidentiality issues. In support of this complexity, these cognitive systems need centralised data collection and to be gathered and analysed, which affects scalability issues and adds fuel to privacy and security breaches. Even though it possesses greater intricacy in its potential application, a substantial factor is maintaining the private preservation of healthcare data against the growing attacks. Thus, this paper presents a distributed privacy-preserving, chaotic encryption-based framework that can be deployed for CH-IoT systems to safeguard sensitive data against message modification, denial of service (DoS), and man-in-the-middle attacks (MIM), guaranteeing privacy and data integrity. The proposed framework integrated the federated learning layered hybrid chaotic encryption strategies by investigating through examination the learning infrastructure of convolutional neural networks (CNN). In the examination, the complete framework was carried out in the Tensorflow Federated Learning Libraries (FLL), and numerous performance metrics such as accuracy, precision, recall, f1-score, transmission efficiency, and overhead ratio were measured and contrasted with the various existing frameworks. For the intensive analysis, formal and informal security experiments were also conducted by NIST (National Institute of science and technology). The analytical results illustrate the importance of the proposed framewor

关键词： Cognitive health care Distributed learning Federated learning libraries Internet of things NIST Privacy and security breaches

来源：评论

学校读者我要写书评

暂无评论

Predictive Coding beyond Correlations 41

Predictive Coding beyond Correlations

引用

41st International Conference on Machine Learning, ICML 2024

作者： Salvatori, Tommaso Pinchetti, Luca M'Charrak, Amine Millidge, Beren Lukasiewicz, Thomas VERSES Research Lab Los AngelesCA90016 United States Institute of Logic and Computation Vienna University of Technology Austria Department of Computer Science University of Oxford United Kingdom MRC Brain Network Dynamics Unit University of Oxford United Kingdom Zyphra Palo AltoCA United States

Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks. First, we show how a simple change in the inference process of predictive coding enables to compute interventions without the need to mutilate or redefine a causal graph. Then, we explore applications in cases where the graph is unknown, and has to be inferred from observational data. Empirically, we show how such findings can be used to improve the performance of predictive coding in image classification tasks, and conclude that such models are able to perform simple end-to-end causal inference tasks. Copyright 2024 by the author(s)

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Drug Discovery: Predicting Drug-Protein Binding Affinities using Graph Convolutional Networks 5

Machine Learning for Drug Discovery: Predicting Drug-Protein...

引用

5th IEEE International Conference on Recent Trends in computer science and technology, ICRTCST 2024

作者： Radhamahendran, S. Dogra, Akriti Mendhe, Dinesh Tilak Babu, S.B.G. Dixit, Shriniket Singh, Surya Pratap Vels Institute of Science Technology and Advanced Studies School of Life Sciences Department of Bioinformatics Chennai Pallavaram India Manav Rachna Dental College Department of Oral & Maxillofacial Surgery Haryana Faridabad India State University of New Jersey Computer and Information Research Scientist Office of Research Computing Rutgers New BrunswickNJ United States Aditya Engineering College Department of ECE Surampalem India Vellore Institute of Technology School of Computer Science Engineering Tamil Nadu Vellore India UPUMS Department of Multi-Disciplinary Research Unit UP Etawah India

ISBN: (纸本)9798350351378

Determining the potential interactions between ligands and proteins is a crucial first step in developing new drugs. Graph BAR, our novel prediction model, makes accurate guesses about the strength of ligand-protein bindings by means of a graph convolutional neural network. When compared to graph convolutional neural networks, standard convolutional neural network models are more resource and time intensive to manage. The interaction between proteins and ligands is shown via a network consisting of many adjacency meshes. The atomic distances dictate the alterations to these matrices. Additionally, the atomic properties can be shown in a feature matrix. Using the PDBbind datasets, we verified the functionality of graph convolution and evaluated Graph BAR's ability to forecast the binding strengths of proteins and ligands. In order to maximize The model's performance was improved by utilizing ways for adding additional input, which took advantage of the processing capability of graph convolutional neural networks. Graph BAR's predictions appear to have potential for use in drug creation due to its great accuracy and quickness. The results of our research suggest that Graph Convolutional Networks have the potential to expedite the discovery of new medications by properly predicting the interactions between pharmaceuticals and proteins. © 2024 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Effects of term weighting approach with and without stop words removing on Arabic text classification 9

Effects of term weighting approach with and without stop wor...

引用

9th International Conference on Optimization and Applications, ICOA 2023

作者： Alhenawi, Esra'a Khurma, Ruba Abu Castillo, Pedro A. Arenas, Maribel G. Al-Hinawi, Ayat Mahmoud Al-Ahliyya Amman University Faculty of Information Technology Department of Software Engineering Amman Jordan Middle East University Meu Research Unit Faculty of Information Technology Department of Computer Science Amman11831 Jordan University of Granada Granada Spain Hashemite University Department of Allied Engineering Sciences Zarqa Jordan

ISBN: (纸本)9798350312546

Text classification is a technique for grouping articles into pre-defined categories. Prior to categorization, text documents have to be set up and organised in a form that is compatible with the data mining techniques. That has produced many term weighting techniques have been developed in the literature to improve the functionality of text categorization systems. This paper compares techniques for text classification based on when stop words are eliminated from the documents once and when they are not. We used an Arabic data set of 322 papers grouped into six subjects (health, politics, science, education, agriculture and finance) to research which is the influence of prior weighting of features approaches on classification outcomes with regard to accuracy, recall, precision, and F-measure values. Each document subset includes 50 documents, except the health one that includes 61. We carried out four experiments and checked results getting that only for precision, the term frequency feature weighting approach with stop word removal are more or less the same than for binary method. Moreover the conclusion for accuracy, recall and F-measure is that Feature weighting approach with stop word outperforms the Binary one. Additionally, if the phrase for weighting is the same for both methods, to remove stop word increases classification accuracy for all the experiments. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Study of Contemporary ML Algorithm on Intrusion Detection Using IIoT Datasets

A Study of Contemporary ML Algorithm on Intrusion Detection ...

引用

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Ajagbe, Sunday A. Kumar, T. Ananth Rajmohan, Rajendrane Balogun, Emmanuel O. Olawoyind, Oluwafemi O. Lawrence, Morolake O. Adigun, Matthew O. Computer Science Department University of Zululand Kwadlangezwa 3886 South Africa Computer Engineering Department Abiola Ajimobi Technical University Ibadan200255 Nigeria Computer Science and Engineering Department IFET College of Engineering India Computing Technologies Department SRM Institute of Science and Technology India ICT Unit Ajayi Crowther University Oyo Oyo Nigeria Computer Science Department Baze University Abuja Nigeria

The global digitization of most activities of corporate and non-corporate bodies has come to stay. The interconnection of physical object "things"embedded with different technologies such as sensors, softwares and other technologies to connect and allow for data exchange with different systems and devices over the internet is known as the Internet of Things (IoT). To guarantee lower expenses and increased operational effectiveness, Data-driven insights for prompt decision-making, complete, remote asset and resource management, Prescriptive, predictive, and real-time insights along with enhanced end-user satisfaction Industrial Internet of Things (IIoT) became a given. Implementing machine learning (ML) algorithms for intrusion detection in IIoT systems entails numerous hurdles, such as data imbalance and adversarial attacks. And different ML algorithms handle data imbalance and adversarial attacks for intrusion detection differently. Therefore, there is a need for comparative studies on ML algorithms to be used as a tool to help prevent unauthorised intrusion into various networks. In this research, an experimental approach has been used to compare contemporary ML algorithms such as Linear SVC, random forest RF, XGBoost, decision tree (DT), logistic regression (LR) on IIoT datasets to detect intrusion. Data exploration, Feature engineering, selection and data partition were done at a rate of 80-20 % ratio for the train set and test set respectively. Performance evaluation was carried out using accuracy, recall, precision and F1-score and a confusion matrix was plotted. The performance evaluation shows the accuracy of 100%, 99.99%, 99.35%, 97.49% and 97.27% for RF, XGBoost, DT, Linear SVC and LR algorithms respectively the test set evaluation. RF outperformed the other algorithm that was experimented. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Parallel matrix multiplication algorithms in Supercomputing 6

Parallel matrix multiplication algorithms in Supercomputing

引用

6th IEEE International Conference on Intelligent Computing and Signal Processing, ICSP 2021

作者： Liao, Xia Li, Shengguo Yu, Wei Lu, Yutong National University of Defense Technology School of Computer Science Changsha China Unit 63768 of Pla Xi'an China

ISBN: (纸本)9780738143705

Nowadays high-performance computing is gradually implementing Exa-scale computing, and the performance of single node has reached several T-flops. Communication problem has become one of the main concerns of parallel matrix multiplication algorithms. This paper surveys the research on PMM algorithms on supercomputers around the world. We first stress the significance of PMM (Parallel Matrix multiplication) algorithms in high performance scientific computing, followed by a background introduction on widely employed PMM algorithms. We introduce the researches on parallel techniques for PMM algorithms from two aspects: classical parallel matrix multiplication and Strassen's fast matrix multiplication. Further, we present the detailed complexity analysis comparison of each algorithm. Finally, we summarize the paper and discuss potential directions of future work. © 2021 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Enhanced view-independent representation method for skeleton-based human action recognition

引用

International Journal of Information and Communication technology 2021年第2期19卷 201-218页

作者： Jiang, Yingguo Lu, Lu Xu, Jun School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Unit 95795 of the People’s Liberation Army Guilin541003 China Unit 95269 of the People’s Liberation Army Guangzhou510075 China

Human action recognition is an important branch of computer vision science. It is a challenging task based on skeletal data because joints have complex spatiotemporal information. In this work, we propose a method for action recognition, which consists of three parts: view-independent representation, combination with cumulative Euclidean distance, and combined model. First, the action sequence becomes view-independent representations independent of the view. Second, these representations are further combined with cumulative Euclidean distances, so the joints more closely associated with the action are emphasised. Then, a combined model is adopted to extract these representation features and classify actions. It consists of two parts, a regular three-layer BLSTM network, and a temporal attention module. Experimental results on two multi-view benchmark datasets, Northwestern-UCLA and NTU RGB + D, demonstrate the effectiveness of our complete method. Despite its simple architecture and the use of only one type of action feature, it can still significantly improve recognition performance and has strong robustness. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Data Quality: revisiting dimensions towards new framework development

引用

Procedia computer science 2025年 253卷 247-256页

作者： André M. Carvalho Sónia Soares João Montenegro Lígia Conceição Reserach & Development Unit for Mechanical and Industrial Engineering (UNIDEMI) NOVA School of Science and Technology Universidade Nova de Lisboa Caparica –Portugal Armis ITS Consulting Porto – Portugal Articial Intelligence and Computer Science Laboratory (LIACC) Faculty of Engineering University of Porto - Portugal

In today’s information-driven world, accessible, reliable, and accurate data is crucial for informed decision-making and effective operations across various domains. Within this context, ensuring Data Quality is crucial to maximizing the added value of the information shared. However, assessing Data Quality presents challenges due to several aspects, such as the lack of consensus on which quality dimensions constitute it, or the absence of systematic methodologies for the development of quality frameworks. This study addresses these issues by identifying commonly used quality dimensions and proposing a structured approach to facilitate and foment effective quality assessment and assurance mechanisms. To that end, we conducted a comprehensive literature review regarding Data Quality dimensions and aggregated the identified ones into an intelligible structure. Through this process, 66 quality dimensions were identified and a coherent arrangement that allows for the proper development of quality frameworks was proposed. The results showcase a robust and adaptable structure offering valuable insights for practitioners and researchers. This contribution significantly enhances the overall understanding and application of data quality dimensions, thereby advancing the development of effective data quality frameworks.

关键词： Data Quality Quality Management Industry 4.0 Data Quality Dimensions

来源：评论

学校读者我要写书评

暂无评论

Automated analysis of fundus images for the diagnosis of retinal diseases: a review

引用

Research on Biomedical Engineering 2024年第1期40卷 225-251页

作者： Berto, Alexa Scarpa, Fabio Tsiknakis, Nikos Manikis, Georgios Fotiadis, Dimitrios I. Marias, Kostas Scarpa, Alberto D-Eye s.r.l. Padua Italy Department of Information Engineering University of Padova Padua35131 Italy Heraklion70013 Greece Department of Biomedical Research Institute of Molecular Biology and Biotechnology FORTH Ioannina45115 Greece Department of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina Ioannina45110 Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion71004 Greece

Purpose: Colour fundus images are widely used in diagnosis treatment decision of several retinal diseases such as diabetic retinopathy (DR), glaucoma and age-related macular degeneration (AMD). These very common conditions must be detected early and monitored to prevent progression and avoid permanent damage. Fundus images revealed to be useful also for the diagnosis of cataracts. In recent years, various automatic diagnostic support methods have been proposed in the literature, with the aim of facilitating widespread screening and obtaining quantitative, objective, and reproducible information. Methods: In this review paper, an overview of traditional, machine learning and modern deep learning techniques for ophthalmic disease diagnosis (i.e. glaucoma, DR, AMD, and cataract) using retinal fundus images is presented. In addition, various publicly available image datasets used for such purposes are described. Results: The current main challenges and findings are identified, as well as common aspects and discrepancies between the various methods developed for the various diseases. Conclusion: The overview of what has been done about all pathologies, rather than only on a specific one, could favour a migration of the best solutions and, hopefully, the development of a more precise and clinically useful automatic analysis of all pathologies. Important critical insights and research trends are also discussed. Graphical abstract: (Figure presented.) © The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering 2023.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

An Automatic Density Cluster Generation Method to Identify the Amount of Tool Flank Wear via Tool Vibration

An Automatic Density Cluster Generation Method to Identify t...

引用

2023 International Research Conference on Smart Computing and Systems Engineering, SCSE 2023

作者： Adikaram, K.K.L.B. Herwan, J. Furukawa, Y. Komoto, H. University of Ruhuna Computer Unit Faculty of Agriculture Mapalana Kamburupitiya81100 Sri Lanka National Institute of Advanced Industrial Science and Technology Industrial Cyber-Physical Systems Research Center 2-3-26 Aomi Koto-ku Tokyo135-0064 Japan

ISBN: (纸本)9798350341454

Determining the amount of tool flank wear (TFW) of a tool during operation is an important and cost-sensitive factor for maintaining the efficiency of the machine and product standards in Industry 4.0. Therefore, a variety of predictive analysis tools have been developed in this regard, with the objective of taking corrective action quickly and efficiently. In this paper, we present a TFW amount estimating method via plotting vibration generated during the cutting process on big data visualization and density cluster generation method known as Graphical Knowledge unit (GKU). GKU generates density clusters by incrementing the RGB color values in the intersected markers due to data overlapping. In our previous work, the TFW amount of a cutting tool attached to a computer Numerical Control (CNC) turning machine was checked. A workpiece of grey cast iron with an initial outer diameter of 110 mm was cut until it reached 60 mm. This process was repeated until the TFW amount, which was measured according to ISO 4288, met the recommended value range (0.3 ± 0.005 mm). After each cut, TFW amount and the surface roughness were measured following ISO 4288. Vibration was recorded using a triaxial accelerometer attached to the tool shank of the turning machine. In the present work, out of 29 cutting circles, vibration along the x-axis against vibration along the y-axis of selected cuttings were plotted using GKU. The density of the center of the plot (fixed point, FP) and the density of the highest density (dynamic point, DP) were measured using the color values of pixels as an index. The results showed a very strong linear correlation (0.95) between the TFW amount and vibration data density projected via pixel color values at FP. This shows that processing of vibration with GKU is a promising method to estimate TFW amount. © 2023 IEEE.

关键词： Machine 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：