检索结果-内蒙古大学图书馆

Matrix Hyper-Basis Function Neural Network and Its Online Learning 12

Matrix Hyper-Basis Function Neural Network and Its Online Le...

12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: technology and Applications, IDAACS 2023

作者： Chala, Olha Bodyanskiy, Yevgeniy Sachenko, Anatoliy Dobrowolski, MacIej Kharkiv National University of Radio Electronics Artificial Intelligence Department Kharkiv Ukraine Kazimierz Pulaski University of Technology and Humanities in Radom Informatics and Teleinformatics Department Poland Research Institute for Intelligent Computer Systems West Ukrainian National University Ternopil Ukraine

ISBN: (纸本)9798350358056

A matrix hyper-basis function neural network and a recurrent online algorithm for its training are proposed. The system aims to process not traditional signals in vector form but matrix ones describing the images of arbitrary nature. It simplifies the architecture of the neural network by eliminating the autoencoders, which are always a part of deep convolutional neural networks. Moreover, a distinctive feature of the proposed approach is the ability to adjust not only the synaptic weights but the parameters of hyper-basis activation functions also, reducing their number compared to traditional RBFN. The proposed system is intended to solve Data Stream Mining issues with a small training set. © 2023 IEEE.

关键词： combined learning HyperBasis Activation Functions matrix signals

来源：评论

学校读者我要写书评

暂无评论

SYN Flood Attack Detection and Prevention Technique (SFaDMT) in Distributed Environment 4

SYN Flood Attack Detection and Prevention Technique (SFaDMT)...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Jalil Fufan, Halawati Abd Riskhan, Basheer Hussain, Khalid Jazri, Husin Bin Alajmani, Samah H. Sharma, Komal School of Computing and Informatics Albukhary International University Alor Setar Malaysia School of Computer Science Taylor's University Subang Jaya Malaysia Taif University Department of Information Technology Taif Saudi Arabia Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR institute of technology and sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

In the modern digital landscape, cyber-attacks have become highly advanced and difficult to detect, especially in distributed systems. These Denial of Service (DoS) or Distributed Denial of Service (DDoS) attacks lead to resource unavailability for legitimate users, causing financial losses for organizations. To counter these threats, researchers have proposed efficient mitigation techniques. According to Kaspersky's Q3 report, SYN Flood is the most prevalent type of D DoS attack, increasing from 76% to 81% compared to the Q2 report. DDoS attacks can be executed directly or indirectly. In a direct attack, control traffic is sent straight from the attackers to the zombies to target the victim host. Conversely, in an indirect DDoS attack, control traffic is sent indirectly to reflectors by zombies to compromise the target host. Reflectors are uncompromised systems that only respond to requests. To mitigate such attacks, traffic shaping and Pushback techniques are employed. Our research introduces an adaptive heuristic-based method called SYN Flood Attack Detection and Mitigation Technique (SFaDMT) to detect DDoS SYN flood attacks. This study proposes an efficient technique for detecting and blocking SYN attacks. The SFaDMT technique is based on a decision support mechanism. The proposed model is simulated and analyzed in the OMNET simulator, and a comparison is made with the latest technique. The results demonstrate an improvement in detection with the proposed solution. © 2024 IEEE.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Translating Natural Language Arguments to Computational Arguments Using LLMs

Translating Natural Language Arguments to Computational Argu...

引用

2024 International Conference on Computational Models of Argument, COMMA 2024

作者： Trajano, Guilherme Engelmann, Débora C. Bordini, Rafel H. Sarkadi, Stefan Mumford, Jack Panisson, Alison R. Department of Computing Federal University of Santa Catarina Brazil Institute of Artificial Intelligence in Health Brazil School of Technology Pontifical Catholic University of Rio Grande do Sul Brazil Department of Informatics King's College London United Kingdom Department of Computer Science University of Liverpool United Kingdom

ISBN: (纸本)9781643685342

Large Language Models (LLMs) have become a significant milestone in the history of artificial intelligence, representing a powerful technology that drives advancements in natural language understanding and generation. In this paper, we propose an approach in which LLMs are utilized to support the task of translating natural language arguments into computational representations. Our approach is grounded in using argumentation schemes to classify arguments, providing context to LLMs for performing the proposed task. Our results demonstrate that LLMs, even with a short context, can handle simple argument structures. Moreover, our findings suggest that a larger context would likely enhance the performance, particularly when dealing with more complex argument structures. © 2024 The Authors.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Feature Selection Using a Hybrid Elephant Herding Optimization with Lĕvy Flight 8th

Enhanced Feature Selection Using a Hybrid Elephant Herding O...

引用

8th National Conference on New Trends in Information and Communications technology Applications, NTICT 2024

作者： Abdullah, Sura Mahmood Al-Bakry, Abbas Mohsin Farhan, Alaa Kadhem Informatics Institute of Postgraduate Studies Information Technology and Communications University Baghdad Iraq Baghdad Iraq Department of Computer Sciences University of Technology-Iraq Baghdad Iraq

ISBN: (纸本)9783031870750

Cardiovascular disease is a major contributor to the worldwide mortality rate, where the enormous amount of cardiac disease data generates substantial datasets with high-dimensional features. The feature selection process reduces processing time, ameliorates prediction accuracy, and aids decision-making by identifying the most pertinent features from the dataset rather than evaluating all available features. This paper proposes a population-based optimizer called Lĕvy Elephant Herding Optimization (LEHO) to address feature selection challenges;it combines the algorithms of Elephant Herding Optimization (EHO) and Lĕvy Flight (LF) to make the search space larger and more diverse, which makes it easier to find better features than with EHO alone. The LEHO optimizer relies on various machine learning models and has been applied to two datasets from Kaggle and our dataset on Coronary Artery Disease to assess its performance. Utilizing an Artificial Neural Network model, the proposed optimizer identified significant features. It attained a high average accuracy of 0.967 and 0.947 with two distinct data splitting ratios (80/20 and 70/30), respectively, for our dataset compared to the Kaggle datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

P4-MTAGG - a Framework for Multi-Tenant P4 Network Devices

P4-MTAGG - a Framework for Multi-Tenant P4 Network Devices

引用

International Conference on Network and Service Management

作者： Fabian Brisch Andreas Kassler Sándor Laki Peter Hudoba Institute of Applied Computer Science Deggendorf Institute of Technology Deggendorf Germany Computer Science Department Karlstads Universitet Karlstad Sweden Faculty of Informatics ELTE Eötvös Loránd University Budapest Hungary

ISBN: (数字)9783903176669

ISBN: (纸本)9798331505158

The current P4 programmability model assumes that a P4 programmable device is owned and controlled by a single tenant. However, in typical NFV scenarios, support for multiple tenants is desirable. When each tenant may want to deploy their own P4 pipeline offering different network functions (NF), supporting multiple co-existing tenant pipelines on a single platform is difficult because it requires pipeline merging, control plane support, and resource management of the platform. In this paper, we present P4-MTAGG, a novel framework for flexibly deploying multiple P4 programmable NFs on a programmable match-action pipeline while supporting multiple tenants. P4-MTAGG consists of i) novel compiler-add-ons for automatic merging multiple P4-pipelines, ii) p4runtime-proxy to allow for control plane access of the aggregated pipelines together with policy-based resource management for the P4 target, and iii) orchestrator to automate the provisioning of a network node utilizing aggregation either in a simulated or real hardware environment. In this demo, we show how P4-MTAGG aggregates multiple NFs of varying complexity in Mininet. The user can orchestrate the aggregation process through a GUI. The per-tenant traffic is routed through the set of NFs using segment routing. Through the GUI, the user can instruct the p4runtime-proxy to enforce per-tenant bandwidth limits, which configure the per-tenant available resources in the data plane.

关键词： Aggregates Pipelines Merging Bandwidth Routing Hardware Complexity theory Resource management Noise measurement Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Electricity Power Consumption Prediction With The Monte Carlo Simulation: Case Study Universitas Widya Dharma Pontianak

Electricity Power Consumption Prediction With The Monte Carl...

引用

International Conference on Information, Communication technology and System (ICTS)

作者： Genrawan Hoendarto Ahmad Saikhu Raden Venantius Hari Ginardi Department of Information Technology Institute Technology of Sepuluh Nopember Surabaya Indonesia Universitas Widya Dharma Pontianak Department of Information Technology Faculty of Intelligent Electrical and Informatics Technology Institute Technology of Sepuluh Nopember Surabaya Indonesia Department of Computer Science Faculty of Intelligent Electrical and Informatics Technology Institute Technology of Sepuluh Nopember Surabaya Indonesia

Predicting electricity consumption for buildings has been a concern lately, as it accounts for 39% of total electricity consumption. One of the buildings that uses a lot of electricity is the campus building. Various methods are being developed and carried out in response to the fossil energy crisis to save electricity consumption. Before taking steps to reduce the use of electricity, it is necessary to predict its use. Monte Carlo simulation is a good option for predicting electricity consumption. The dataset used in this study was collected over the past year and recorded several times a day. According to the lecture days, the data used is only from Monday to Friday. Since the recording is done randomly over a day, we preprocess the data using tree regression. After the data pre-processing stage produces data in minutes, the last stage is the quartile search process to find the hourly average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine and Deep Learning Dominate Recent Innovations in Sensors, Signals and Imaging informatics

引用

Yearbook of Medical informatics 2023年第1期32卷 282-285页

作者： Baumgartner, Christian Rittner, Leticia Deserno, Thomas M. Institute of Health Care Engineering with European Testing Center of Medical Devices Graz University of Technology Austria Medical Imaging Computing Lab (MICLab) School of Electrical and Computer Engineering University of Campinas Brazil Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Braunschweig Germany

OBJECTIVES: This review presents research papers highlighting notable developments and trends in sensors, signals, and imaging informatics (SSII) in 2022. METHOD: We performed a bibliographic search in PubMed combining Medical Subject Heading (MeSH) terms and keywords to create particular queries for sensors, signals, and imaging informatics. Only papers published in journals containing greater than three articles in the search query were considered. Using a three-point Likert scale (1 = not include, 2 = perhaps include, 3 = include), we reviewed the titles and abstracts of all database results. Only articles that scored three times Likert scale 3, or two times Likert scale 3, and one time Likert scale 2 were considered for full paper review. On this pre-selection, only papers with a total of at least eight points of the three section co-editors were considered for external review. Based on the external reviewers, we selected the top two papers representing significant research in SSII. RESULTS: Among the 469 returned papers published in 2022 in the various areas of SSII, 90, 31, and 348 papers for sensors, signals, and imaging informatics, and then, the full review process selected the two best papers. From the 469 papers, the section co-editors identified 29 candidate papers with at least 8 Likert points in total, of which 9 were nominated as the best contributions after a full paper assessment. Five external reviewers evaluated the nominated papers, and the two highest-scoring papers were selected based on the overall scores of all external reviewers. A consensus of the International Medical informatics Association (IMIA) Yearbook editorial board finally approved the nominated papers. Machine and deep learning-based techniques continue to be the dominant theme in this field. CONCLUSIONS: Sensors, signals, and imaging informatics is a dynamic field of intensive research with increasing practical applications to support medical decision-making on a personalized bas

关键词： Biomedical informatics deep learning machine learning personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Architecture Open Workspace Concept for Prescriptive Model of Digital Twin 9

Architecture Open Workspace Concept for Prescriptive Model o...

引用

9th International Conference on ICT for Smart Society, ICISS 2022

作者： Supangkat, Suhono Harso Supangkat, Suhono Harso Leksono, Edi Ramelan, Agus Latifah, Ayu School of Electrical and Informatics Engineering Bandung Institute of Technology Bandung Indonesia Engineering Physics Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia Electrical Engineering Departement Universitas Sebelas Maret Solo Indonesia Department of Computer Science Institut Teknologi Garut Garut Indonesia

ISBN: (数字)9781665471350

ISBN: (纸本)9781665471350

The workspace is a portion of a structure that can currently apply a smart building system adaption for more ideal design outcomes. Millions of hours are reportedly wasted each year as a result of the harmful effects that poor environmental quality has on workers' productivity and health, according to the findings of several studies. Therefore, a centralized approach is required to be able to give quick and accurate information. This may be accomplished via digital twin technology, which will result in a workspace design that is more ideal in the future. The major goal of this research is to create a digital twin prescriptive model in a physical workspace environment that can create a strategic space design plan and be flexible enough to react to changes in the physical environment, which will improve user comfort and productivity. A life cycle model was employed as the study methodology, which begins with the identification of the model's requirements and ends with its maintenance. This model is employed to offer suggestions for preventative and remedial activities on actual things. © 2022 IEEE.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

On a Piecewise Linear Function Approximation for Quantum Computation

On a Piecewise Linear Function Approximation for Quantum Com...

引用

IEEE Asia-Pacific Conference on Circuits and Systems

作者： Hideaki Okazaki Dept. of Informatics Faculty of Informatics Computer Science Course (or Field) Graduate school of Electrical and Information Engineering Shonan Institute of Technology Fujisawa Kanagawa Japan

In quantum computing, although correspondences between quantum circuits and polynomials have been explored, a correspondence between a quantum circuit and a low-degree polynomial, even a linear function has not fully clarified. In this paper, a quantum circuit approximating a linear function for building piecewise linear functions, is proposed. First, for qubit operations, a dimensionless form in $[0,1]$ of a linear function is provided. Secondly, a theorem of a parameterized quantum circuit approximating linear functions are provided. Thirdly, by using Yao: an open source Julia package, the quantum circuit simulation results to approximate the linear functions are presented. Finally, the principal results are summarized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Employing Deep Neural Networks for Real-Time Anomaly Detection and Mitigation in IoT-Based Smart Grid Cybersecurity Systems 3

Employing Deep Neural Networks for Real-Time Anomaly Detecti...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Quraishi, Aadam Rusho, Maher Ali Prasad, Anurag Keshta, Ismail Rivera, Richard Bhatt, Mohammed Wasim Intervention Treatment Institute Research HoustonTX United States University Of Colorado Boulder Department Of Lockheed Martin Engineering Management BoulderCO United States Gurugram India College Of Applied Sciences AlMaarefa University Computer Science And Information Systems Department Riyadh Saudi Arabia Escuela Politécnica Nacional Department Of Informatics And Computer Science Quito Ecuador Model Institute Of Engineering And Technology J&K Jammu India

ISBN: (纸本)9798350318609

This research introduces a novel anomaly detection framework for IoT -based Smart Grid Cybersecurity Systems. Leveraging autoencoders, LSTM networks, GANs, SOMs, and transfer learning, our approach achieves superior precision, recall, and execution time compared to existing methods. Visualizations and an ablation study further validate the method's efficiency, emphasizing the critical roles of attention mechanisms and transfer learning. This comprehensive solution addresses the dynamic challenges of smart grid cybersecurity, offering a versatile and adaptive anomaly detection mechanism for real-world applications. This indicates the real-time efficacy of our anomaly detection method. Through our study of ablation and all aspects of computing, we discovered that attention processes and transfer learning facilitate faster problem solving in a dynamic smart grid. Our method is distinct and adaptable enough to address every problem arising from the discovery of anomalies in IoT-driven Smart Grid Cybersecurity Systems. © 2024 IEEE.

关键词： Anomaly detection

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：